diff --git "a/checkpoint-2747520/trainer_state.json" "b/checkpoint-2747520/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2747520/trainer_state.json" @@ -0,0 +1,32509 @@ +{ + "best_metric": 3.8450353145599365, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/transformer/1/checkpoints/checkpoint-992160", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2747520, + "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": 11.0349, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8119, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.188, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9793, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8074, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.6987, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5939, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5293, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4394, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3947, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3436, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3029, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2501, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2025, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1605, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1281, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.0983, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0846, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0412, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.021, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0107, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9653, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9416, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9255, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9185, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8828, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8641, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8569, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8349, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8096, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.7946, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740117521192533e-05, + "loss": 4.7898, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731731573682013e-05, + "loss": 4.7776, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7744, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7505, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7358, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.74, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7022, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.6978, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6838, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6831, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6613, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6745, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6423, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6471, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6362, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6279, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6255, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6015, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 4.5886, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.6025, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.5884, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.5707, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 4.5589, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954732262246923e-05, + "loss": 4.5672, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953893667495871e-05, + "loss": 4.5503, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 4.5625, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5352, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5332, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5366, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5176, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5018, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5068, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4904, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4913, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5002, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.4929, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4799, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4668, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4594, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 4.4726, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.467, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396441082494794e-05, + "loss": 4.4599, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388055134984274e-05, + "loss": 4.4575, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.4619, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4541, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.4283, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.4385, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4344, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.42, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4327, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4224, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.429, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.418, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.392, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928747290126923e-05, + "loss": 4.4016, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927908695375871e-05, + "loss": 4.4018, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927070100624819e-05, + "loss": 4.4014, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926231505873767e-05, + "loss": 4.394, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925394549003088e-05, + "loss": 4.3858, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924555954252036e-05, + "loss": 4.3892, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923717359500984e-05, + "loss": 4.3773, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.9228804026303046e-05, + "loss": 4.3709, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922041807879253e-05, + "loss": 4.3721, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921203213128201e-05, + "loss": 4.368, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920364618377149e-05, + "loss": 4.379, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919526023626097e-05, + "loss": 4.3552, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918687428875045e-05, + "loss": 4.3514, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917848834123993e-05, + "loss": 4.3505, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.3605, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916173282502262e-05, + "loss": 4.3566, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.91533468775121e-05, + "loss": 4.3432, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914496093000158e-05, + "loss": 4.3415, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913657498249106e-05, + "loss": 4.3243, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912818903498054e-05, + "loss": 4.3379, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911980308747002e-05, + "loss": 4.3236, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3204, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.3271, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3251, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.3197, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3161, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3088, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3154, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052748264993326e-05, + "loss": 4.3027, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.90443623174828e-05, + "loss": 4.303, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903597636997228e-05, + "loss": 4.3086, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.3059, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019237232558704e-05, + "loss": 4.3034, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010851285048184e-05, + "loss": 4.2953, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900246533753767e-05, + "loss": 4.2997, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899407939002715e-05, + "loss": 4.2948, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985693442516624e-05, + "loss": 4.2816, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977307495006104e-05, + "loss": 4.2985, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968921547495584e-05, + "loss": 4.2837, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2912, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.2744, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.2699, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2664, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.27, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2611, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891023629372567e-05, + "loss": 4.2774, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.2738, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2583, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888509482999785e-05, + "loss": 4.2609, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887670888248733e-05, + "loss": 4.2657, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886832293497681e-05, + "loss": 4.2613, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.2666, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515674187595e-05, + "loss": 4.2625, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2489, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2541, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.25, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.2412, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88096376812069e-05, + "loss": 4.2518, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880125173369638e-05, + "loss": 4.2394, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.8792882164989586e-05, + "loss": 4.2287, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2524, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.2314, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876772432245803e-05, + "loss": 4.2292, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875933837494751e-05, + "loss": 4.2312, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875096880624072e-05, + "loss": 4.2241, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.197596073150635, + "eval_runtime": 303.2397, + "eval_samples_per_second": 1258.381, + "eval_steps_per_second": 39.325, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.87425828587302e-05, + "loss": 4.2094, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873419691121968e-05, + "loss": 4.2203, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.2365, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2139, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.2286, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.2034, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.2152, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.1994, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675528036253507e-05, + "loss": 4.2105, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667142088742986e-05, + "loss": 4.206, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865875614123246e-05, + "loss": 4.2093, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865037019372194e-05, + "loss": 4.207, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642000625015155e-05, + "loss": 4.1923, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633614677504635e-05, + "loss": 4.1855, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862522872999411e-05, + "loss": 4.1848, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861684278248359e-05, + "loss": 4.1894, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860845683497307e-05, + "loss": 4.1964, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860007088746255e-05, + "loss": 4.1837, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859168493995203e-05, + "loss": 4.1906, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858329899244151e-05, + "loss": 4.206, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574913044930995e-05, + "loss": 4.1814, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.1752, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.1791, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549771581203164e-05, + "loss": 4.1889, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541385633692644e-05, + "loss": 4.1685, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532999686182124e-05, + "loss": 4.1742, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524613738671604e-05, + "loss": 4.1736, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.1675, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.1541, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.161, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849108632743325e-05, + "loss": 4.1567, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.1667, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847431443241221e-05, + "loss": 4.1729, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846592848490169e-05, + "loss": 4.1561, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.1534, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844917296868439e-05, + "loss": 4.1656, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844078702117387e-05, + "loss": 4.1412, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843240107366335e-05, + "loss": 4.1478, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.1387, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841564555744604e-05, + "loss": 4.145, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840725960993552e-05, + "loss": 4.1377, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398873662425e-05, + "loss": 4.1552, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839050409371821e-05, + "loss": 4.1406, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382118146207687e-05, + "loss": 4.1414, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373732198697167e-05, + "loss": 4.1376, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.8365346251186646e-05, + "loss": 4.1422, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835697668247986e-05, + "loss": 4.1352, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834859073496934e-05, + "loss": 4.1264, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834020478745882e-05, + "loss": 4.1185, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331818839948295e-05, + "loss": 4.1403, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323432892437775e-05, + "loss": 4.1304, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315046944927255e-05, + "loss": 4.1191, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830667737622047e-05, + "loss": 4.1173, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298291428709944e-05, + "loss": 4.1257, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289905481199424e-05, + "loss": 4.1144, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281519533688904e-05, + "loss": 4.1291, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827314996498212e-05, + "loss": 4.1141, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.82647640174716e-05, + "loss": 4.1153, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825637806996108e-05, + "loss": 4.1266, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824799212245056e-05, + "loss": 4.1049, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823962255374377e-05, + "loss": 4.102, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823123660623325e-05, + "loss": 4.1116, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822285065872273e-05, + "loss": 4.0943, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821446471121221e-05, + "loss": 4.1002, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820609514250542e-05, + "loss": 4.1124, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.81977091949949e-05, + "loss": 4.1143, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818932324748438e-05, + "loss": 4.1028, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818093729997386e-05, + "loss": 4.0966, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172567731267074e-05, + "loss": 4.0864, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164181783756554e-05, + "loss": 4.1062, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155795836246034e-05, + "loss": 4.104, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147409888735514e-05, + "loss": 4.1037, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813904032002872e-05, + "loss": 4.1042, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.81306543725182e-05, + "loss": 4.1066, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812226842500768e-05, + "loss": 4.1062, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811388247749716e-05, + "loss": 4.0819, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810551290879037e-05, + "loss": 4.0976, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809712696127985e-05, + "loss": 4.0966, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808874101376933e-05, + "loss": 4.0811, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808035506625881e-05, + "loss": 4.1023, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807198549755203e-05, + "loss": 4.0945, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806359955004151e-05, + "loss": 4.1003, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805521360253099e-05, + "loss": 4.0971, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804682765502047e-05, + "loss": 4.0739, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.8038458086313677e-05, + "loss": 4.0847, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.8030072138803156e-05, + "loss": 4.0838, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.8021686191292636e-05, + "loss": 4.0881, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.8013300243782116e-05, + "loss": 4.0832, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004914296271596e-05, + "loss": 4.0752, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996544727564805e-05, + "loss": 4.0851, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988158780054285e-05, + "loss": 4.0794, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979789211347494e-05, + "loss": 4.0653, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797140326383698e-05, + "loss": 4.0728, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796301731632646e-05, + "loss": 4.0785, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795463136881594e-05, + "loss": 4.0875, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794624542130542e-05, + "loss": 4.0694, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.79378594737949e-05, + "loss": 4.0568, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792947352628438e-05, + "loss": 4.0675, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792108757877386e-05, + "loss": 4.0752, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.79127343888708e-05, + "loss": 4.0757, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790434844136028e-05, + "loss": 4.0686, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789596249384976e-05, + "loss": 4.0625, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788757654633924e-05, + "loss": 4.0524, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787919059882872e-05, + "loss": 4.0657, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.78708046513182e-05, + "loss": 4.0519, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786241870380768e-05, + "loss": 4.0563, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854049135100895e-05, + "loss": 4.0615, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845663187590375e-05, + "loss": 4.0592, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837277240079855e-05, + "loss": 4.055, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828891292569335e-05, + "loss": 4.0609, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820505345058815e-05, + "loss": 4.0503, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812119397548295e-05, + "loss": 4.0559, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803733450037775e-05, + "loss": 4.0504, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779534750252725e-05, + "loss": 4.0482, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786977933820464e-05, + "loss": 4.0606, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.7778591986309944e-05, + "loss": 4.0592, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777022241760315e-05, + "loss": 4.0548, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776183647009263e-05, + "loss": 4.0476, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775345052258212e-05, + "loss": 4.0524, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.77450645750716e-05, + "loss": 4.0508, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773667862756108e-05, + "loss": 4.0398, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772829268005055e-05, + "loss": 4.0598, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771990673254003e-05, + "loss": 4.0436, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771152078502951e-05, + "loss": 4.0526, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770315121632272e-05, + "loss": 4.0374, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.76947652688122e-05, + "loss": 4.0377, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768637932130168e-05, + "loss": 4.0333, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767799337379116e-05, + "loss": 4.035, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766962380508437e-05, + "loss": 4.0335, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766123785757386e-05, + "loss": 4.0478, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765285191006334e-05, + "loss": 4.0488, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764446596255282e-05, + "loss": 4.0361, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.7636096393846026e-05, + "loss": 4.0292, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.7627710446335506e-05, + "loss": 4.0414, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.7619324498824986e-05, + "loss": 4.0397, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7610938551314466e-05, + "loss": 4.0463, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602568982607675e-05, + "loss": 4.04, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594183035097155e-05, + "loss": 4.0343, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.7585797087586635e-05, + "loss": 4.029, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577411140076115e-05, + "loss": 4.0395, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569041571369324e-05, + "loss": 4.0283, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756065562385881e-05, + "loss": 4.0324, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755226967634829e-05, + "loss": 4.0301, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754388372883777e-05, + "loss": 4.0212, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753551416013098e-05, + "loss": 4.0435, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752712821262046e-05, + "loss": 4.0235, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751874226510994e-05, + "loss": 4.0202, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751035631759942e-05, + "loss": 4.0227, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750198674889263e-05, + "loss": 4.0185, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.028837203979492, + "eval_runtime": 303.893, + "eval_samples_per_second": 1255.675, + "eval_steps_per_second": 39.241, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749360080138211e-05, + "loss": 4.0037, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748521485387159e-05, + "loss": 4.0188, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747682890636107e-05, + "loss": 4.0332, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746844295885055e-05, + "loss": 4.0175, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.746005701134003e-05, + "loss": 4.0303, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745167106382951e-05, + "loss": 4.0088, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744328511631899e-05, + "loss": 4.0208, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434899168808475e-05, + "loss": 4.0015, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426529600101684e-05, + "loss": 4.0181, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7418143652591164e-05, + "loss": 4.0142, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.7409757705080644e-05, + "loss": 4.0141, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401371757570124e-05, + "loss": 4.0229, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739300218886333e-05, + "loss": 4.0026, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738461624135281e-05, + "loss": 3.9977, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737623029384229e-05, + "loss": 3.9976, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736784434633177e-05, + "loss": 4.0064, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735945839882125e-05, + "loss": 4.0094, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735107245131073e-05, + "loss": 4.0025, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734268650380021e-05, + "loss": 4.0066, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733430055628969e-05, + "loss": 4.0246, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732591460877917e-05, + "loss": 3.9993, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731752866126865e-05, + "loss": 3.9954, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730914271375813e-05, + "loss": 4.0023, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730077314505134e-05, + "loss": 4.0084, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729238719754082e-05, + "loss": 3.9934, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728401762883403e-05, + "loss": 3.9974, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727563168132351e-05, + "loss": 3.9979, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726724573381299e-05, + "loss": 3.9935, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725885978630247e-05, + "loss": 3.9826, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725049021759568e-05, + "loss": 3.9901, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724210427008517e-05, + "loss": 3.989, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233718322574647e-05, + "loss": 3.9929, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225332375064127e-05, + "loss": 4.0066, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216946427553606e-05, + "loss": 3.9853, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208560480043086e-05, + "loss": 3.9856, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200174532532566e-05, + "loss": 3.9973, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191788585022046e-05, + "loss": 3.9807, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183419016315255e-05, + "loss": 3.9787, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175033068804735e-05, + "loss": 3.9743, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166647121294215e-05, + "loss": 3.9843, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158261173783695e-05, + "loss": 3.9732, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149891605076904e-05, + "loss": 3.9965, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141505657566384e-05, + "loss": 3.9753, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133119710055864e-05, + "loss": 3.9859, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712475014134908e-05, + "loss": 3.9805, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711636419383856e-05, + "loss": 3.9802, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710797824632804e-05, + "loss": 3.9787, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709959229881752e-05, + "loss": 3.9669, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709122273011073e-05, + "loss": 3.9646, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708283678260021e-05, + "loss": 3.9848, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707445083508969e-05, + "loss": 3.9775, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706606488757917e-05, + "loss": 3.9651, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705769531887238e-05, + "loss": 3.9684, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704932575016559e-05, + "loss": 3.9764, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040939802655074e-05, + "loss": 3.9563, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032553855144554e-05, + "loss": 3.9761, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024167907634034e-05, + "loss": 3.9664, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015781960123514e-05, + "loss": 3.9647, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007396012612994e-05, + "loss": 3.9826, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6999010065102474e-05, + "loss": 3.9578, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990624117591954e-05, + "loss": 3.9547, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698225454888516e-05, + "loss": 3.9657, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697386860137464e-05, + "loss": 3.9502, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696548265386412e-05, + "loss": 3.955, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69570967063536e-05, + "loss": 3.9678, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694872713764681e-05, + "loss": 3.9698, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694034119013629e-05, + "loss": 3.9539, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693195524262577e-05, + "loss": 3.9561, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692358567391899e-05, + "loss": 3.9435, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691519972640847e-05, + "loss": 3.9648, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690681377889795e-05, + "loss": 3.96, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689842783138743e-05, + "loss": 3.9665, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689004188387691e-05, + "loss": 3.9611, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688165593636639e-05, + "loss": 3.9647, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873286367659596e-05, + "loss": 3.9722, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864900420149076e-05, + "loss": 3.9437, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856514472638556e-05, + "loss": 3.9585, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848128525128036e-05, + "loss": 3.9628, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683974257761751e-05, + "loss": 3.9447, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831356630106996e-05, + "loss": 3.965, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822970682596476e-05, + "loss": 3.9592, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.6814584735085956e-05, + "loss": 3.9648, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.68062315451829e-05, + "loss": 3.9625, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679784559767238e-05, + "loss": 3.9401, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678945965016186e-05, + "loss": 3.9525, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678107370265134e-05, + "loss": 3.9503, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772687755140814e-05, + "loss": 3.9584, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764301807630294e-05, + "loss": 3.9487, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675593223892351e-05, + "loss": 3.9471, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674754629141298e-05, + "loss": 3.9532, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673916034390246e-05, + "loss": 3.95, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673077439639194e-05, + "loss": 3.936, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672238844888143e-05, + "loss": 3.9429, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671400250137091e-05, + "loss": 3.9526, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670563293266412e-05, + "loss": 3.9567, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.66972469851536e-05, + "loss": 3.9462, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668886103764308e-05, + "loss": 3.9278, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668047509013256e-05, + "loss": 3.9411, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667210552142577e-05, + "loss": 3.948, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666371957391525e-05, + "loss": 3.9476, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665533362640473e-05, + "loss": 3.9441, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664694767889421e-05, + "loss": 3.9383, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663856173138369e-05, + "loss": 3.9274, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663017578387317e-05, + "loss": 3.9463, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662178983636265e-05, + "loss": 3.9233, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661340388885213e-05, + "loss": 3.9363, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660503432014534e-05, + "loss": 3.9313, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659664837263482e-05, + "loss": 3.9434, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.65882624251243e-05, + "loss": 3.928, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657987647761378e-05, + "loss": 3.9404, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657149053010326e-05, + "loss": 3.9312, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656310458259274e-05, + "loss": 3.9305, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655473501388595e-05, + "loss": 3.9359, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654634906637543e-05, + "loss": 3.9262, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653796311886491e-05, + "loss": 3.941, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652957717135439e-05, + "loss": 3.9399, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.65212076026476e-05, + "loss": 3.9373, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651282165513708e-05, + "loss": 3.9297, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650443570762657e-05, + "loss": 3.9329, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649604976011605e-05, + "loss": 3.9367, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648768019140926e-05, + "loss": 3.9187, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647929424389874e-05, + "loss": 3.9408, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647090829638822e-05, + "loss": 3.9298, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.64625223488777e-05, + "loss": 3.9347, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645413640136718e-05, + "loss": 3.9242, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644575045385665e-05, + "loss": 3.9268, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643736450634613e-05, + "loss": 3.9145, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6428994937639346e-05, + "loss": 3.9213, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642060899012882e-05, + "loss": 3.9201, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412223042618306e-05, + "loss": 3.9341, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.6403837095107786e-05, + "loss": 3.9352, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395467526401e-05, + "loss": 3.9255, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387081578890475e-05, + "loss": 3.9173, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378695631379955e-05, + "loss": 3.9272, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370309683869435e-05, + "loss": 3.9288, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636194011516265e-05, + "loss": 3.9334, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353554167652124e-05, + "loss": 3.9279, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345168220141604e-05, + "loss": 3.9191, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336782272631084e-05, + "loss": 3.9253, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328396325120564e-05, + "loss": 3.9297, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320010377610043e-05, + "loss": 3.9167, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311624430099523e-05, + "loss": 3.9222, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630325486139274e-05, + "loss": 3.9206, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629486891388222e-05, + "loss": 3.9121, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.62864829663717e-05, + "loss": 3.9349, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627809701886118e-05, + "loss": 3.9176, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626971107135066e-05, + "loss": 3.912, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626134150264387e-05, + "loss": 3.9133, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625295555513335e-05, + "loss": 3.9098, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9549131393432617, + "eval_runtime": 303.0366, + "eval_samples_per_second": 1259.224, + "eval_steps_per_second": 39.352, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624456960762283e-05, + "loss": 3.9038, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623618366011231e-05, + "loss": 3.9111, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622781409140552e-05, + "loss": 3.9277, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219428143895e-05, + "loss": 3.9124, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621104219638448e-05, + "loss": 3.9321, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620265624887396e-05, + "loss": 3.8982, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619428668016717e-05, + "loss": 3.9187, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618590073265665e-05, + "loss": 3.8965, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617751478514613e-05, + "loss": 3.914, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616912883763561e-05, + "loss": 3.9126, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616074289012509e-05, + "loss": 3.908, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.61523733214183e-05, + "loss": 3.9185, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614400375271151e-05, + "loss": 3.9001, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613561780520099e-05, + "loss": 3.8977, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612723185769047e-05, + "loss": 3.8967, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611884591017995e-05, + "loss": 3.9037, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611045996266943e-05, + "loss": 3.9073, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610207401515891e-05, + "loss": 3.9041, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609368806764839e-05, + "loss": 3.905, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608530212013788e-05, + "loss": 3.9227, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607691617262736e-05, + "loss": 3.9021, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068546603920566e-05, + "loss": 3.9007, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6060160656410046e-05, + "loss": 3.9044, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051774708899526e-05, + "loss": 3.9083, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043388761389006e-05, + "loss": 3.8937, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603500281387848e-05, + "loss": 3.9019, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.6026633245171695e-05, + "loss": 3.902, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018247297661175e-05, + "loss": 3.893, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009861350150655e-05, + "loss": 3.8882, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600147540264013e-05, + "loss": 3.8876, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5993089455129615e-05, + "loss": 3.8973, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.5984703507619095e-05, + "loss": 3.895, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597633393891231e-05, + "loss": 3.9109, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5967947991401784e-05, + "loss": 3.8976, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959562043891264e-05, + "loss": 3.8839, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.5951176096380744e-05, + "loss": 3.8999, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594280652767395e-05, + "loss": 3.8924, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593442058016343e-05, + "loss": 3.8819, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592603463265291e-05, + "loss": 3.8831, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591764868514239e-05, + "loss": 3.8874, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590926273763187e-05, + "loss": 3.882, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590087679012135e-05, + "loss": 3.9032, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589250722141457e-05, + "loss": 3.8856, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588412127390405e-05, + "loss": 3.8918, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587573532639353e-05, + "loss": 3.8904, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586734937888301e-05, + "loss": 3.8857, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585897981017622e-05, + "loss": 3.889, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.58505938626657e-05, + "loss": 3.8741, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584220791515518e-05, + "loss": 3.8659, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583382196764466e-05, + "loss": 3.8969, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582543602013414e-05, + "loss": 3.8843, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581706645142735e-05, + "loss": 3.8796, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580868050391683e-05, + "loss": 3.8742, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580029455640631e-05, + "loss": 3.882, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579190860889579e-05, + "loss": 3.8682, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783539040189e-05, + "loss": 3.8846, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577515309267848e-05, + "loss": 3.8821, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576676714516796e-05, + "loss": 3.8763, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575838119765744e-05, + "loss": 3.8896, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.575001162895065e-05, + "loss": 3.8681, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574162568144013e-05, + "loss": 3.8659, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573323973392961e-05, + "loss": 3.8812, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572485378641909e-05, + "loss": 3.8596, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.57164842177123e-05, + "loss": 3.8626, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570809827020178e-05, + "loss": 3.8827, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569971232269126e-05, + "loss": 3.8838, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569132637518074e-05, + "loss": 3.8637, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568294042767022e-05, + "loss": 3.8755, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674570858963436e-05, + "loss": 3.8561, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5666184911452916e-05, + "loss": 3.8781, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.5657798963942396e-05, + "loss": 3.8734, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.5649413016431876e-05, + "loss": 3.88, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.5641043447725085e-05, + "loss": 3.8726, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632657500214565e-05, + "loss": 3.8804, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624271552704045e-05, + "loss": 3.8873, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.5615885605193525e-05, + "loss": 3.8571, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.5607516036486734e-05, + "loss": 3.8762, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.5599130088976214e-05, + "loss": 3.879, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590744141465694e-05, + "loss": 3.8545, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.5582358193955174e-05, + "loss": 3.8843, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557398862524839e-05, + "loss": 3.8759, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556560267773787e-05, + "loss": 3.8778, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555721673022735e-05, + "loss": 3.8823, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554883078271683e-05, + "loss": 3.859, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554044483520631e-05, + "loss": 3.8631, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553207526649952e-05, + "loss": 3.8684, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.5523689318989e-05, + "loss": 3.8754, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551530337147848e-05, + "loss": 3.8665, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550691742396796e-05, + "loss": 3.8662, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549854785526117e-05, + "loss": 3.8654, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549016190775065e-05, + "loss": 3.8745, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548177596024013e-05, + "loss": 3.8541, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547339001272961e-05, + "loss": 3.8602, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546500406521909e-05, + "loss": 3.8709, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.54566344965123e-05, + "loss": 3.8761, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544824854900178e-05, + "loss": 3.8654, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543986260149126e-05, + "loss": 3.8482, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431476653980736e-05, + "loss": 3.8594, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542310708527395e-05, + "loss": 3.8638, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541472113776343e-05, + "loss": 3.8673, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540633519025291e-05, + "loss": 3.8661, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5397949242742385e-05, + "loss": 3.8596, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.53895796740356e-05, + "loss": 3.8491, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538119372652508e-05, + "loss": 3.8652, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537280777901456e-05, + "loss": 3.8467, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536442183150404e-05, + "loss": 3.8566, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535605226279726e-05, + "loss": 3.8494, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534766631528674e-05, + "loss": 3.8644, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533928036777621e-05, + "loss": 3.8504, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533089442026569e-05, + "loss": 3.8678, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322524851558906e-05, + "loss": 3.8483, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314138904048386e-05, + "loss": 3.8537, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530575295653786e-05, + "loss": 3.856, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529736700902734e-05, + "loss": 3.8525, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528898106151682e-05, + "loss": 3.8604, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280611492810035e-05, + "loss": 3.8671, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527224192410325e-05, + "loss": 3.858, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526385597659273e-05, + "loss": 3.8517, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525547002908221e-05, + "loss": 3.8573, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247084081571684e-05, + "loss": 3.8589, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238698134061164e-05, + "loss": 3.8424, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.5230312186550644e-05, + "loss": 3.8634, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.5221926239040124e-05, + "loss": 3.8486, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213540291529604e-05, + "loss": 3.8612, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5205154344019084e-05, + "loss": 3.8494, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519678477531229e-05, + "loss": 3.8513, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518839882780177e-05, + "loss": 3.8362, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.518001288029125e-05, + "loss": 3.8519, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517162693278074e-05, + "loss": 3.8445, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516325736407395e-05, + "loss": 3.8552, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515487141656343e-05, + "loss": 3.8581, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514648546905291e-05, + "loss": 3.8535, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513809952154239e-05, + "loss": 3.8405, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.51297299528356e-05, + "loss": 3.8549, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512134400532508e-05, + "loss": 3.856, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511295805781456e-05, + "loss": 3.8568, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510457211030404e-05, + "loss": 3.8543, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5096202541597246e-05, + "loss": 3.8474, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087816594086726e-05, + "loss": 3.8483, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079430646576206e-05, + "loss": 3.8577, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507104469906569e-05, + "loss": 3.8427, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506265875155517e-05, + "loss": 3.8509, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505428918284838e-05, + "loss": 3.8433, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504590323533786e-05, + "loss": 3.8456, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503751728782734e-05, + "loss": 3.8604, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502913134031682e-05, + "loss": 3.8473, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502076177161003e-05, + "loss": 3.8384, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501237582409951e-05, + "loss": 3.8384, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500398987658899e-05, + "loss": 3.8424, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9138612747192383, + "eval_runtime": 304.2723, + "eval_samples_per_second": 1254.11, + "eval_steps_per_second": 39.192, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499560392907847e-05, + "loss": 3.8267, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498721798156795e-05, + "loss": 3.8412, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497883203405743e-05, + "loss": 3.8532, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497044608654691e-05, + "loss": 3.8441, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496206013903639e-05, + "loss": 3.8601, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495367419152587e-05, + "loss": 3.8365, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494528824401535e-05, + "loss": 3.8433, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493690229650483e-05, + "loss": 3.8312, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928532727798047e-05, + "loss": 3.8381, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492014678028752e-05, + "loss": 3.8429, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911760832777e-05, + "loss": 3.8404, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490337488526648e-05, + "loss": 3.8489, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4895021695363425e-05, + "loss": 3.8301, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886635747852905e-05, + "loss": 3.8295, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878249800342385e-05, + "loss": 3.8281, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.4869863852831864e-05, + "loss": 3.8316, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.4861477905321344e-05, + "loss": 3.8398, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853091957810824e-05, + "loss": 3.8321, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844706010300304e-05, + "loss": 3.838, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836320062789784e-05, + "loss": 3.8535, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4827950494082993e-05, + "loss": 3.838, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481956454657247e-05, + "loss": 3.8333, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481117859906195e-05, + "loss": 3.8329, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480279265155143e-05, + "loss": 3.8374, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479442308284464e-05, + "loss": 3.8255, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478603713533412e-05, + "loss": 3.8359, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.47776511878236e-05, + "loss": 3.8327, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476926524031308e-05, + "loss": 3.828, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.47608956716063e-05, + "loss": 3.8234, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475250972409578e-05, + "loss": 3.823, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474412377658526e-05, + "loss": 3.8275, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473573782907474e-05, + "loss": 3.8302, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472736826036795e-05, + "loss": 3.8433, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471898231285743e-05, + "loss": 3.8308, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471059636534691e-05, + "loss": 3.8184, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470221041783639e-05, + "loss": 3.8323, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693840849129596e-05, + "loss": 3.8327, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.4685454901619076e-05, + "loss": 3.8125, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4677068954108556e-05, + "loss": 3.8142, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668683006598036e-05, + "loss": 3.8248, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466031343789125e-05, + "loss": 3.8155, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465192749038073e-05, + "loss": 3.8379, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464354154287021e-05, + "loss": 3.8211, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463515559535969e-05, + "loss": 3.823, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.46267860266529e-05, + "loss": 3.8248, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461840007914238e-05, + "loss": 3.8259, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.461001413163186e-05, + "loss": 3.8239, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460162818412134e-05, + "loss": 3.8099, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459325861541455e-05, + "loss": 3.7994, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458487266790403e-05, + "loss": 3.836, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457648672039351e-05, + "loss": 3.8172, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456810077288299e-05, + "loss": 3.8185, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559731204176205e-05, + "loss": 3.8151, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551345256665685e-05, + "loss": 3.8129, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542959309155165e-05, + "loss": 3.8081, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534573361644645e-05, + "loss": 3.8175, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526203792937854e-05, + "loss": 3.8194, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517817845427334e-05, + "loss": 3.8125, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509431897916814e-05, + "loss": 3.831, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4501045950406294e-05, + "loss": 3.8031, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.44926763816995e-05, + "loss": 3.8011, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448429043418898e-05, + "loss": 3.8238, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447590448667846e-05, + "loss": 3.7943, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446751853916794e-05, + "loss": 3.7999, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445914897046116e-05, + "loss": 3.8227, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445076302295064e-05, + "loss": 3.8234, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444237707544012e-05, + "loss": 3.802, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.44339911279296e-05, + "loss": 3.8128, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442562155922281e-05, + "loss": 3.7949, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441723561171229e-05, + "loss": 3.8142, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440884966420177e-05, + "loss": 3.8093, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440046371669125e-05, + "loss": 3.8179, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439209414798446e-05, + "loss": 3.8104, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438370820047394e-05, + "loss": 3.8196, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437532225296342e-05, + "loss": 3.8264, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.43669363054529e-05, + "loss": 3.8007, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435856673674611e-05, + "loss": 3.8108, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435018078923559e-05, + "loss": 3.8195, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434179484172507e-05, + "loss": 3.7947, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433340889421455e-05, + "loss": 3.8213, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432503932550776e-05, + "loss": 3.8197, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431665337799724e-05, + "loss": 3.819, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430826743048672e-05, + "loss": 3.8208, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.42998814829762e-05, + "loss": 3.8011, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429151191426941e-05, + "loss": 3.7996, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428312596675889e-05, + "loss": 3.808, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427474001924837e-05, + "loss": 3.8185, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426635407173785e-05, + "loss": 3.807, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257984503031066e-05, + "loss": 3.8049, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249598555520546e-05, + "loss": 3.8044, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241212608010026e-05, + "loss": 3.8156, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232826660499506e-05, + "loss": 3.7997, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224457091792715e-05, + "loss": 3.8, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216071144282195e-05, + "loss": 3.8078, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207685196771675e-05, + "loss": 3.8193, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199299249261155e-05, + "loss": 3.8088, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190929680554364e-05, + "loss": 3.7935, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182543733043844e-05, + "loss": 3.7993, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174157785533324e-05, + "loss": 3.8051, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165771838022804e-05, + "loss": 3.8114, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157385890512284e-05, + "loss": 3.8061, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.41490163218055e-05, + "loss": 3.8037, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414063037429498e-05, + "loss": 3.7914, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413224442678446e-05, + "loss": 3.8026, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412385847927394e-05, + "loss": 3.7907, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411548891056715e-05, + "loss": 3.8024, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410710296305663e-05, + "loss": 3.7853, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409871701554611e-05, + "loss": 3.8146, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409034744683932e-05, + "loss": 3.7939, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.40819614993288e-05, + "loss": 3.8024, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407357555181828e-05, + "loss": 3.7968, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406518960430776e-05, + "loss": 3.7947, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056820035600974e-05, + "loss": 3.7992, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.4048434088090454e-05, + "loss": 3.7973, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4040048140579934e-05, + "loss": 3.8023, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031662193069414e-05, + "loss": 3.8095, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402330900316635e-05, + "loss": 3.8007, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401492305565583e-05, + "loss": 3.7973, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400653710814531e-05, + "loss": 3.8, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399815116063479e-05, + "loss": 3.8057, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398976521312427e-05, + "loss": 3.7826, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398137926561375e-05, + "loss": 3.8063, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397299331810323e-05, + "loss": 3.7911, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396460737059271e-05, + "loss": 3.8043, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395623780188593e-05, + "loss": 3.7941, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394785185437541e-05, + "loss": 3.7978, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393946590686489e-05, + "loss": 3.7821, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393107995935437e-05, + "loss": 3.793, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922710390647576e-05, + "loss": 3.7933, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914324443137056e-05, + "loss": 3.7972, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905938495626536e-05, + "loss": 3.7978, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897552548116016e-05, + "loss": 3.8024, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889182979409225e-05, + "loss": 3.7832, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880797031898705e-05, + "loss": 3.7982, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872411084388185e-05, + "loss": 3.8031, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3864025136877665e-05, + "loss": 3.8006, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385565556817088e-05, + "loss": 3.7958, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384726962066036e-05, + "loss": 3.797, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383888367314984e-05, + "loss": 3.7902, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830497725639314e-05, + "loss": 3.8041, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382212815693253e-05, + "loss": 3.7865, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381374220942201e-05, + "loss": 3.798, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380535626191148e-05, + "loss": 3.7899, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379697031440096e-05, + "loss": 3.7907, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378860074569418e-05, + "loss": 3.8064, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378021479818366e-05, + "loss": 3.7936, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377182885067313e-05, + "loss": 3.7887, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376344290316262e-05, + "loss": 3.7794, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3755073334455835e-05, + "loss": 3.7897, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8884811401367188, + "eval_runtime": 302.7215, + "eval_samples_per_second": 1260.535, + "eval_steps_per_second": 39.393, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746687386945315e-05, + "loss": 3.783, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373830143943479e-05, + "loss": 3.7837, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372991549192427e-05, + "loss": 3.8004, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.3721545923217484e-05, + "loss": 3.7937, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371315997570696e-05, + "loss": 3.8071, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370477402819644e-05, + "loss": 3.7853, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369638808068592e-05, + "loss": 3.7841, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368801851197913e-05, + "loss": 3.782, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.3679632564468606e-05, + "loss": 3.783, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.3671246616958086e-05, + "loss": 3.7908, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366286066944757e-05, + "loss": 3.7901, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365449110074079e-05, + "loss": 3.7922, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.3646121532034e-05, + "loss": 3.7831, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363773558452348e-05, + "loss": 3.7776, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362934963701296e-05, + "loss": 3.7759, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362096368950243e-05, + "loss": 3.7783, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361257774199191e-05, + "loss": 3.7863, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360419179448139e-05, + "loss": 3.7835, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359580584697087e-05, + "loss": 3.7864, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358741989946035e-05, + "loss": 3.8006, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357905033075356e-05, + "loss": 3.7885, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357066438324304e-05, + "loss": 3.7776, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.3562278435732526e-05, + "loss": 3.7836, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.3553892488222006e-05, + "loss": 3.7846, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.3545522919515215e-05, + "loss": 3.7766, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.3537136972004695e-05, + "loss": 3.7853, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.3528751024494175e-05, + "loss": 3.7809, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3520365076983655e-05, + "loss": 3.7792, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3511995508276864e-05, + "loss": 3.7751, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503609560766344e-05, + "loss": 3.7671, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3495223613255824e-05, + "loss": 3.7771, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486837665745304e-05, + "loss": 3.7792, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347846809703851e-05, + "loss": 3.7886, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.347008214952799e-05, + "loss": 3.7814, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346169620201748e-05, + "loss": 3.768, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345332663331069e-05, + "loss": 3.786, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344494068580017e-05, + "loss": 3.7811, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343655473828965e-05, + "loss": 3.7598, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342816879077913e-05, + "loss": 3.7719, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341979922207234e-05, + "loss": 3.7712, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341141327456182e-05, + "loss": 3.7688, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.34030273270513e-05, + "loss": 3.787, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339464137954078e-05, + "loss": 3.7727, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338627181083399e-05, + "loss": 3.7735, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337788586332347e-05, + "loss": 3.7734, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336949991581295e-05, + "loss": 3.7747, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3361113968302434e-05, + "loss": 3.779, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335274439959564e-05, + "loss": 3.7601, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334435845208512e-05, + "loss": 3.7461, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.33359725045746e-05, + "loss": 3.7891, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332758655706408e-05, + "loss": 3.768, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331921698835729e-05, + "loss": 3.7773, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331083104084677e-05, + "loss": 3.7615, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330244509333625e-05, + "loss": 3.7647, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329405914582573e-05, + "loss": 3.7619, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328568957711894e-05, + "loss": 3.7661, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327730362960842e-05, + "loss": 3.7723, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.32689176820979e-05, + "loss": 3.7613, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326053173458739e-05, + "loss": 3.7831, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.3252162165880596e-05, + "loss": 3.7583, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.3243776218370076e-05, + "loss": 3.7519, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.3235390270859556e-05, + "loss": 3.7755, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.3227004323349036e-05, + "loss": 3.7508, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.3218634754642245e-05, + "loss": 3.7497, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.3210248807131725e-05, + "loss": 3.773, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.3201862859621205e-05, + "loss": 3.7706, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3193476912110685e-05, + "loss": 3.7586, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3185107343403894e-05, + "loss": 3.7666, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.3176721395893374e-05, + "loss": 3.7466, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3168335448382854e-05, + "loss": 3.7682, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315994950087234e-05, + "loss": 3.7602, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315157993216555e-05, + "loss": 3.7725, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314319398465503e-05, + "loss": 3.7649, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313480803714451e-05, + "loss": 3.7688, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312642208963399e-05, + "loss": 3.7802, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.31180525209272e-05, + "loss": 3.7529, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310966657341668e-05, + "loss": 3.7673, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310128062590616e-05, + "loss": 3.7685, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309289467839564e-05, + "loss": 3.7501, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308452510968885e-05, + "loss": 3.7727, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307613916217833e-05, + "loss": 3.7756, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306775321466781e-05, + "loss": 3.7683, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305936726715729e-05, + "loss": 3.7802, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3050997698450504e-05, + "loss": 3.7534, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042611750939984e-05, + "loss": 3.7509, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3034225803429464e-05, + "loss": 3.7632, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025839855918944e-05, + "loss": 3.7665, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301747028721215e-05, + "loss": 3.7668, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300908433970163e-05, + "loss": 3.7577, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300069839219111e-05, + "loss": 3.755, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299231244468059e-05, + "loss": 3.7691, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298395925477753e-05, + "loss": 3.754, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297557330726702e-05, + "loss": 3.7541, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.29671873597565e-05, + "loss": 3.7618, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295880141224598e-05, + "loss": 3.7748, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295041546473546e-05, + "loss": 3.7646, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294202951722494e-05, + "loss": 3.745, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293364356971442e-05, + "loss": 3.7528, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.29252576222039e-05, + "loss": 3.7602, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.2916888053497106e-05, + "loss": 3.7644, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.2908502105986586e-05, + "loss": 3.763, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.2900116158476066e-05, + "loss": 3.7577, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.2891730210965546e-05, + "loss": 3.7447, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.2883360642258755e-05, + "loss": 3.7539, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.2874974694748235e-05, + "loss": 3.7504, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.2866588747237715e-05, + "loss": 3.7558, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858202799727195e-05, + "loss": 3.7393, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284983323102041e-05, + "loss": 3.7707, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284146366231362e-05, + "loss": 3.7493, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.28330777148031e-05, + "loss": 3.7579, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282469176729258e-05, + "loss": 3.7464, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281630581978206e-05, + "loss": 3.7564, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280791987227154e-05, + "loss": 3.754, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279953392476102e-05, + "loss": 3.7483, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.27911479772505e-05, + "loss": 3.7585, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278276202973998e-05, + "loss": 3.7665, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277440883983692e-05, + "loss": 3.7506, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2766022892326405e-05, + "loss": 3.7613, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757636944815885e-05, + "loss": 3.7506, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2749250997305365e-05, + "loss": 3.7621, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.2740865049794845e-05, + "loss": 3.7429, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.2732479102284325e-05, + "loss": 3.7614, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.2724093154773805e-05, + "loss": 3.7452, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.2715707207263285e-05, + "loss": 3.7586, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.2707337638556494e-05, + "loss": 3.751, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.2698951691045974e-05, + "loss": 3.7521, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.2690565743535454e-05, + "loss": 3.7375, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268217979602493e-05, + "loss": 3.75, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267381022731814e-05, + "loss": 3.7506, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266542427980762e-05, + "loss": 3.7577, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.26570383322971e-05, + "loss": 3.7494, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264865238478658e-05, + "loss": 3.7594, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.26402828160798e-05, + "loss": 3.7438, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263189686856928e-05, + "loss": 3.7528, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262351092105876e-05, + "loss": 3.7586, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261512497354823e-05, + "loss": 3.7602, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260675540484145e-05, + "loss": 3.7506, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259836945733093e-05, + "loss": 3.7527, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.25899835098204e-05, + "loss": 3.7455, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258159756230988e-05, + "loss": 3.7652, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.2573227993603096e-05, + "loss": 3.743, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.2564842046092576e-05, + "loss": 3.756, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.2556456098582056e-05, + "loss": 3.745, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.2548070151071536e-05, + "loss": 3.7493, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253970058236475e-05, + "loss": 3.7614, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253131463485423e-05, + "loss": 3.7493, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.2522928687343705e-05, + "loss": 3.7501, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.2514542739833185e-05, + "loss": 3.7355, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.25061731711264e-05, + "loss": 3.7495, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.872626304626465, + "eval_runtime": 301.7778, + "eval_samples_per_second": 1264.477, + "eval_steps_per_second": 39.516, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2497787223615874e-05, + "loss": 3.7408, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2489401276105354e-05, + "loss": 3.7379, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2481015328594834e-05, + "loss": 3.7558, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472629381084314e-05, + "loss": 3.7527, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464243433573794e-05, + "loss": 3.7626, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245585748606328e-05, + "loss": 3.7433, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244747153855276e-05, + "loss": 3.7428, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243908559104224e-05, + "loss": 3.7417, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243071602233545e-05, + "loss": 3.7402, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242233007482493e-05, + "loss": 3.7516, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241394412731441e-05, + "loss": 3.7438, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240555817980389e-05, + "loss": 3.7498, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239720498990083e-05, + "loss": 3.7423, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238881904239031e-05, + "loss": 3.7359, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238043309487979e-05, + "loss": 3.7361, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237204714736927e-05, + "loss": 3.7331, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236366119985875e-05, + "loss": 3.7468, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355275252348234e-05, + "loss": 3.7425, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346889304837714e-05, + "loss": 3.7416, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.2338503357327194e-05, + "loss": 3.7582, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.23301337886204e-05, + "loss": 3.7524, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232174784110988e-05, + "loss": 3.739, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231336189359936e-05, + "loss": 3.7376, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230497594608884e-05, + "loss": 3.7448, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229660637738205e-05, + "loss": 3.739, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228822042987153e-05, + "loss": 3.7423, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227983448236101e-05, + "loss": 3.7412, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227144853485049e-05, + "loss": 3.7397, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.22630789661437e-05, + "loss": 3.7335, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225469301863319e-05, + "loss": 3.7298, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224630707112267e-05, + "loss": 3.7296, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223792112361215e-05, + "loss": 3.7393, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222955155490536e-05, + "loss": 3.7479, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222116560739484e-05, + "loss": 3.7456, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221277965988432e-05, + "loss": 3.728, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2204410091177526e-05, + "loss": 3.7397, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2196024143667006e-05, + "loss": 3.7423, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187638196156486e-05, + "loss": 3.7224, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2179252248645966e-05, + "loss": 3.7325, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170882679939175e-05, + "loss": 3.7315, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2162496732428655e-05, + "loss": 3.7239, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2154110784918135e-05, + "loss": 3.7442, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214572483740762e-05, + "loss": 3.7334, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213735526870083e-05, + "loss": 3.737, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212896932119031e-05, + "loss": 3.7338, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212058337367979e-05, + "loss": 3.7335, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211219742616927e-05, + "loss": 3.7413, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210382785746248e-05, + "loss": 3.7231, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209544190995196e-05, + "loss": 3.7014, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208705596244144e-05, + "loss": 3.7487, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207867001493092e-05, + "loss": 3.7287, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207030044622413e-05, + "loss": 3.7378, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206191449871361e-05, + "loss": 3.7245, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205352855120309e-05, + "loss": 3.7249, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045142603692575e-05, + "loss": 3.7176, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036773034985784e-05, + "loss": 3.73, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028387087475264e-05, + "loss": 3.7345, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2020001139964744e-05, + "loss": 3.7203, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011615192454224e-05, + "loss": 3.7411, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200324562374743e-05, + "loss": 3.7242, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199485967623691e-05, + "loss": 3.7128, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198647372872639e-05, + "loss": 3.7302, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197808778121587e-05, + "loss": 3.7152, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196971821250908e-05, + "loss": 3.7092, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196133226499856e-05, + "loss": 3.7365, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195294631748804e-05, + "loss": 3.7333, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194456036997753e-05, + "loss": 3.7203, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193619080127074e-05, + "loss": 3.7253, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192780485376022e-05, + "loss": 3.7122, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191943528505343e-05, + "loss": 3.7282, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191104933754291e-05, + "loss": 3.7261, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190266339003239e-05, + "loss": 3.7303, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189427744252187e-05, + "loss": 3.7261, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188589149501135e-05, + "loss": 3.7304, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187750554750083e-05, + "loss": 3.7426, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.18691195999903e-05, + "loss": 3.7146, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186073365247978e-05, + "loss": 3.7316, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185238046257673e-05, + "loss": 3.7255, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184399451506621e-05, + "loss": 3.7153, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183560856755569e-05, + "loss": 3.7336, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182722262004517e-05, + "loss": 3.7394, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181883667253465e-05, + "loss": 3.7282, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181045072502413e-05, + "loss": 3.7422, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1802064777513605e-05, + "loss": 3.7163, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793678830003085e-05, + "loss": 3.715, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.17853092612963e-05, + "loss": 3.7244, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776923313785774e-05, + "loss": 3.7328, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1768537366275254e-05, + "loss": 3.7201, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760151418764734e-05, + "loss": 3.7242, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175178185005795e-05, + "loss": 3.7211, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174339590254743e-05, + "loss": 3.7299, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173500995503691e-05, + "loss": 3.717, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172662400752639e-05, + "loss": 3.718, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1718254438819605e-05, + "loss": 3.7247, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170986849130908e-05, + "loss": 3.7375, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170148254379856e-05, + "loss": 3.7263, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169309659628804e-05, + "loss": 3.7066, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168472702758125e-05, + "loss": 3.7202, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167634108007073e-05, + "loss": 3.7198, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166795513256021e-05, + "loss": 3.729, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165956918504969e-05, + "loss": 3.7235, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.16511996163429e-05, + "loss": 3.7203, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164281366883238e-05, + "loss": 3.7101, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163442772132186e-05, + "loss": 3.713, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162604177381134e-05, + "loss": 3.7214, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161767220510455e-05, + "loss": 3.7156, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160928625759403e-05, + "loss": 3.7038, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160090031008351e-05, + "loss": 3.7344, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159253074137672e-05, + "loss": 3.7123, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.15841447938662e-05, + "loss": 3.7178, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157575884635568e-05, + "loss": 3.7123, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156737289884516e-05, + "loss": 3.7179, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155898695133464e-05, + "loss": 3.7199, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155060100382413e-05, + "loss": 3.7124, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154221505631361e-05, + "loss": 3.722, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153382910880309e-05, + "loss": 3.7244, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.1525475918900026e-05, + "loss": 3.7199, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.1517089971389506e-05, + "loss": 3.7248, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.1508704023878986e-05, + "loss": 3.7132, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1500318076368466e-05, + "loss": 3.7239, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.1491932128857946e-05, + "loss": 3.7095, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1483546181347426e-05, + "loss": 3.7235, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1475160233836906e-05, + "loss": 3.7098, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466774286326386e-05, + "loss": 3.7221, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458404717619595e-05, + "loss": 3.7188, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.145001877010908e-05, + "loss": 3.7158, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144163282259856e-05, + "loss": 3.7049, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143324687508804e-05, + "loss": 3.7113, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142487730638125e-05, + "loss": 3.7106, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141649135887073e-05, + "loss": 3.7234, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140810541136021e-05, + "loss": 3.7105, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139971946384969e-05, + "loss": 3.7253, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.13913498951429e-05, + "loss": 3.7052, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138296394763238e-05, + "loss": 3.7186, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137457800012186e-05, + "loss": 3.7221, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136619205261134e-05, + "loss": 3.7247, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135782248390455e-05, + "loss": 3.7177, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349436536394035e-05, + "loss": 3.7167, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1341050588883515e-05, + "loss": 3.709, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1332664641372995e-05, + "loss": 3.7287, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324295072666204e-05, + "loss": 3.706, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315909125155684e-05, + "loss": 3.7195, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307523177645164e-05, + "loss": 3.7099, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1299137230134644e-05, + "loss": 3.7198, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129076766142785e-05, + "loss": 3.7172, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128238171391733e-05, + "loss": 3.7131, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127399576640681e-05, + "loss": 3.7151, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126560981889629e-05, + "loss": 3.7022, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125722387138577e-05, + "loss": 3.7173, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.8620269298553467, + "eval_runtime": 321.06, + "eval_samples_per_second": 1188.535, + "eval_steps_per_second": 37.143, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124883792387525e-05, + "loss": 3.7069, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.124045197636473e-05, + "loss": 3.7011, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123206602885421e-05, + "loss": 3.7186, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122369646014743e-05, + "loss": 3.7164, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121531051263691e-05, + "loss": 3.727, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120692456512638e-05, + "loss": 3.7115, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119853861761586e-05, + "loss": 3.7082, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119016904890908e-05, + "loss": 3.707, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118178310139856e-05, + "loss": 3.7046, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117339715388803e-05, + "loss": 3.7156, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116501120637751e-05, + "loss": 3.7066, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1156641637670727e-05, + "loss": 3.7144, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1148272068963936e-05, + "loss": 3.7137, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113988612145342e-05, + "loss": 3.6999, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.11315001739429e-05, + "loss": 3.6968, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112311422643238e-05, + "loss": 3.6998, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.1114728278921855e-05, + "loss": 3.7144, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.1106342331411335e-05, + "loss": 3.7094, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.1097956383900815e-05, + "loss": 3.7031, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.1089570436390295e-05, + "loss": 3.7245, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.1081200867683504e-05, + "loss": 3.7174, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.1072814920172984e-05, + "loss": 3.7076, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.1064428972662464e-05, + "loss": 3.7062, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1056043025151944e-05, + "loss": 3.7032, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104767345644516e-05, + "loss": 3.7071, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103928750893464e-05, + "loss": 3.7068, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103090156142412e-05, + "loss": 3.7075, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.10225156139136e-05, + "loss": 3.7093, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101414604520681e-05, + "loss": 3.6991, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100576009769629e-05, + "loss": 3.6958, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099737415018577e-05, + "loss": 3.692, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098898820267525e-05, + "loss": 3.7081, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.098061863396846e-05, + "loss": 3.7141, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097223268645794e-05, + "loss": 3.7098, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096384673894742e-05, + "loss": 3.6993, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.09554607914369e-05, + "loss": 3.6973, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0947091222730114e-05, + "loss": 3.71, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0938705275219594e-05, + "loss": 3.6944, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930319327709074e-05, + "loss": 3.6942, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092194975900228e-05, + "loss": 3.6992, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091356381149176e-05, + "loss": 3.6932, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090517786398124e-05, + "loss": 3.7063, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089679191647072e-05, + "loss": 3.7025, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088842234776393e-05, + "loss": 3.7048, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.088003640025341e-05, + "loss": 3.6973, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087165045274289e-05, + "loss": 3.7024, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086326450523237e-05, + "loss": 3.7059, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085489493652558e-05, + "loss": 3.6915, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084650898901507e-05, + "loss": 3.6699, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083812304150455e-05, + "loss": 3.713, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082973709399403e-05, + "loss": 3.6964, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.0821367525287237e-05, + "loss": 3.7054, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.0812981577776716e-05, + "loss": 3.6913, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.0804595630266196e-05, + "loss": 3.6943, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.0796209682755676e-05, + "loss": 3.6806, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.0787840114048885e-05, + "loss": 3.6965, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.0779454166538365e-05, + "loss": 3.7047, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0771068219027845e-05, + "loss": 3.6866, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0762682271517325e-05, + "loss": 3.7122, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0754312702810534e-05, + "loss": 3.6918, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074592675530002e-05, + "loss": 3.6798, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.07375408077895e-05, + "loss": 3.695, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072915486027898e-05, + "loss": 3.6847, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072078529157219e-05, + "loss": 3.68, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071239934406167e-05, + "loss": 3.702, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070401339655115e-05, + "loss": 3.701, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069562744904063e-05, + "loss": 3.6873, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068725788033384e-05, + "loss": 3.6953, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067887193282332e-05, + "loss": 3.6763, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067050236411653e-05, + "loss": 3.6987, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066211641660601e-05, + "loss": 3.6904, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065373046909549e-05, + "loss": 3.696, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.0645344521584975e-05, + "loss": 3.6999, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636958574074455e-05, + "loss": 3.6928, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0628572626563935e-05, + "loss": 3.7114, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620186679053415e-05, + "loss": 3.6826, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611800731542895e-05, + "loss": 3.6983, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0603431162836104e-05, + "loss": 3.6923, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0595045215325584e-05, + "loss": 3.6833, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0586659267815064e-05, + "loss": 3.6996, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578273320304544e-05, + "loss": 3.7054, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056990375159775e-05, + "loss": 3.6984, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056151780408723e-05, + "loss": 3.7094, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055313185657671e-05, + "loss": 3.6857, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054476228786993e-05, + "loss": 3.6803, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053637634035941e-05, + "loss": 3.6915, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052799039284889e-05, + "loss": 3.7038, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051960444533837e-05, + "loss": 3.6865, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051123487663158e-05, + "loss": 3.6957, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050284892912106e-05, + "loss": 3.6873, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049446298161054e-05, + "loss": 3.6978, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048607703410002e-05, + "loss": 3.6886, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.0477707465393226e-05, + "loss": 3.6836, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.0469321517882706e-05, + "loss": 3.6928, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.0460935570372186e-05, + "loss": 3.7051, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.0452549622861666e-05, + "loss": 3.6944, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.0444180054154875e-05, + "loss": 3.6735, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043579410664436e-05, + "loss": 3.6866, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042740815913384e-05, + "loss": 3.6873, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041902221162332e-05, + "loss": 3.6997, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.041065264291653e-05, + "loss": 3.6951, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040226669540601e-05, + "loss": 3.6871, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039388074789549e-05, + "loss": 3.6805, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038549480038497e-05, + "loss": 3.6796, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037712523167818e-05, + "loss": 3.6902, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036873928416766e-05, + "loss": 3.6832, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036035333665714e-05, + "loss": 3.675, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035196738914662e-05, + "loss": 3.6985, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0343614199243565e-05, + "loss": 3.6849, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.0335228251733045e-05, + "loss": 3.6837, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.0326842304222525e-05, + "loss": 3.6852, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0318456356712005e-05, + "loss": 3.6824, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.0310070409201485e-05, + "loss": 3.691, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0301684461690965e-05, + "loss": 3.6818, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0293298514180445e-05, + "loss": 3.693, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284912566669925e-05, + "loss": 3.6954, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0276542997963134e-05, + "loss": 3.686, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026817342925634e-05, + "loss": 3.6936, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025978748174582e-05, + "loss": 3.6818, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.02514015342353e-05, + "loss": 3.6963, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024301558672478e-05, + "loss": 3.6802, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023462963921427e-05, + "loss": 3.6863, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022624369170375e-05, + "loss": 3.6817, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021785774419323e-05, + "loss": 3.6936, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020948817548644e-05, + "loss": 3.6914, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020110222797592e-05, + "loss": 3.6826, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.01927162804654e-05, + "loss": 3.669, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018433033295488e-05, + "loss": 3.6853, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017596076424809e-05, + "loss": 3.6802, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016757481673757e-05, + "loss": 3.6886, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015918886922705e-05, + "loss": 3.6831, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015080292171653e-05, + "loss": 3.6934, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.0142433353009736e-05, + "loss": 3.6741, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013404740549922e-05, + "loss": 3.6933, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.01256614579887e-05, + "loss": 3.6896, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011727551047818e-05, + "loss": 3.6968, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010890594177139e-05, + "loss": 3.6859, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010051999426087e-05, + "loss": 3.6829, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009213404675035e-05, + "loss": 3.682, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008376447804356e-05, + "loss": 3.6983, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007537853053304e-05, + "loss": 3.6756, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006699258302252e-05, + "loss": 3.6885, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.0058606635512e-05, + "loss": 3.685, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.0050220688001474e-05, + "loss": 3.6853, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004185111929469e-05, + "loss": 3.686, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003346517178418e-05, + "loss": 3.6861, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002507922427366e-05, + "loss": 3.6825, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001669327676313e-05, + "loss": 3.6735, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000830732925261e-05, + "loss": 3.6848, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.8553621768951416, + "eval_runtime": 305.6215, + "eval_samples_per_second": 1248.574, + "eval_steps_per_second": 39.019, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999992138174209e-05, + "loss": 3.6742, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999153543423157e-05, + "loss": 3.6739, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998314948672105e-05, + "loss": 3.6873, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997476353921053e-05, + "loss": 3.6868, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996637759170001e-05, + "loss": 3.7, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995799164418949e-05, + "loss": 3.6776, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994960569667897e-05, + "loss": 3.6796, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994121974916845e-05, + "loss": 3.6803, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993285018046166e-05, + "loss": 3.6735, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.9924464232951145e-05, + "loss": 3.6887, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.9916078285440625e-05, + "loss": 3.676, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.9907692337930105e-05, + "loss": 3.6817, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9899339148027044e-05, + "loss": 3.6906, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890953200516523e-05, + "loss": 3.665, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882567253006003e-05, + "loss": 3.6679, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987418130549548e-05, + "loss": 3.6698, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986579535798496e-05, + "loss": 3.6881, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985740941047444e-05, + "loss": 3.6779, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984902346296392e-05, + "loss": 3.6744, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.98406375154534e-05, + "loss": 3.6923, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983226794674661e-05, + "loss": 3.6878, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.98238819992361e-05, + "loss": 3.6762, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981549605172558e-05, + "loss": 3.6784, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980711010421506e-05, + "loss": 3.6749, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979874053550827e-05, + "loss": 3.68, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979035458799775e-05, + "loss": 3.6752, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978196864048723e-05, + "loss": 3.6756, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977358269297671e-05, + "loss": 3.6839, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976521312426992e-05, + "loss": 3.6669, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.97568271767594e-05, + "loss": 3.666, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974844122924888e-05, + "loss": 3.67, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.974005528173836e-05, + "loss": 3.6732, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.9731685713031566e-05, + "loss": 3.6792, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.9723299765521046e-05, + "loss": 3.6878, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971491381801053e-05, + "loss": 3.6689, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970652787050001e-05, + "loss": 3.6721, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969815830179322e-05, + "loss": 3.6832, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.96897723542827e-05, + "loss": 3.6635, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968138640677218e-05, + "loss": 3.6642, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967301683806539e-05, + "loss": 3.6728, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966463089055487e-05, + "loss": 3.6618, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965624494304435e-05, + "loss": 3.6729, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964785899553383e-05, + "loss": 3.6752, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963948942682704e-05, + "loss": 3.6775, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963110347931652e-05, + "loss": 3.6664, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9622717531806e-05, + "loss": 3.6787, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9614331584295486e-05, + "loss": 3.6755, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.9605962015588695e-05, + "loss": 3.6666, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9597576068078175e-05, + "loss": 3.6435, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.9589190120567655e-05, + "loss": 3.6819, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.9580804173057135e-05, + "loss": 3.6643, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.9572434604350344e-05, + "loss": 3.6767, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.9564048656839824e-05, + "loss": 3.6658, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9555662709329304e-05, + "loss": 3.6601, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954729314062251e-05, + "loss": 3.6574, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953890719311199e-05, + "loss": 3.6643, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953052124560147e-05, + "loss": 3.6797, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952213529809095e-05, + "loss": 3.6542, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951374935058043e-05, + "loss": 3.6845, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950536340306991e-05, + "loss": 3.6655, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949697745555939e-05, + "loss": 3.6499, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948859150804887e-05, + "loss": 3.6687, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.948022193934208e-05, + "loss": 3.6569, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947183599183156e-05, + "loss": 3.6543, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946345004432104e-05, + "loss": 3.6694, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945506409681052e-05, + "loss": 3.6748, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944669452810373e-05, + "loss": 3.655, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943830858059321e-05, + "loss": 3.6718, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942992263308269e-05, + "loss": 3.6468, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942155306437591e-05, + "loss": 3.6686, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941316711686539e-05, + "loss": 3.6659, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940478116935487e-05, + "loss": 3.6647, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939639522184435e-05, + "loss": 3.673, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938800927433383e-05, + "loss": 3.6673, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937962332682331e-05, + "loss": 3.6831, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937123737931279e-05, + "loss": 3.6554, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.9362851431802267e-05, + "loss": 3.6697, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.9354498241899205e-05, + "loss": 3.6636, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9346112294388685e-05, + "loss": 3.6568, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9337726346878165e-05, + "loss": 3.6733, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329340399367645e-05, + "loss": 3.6723, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932095445185713e-05, + "loss": 3.6743, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931256850434661e-05, + "loss": 3.6827, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930418255683609e-05, + "loss": 3.6606, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929579660932557e-05, + "loss": 3.6535, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928742704061878e-05, + "loss": 3.662, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927904109310826e-05, + "loss": 3.6754, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927065514559774e-05, + "loss": 3.659, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926226919808722e-05, + "loss": 3.6655, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925389962938043e-05, + "loss": 3.6648, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924551368186991e-05, + "loss": 3.6659, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923712773435939e-05, + "loss": 3.6632, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.92287581656526e-05, + "loss": 3.6568, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9220372218142085e-05, + "loss": 3.6666, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211986270631565e-05, + "loss": 3.6763, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9203600323121045e-05, + "loss": 3.6681, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9195214375610525e-05, + "loss": 3.6507, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.9186844806903734e-05, + "loss": 3.6594, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178458859393214e-05, + "loss": 3.6615, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9170072911882694e-05, + "loss": 3.6686, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161686964372174e-05, + "loss": 3.6699, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9153301016861654e-05, + "loss": 3.6586, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144915069351134e-05, + "loss": 3.6555, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9136529121840614e-05, + "loss": 3.6495, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912814317433009e-05, + "loss": 3.6611, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.91197736056233e-05, + "loss": 3.6575, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911138765811278e-05, + "loss": 3.6497, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910300171060226e-05, + "loss": 3.6679, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909461576309174e-05, + "loss": 3.6565, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908622981558122e-05, + "loss": 3.6589, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.90778438680707e-05, + "loss": 3.6533, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906947429936392e-05, + "loss": 3.6525, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906108835185339e-05, + "loss": 3.6655, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905270240434287e-05, + "loss": 3.6526, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904431645683235e-05, + "loss": 3.6651, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903593050932183e-05, + "loss": 3.6676, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902754456181131e-05, + "loss": 3.6605, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901917499310452e-05, + "loss": 3.6658, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010789045594e-05, + "loss": 3.656, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900240309808349e-05, + "loss": 3.6682, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899401715057297e-05, + "loss": 3.6559, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898563120306245e-05, + "loss": 3.6609, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897724525555193e-05, + "loss": 3.6565, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896885930804141e-05, + "loss": 3.6627, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8960489739334616e-05, + "loss": 3.6683, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8952103791824096e-05, + "loss": 3.6533, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8943717844313576e-05, + "loss": 3.6446, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8935331896803056e-05, + "loss": 3.6542, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8926962328096265e-05, + "loss": 3.6561, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.8918576380585745e-05, + "loss": 3.6631, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.8910190433075225e-05, + "loss": 3.6553, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.8901804485564705e-05, + "loss": 3.6655, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889343491685792e-05, + "loss": 3.6476, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.88850489693474e-05, + "loss": 3.6728, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887666302183688e-05, + "loss": 3.6582, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886827707432636e-05, + "loss": 3.666, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885990750561957e-05, + "loss": 3.6595, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885152155810905e-05, + "loss": 3.6559, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884313561059853e-05, + "loss": 3.6535, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883476604189174e-05, + "loss": 3.6729, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882638009438122e-05, + "loss": 3.6489, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.88179941468707e-05, + "loss": 3.6632, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880960819936018e-05, + "loss": 3.6566, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880122225184966e-05, + "loss": 3.6589, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792852683142875e-05, + "loss": 3.6603, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8784466735632355e-05, + "loss": 3.66, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8776080788121834e-05, + "loss": 3.6548, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.8767694840611314e-05, + "loss": 3.6546, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8759308893100794e-05, + "loss": 3.656, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.851210594177246, + "eval_runtime": 303.2293, + "eval_samples_per_second": 1258.424, + "eval_steps_per_second": 39.327, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750922945590274e-05, + "loss": 3.6472, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742536998079754e-05, + "loss": 3.6456, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873415105056923e-05, + "loss": 3.6576, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872578148186244e-05, + "loss": 3.664, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871739553435192e-05, + "loss": 3.6729, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.8709009586841397e-05, + "loss": 3.6484, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870064001813461e-05, + "loss": 3.6533, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869225407062409e-05, + "loss": 3.6557, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868386812311358e-05, + "loss": 3.6465, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867548217560305e-05, + "loss": 3.6625, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866709622809253e-05, + "loss": 3.6494, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865872665938575e-05, + "loss": 3.6551, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865035709067896e-05, + "loss": 3.667, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864197114316844e-05, + "loss": 3.6399, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863358519565792e-05, + "loss": 3.6402, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.86251992481474e-05, + "loss": 3.6447, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861681330063687e-05, + "loss": 3.66, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860842735312635e-05, + "loss": 3.6579, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.860004140561583e-05, + "loss": 3.644, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859165545810532e-05, + "loss": 3.6645, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.8583285889398526e-05, + "loss": 3.664, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.8574899941888006e-05, + "loss": 3.6518, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8566513994377486e-05, + "loss": 3.6531, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.8558128046866966e-05, + "loss": 3.6515, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8549742099356446e-05, + "loss": 3.6538, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.8541356151845926e-05, + "loss": 3.6502, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.8532970204335406e-05, + "loss": 3.6481, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.8524584256824886e-05, + "loss": 3.6574, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.8516214688118095e-05, + "loss": 3.6444, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8507828740607575e-05, + "loss": 3.6396, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.8499442793097055e-05, + "loss": 3.6453, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.8491056845586535e-05, + "loss": 3.6493, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848268727687975e-05, + "loss": 3.65, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847430132936923e-05, + "loss": 3.6646, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846591538185871e-05, + "loss": 3.6457, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845752943434819e-05, + "loss": 3.643, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.84491598656414e-05, + "loss": 3.6615, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.844077391813088e-05, + "loss": 3.6335, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843238797062036e-05, + "loss": 3.6429, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842400202310984e-05, + "loss": 3.6472, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841563245440305e-05, + "loss": 3.6379, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840724650689253e-05, + "loss": 3.644, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839886055938201e-05, + "loss": 3.6519, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839047461187149e-05, + "loss": 3.6527, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8382105043164704e-05, + "loss": 3.6406, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8373719095654184e-05, + "loss": 3.6526, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8365333148143664e-05, + "loss": 3.6488, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356947200633144e-05, + "loss": 3.6411, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834857763192635e-05, + "loss": 3.6225, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.834019168441583e-05, + "loss": 3.6528, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833180573690531e-05, + "loss": 3.6407, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832341978939479e-05, + "loss": 3.6572, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.8315050220688e-05, + "loss": 3.6352, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830666427317748e-05, + "loss": 3.6373, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829829470447069e-05, + "loss": 3.6325, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828990875696017e-05, + "loss": 3.6377, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828152280944966e-05, + "loss": 3.6568, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827313686193914e-05, + "loss": 3.6319, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826475091442862e-05, + "loss": 3.658, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.82563649669181e-05, + "loss": 3.643, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824797901940758e-05, + "loss": 3.6259, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823959307189706e-05, + "loss": 3.64, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823122350319027e-05, + "loss": 3.6291, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822283755567975e-05, + "loss": 3.6343, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.8214451608169227e-05, + "loss": 3.642, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8206082039462436e-05, + "loss": 3.6506, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8197696091951916e-05, + "loss": 3.631, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8189310144441396e-05, + "loss": 3.6462, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180924196930876e-05, + "loss": 3.6229, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817255462822409e-05, + "loss": 3.6434, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816416868071357e-05, + "loss": 3.6414, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815578273320305e-05, + "loss": 3.6441, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814739678569253e-05, + "loss": 3.6428, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8139010838182004e-05, + "loss": 3.6424, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.8130624890671484e-05, + "loss": 3.6592, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.8122238943160964e-05, + "loss": 3.6312, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.8113852995650444e-05, + "loss": 3.646, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.8105483426943653e-05, + "loss": 3.6394, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.8097097479433133e-05, + "loss": 3.6306, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808871153192261e-05, + "loss": 3.6464, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808034196321583e-05, + "loss": 3.6502, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807195601570531e-05, + "loss": 3.6485, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806357006819479e-05, + "loss": 3.6599, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805518412068427e-05, + "loss": 3.6374, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804679817317375e-05, + "loss": 3.6268, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803841222566323e-05, + "loss": 3.6366, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.803002627815271e-05, + "loss": 3.6497, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802164033064219e-05, + "loss": 3.6357, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801328714073913e-05, + "loss": 3.6419, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800490119322861e-05, + "loss": 3.6386, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799651524571809e-05, + "loss": 3.644, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798812929820757e-05, + "loss": 3.6398, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797974335069705e-05, + "loss": 3.6315, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.7971357403186534e-05, + "loss": 3.6403, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7962971455676014e-05, + "loss": 3.6538, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7954585508165494e-05, + "loss": 3.6455, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.79462159394587e-05, + "loss": 3.6223, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793782999194818e-05, + "loss": 3.6364, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792944404443766e-05, + "loss": 3.637, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792105809692714e-05, + "loss": 3.6453, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791268852822035e-05, + "loss": 3.6466, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790431895951356e-05, + "loss": 3.634, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789593301200304e-05, + "loss": 3.6324, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788754706449252e-05, + "loss": 3.6266, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7879161116982e-05, + "loss": 3.6398, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787077516947149e-05, + "loss": 3.6323, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786238922196097e-05, + "loss": 3.6301, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785400327445045e-05, + "loss": 3.6373, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784561732693993e-05, + "loss": 3.6371, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.7837247758233136e-05, + "loss": 3.6334, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.7828861810722616e-05, + "loss": 3.6314, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.7820475863212096e-05, + "loss": 3.6285, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.7812089915701576e-05, + "loss": 3.6443, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.7803703968191056e-05, + "loss": 3.6244, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.7795318020680536e-05, + "loss": 3.6426, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.7786932073170016e-05, + "loss": 3.6458, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7778562504463225e-05, + "loss": 3.6358, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777019293575644e-05, + "loss": 3.6418, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776180698824592e-05, + "loss": 3.6357, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.77534210407354e-05, + "loss": 3.643, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774503509322488e-05, + "loss": 3.6339, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773664914571436e-05, + "loss": 3.6337, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772826319820384e-05, + "loss": 3.6354, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719877250693314e-05, + "loss": 3.6363, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771150768198653e-05, + "loss": 3.6401, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770312173447601e-05, + "loss": 3.6333, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769473578696549e-05, + "loss": 3.6216, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768634983945496e-05, + "loss": 3.6327, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767798027074818e-05, + "loss": 3.6263, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766959432323766e-05, + "loss": 3.6422, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766120837572714e-05, + "loss": 3.6333, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765282242821662e-05, + "loss": 3.6411, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.7644452859509835e-05, + "loss": 3.6244, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.7636066911999315e-05, + "loss": 3.6468, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762768096448879e-05, + "loss": 3.6343, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761929501697827e-05, + "loss": 3.6494, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.761090906946775e-05, + "loss": 3.6355, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760252312195723e-05, + "loss": 3.6335, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759413717444671e-05, + "loss": 3.6271, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758576760573992e-05, + "loss": 3.6523, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7577381658229397e-05, + "loss": 3.6239, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568995710718877e-05, + "loss": 3.6423, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.7560609763208356e-05, + "loss": 3.6325, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755222381569784e-05, + "loss": 3.6345, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754385424699105e-05, + "loss": 3.6391, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753546829948053e-05, + "loss": 3.6326, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752708235197001e-05, + "loss": 3.6319, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751869640445949e-05, + "loss": 3.6342, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751031045694897e-05, + "loss": 3.6306, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.8475914001464844, + "eval_runtime": 303.1576, + "eval_samples_per_second": 1258.721, + "eval_steps_per_second": 39.336, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750192450943845e-05, + "loss": 3.6184, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749353856192793e-05, + "loss": 3.6235, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748515261441741e-05, + "loss": 3.6361, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747676666690689e-05, + "loss": 3.6403, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746838071939637e-05, + "loss": 3.6505, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459994771885845e-05, + "loss": 3.626, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745162520317906e-05, + "loss": 3.6285, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744323925566854e-05, + "loss": 3.6355, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743485330815803e-05, + "loss": 3.623, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.74264673606475e-05, + "loss": 3.6325, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741809779194072e-05, + "loss": 3.6325, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.74097118444302e-05, + "loss": 3.6334, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.7401342275723406e-05, + "loss": 3.6443, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7392956328212886e-05, + "loss": 3.6179, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.7384570380702366e-05, + "loss": 3.6173, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.7376184433191846e-05, + "loss": 3.6178, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736779848568132e-05, + "loss": 3.6415, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.73594125381708e-05, + "loss": 3.6317, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735102659066028e-05, + "loss": 3.6207, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7342640643149765e-05, + "loss": 3.6397, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7334271074442975e-05, + "loss": 3.642, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7325885126932455e-05, + "loss": 3.6289, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7317499179421934e-05, + "loss": 3.629, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7309113231911414e-05, + "loss": 3.6272, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.7300727284400894e-05, + "loss": 3.6354, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.7292341336890374e-05, + "loss": 3.6269, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7283955389379854e-05, + "loss": 3.6215, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7275569441869334e-05, + "loss": 3.6347, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726719987316254e-05, + "loss": 3.6208, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725881392565202e-05, + "loss": 3.6127, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.72504279781415e-05, + "loss": 3.627, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724204203063098e-05, + "loss": 3.6246, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.72336724619242e-05, + "loss": 3.6302, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722528651441368e-05, + "loss": 3.6424, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721690056690316e-05, + "loss": 3.6194, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720853099819637e-05, + "loss": 3.6243, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.720014505068585e-05, + "loss": 3.6398, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719175910317533e-05, + "loss": 3.6099, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718337315566481e-05, + "loss": 3.6198, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717498720815429e-05, + "loss": 3.6246, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716660126064377e-05, + "loss": 3.6162, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715821531313325e-05, + "loss": 3.6233, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714982936562273e-05, + "loss": 3.6279, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714145979691594e-05, + "loss": 3.6321, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713307384940542e-05, + "loss": 3.6206, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712470428069863e-05, + "loss": 3.6237, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711631833318811e-05, + "loss": 3.6258, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710793238567759e-05, + "loss": 3.6197, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709954643816707e-05, + "loss": 3.6007, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709117686946028e-05, + "loss": 3.6303, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708279092194976e-05, + "loss": 3.6221, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707440497443924e-05, + "loss": 3.6308, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706601902692872e-05, + "loss": 3.6202, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.70576330794182e-05, + "loss": 3.6089, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704926351071141e-05, + "loss": 3.6125, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704087756320089e-05, + "loss": 3.6157, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703249161569037e-05, + "loss": 3.6308, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702410566817985e-05, + "loss": 3.6101, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701571972066934e-05, + "loss": 3.6312, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700733377315881e-05, + "loss": 3.6244, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699894782564829e-05, + "loss": 3.6023, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699056187813777e-05, + "loss": 3.62, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6982192309430986e-05, + "loss": 3.6041, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697380636192046e-05, + "loss": 3.6109, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696542041440994e-05, + "loss": 3.6154, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6957050845703155e-05, + "loss": 3.6307, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694866489819263e-05, + "loss": 3.61, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694027895068211e-05, + "loss": 3.6221, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693189300317159e-05, + "loss": 3.6032, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923523434464804e-05, + "loss": 3.6209, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.6915137486954284e-05, + "loss": 3.6191, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6906751539443764e-05, + "loss": 3.6217, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.6898365591933244e-05, + "loss": 3.6188, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688999602322646e-05, + "loss": 3.6183, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688161007571593e-05, + "loss": 3.6374, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687322412820541e-05, + "loss": 3.6099, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686483818069489e-05, + "loss": 3.6194, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.68564686119881e-05, + "loss": 3.6183, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684808266447758e-05, + "loss": 3.6131, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683969671696706e-05, + "loss": 3.6256, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683131076945654e-05, + "loss": 3.6238, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682292482194603e-05, + "loss": 3.627, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681455525323924e-05, + "loss": 3.6353, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680616930572872e-05, + "loss": 3.624, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.67977833582182e-05, + "loss": 3.6015, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678939741070768e-05, + "loss": 3.6122, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678101146319716e-05, + "loss": 3.627, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677262551568664e-05, + "loss": 3.6166, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676425594697985e-05, + "loss": 3.6192, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6755869999469327e-05, + "loss": 3.6166, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6747484051958807e-05, + "loss": 3.6202, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6739098104448286e-05, + "loss": 3.617, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6730712156937766e-05, + "loss": 3.6104, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6722326209427246e-05, + "loss": 3.6226, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6713940261916726e-05, + "loss": 3.6282, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670557069320994e-05, + "loss": 3.624, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669718474569942e-05, + "loss": 3.6017, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.66887987981889e-05, + "loss": 3.6143, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668041285067838e-05, + "loss": 3.6181, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667202690316786e-05, + "loss": 3.622, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666364095565734e-05, + "loss": 3.6247, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665527138695055e-05, + "loss": 3.6118, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664688543944003e-05, + "loss": 3.6093, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663849949192951e-05, + "loss": 3.6053, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.663011354441899e-05, + "loss": 3.6152, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6621727596908464e-05, + "loss": 3.612, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661335802820168e-05, + "loss": 3.6075, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660497208069116e-05, + "loss": 3.6198, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659658613318065e-05, + "loss": 3.6121, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658820018567012e-05, + "loss": 3.6113, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.65798142381596e-05, + "loss": 3.6115, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6571444669452816e-05, + "loss": 3.6047, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656305872194229e-05, + "loss": 3.6206, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655467277443177e-05, + "loss": 3.6076, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654628682692125e-05, + "loss": 3.6154, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653790087941073e-05, + "loss": 3.6221, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652951493190021e-05, + "loss": 3.6166, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652112898438969e-05, + "loss": 3.6187, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651274303687917e-05, + "loss": 3.6163, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.6504373468172384e-05, + "loss": 3.6201, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.6496003899465594e-05, + "loss": 3.6193, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.6487617951955074e-05, + "loss": 3.6103, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6479232004444554e-05, + "loss": 3.6116, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6470846056934033e-05, + "loss": 3.6146, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6462460109423513e-05, + "loss": 3.6202, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645407416191299e-05, + "loss": 3.6102, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644568821440247e-05, + "loss": 3.6003, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643731864569568e-05, + "loss": 3.6096, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642893269818516e-05, + "loss": 3.6051, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642054675067464e-05, + "loss": 3.6193, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641216080316412e-05, + "loss": 3.6102, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.64037748556536e-05, + "loss": 3.6205, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639540528694682e-05, + "loss": 3.6062, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.63870193394363e-05, + "loss": 3.6209, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637863339192578e-05, + "loss": 3.6124, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637024744441526e-05, + "loss": 3.6282, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636186149690474e-05, + "loss": 3.6142, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635347554939422e-05, + "loss": 3.6128, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.63450896018837e-05, + "loss": 3.6096, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633672003317691e-05, + "loss": 3.6263, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632833408566639e-05, + "loss": 3.6047, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631994813815587e-05, + "loss": 3.6165, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631156219064535e-05, + "loss": 3.613, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630317624313483e-05, + "loss": 3.6124, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6294806674428036e-05, + "loss": 3.6165, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628642072691752e-05, + "loss": 3.6149, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6278034779407e-05, + "loss": 3.6114, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6269648831896476e-05, + "loss": 3.6154, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626127926318969e-05, + "loss": 3.6077, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8454489707946777, + "eval_runtime": 305.9497, + "eval_samples_per_second": 1247.234, + "eval_steps_per_second": 38.977, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625289331567917e-05, + "loss": 3.602, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624450736816865e-05, + "loss": 3.6013, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6236121420658125e-05, + "loss": 3.6151, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.6227735473147605e-05, + "loss": 3.6198, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.6219349525637085e-05, + "loss": 3.6277, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.62109799569303e-05, + "loss": 3.6042, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.6202594009419774e-05, + "loss": 3.6093, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619420806190926e-05, + "loss": 3.6143, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618582211439874e-05, + "loss": 3.6039, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617745254569195e-05, + "loss": 3.6051, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616906659818143e-05, + "loss": 3.6162, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616068065067091e-05, + "loss": 3.6104, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6152311081964125e-05, + "loss": 3.6245, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.61439251344536e-05, + "loss": 3.5969, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613553918694308e-05, + "loss": 3.5955, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612715323943256e-05, + "loss": 3.5982, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611876729192204e-05, + "loss": 3.6178, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611038134441152e-05, + "loss": 3.6137, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.6101995396901e-05, + "loss": 3.6001, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609360944939048e-05, + "loss": 3.6165, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.6085239880683694e-05, + "loss": 3.6227, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.6076853933173174e-05, + "loss": 3.606, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6068467985662654e-05, + "loss": 3.6106, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.6060082038152134e-05, + "loss": 3.6072, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051696090641614e-05, + "loss": 3.6176, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.6043310143131094e-05, + "loss": 3.6013, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6034924195620574e-05, + "loss": 3.6017, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6026538248110054e-05, + "loss": 3.6196, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601816867940326e-05, + "loss": 3.597, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600978273189274e-05, + "loss": 3.5952, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600141316318595e-05, + "loss": 3.6017, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599302721567543e-05, + "loss": 3.6027, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598464126816491e-05, + "loss": 3.6137, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597625532065439e-05, + "loss": 3.6202, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596786937314388e-05, + "loss": 3.5952, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595948342563336e-05, + "loss": 3.6056, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595111385692657e-05, + "loss": 3.617, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594272790941605e-05, + "loss": 3.5893, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593434196190553e-05, + "loss": 3.5977, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592595601439501e-05, + "loss": 3.6056, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591757006688449e-05, + "loss": 3.5932, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590918411937396e-05, + "loss": 3.604, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590079817186344e-05, + "loss": 3.6104, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589241222435292e-05, + "loss": 3.6082, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5884042655646136e-05, + "loss": 3.5979, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5875656708135616e-05, + "loss": 3.6076, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586728713942883e-05, + "loss": 3.6019, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585890119191831e-05, + "loss": 3.6016, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5850515244407785e-05, + "loss": 3.5797, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5842129296897265e-05, + "loss": 3.6059, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.5833743349386745e-05, + "loss": 3.6043, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.5825357401876225e-05, + "loss": 3.6082, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5816987833169434e-05, + "loss": 3.5976, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5808601885658914e-05, + "loss": 3.5922, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5800215938148394e-05, + "loss": 3.5913, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5791829990637874e-05, + "loss": 3.5956, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5783444043127354e-05, + "loss": 3.6135, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.5775058095616834e-05, + "loss": 3.59, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576668852691005e-05, + "loss": 3.6036, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575830257939953e-05, + "loss": 3.6056, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574991663188901e-05, + "loss": 3.5863, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574153068437849e-05, + "loss": 3.5958, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.57331611156717e-05, + "loss": 3.5891, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572477516816118e-05, + "loss": 3.5935, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571638922065066e-05, + "loss": 3.5904, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570800327314014e-05, + "loss": 3.6125, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569961732562962e-05, + "loss": 3.5935, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.56912313781191e-05, + "loss": 3.5944, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568284543060858e-05, + "loss": 3.5867, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567447586190179e-05, + "loss": 3.597, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566608991439127e-05, + "loss": 3.5985, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.5657703966880754e-05, + "loss": 3.599, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.5649318019370234e-05, + "loss": 3.6028, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5640948450663443e-05, + "loss": 3.6009, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563256250315292e-05, + "loss": 3.6123, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.56241765556424e-05, + "loss": 3.5915, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561579060813188e-05, + "loss": 3.6003, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560742103942509e-05, + "loss": 3.5997, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559903509191457e-05, + "loss": 3.5921, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559064914440405e-05, + "loss": 3.6078, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558226319689353e-05, + "loss": 3.6, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557387724938301e-05, + "loss": 3.6098, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556550768067622e-05, + "loss": 3.614, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555712173316571e-05, + "loss": 3.6075, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554873578565519e-05, + "loss": 3.5801, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554034983814467e-05, + "loss": 3.5942, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553196389063415e-05, + "loss": 3.6038, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552357794312362e-05, + "loss": 3.6008, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551520837441684e-05, + "loss": 3.597, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550682242690632e-05, + "loss": 3.5985, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.54984364793958e-05, + "loss": 3.6011, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549005053188527e-05, + "loss": 3.5942, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548166458437475e-05, + "loss": 3.5927, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473295015667966e-05, + "loss": 3.6014, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5464909068157446e-05, + "loss": 3.6045, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5456523120646926e-05, + "loss": 3.6097, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5448137173136406e-05, + "loss": 3.5802, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543976760442962e-05, + "loss": 3.5936, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5431381656919095e-05, + "loss": 3.5981, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.5422995709408575e-05, + "loss": 3.604, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.5414609761898055e-05, + "loss": 3.6048, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540624019319127e-05, + "loss": 3.5915, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.5397854245680744e-05, + "loss": 3.5927, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.5389468298170224e-05, + "loss": 3.5825, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.5381082350659704e-05, + "loss": 3.5998, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.5372696403149184e-05, + "loss": 3.5892, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.5364310455638664e-05, + "loss": 3.5883, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.5355924508128144e-05, + "loss": 3.5994, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.5347538560617623e-05, + "loss": 3.5939, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533916899191084e-05, + "loss": 3.5888, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533078304440032e-05, + "loss": 3.5951, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.53223970968898e-05, + "loss": 3.5845, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531401114937928e-05, + "loss": 3.6024, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530562520186876e-05, + "loss": 3.586, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529723925435824e-05, + "loss": 3.5972, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528885330684772e-05, + "loss": 3.596, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528048373814093e-05, + "loss": 3.5993, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527209779063041e-05, + "loss": 3.5957, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526371184311989e-05, + "loss": 3.5948, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525532589560937e-05, + "loss": 3.6042, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524695632690258e-05, + "loss": 3.599, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.5238570379392064e-05, + "loss": 3.5903, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.5230184431881544e-05, + "loss": 3.5911, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.5221798484371024e-05, + "loss": 3.5915, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.5213412536860504e-05, + "loss": 3.5993, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.5205026589349984e-05, + "loss": 3.5896, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519664064183946e-05, + "loss": 3.5865, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518827107313267e-05, + "loss": 3.5865, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517988512562215e-05, + "loss": 3.5887, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517149917811163e-05, + "loss": 3.5981, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5163113230601106e-05, + "loss": 3.5905, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5154727283090586e-05, + "loss": 3.6051, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.51463577143838e-05, + "loss": 3.5835, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513797176687328e-05, + "loss": 3.6013, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512958581936276e-05, + "loss": 3.5966, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512119987185224e-05, + "loss": 3.6024, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511281392434172e-05, + "loss": 3.5939, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.51044279768312e-05, + "loss": 3.5927, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509604202932068e-05, + "loss": 3.5915, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508767246061389e-05, + "loss": 3.6061, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507928651310337e-05, + "loss": 3.5895, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507090056559285e-05, + "loss": 3.5928, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506251461808233e-05, + "loss": 3.597, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505412867057181e-05, + "loss": 3.5918, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504575910186502e-05, + "loss": 3.5936, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.50373731543545e-05, + "loss": 3.6021, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5028987206843986e-05, + "loss": 3.5885, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.5020601259333466e-05, + "loss": 3.5936, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.5012231690626675e-05, + "loss": 3.5894, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.846160650253296, + "eval_runtime": 302.1199, + "eval_samples_per_second": 1263.045, + "eval_steps_per_second": 39.471, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5003845743116155e-05, + "loss": 3.5955, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.4995459795605635e-05, + "loss": 3.5772, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.4987073848095115e-05, + "loss": 3.5967, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.4978687900584595e-05, + "loss": 3.6023, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970301953074075e-05, + "loss": 3.6043, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.4961932384367284e-05, + "loss": 3.5929, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4953546436856764e-05, + "loss": 3.5905, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4945160489346244e-05, + "loss": 3.5936, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.4936774541835724e-05, + "loss": 3.584, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492840497312894e-05, + "loss": 3.5888, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.492001902561842e-05, + "loss": 3.5942, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.49116330781079e-05, + "loss": 3.5919, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490326350940111e-05, + "loss": 3.6068, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489487756189059e-05, + "loss": 3.5783, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488649161438007e-05, + "loss": 3.5754, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487810566686955e-05, + "loss": 3.5778, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486971971935903e-05, + "loss": 3.6011, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486133377184851e-05, + "loss": 3.5899, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485294782433799e-05, + "loss": 3.5832, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484456187682746e-05, + "loss": 3.598, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483619230812068e-05, + "loss": 3.6025, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482780636061016e-05, + "loss": 3.5885, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481942041309964e-05, + "loss": 3.5876, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481103446558912e-05, + "loss": 3.5876, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.48026485180786e-05, + "loss": 3.6023, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479426257056808e-05, + "loss": 3.5815, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478587662305756e-05, + "loss": 3.5814, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477749067554704e-05, + "loss": 3.6015, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4769121106840246e-05, + "loss": 3.5734, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760735159329726e-05, + "loss": 3.5771, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4752349211819206e-05, + "loss": 3.5821, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4743979643112415e-05, + "loss": 3.5849, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4735593695601895e-05, + "loss": 3.5935, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4727207748091375e-05, + "loss": 3.5986, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4718821800580855e-05, + "loss": 3.5827, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471045223187407e-05, + "loss": 3.5837, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470206628436355e-05, + "loss": 3.5967, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469368033685303e-05, + "loss": 3.5728, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468529438934251e-05, + "loss": 3.583, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467692482063572e-05, + "loss": 3.5835, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.46685388731252e-05, + "loss": 3.5747, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466015292561468e-05, + "loss": 3.5838, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465176697810416e-05, + "loss": 3.5952, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464338103059364e-05, + "loss": 3.5852, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463501146188685e-05, + "loss": 3.58, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462662551437633e-05, + "loss": 3.5926, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461823956686581e-05, + "loss": 3.5821, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4609853619355296e-05, + "loss": 3.5856, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4601484050648505e-05, + "loss": 3.5585, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4593098103137985e-05, + "loss": 3.5852, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4584712155627465e-05, + "loss": 3.5899, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4576326208116945e-05, + "loss": 3.588, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4567956639410154e-05, + "loss": 3.5768, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4559570691899634e-05, + "loss": 3.577, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4551184744389114e-05, + "loss": 3.5701, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4542798796878594e-05, + "loss": 3.5706, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4534412849368073e-05, + "loss": 3.6003, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452604328066128e-05, + "loss": 3.5737, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451765733315076e-05, + "loss": 3.5813, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450927138564025e-05, + "loss": 3.5879, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450088543812973e-05, + "loss": 3.5682, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449249949061921e-05, + "loss": 3.5764, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448411354310869e-05, + "loss": 3.5705, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447572759559817e-05, + "loss": 3.5715, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446734164808765e-05, + "loss": 3.5761, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445897207938086e-05, + "loss": 3.5894, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445058613187034e-05, + "loss": 3.5816, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444220018435982e-05, + "loss": 3.5752, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.44338142368493e-05, + "loss": 3.5664, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442544466814251e-05, + "loss": 3.5799, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441705872063199e-05, + "loss": 3.5809, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440867277312147e-05, + "loss": 3.5841, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440028682561095e-05, + "loss": 3.5802, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439191725690416e-05, + "loss": 3.5822, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438353130939364e-05, + "loss": 3.5916, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437514536188312e-05, + "loss": 3.5739, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.4366759414372596e-05, + "loss": 3.5768, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435838984566581e-05, + "loss": 3.5852, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435000389815529e-05, + "loss": 3.5751, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434161795064477e-05, + "loss": 3.585, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.4333232003134245e-05, + "loss": 3.585, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.4324846055623725e-05, + "loss": 3.5889, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431647648691694e-05, + "loss": 3.5994, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430809053940642e-05, + "loss": 3.587, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.42997045918959e-05, + "loss": 3.5634, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429131864438538e-05, + "loss": 3.5739, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428293269687486e-05, + "loss": 3.5879, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427454674936434e-05, + "loss": 3.5826, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426617718065755e-05, + "loss": 3.5756, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425779123314703e-05, + "loss": 3.5845, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424940528563651e-05, + "loss": 3.5837, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424101933812599e-05, + "loss": 3.5739, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423263339061547e-05, + "loss": 3.5751, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422426382190868e-05, + "loss": 3.5827, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421587787439816e-05, + "loss": 3.5793, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420749192688764e-05, + "loss": 3.5894, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4199105979377125e-05, + "loss": 3.5704, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.4190736410670334e-05, + "loss": 3.5744, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.4182350463159814e-05, + "loss": 3.5841, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4173964515649294e-05, + "loss": 3.5833, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.4165578568138774e-05, + "loss": 3.5871, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4157192620628254e-05, + "loss": 3.5741, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4148806673117734e-05, + "loss": 3.5736, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414043710441094e-05, + "loss": 3.5635, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413205115690042e-05, + "loss": 3.5817, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.41236652093899e-05, + "loss": 3.5706, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411527926187938e-05, + "loss": 3.572, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410690969317259e-05, + "loss": 3.5817, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409852374566207e-05, + "loss": 3.5733, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409013779815156e-05, + "loss": 3.5743, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408175185064104e-05, + "loss": 3.5775, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407338228193425e-05, + "loss": 3.5628, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406499633442373e-05, + "loss": 3.5827, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405661038691321e-05, + "loss": 3.5716, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404822443940269e-05, + "loss": 3.5771, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403983849189217e-05, + "loss": 3.5812, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403146892318538e-05, + "loss": 3.5842, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402308297567486e-05, + "loss": 3.5773, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401469702816434e-05, + "loss": 3.5769, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400631108065382e-05, + "loss": 3.5846, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.3997941511947026e-05, + "loss": 3.5782, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398955556443651e-05, + "loss": 3.5721, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398116961692599e-05, + "loss": 3.5783, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397278366941547e-05, + "loss": 3.5706, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396439772190495e-05, + "loss": 3.5843, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395602815319816e-05, + "loss": 3.5671, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394764220568764e-05, + "loss": 3.571, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393925625817712e-05, + "loss": 3.5672, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.39308703106666e-05, + "loss": 3.5725, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392248436315608e-05, + "loss": 3.5818, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391411479444929e-05, + "loss": 3.5712, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390572884693877e-05, + "loss": 3.5859, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389734289942825e-05, + "loss": 3.5714, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388895695191773e-05, + "loss": 3.5815, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388057100440721e-05, + "loss": 3.5775, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3872201435700426e-05, + "loss": 3.5833, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.3863815488189906e-05, + "loss": 3.5744, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385542954067938e-05, + "loss": 3.5759, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384704359316886e-05, + "loss": 3.5754, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.3838674024462075e-05, + "loss": 3.5861, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.3830288076951555e-05, + "loss": 3.5725, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382190212944103e-05, + "loss": 3.5756, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381351618193051e-05, + "loss": 3.5796, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380513023441999e-05, + "loss": 3.5736, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.3796760665713204e-05, + "loss": 3.5734, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788374718202684e-05, + "loss": 3.5868, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3779988770692164e-05, + "loss": 3.5699, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3771602823181644e-05, + "loss": 3.5758, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376323325447485e-05, + "loss": 3.5702, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.8450353145599365, + "eval_runtime": 304.6234, + "eval_samples_per_second": 1252.665, + "eval_steps_per_second": 39.147, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375484730696433e-05, + "loss": 3.5692, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374646135945381e-05, + "loss": 3.5596, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373807541194329e-05, + "loss": 3.5764, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372968946443277e-05, + "loss": 3.5883, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372131989572598e-05, + "loss": 3.58, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371293394821546e-05, + "loss": 3.5789, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370454800070494e-05, + "loss": 3.5669, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369616205319442e-05, + "loss": 3.5767, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368779248448764e-05, + "loss": 3.5662, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367940653697712e-05, + "loss": 3.575, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.36710205894666e-05, + "loss": 3.5734, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366263464195608e-05, + "loss": 3.5743, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.3654265073249287e-05, + "loss": 3.5882, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.3645879125738766e-05, + "loss": 3.5597, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3637493178228246e-05, + "loss": 3.5584, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.3629107230717726e-05, + "loss": 3.5614, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.3620721283207206e-05, + "loss": 3.5842, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.3612351714500415e-05, + "loss": 3.5697, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.3603965766989895e-05, + "loss": 3.5685, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.3595579819479375e-05, + "loss": 3.58, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.3587193871968855e-05, + "loss": 3.585, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357882430326207e-05, + "loss": 3.5721, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357043835575155e-05, + "loss": 3.5677, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356205240824103e-05, + "loss": 3.5706, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355368283953424e-05, + "loss": 3.5836, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354529689202372e-05, + "loss": 3.5674, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.35369109445132e-05, + "loss": 3.5634, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352852499700268e-05, + "loss": 3.5852, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.352013904949216e-05, + "loss": 3.553, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351175310198164e-05, + "loss": 3.5618, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350336715447112e-05, + "loss": 3.5624, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349499758576433e-05, + "loss": 3.5657, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348661163825381e-05, + "loss": 3.5743, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347822569074329e-05, + "loss": 3.5837, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3469839743232776e-05, + "loss": 3.5643, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.3461470174525985e-05, + "loss": 3.5664, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3453084227015465e-05, + "loss": 3.5791, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3444698279504945e-05, + "loss": 3.5561, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.3436312331994425e-05, + "loss": 3.5656, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.3427942763287634e-05, + "loss": 3.5632, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.3419556815777114e-05, + "loss": 3.5641, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.3411170868266594e-05, + "loss": 3.5601, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.3402784920756074e-05, + "loss": 3.5829, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339441535204928e-05, + "loss": 3.5651, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338602940453876e-05, + "loss": 3.5685, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337764345702824e-05, + "loss": 3.5734, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336925750951773e-05, + "loss": 3.5674, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336087156200721e-05, + "loss": 3.5638, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335250199330042e-05, + "loss": 3.5455, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.33441160457899e-05, + "loss": 3.5621, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333573009827938e-05, + "loss": 3.5762, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332734415076886e-05, + "loss": 3.5739, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331897458206207e-05, + "loss": 3.5583, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331058863455155e-05, + "loss": 3.5552, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330220268704103e-05, + "loss": 3.5602, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329381673953051e-05, + "loss": 3.5504, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.3285447170823716e-05, + "loss": 3.5834, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.3277061223313196e-05, + "loss": 3.555, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326867527580268e-05, + "loss": 3.5684, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.326028932829216e-05, + "loss": 3.5687, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325191975958537e-05, + "loss": 3.5481, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324353381207485e-05, + "loss": 3.5604, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323514786456433e-05, + "loss": 3.5527, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3226761917053805e-05, + "loss": 3.5543, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.3218375969543285e-05, + "loss": 3.5565, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.32100064008365e-05, + "loss": 3.572, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320162045332598e-05, + "loss": 3.5653, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.3193234505815454e-05, + "loss": 3.5604, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.3184848558304934e-05, + "loss": 3.549, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317647898959815e-05, + "loss": 3.5604, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316809304208764e-05, + "loss": 3.5649, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315970709457711e-05, + "loss": 3.5671, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315132114706659e-05, + "loss": 3.5621, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.3142951578359806e-05, + "loss": 3.5642, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313456563084928e-05, + "loss": 3.5781, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312617968333876e-05, + "loss": 3.5568, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311779373582824e-05, + "loss": 3.5592, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3109424167121455e-05, + "loss": 3.5628, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310103821961093e-05, + "loss": 3.5638, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309265227210041e-05, + "loss": 3.569, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308426632458989e-05, + "loss": 3.5698, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.3075880377079374e-05, + "loss": 3.5726, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3067510808372584e-05, + "loss": 3.5769, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.3059124860862063e-05, + "loss": 3.5697, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3050738913351543e-05, + "loss": 3.5494, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3042352965841023e-05, + "loss": 3.5541, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.30339670183305e-05, + "loss": 3.5715, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302558107081998e-05, + "loss": 3.5684, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301721150211319e-05, + "loss": 3.5607, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300882555460267e-05, + "loss": 3.5629, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300043960709215e-05, + "loss": 3.5721, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299205365958163e-05, + "loss": 3.5565, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298366771207111e-05, + "loss": 3.5554, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297529814336433e-05, + "loss": 3.5666, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296691219585381e-05, + "loss": 3.5614, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295852624834329e-05, + "loss": 3.5762, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295014030083277e-05, + "loss": 3.5531, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294177073212598e-05, + "loss": 3.5541, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293338478461546e-05, + "loss": 3.5666, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292499883710494e-05, + "loss": 3.5652, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291661288959442e-05, + "loss": 3.5685, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.2908243320887626e-05, + "loss": 3.5598, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.2899857373377106e-05, + "loss": 3.5549, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2891471425866586e-05, + "loss": 3.5457, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.2883085478356066e-05, + "loss": 3.5663, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.2874699530845546e-05, + "loss": 3.5524, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.2866313583335026e-05, + "loss": 3.5543, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285794401462824e-05, + "loss": 3.5658, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284955806711772e-05, + "loss": 3.5591, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.28411721196072e-05, + "loss": 3.552, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283278617209668e-05, + "loss": 3.5632, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282441660338989e-05, + "loss": 3.5469, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281603065587937e-05, + "loss": 3.5645, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280764470836885e-05, + "loss": 3.5568, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279925876085833e-05, + "loss": 3.5585, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279087281334781e-05, + "loss": 3.5659, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278250324464102e-05, + "loss": 3.5658, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.27741172971305e-05, + "loss": 3.5594, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276573134961998e-05, + "loss": 3.5606, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275734540210946e-05, + "loss": 3.5711, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2748975833402675e-05, + "loss": 3.5594, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.2740589885892155e-05, + "loss": 3.555, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.2732203938381635e-05, + "loss": 3.5612, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2723817990871115e-05, + "loss": 3.5602, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.2715448422164324e-05, + "loss": 3.5652, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2707062474653804e-05, + "loss": 3.5522, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.2698676527143284e-05, + "loss": 3.5542, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.2690290579632764e-05, + "loss": 3.5554, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268190463212224e-05, + "loss": 3.5514, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267353506341545e-05, + "loss": 3.5631, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266514911590493e-05, + "loss": 3.5616, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265676316839441e-05, + "loss": 3.5669, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264837722088389e-05, + "loss": 3.5531, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.264000765217711e-05, + "loss": 3.5656, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263162170466659e-05, + "loss": 3.5602, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262323575715606e-05, + "loss": 3.5703, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261484980964554e-05, + "loss": 3.5554, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260648024093876e-05, + "loss": 3.5592, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259809429342824e-05, + "loss": 3.5585, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258970834591771e-05, + "loss": 3.5692, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258132239840719e-05, + "loss": 3.5565, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257295282970041e-05, + "loss": 3.5559, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256456688218989e-05, + "loss": 3.564, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255618093467937e-05, + "loss": 3.5558, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254779498716885e-05, + "loss": 3.5569, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253940903965833e-05, + "loss": 3.5713, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253102309214781e-05, + "loss": 3.5492, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.2522653523441016e-05, + "loss": 3.5656, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.2514267575930496e-05, + "loss": 3.5528, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.845576286315918, + "eval_runtime": 304.7787, + "eval_samples_per_second": 1252.027, + "eval_steps_per_second": 39.127, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.2505881628419976e-05, + "loss": 3.558, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.2497495680909456e-05, + "loss": 3.5444, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2489109733398936e-05, + "loss": 3.5587, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2480723785888416e-05, + "loss": 3.5726, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.2472354217181625e-05, + "loss": 3.5646, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.2463968269671105e-05, + "loss": 3.5615, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245558232216059e-05, + "loss": 3.5469, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244719637465007e-05, + "loss": 3.5597, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243882680594328e-05, + "loss": 3.5539, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243044085843276e-05, + "loss": 3.5567, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242205491092224e-05, + "loss": 3.5573, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241366896341172e-05, + "loss": 3.5587, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240529939470493e-05, + "loss": 3.5724, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239691344719441e-05, + "loss": 3.5463, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238852749968389e-05, + "loss": 3.5392, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238014155217337e-05, + "loss": 3.5476, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237175560466285e-05, + "loss": 3.5645, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236336965715233e-05, + "loss": 3.5564, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2355000088445545e-05, + "loss": 3.5502, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2346614140935025e-05, + "loss": 3.558, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338228193424505e-05, + "loss": 3.5711, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2329842245913985e-05, + "loss": 3.5544, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321472677207194e-05, + "loss": 3.5534, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2313086729696674e-05, + "loss": 3.5568, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2304700782186154e-05, + "loss": 3.5703, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2296314834675634e-05, + "loss": 3.5486, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2287928887165114e-05, + "loss": 3.5495, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.2279542939654594e-05, + "loss": 3.5655, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2271156992144074e-05, + "loss": 3.5425, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226277104463355e-05, + "loss": 3.5441, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225440147592676e-05, + "loss": 3.5435, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224603190721998e-05, + "loss": 3.5549, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223764595970946e-05, + "loss": 3.5572, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222926001219894e-05, + "loss": 3.5663, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222087406468842e-05, + "loss": 3.5535, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221250449598163e-05, + "loss": 3.5497, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220411854847111e-05, + "loss": 3.5618, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219573260096059e-05, + "loss": 3.5409, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218734665345007e-05, + "loss": 3.549, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.2178977084743277e-05, + "loss": 3.5474, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2170591137232756e-05, + "loss": 3.5514, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.2162205189722236e-05, + "loss": 3.541, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.2153819242211716e-05, + "loss": 3.5656, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.2145433294701196e-05, + "loss": 3.5474, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213706372599441e-05, + "loss": 3.5542, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212867777848389e-05, + "loss": 3.5549, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212029183097337e-05, + "loss": 3.5507, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2111905883462845e-05, + "loss": 3.55, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210353631475606e-05, + "loss": 3.5312, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209515036724554e-05, + "loss": 3.5477, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208676441973502e-05, + "loss": 3.5594, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.2078378472224494e-05, + "loss": 3.5516, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207000890351771e-05, + "loss": 3.5442, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206162295600719e-05, + "loss": 3.5377, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205323700849667e-05, + "loss": 3.5451, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204485106098615e-05, + "loss": 3.5327, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.2036481492279366e-05, + "loss": 3.5677, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.2028095544768846e-05, + "loss": 3.5428, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201970959725832e-05, + "loss": 3.5486, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.20113236497478e-05, + "loss": 3.5544, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200293770223728e-05, + "loss": 3.5345, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1994568133530495e-05, + "loss": 3.5423, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198618218601997e-05, + "loss": 3.5397, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197779623850945e-05, + "loss": 3.5378, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196941029099893e-05, + "loss": 3.536, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.1961040722292144e-05, + "loss": 3.5582, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.1952654774781624e-05, + "loss": 3.5498, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.1944268827271104e-05, + "loss": 3.5436, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.1935882879760584e-05, + "loss": 3.5341, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192751331105379e-05, + "loss": 3.5439, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191912736354327e-05, + "loss": 3.5483, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191074141603275e-05, + "loss": 3.5513, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190235546852223e-05, + "loss": 3.5463, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189398589981544e-05, + "loss": 3.5513, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188559995230492e-05, + "loss": 3.5593, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.18772140047944e-05, + "loss": 3.5483, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186882805728388e-05, + "loss": 3.5402, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186045848857709e-05, + "loss": 3.5508, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185207254106658e-05, + "loss": 3.5475, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184368659355606e-05, + "loss": 3.5488, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183530064604554e-05, + "loss": 3.5535, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182691469853502e-05, + "loss": 3.5545, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1818545129828226e-05, + "loss": 3.5617, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.1810159182317706e-05, + "loss": 3.5524, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1801773234807186e-05, + "loss": 3.5362, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1793387287296666e-05, + "loss": 3.5405, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.1785017718589875e-05, + "loss": 3.5563, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1776631771079355e-05, + "loss": 3.5485, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1768245823568835e-05, + "loss": 3.5441, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1759859876058315e-05, + "loss": 3.5458, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175149030735153e-05, + "loss": 3.5541, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174310435984101e-05, + "loss": 3.5415, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173471841233049e-05, + "loss": 3.5455, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172633246481997e-05, + "loss": 3.5446, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171794651730945e-05, + "loss": 3.5487, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170957694860266e-05, + "loss": 3.5551, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170119100109214e-05, + "loss": 3.5475, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169280505358162e-05, + "loss": 3.5323, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.16844191060711e-05, + "loss": 3.5517, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167604953736431e-05, + "loss": 3.5489, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166766358985379e-05, + "loss": 3.5513, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165927764234327e-05, + "loss": 3.5459, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165089169483275e-05, + "loss": 3.5374, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1642522126125965e-05, + "loss": 3.5339, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1634136178615445e-05, + "loss": 3.5475, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1625750231104925e-05, + "loss": 3.5375, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.1617364283594405e-05, + "loss": 3.5384, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1608994714887614e-05, + "loss": 3.5499, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.1600608767377094e-05, + "loss": 3.5454, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1592222819866574e-05, + "loss": 3.5359, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.1583836872356054e-05, + "loss": 3.546, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157546730364926e-05, + "loss": 3.5334, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156708135613874e-05, + "loss": 3.5489, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155869540862822e-05, + "loss": 3.5403, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.15503094611177e-05, + "loss": 3.5441, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154192351360718e-05, + "loss": 3.5482, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.15335539449004e-05, + "loss": 3.5522, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152516799738988e-05, + "loss": 3.5446, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151678204987936e-05, + "loss": 3.5457, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150839610236884e-05, + "loss": 3.5537, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150001015485832e-05, + "loss": 3.5444, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149164058615153e-05, + "loss": 3.5358, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148325463864101e-05, + "loss": 3.5484, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147486869113049e-05, + "loss": 3.5416, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146648274361997e-05, + "loss": 3.5508, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1458113174913176e-05, + "loss": 3.5381, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1449727227402656e-05, + "loss": 3.5379, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.1441341279892136e-05, + "loss": 3.5394, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143295533238162e-05, + "loss": 3.5422, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142458576367483e-05, + "loss": 3.5395, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141619981616431e-05, + "loss": 3.5481, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140781386865379e-05, + "loss": 3.5501, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139942792114327e-05, + "loss": 3.5363, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.1391041973632745e-05, + "loss": 3.549, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.1382656026122225e-05, + "loss": 3.5467, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137428645741544e-05, + "loss": 3.5551, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136590050990492e-05, + "loss": 3.5391, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.1357514562394394e-05, + "loss": 3.544, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1349128614883874e-05, + "loss": 3.5484, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134075904617709e-05, + "loss": 3.5498, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133237309866657e-05, + "loss": 3.5419, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132398715115605e-05, + "loss": 3.5426, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131560120364553e-05, + "loss": 3.5481, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130721525613501e-05, + "loss": 3.5403, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129884568742822e-05, + "loss": 3.5385, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.12904597399177e-05, + "loss": 3.5587, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128207379240718e-05, + "loss": 3.5368, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127368784489666e-05, + "loss": 3.5475, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126531827618987e-05, + "loss": 3.537, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8471779823303223, + "eval_runtime": 302.7853, + "eval_samples_per_second": 1260.269, + "eval_steps_per_second": 39.384, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125693232867935e-05, + "loss": 3.537, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124854638116883e-05, + "loss": 3.5329, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.1240160433658314e-05, + "loss": 3.5433, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1231774486147794e-05, + "loss": 3.5548, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.1223404917441e-05, + "loss": 3.5483, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121501896993048e-05, + "loss": 3.5519, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120663302241996e-05, + "loss": 3.5342, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119824707490944e-05, + "loss": 3.5435, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118986112739892e-05, + "loss": 3.5347, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118149155869213e-05, + "loss": 3.5445, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117310561118161e-05, + "loss": 3.5391, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116471966367109e-05, + "loss": 3.5465, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.11563500949643e-05, + "loss": 3.5595, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114796414745378e-05, + "loss": 3.5318, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113957819994326e-05, + "loss": 3.5254, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113119225243275e-05, + "loss": 3.5288, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112280630492223e-05, + "loss": 3.5454, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111443673621544e-05, + "loss": 3.5432, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110605078870492e-05, + "loss": 3.5371, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.10976648411944e-05, + "loss": 3.5397, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108927889368388e-05, + "loss": 3.5623, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.1080909324977086e-05, + "loss": 3.5396, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.1072523377466566e-05, + "loss": 3.5362, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.1064137429956046e-05, + "loss": 3.5426, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.1055751482445526e-05, + "loss": 3.5537, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.1047381913738735e-05, + "loss": 3.5297, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.1038995966228215e-05, + "loss": 3.5376, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.10306100187177e-05, + "loss": 3.5464, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102222407120718e-05, + "loss": 3.5339, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101383812369666e-05, + "loss": 3.5289, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100546855498987e-05, + "loss": 3.5273, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099708260747935e-05, + "loss": 3.5377, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098869665996883e-05, + "loss": 3.5465, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.098031071245831e-05, + "loss": 3.5448, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097194114375152e-05, + "loss": 3.542, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0963555196241e-05, + "loss": 3.5319, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095516924873048e-05, + "loss": 3.5456, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094678330121996e-05, + "loss": 3.527, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093839735370944e-05, + "loss": 3.5349, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0930027785002655e-05, + "loss": 3.5302, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0921641837492135e-05, + "loss": 3.5335, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.0913255889981615e-05, + "loss": 3.5264, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.0904869942471095e-05, + "loss": 3.5514, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.0896500373764304e-05, + "loss": 3.5315, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.0888114426253784e-05, + "loss": 3.5392, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.0879728478743264e-05, + "loss": 3.5413, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.0871342531232744e-05, + "loss": 3.5334, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.0862956583722224e-05, + "loss": 3.5339, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085458701501543e-05, + "loss": 3.5188, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084620106750491e-05, + "loss": 3.53, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083781511999439e-05, + "loss": 3.543, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082942917248387e-05, + "loss": 3.5392, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082104322497335e-05, + "loss": 3.5275, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081267365626657e-05, + "loss": 3.5239, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080428770875605e-05, + "loss": 3.531, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079590176124553e-05, + "loss": 3.5212, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0787515813735e-05, + "loss": 3.5482, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077914624502822e-05, + "loss": 3.5301, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.07707602975177e-05, + "loss": 3.5328, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076237435000718e-05, + "loss": 3.5456, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075398840249665e-05, + "loss": 3.517, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074561883378987e-05, + "loss": 3.5259, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073723288627935e-05, + "loss": 3.5279, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072884693876883e-05, + "loss": 3.521, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.0720460991258307e-05, + "loss": 3.525, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.0712075043747787e-05, + "loss": 3.5379, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.0703689096237267e-05, + "loss": 3.539, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.0695319527530476e-05, + "loss": 3.529, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.0686933580019956e-05, + "loss": 3.5184, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.0678547632509436e-05, + "loss": 3.5305, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.0670161684998915e-05, + "loss": 3.5335, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.0661792116292125e-05, + "loss": 3.5342, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.0653406168781605e-05, + "loss": 3.5361, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0645020221271084e-05, + "loss": 3.534, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.0636634273760564e-05, + "loss": 3.5421, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0628248326250044e-05, + "loss": 3.5345, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.061987875754326e-05, + "loss": 3.5207, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061149281003274e-05, + "loss": 3.5383, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060310686252222e-05, + "loss": 3.5323, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.05947209150117e-05, + "loss": 3.5315, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058635134630491e-05, + "loss": 3.5416, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057796539879439e-05, + "loss": 3.5398, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056957945128387e-05, + "loss": 3.5502, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056119350377335e-05, + "loss": 3.5398, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055280755626283e-05, + "loss": 3.5233, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054442160875231e-05, + "loss": 3.5242, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053603566124179e-05, + "loss": 3.5356, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0527666092535e-05, + "loss": 3.5401, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051928014502448e-05, + "loss": 3.5305, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.051089419751396e-05, + "loss": 3.5299, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.050250825000344e-05, + "loss": 3.5391, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494138681296654e-05, + "loss": 3.5275, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0485752733786134e-05, + "loss": 3.5312, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477366786275614e-05, + "loss": 3.5285, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0468980838765094e-05, + "loss": 3.5327, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460611270058303e-05, + "loss": 3.5443, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452225322547783e-05, + "loss": 3.5314, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0443839375037263e-05, + "loss": 3.519, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435453427526746e-05, + "loss": 3.5348, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427083858819955e-05, + "loss": 3.5346, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0418697911309435e-05, + "loss": 3.5373, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410311963798915e-05, + "loss": 3.5297, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0401926016288395e-05, + "loss": 3.5256, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393540068777875e-05, + "loss": 3.518, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0385170500071087e-05, + "loss": 3.5356, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0376784552560567e-05, + "loss": 3.5206, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368398605050047e-05, + "loss": 3.5263, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360012657539527e-05, + "loss": 3.5362, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0351643088832736e-05, + "loss": 3.5269, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0343257141322216e-05, + "loss": 3.5243, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.03348711938117e-05, + "loss": 3.5286, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.032648524630118e-05, + "loss": 3.522, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.031809929879066e-05, + "loss": 3.5347, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.030972973008387e-05, + "loss": 3.5247, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.030134378257335e-05, + "loss": 3.5295, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.029295783506283e-05, + "loss": 3.5302, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.028457188755231e-05, + "loss": 3.5402, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.027620231884552e-05, + "loss": 3.5291, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0267816371335e-05, + "loss": 3.5327, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.025943042382448e-05, + "loss": 3.5361, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251044476313954e-05, + "loss": 3.5316, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.024267490760717e-05, + "loss": 3.5154, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234288960096653e-05, + "loss": 3.5364, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0225903012586133e-05, + "loss": 3.526, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217517065075606e-05, + "loss": 3.5386, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0209147496368822e-05, + "loss": 3.5218, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0200761548858302e-05, + "loss": 3.5244, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192375601347782e-05, + "loss": 3.5221, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018398965383726e-05, + "loss": 3.5246, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017560370632674e-05, + "loss": 3.5228, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167234137619955e-05, + "loss": 3.5345, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0158848190109428e-05, + "loss": 3.5391, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150462242598908e-05, + "loss": 3.5248, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.014207629508839e-05, + "loss": 3.5287, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0133706726381604e-05, + "loss": 3.5327, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.012532077887108e-05, + "loss": 3.5381, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.011693483136056e-05, + "loss": 3.5317, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.010854888385004e-05, + "loss": 3.5275, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.010016293633952e-05, + "loss": 3.5354, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0091793367632733e-05, + "loss": 3.5337, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083407420122213e-05, + "loss": 3.5288, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075021472611692e-05, + "loss": 3.5276, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066635525101172e-05, + "loss": 3.5331, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.005826595639438e-05, + "loss": 3.527, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.004988000888386e-05, + "loss": 3.5218, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.004149406137334e-05, + "loss": 3.5476, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033108113862825e-05, + "loss": 3.5259, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0024738545156034e-05, + "loss": 3.5287, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016352597645514e-05, + "loss": 3.5253, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0007966650134994e-05, + "loss": 3.5234, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.8479466438293457, + "eval_runtime": 302.4309, + "eval_samples_per_second": 1261.746, + "eval_steps_per_second": 39.43, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999580702624474e-05, + "loss": 3.5146, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991194755113954e-05, + "loss": 3.5288, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9982808807603434e-05, + "loss": 3.5393, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974422860092917e-05, + "loss": 3.5346, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966053291386126e-05, + "loss": 3.5371, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9957667343875606e-05, + "loss": 3.5216, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949281396365086e-05, + "loss": 3.5275, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9940895448854566e-05, + "loss": 3.5188, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.993252588014778e-05, + "loss": 3.5303, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992413993263726e-05, + "loss": 3.5278, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991575398512674e-05, + "loss": 3.5309, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990736803761622e-05, + "loss": 3.5341, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9898998468909427e-05, + "loss": 3.5249, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890612521398907e-05, + "loss": 3.5094, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882226573888387e-05, + "loss": 3.5192, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987384062637787e-05, + "loss": 3.5219, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.986547105767108e-05, + "loss": 3.5299, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.985708511016056e-05, + "loss": 3.5214, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.984869916265004e-05, + "loss": 3.5268, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.984031321513952e-05, + "loss": 3.5504, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9831943646432732e-05, + "loss": 3.5257, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823557698922212e-05, + "loss": 3.5227, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815171751411692e-05, + "loss": 3.5268, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9806785803901172e-05, + "loss": 3.5395, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.979841623519438e-05, + "loss": 3.5156, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.979003028768386e-05, + "loss": 3.5198, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.978164434017334e-05, + "loss": 3.5362, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773258392662824e-05, + "loss": 3.521, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9764872445152304e-05, + "loss": 3.5101, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756502876445513e-05, + "loss": 3.5115, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748116928934993e-05, + "loss": 3.5263, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9739730981424473e-05, + "loss": 3.5299, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731345033913953e-05, + "loss": 3.5361, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9722975465207166e-05, + "loss": 3.5217, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714589517696646e-05, + "loss": 3.5153, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706203570186126e-05, + "loss": 3.5325, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9697817622675606e-05, + "loss": 3.5123, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689431675165086e-05, + "loss": 3.5209, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681062106458295e-05, + "loss": 3.5149, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9672676158947778e-05, + "loss": 3.5225, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664290211437258e-05, + "loss": 3.5126, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9655904263926738e-05, + "loss": 3.5394, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647534695219947e-05, + "loss": 3.519, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639148747709427e-05, + "loss": 3.5229, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9630762800198907e-05, + "loss": 3.5267, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622376852688387e-05, + "loss": 3.5243, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.96140072839816e-05, + "loss": 3.5195, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.960562133647108e-05, + "loss": 3.51, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.959723538896056e-05, + "loss": 3.5131, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9588849441450032e-05, + "loss": 3.5293, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.958047987274325e-05, + "loss": 3.5218, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.957209392523273e-05, + "loss": 3.5144, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.956370797772221e-05, + "loss": 3.5103, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555322030211685e-05, + "loss": 3.5196, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9546936082701165e-05, + "loss": 3.5081, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.953856651399438e-05, + "loss": 3.5277, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.953018056648386e-05, + "loss": 3.5162, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9521794618973337e-05, + "loss": 3.5182, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513408671462817e-05, + "loss": 3.526, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505039102756033e-05, + "loss": 3.5131, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9496653155245506e-05, + "loss": 3.5078, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488267207734986e-05, + "loss": 3.5157, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.947988126022447e-05, + "loss": 3.5068, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471511691517685e-05, + "loss": 3.5118, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.946312574400716e-05, + "loss": 3.5238, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.945473979649664e-05, + "loss": 3.5289, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944635384898612e-05, + "loss": 3.5114, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943798428027933e-05, + "loss": 3.5101, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.942959833276881e-05, + "loss": 3.5105, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.942121238525829e-05, + "loss": 3.5178, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.941282643774777e-05, + "loss": 3.5219, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.940445686904098e-05, + "loss": 3.5223, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.939607092153046e-05, + "loss": 3.5196, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.938768497401994e-05, + "loss": 3.5273, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379299026509423e-05, + "loss": 3.5248, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9370929457802632e-05, + "loss": 3.5047, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9362543510292112e-05, + "loss": 3.5219, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9354157562781592e-05, + "loss": 3.5221, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9345771615271072e-05, + "loss": 3.5145, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337402046564285e-05, + "loss": 3.5296, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329016099053765e-05, + "loss": 3.5243, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320630151543244e-05, + "loss": 3.5359, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312244204032724e-05, + "loss": 3.5272, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9303874635325934e-05, + "loss": 3.5073, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295488687815413e-05, + "loss": 3.512, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287102740304893e-05, + "loss": 3.522, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9278716792794373e-05, + "loss": 3.5239, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270330845283857e-05, + "loss": 3.5177, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9261961276577066e-05, + "loss": 3.5162, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253575329066546e-05, + "loss": 3.5218, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245189381556026e-05, + "loss": 3.5146, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9236803434045506e-05, + "loss": 3.5125, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228433865338718e-05, + "loss": 3.5138, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220047917828198e-05, + "loss": 3.5203, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9211661970317678e-05, + "loss": 3.5344, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203276022807158e-05, + "loss": 3.5142, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9194906454100367e-05, + "loss": 3.5073, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186520506589847e-05, + "loss": 3.5173, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178134559079327e-05, + "loss": 3.5194, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.916974861156881e-05, + "loss": 3.5249, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.916137904286202e-05, + "loss": 3.5152, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.91529930953515e-05, + "loss": 3.5172, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.914460714784098e-05, + "loss": 3.4981, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.913622120033046e-05, + "loss": 3.5213, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.912783525281994e-05, + "loss": 3.5107, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119465684113152e-05, + "loss": 3.5109, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111079736602632e-05, + "loss": 3.5173, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102693789092112e-05, + "loss": 3.5156, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.909430784158159e-05, + "loss": 3.5087, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.90859382728748e-05, + "loss": 3.517, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.907755232536428e-05, + "loss": 3.509, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069166377853764e-05, + "loss": 3.5184, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9060780430343244e-05, + "loss": 3.5091, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052394482832724e-05, + "loss": 3.5149, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044008535322204e-05, + "loss": 3.5183, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035638966615413e-05, + "loss": 3.5218, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027253019104893e-05, + "loss": 3.5166, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9018867071594373e-05, + "loss": 3.5188, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010481124083856e-05, + "loss": 3.5242, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002111555377065e-05, + "loss": 3.5175, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8993725607866545e-05, + "loss": 3.504, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985339660356025e-05, + "loss": 3.5246, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8976953712845505e-05, + "loss": 3.513, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968584144138718e-05, + "loss": 3.521, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960198196628198e-05, + "loss": 3.512, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8951812249117678e-05, + "loss": 3.5105, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943426301607158e-05, + "loss": 3.5059, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935040354096638e-05, + "loss": 3.5129, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8926670785389847e-05, + "loss": 3.5105, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918284837879327e-05, + "loss": 3.5216, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.890989889036881e-05, + "loss": 3.5255, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.890151294285829e-05, + "loss": 3.509, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.88931433741515e-05, + "loss": 3.5129, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.888475742664098e-05, + "loss": 3.5167, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887637147913046e-05, + "loss": 3.5224, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.886798553161994e-05, + "loss": 3.5211, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859599584109415e-05, + "loss": 3.5171, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.885123001540263e-05, + "loss": 3.5163, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884284406789211e-05, + "loss": 3.5161, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834458120381584e-05, + "loss": 3.5148, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826072172871064e-05, + "loss": 3.5135, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.881770260416428e-05, + "loss": 3.5214, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809316656653764e-05, + "loss": 3.5141, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8800930709143237e-05, + "loss": 3.5035, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792544761632717e-05, + "loss": 3.5357, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784175192925933e-05, + "loss": 3.5125, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.877578924541541e-05, + "loss": 3.5151, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.876740329790489e-05, + "loss": 3.5101, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.875901735039437e-05, + "loss": 3.5086, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.8488831520080566, + "eval_runtime": 303.2918, + "eval_samples_per_second": 1258.165, + "eval_steps_per_second": 39.319, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.875063140288385e-05, + "loss": 3.5026, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742261834177058e-05, + "loss": 3.5175, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8733875886666538e-05, + "loss": 3.5279, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725489939156018e-05, + "loss": 3.5116, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.87171039916455e-05, + "loss": 3.5299, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.870873442293871e-05, + "loss": 3.5033, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.870034847542819e-05, + "loss": 3.5158, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.869196252791767e-05, + "loss": 3.5059, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.868357658040715e-05, + "loss": 3.5169, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8675207011700363e-05, + "loss": 3.5149, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8666821064189843e-05, + "loss": 3.5147, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8658435116679323e-05, + "loss": 3.5214, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8650065547972532e-05, + "loss": 3.51, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8641679600462012e-05, + "loss": 3.5, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8633293652951492e-05, + "loss": 3.5052, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8624907705440972e-05, + "loss": 3.512, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8616521757930455e-05, + "loss": 3.5157, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8608135810419935e-05, + "loss": 3.5075, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8599749862909415e-05, + "loss": 3.5142, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591363915398895e-05, + "loss": 3.5358, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8582994346692104e-05, + "loss": 3.5124, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8574608399181584e-05, + "loss": 3.507, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566222451671064e-05, + "loss": 3.5139, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8557836504160544e-05, + "loss": 3.5233, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549466935453756e-05, + "loss": 3.5033, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541080987943236e-05, + "loss": 3.5123, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8532695040432716e-05, + "loss": 3.5165, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524309092922196e-05, + "loss": 3.5115, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8515923145411676e-05, + "loss": 3.4946, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.850755357670489e-05, + "loss": 3.5031, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.849916762919437e-05, + "loss": 3.5085, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.849078168168385e-05, + "loss": 3.5168, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.848239573417333e-05, + "loss": 3.524, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.847400978666281e-05, + "loss": 3.5107, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8465640217956018e-05, + "loss": 3.5034, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457254270445498e-05, + "loss": 3.52, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.844886832293498e-05, + "loss": 3.4991, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.844048237542446e-05, + "loss": 3.5087, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843211280671767e-05, + "loss": 3.4997, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.842372685920715e-05, + "loss": 3.5073, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.841534091169663e-05, + "loss": 3.499, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.840695496418611e-05, + "loss": 3.5246, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398585395479322e-05, + "loss": 3.5087, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390199447968802e-05, + "loss": 3.5076, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8381813500458282e-05, + "loss": 3.5103, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8373427552947762e-05, + "loss": 3.515, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.836505798424097e-05, + "loss": 3.5021, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835667203673045e-05, + "loss": 3.4986, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348286089219935e-05, + "loss": 3.4973, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8339900141709415e-05, + "loss": 3.5175, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331530573002624e-05, + "loss": 3.506, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323144625492104e-05, + "loss": 3.5013, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8314758677981584e-05, + "loss": 3.4983, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306372730471064e-05, + "loss": 3.5051, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8298003161764276e-05, + "loss": 3.4935, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8289617214253756e-05, + "loss": 3.5144, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281231266743236e-05, + "loss": 3.5035, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8272845319232716e-05, + "loss": 3.506, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.826445937172219e-05, + "loss": 3.5158, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8256089803015405e-05, + "loss": 3.4943, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8247703855504888e-05, + "loss": 3.496, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239317907994368e-05, + "loss": 3.5062, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.823093196048384e-05, + "loss": 3.4934, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8222562391777057e-05, + "loss": 3.4965, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214176444266537e-05, + "loss": 3.507, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8205790496756017e-05, + "loss": 3.5171, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197404549245494e-05, + "loss": 3.4987, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8189018601734974e-05, + "loss": 3.4972, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.818064903302819e-05, + "loss": 3.4931, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172263085517663e-05, + "loss": 3.5055, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8163877138007143e-05, + "loss": 3.5059, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155491190496626e-05, + "loss": 3.5088, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147121621789842e-05, + "loss": 3.5075, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8138735674279315e-05, + "loss": 3.5117, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130349726768795e-05, + "loss": 3.5144, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8121963779258275e-05, + "loss": 3.4919, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113577831747755e-05, + "loss": 3.5085, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105208263040967e-05, + "loss": 3.51, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8096822315530447e-05, + "loss": 3.4968, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8088436368019927e-05, + "loss": 3.5182, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080050420509407e-05, + "loss": 3.5127, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8071680851802616e-05, + "loss": 3.5182, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063294904292096e-05, + "loss": 3.5141, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.805490895678158e-05, + "loss": 3.4934, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.804652300927106e-05, + "loss": 3.5034, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803813706176054e-05, + "loss": 3.5065, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.802976749305375e-05, + "loss": 3.5104, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.802138154554323e-05, + "loss": 3.5049, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.801299559803271e-05, + "loss": 3.5024, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.800460965052219e-05, + "loss": 3.5124, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.79962400818154e-05, + "loss": 3.5039, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.798785413430488e-05, + "loss": 3.4962, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.797946818679436e-05, + "loss": 3.5018, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.797108223928384e-05, + "loss": 3.5095, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.796269629177332e-05, + "loss": 3.5211, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954326723066533e-05, + "loss": 3.5025, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7945940775556013e-05, + "loss": 3.4914, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7937554828045493e-05, + "loss": 3.5059, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929168880534973e-05, + "loss": 3.5064, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7920799311828182e-05, + "loss": 3.5115, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912413364317662e-05, + "loss": 3.5041, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7904027416807142e-05, + "loss": 3.5011, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7895641469296626e-05, + "loss": 3.489, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887271900589835e-05, + "loss": 3.5063, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7878885953079315e-05, + "loss": 3.4959, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870500005568795e-05, + "loss": 3.4995, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862114058058275e-05, + "loss": 3.5032, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7853728110547755e-05, + "loss": 3.5055, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7845358541840967e-05, + "loss": 3.4983, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7836972594330447e-05, + "loss": 3.5058, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7828586646819927e-05, + "loss": 3.4978, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820200699309407e-05, + "loss": 3.5005, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7811814751798887e-05, + "loss": 3.4969, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7803445183092096e-05, + "loss": 3.4988, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795059235581576e-05, + "loss": 3.5083, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.778667328807106e-05, + "loss": 3.5115, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.777828734056054e-05, + "loss": 3.5034, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.776990139305002e-05, + "loss": 3.5043, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761531824343228e-05, + "loss": 3.5089, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753145876832708e-05, + "loss": 3.503, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7744759929322188e-05, + "loss": 3.4918, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736373981811668e-05, + "loss": 3.511, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.772800441310488e-05, + "loss": 3.5001, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.771961846559436e-05, + "loss": 3.508, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.771123251808384e-05, + "loss": 3.4946, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.770284657057332e-05, + "loss": 3.4981, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694460623062797e-05, + "loss": 3.4933, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7686091054356013e-05, + "loss": 3.4955, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7677705106845493e-05, + "loss": 3.497, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7669319159334973e-05, + "loss": 3.5083, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7660933211824446e-05, + "loss": 3.5146, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7652547264313926e-05, + "loss": 3.5033, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7644177695607142e-05, + "loss": 3.494, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7635791748096622e-05, + "loss": 3.5057, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.76274058005861e-05, + "loss": 3.5078, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7619019853075578e-05, + "loss": 3.5096, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7610650284368794e-05, + "loss": 3.5037, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602264336858267e-05, + "loss": 3.5045, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.759387838934775e-05, + "loss": 3.4958, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.758549244183723e-05, + "loss": 3.5079, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577122873130447e-05, + "loss": 3.4998, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.756873692561992e-05, + "loss": 3.5034, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.75603509781094e-05, + "loss": 3.5035, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.755196503059888e-05, + "loss": 3.4938, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.754357908308836e-05, + "loss": 3.5197, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535209514381572e-05, + "loss": 3.503, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7526823566871052e-05, + "loss": 3.5, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518437619360532e-05, + "loss": 3.4994, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510051671850012e-05, + "loss": 3.4939, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.8503193855285645, + "eval_runtime": 302.6158, + "eval_samples_per_second": 1260.975, + "eval_steps_per_second": 39.406, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7501665724339492e-05, + "loss": 3.4867, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493279776828972e-05, + "loss": 3.5064, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7484893829318452e-05, + "loss": 3.5142, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476507881807935e-05, + "loss": 3.5002, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468138313101144e-05, + "loss": 3.5156, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7459752365590624e-05, + "loss": 3.4934, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451366418080104e-05, + "loss": 3.5036, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7442980470569584e-05, + "loss": 3.489, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7434610901862797e-05, + "loss": 3.5044, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426224954352277e-05, + "loss": 3.5015, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7417839006841756e-05, + "loss": 3.4982, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409453059331236e-05, + "loss": 3.5137, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401083490624446e-05, + "loss": 3.4959, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7392697543113926e-05, + "loss": 3.4878, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384311595603405e-05, + "loss": 3.4916, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.737592564809289e-05, + "loss": 3.4981, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7367556079386098e-05, + "loss": 3.5032, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359170131875578e-05, + "loss": 3.4951, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7350784184365058e-05, + "loss": 3.5006, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342398236854538e-05, + "loss": 3.5215, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.733402866814775e-05, + "loss": 3.4992, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.732564272063723e-05, + "loss": 3.4938, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.731725677312671e-05, + "loss": 3.5012, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.730887082561619e-05, + "loss": 3.5091, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.73005012569094e-05, + "loss": 3.4909, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.729211530939888e-05, + "loss": 3.4991, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.728372936188836e-05, + "loss": 3.5003, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275343414377842e-05, + "loss": 3.4957, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7266957466867322e-05, + "loss": 3.4841, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725858789816053e-05, + "loss": 3.4915, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.725020195065001e-05, + "loss": 3.4978, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.724181600313949e-05, + "loss": 3.4989, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.723343005562897e-05, + "loss": 3.5144, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.722504410811845e-05, + "loss": 3.4942, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7216674539411664e-05, + "loss": 3.4922, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208288591901144e-05, + "loss": 3.5044, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7199902644390624e-05, + "loss": 3.4913, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191516696880104e-05, + "loss": 3.4904, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183147128173313e-05, + "loss": 3.4859, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7174761180662793e-05, + "loss": 3.4946, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166375233152276e-05, + "loss": 3.4845, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7157989285641756e-05, + "loss": 3.5141, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.714960333813123e-05, + "loss": 3.4899, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141233769424445e-05, + "loss": 3.4982, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7132847821913925e-05, + "loss": 3.4982, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.71244618744034e-05, + "loss": 3.4947, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.711607592689288e-05, + "loss": 3.4935, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.710768997938236e-05, + "loss": 3.4854, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099320410675577e-05, + "loss": 3.4834, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.709093446316505e-05, + "loss": 3.5046, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.708254851565453e-05, + "loss": 3.4946, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074162568144014e-05, + "loss": 3.4878, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7065776620633494e-05, + "loss": 3.4891, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057407051926703e-05, + "loss": 3.4963, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049021104416183e-05, + "loss": 3.4758, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7040635156905663e-05, + "loss": 3.5004, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032249209395143e-05, + "loss": 3.4903, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7023879640688355e-05, + "loss": 3.4896, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015493693177835e-05, + "loss": 3.5057, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007107745667315e-05, + "loss": 3.4848, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6998721798156795e-05, + "loss": 3.4831, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990352229450004e-05, + "loss": 3.4933, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6981966281939484e-05, + "loss": 3.4815, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973580334428968e-05, + "loss": 3.4826, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6965194386918448e-05, + "loss": 3.4959, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6956808439407927e-05, + "loss": 3.4997, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6948438870701137e-05, + "loss": 3.4839, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940052923190617e-05, + "loss": 3.4867, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6931666975680096e-05, + "loss": 3.4793, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923281028169576e-05, + "loss": 3.494, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.691491145946279e-05, + "loss": 3.4909, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.690652551195227e-05, + "loss": 3.4965, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.689813956444175e-05, + "loss": 3.4936, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.688975361693123e-05, + "loss": 3.4992, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881384048224438e-05, + "loss": 3.5065, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.687299810071392e-05, + "loss": 3.4797, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.68646121532034e-05, + "loss": 3.4939, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.685622620569288e-05, + "loss": 3.4989, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.684785663698609e-05, + "loss": 3.4827, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.683947068947557e-05, + "loss": 3.5056, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.683108474196505e-05, + "loss": 3.5001, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.682269879445453e-05, + "loss": 3.5051, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814329225747743e-05, + "loss": 3.5011, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6805943278237223e-05, + "loss": 3.4804, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797557330726702e-05, + "loss": 3.4908, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789171383216182e-05, + "loss": 3.491, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6780785435705662e-05, + "loss": 3.4997, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772415866998875e-05, + "loss": 3.4917, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764029919488355e-05, + "loss": 3.4899, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6755643971977835e-05, + "loss": 3.4974, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747258024467315e-05, + "loss": 3.4957, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6738872076956795e-05, + "loss": 3.4819, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730502508250004e-05, + "loss": 3.4889, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722116560739484e-05, + "loss": 3.4971, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6713730613228967e-05, + "loss": 3.5073, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705344665718447e-05, + "loss": 3.4939, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6696975097011656e-05, + "loss": 3.4778, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688589149501136e-05, + "loss": 3.4928, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680203201990616e-05, + "loss": 3.4962, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6671817254480096e-05, + "loss": 3.4961, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.666344768577331e-05, + "loss": 3.4928, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.665506173826279e-05, + "loss": 3.4909, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664667579075227e-05, + "loss": 3.476, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.663828984324175e-05, + "loss": 3.4974, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.662990389573123e-05, + "loss": 3.4758, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6621517948220708e-05, + "loss": 3.4918, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.661314837951392e-05, + "loss": 3.4823, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.66047624320034e-05, + "loss": 3.4969, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.659637648449288e-05, + "loss": 3.4805, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.658799053698236e-05, + "loss": 3.4948, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.657962096827557e-05, + "loss": 3.4881, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.657123502076505e-05, + "loss": 3.4846, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.656284907325453e-05, + "loss": 3.4899, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554463125744006e-05, + "loss": 3.4838, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546093557037222e-05, + "loss": 3.497, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6537707609526702e-05, + "loss": 3.4984, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529321662016182e-05, + "loss": 3.4922, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.652093571450566e-05, + "loss": 3.4892, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512566145798874e-05, + "loss": 3.4966, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504180198288354e-05, + "loss": 3.4945, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6495794250777834e-05, + "loss": 3.4753, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487408303267308e-05, + "loss": 3.4977, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479038734560523e-05, + "loss": 3.4897, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6470652787050003e-05, + "loss": 3.492, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.646226683953948e-05, + "loss": 3.4868, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.645388089202896e-05, + "loss": 3.4896, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.644549494451844e-05, + "loss": 3.4777, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437125375811656e-05, + "loss": 3.484, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.642873942830113e-05, + "loss": 3.4838, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6420353480790612e-05, + "loss": 3.4937, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6411967533280092e-05, + "loss": 3.5021, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403597964573308e-05, + "loss": 3.4894, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.639521201706278e-05, + "loss": 3.4826, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.638682606955226e-05, + "loss": 3.4912, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.637844012204174e-05, + "loss": 3.4956, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370070553334954e-05, + "loss": 3.4962, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6361684605824434e-05, + "loss": 3.4911, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353298658313914e-05, + "loss": 3.4882, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6344912710803393e-05, + "loss": 3.4906, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6336526763292873e-05, + "loss": 3.4955, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328157194586083e-05, + "loss": 3.4868, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6319771247075563e-05, + "loss": 3.4923, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311385299565046e-05, + "loss": 3.4897, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6302999352054526e-05, + "loss": 3.4839, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6294629783347735e-05, + "loss": 3.504, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286243835837215e-05, + "loss": 3.4914, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6277857888326695e-05, + "loss": 3.4876, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6269471940816175e-05, + "loss": 3.4841, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6261102372109387e-05, + "loss": 3.481, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.8515334129333496, + "eval_runtime": 302.6887, + "eval_samples_per_second": 1260.671, + "eval_steps_per_second": 39.397, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6252716424598867e-05, + "loss": 3.4796, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244330477088347e-05, + "loss": 3.4901, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6235944529577827e-05, + "loss": 3.5007, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6227574960871036e-05, + "loss": 3.4895, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6219189013360516e-05, + "loss": 3.5088, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.621080306585e-05, + "loss": 3.4768, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.620241711833948e-05, + "loss": 3.4939, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.619403117082896e-05, + "loss": 3.4747, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.618566160212217e-05, + "loss": 3.4926, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.617727565461165e-05, + "loss": 3.4907, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.616888970710113e-05, + "loss": 3.4848, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.616050375959061e-05, + "loss": 3.4996, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.615213419088382e-05, + "loss": 3.4831, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.61437482433733e-05, + "loss": 3.4774, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.613536229586278e-05, + "loss": 3.4779, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.612697634835226e-05, + "loss": 3.4851, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.611860677964547e-05, + "loss": 3.4896, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6110220832134953e-05, + "loss": 3.4815, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6101834884624433e-05, + "loss": 3.489, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6093448937113913e-05, + "loss": 3.5047, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085079368407122e-05, + "loss": 3.4886, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6076693420896602e-05, + "loss": 3.4851, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6068307473386082e-05, + "loss": 3.4881, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6059921525875562e-05, + "loss": 3.4942, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6051551957168775e-05, + "loss": 3.4786, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6043166009658255e-05, + "loss": 3.4889, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6034780062147734e-05, + "loss": 3.4893, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026394114637214e-05, + "loss": 3.4815, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018024545930424e-05, + "loss": 3.4748, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6009638598419907e-05, + "loss": 3.4766, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.6001252650909387e-05, + "loss": 3.4899, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5992866703398867e-05, + "loss": 3.4849, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5984480755888347e-05, + "loss": 3.5013, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976094808377827e-05, + "loss": 3.4874, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5967725239671036e-05, + "loss": 3.4739, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5959339292160516e-05, + "loss": 3.4885, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.595095334465e-05, + "loss": 3.485, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.594256739713948e-05, + "loss": 3.4751, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5934197828432688e-05, + "loss": 3.4766, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5925811880922168e-05, + "loss": 3.4816, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5917425933411648e-05, + "loss": 3.476, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5909039985901128e-05, + "loss": 3.4996, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.590067041719434e-05, + "loss": 3.4826, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.589228446968382e-05, + "loss": 3.487, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.58838985221733e-05, + "loss": 3.4894, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.587551257466278e-05, + "loss": 3.4813, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.586712662715226e-05, + "loss": 3.4845, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.585875705844547e-05, + "loss": 3.4717, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5850371110934953e-05, + "loss": 3.4636, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5841985163424433e-05, + "loss": 3.4958, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5833599215913913e-05, + "loss": 3.4828, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5825229647207122e-05, + "loss": 3.4794, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5816843699696602e-05, + "loss": 3.4749, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.580845775218608e-05, + "loss": 3.4811, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800071804675558e-05, + "loss": 3.4653, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5791685857165038e-05, + "loss": 3.4859, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783316288458254e-05, + "loss": 3.4828, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5774930340947734e-05, + "loss": 3.4789, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5766544393437207e-05, + "loss": 3.4894, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.575815844592669e-05, + "loss": 3.4711, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5749788877219906e-05, + "loss": 3.4725, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741402929709386e-05, + "loss": 3.4872, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.573301698219886e-05, + "loss": 3.4649, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.572463103468834e-05, + "loss": 3.4687, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716261465981555e-05, + "loss": 3.4878, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5707875518471032e-05, + "loss": 3.4886, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5699489570960512e-05, + "loss": 3.468, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5691103623449992e-05, + "loss": 3.481, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5682734054743208e-05, + "loss": 3.465, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.567434810723268e-05, + "loss": 3.4828, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.566596215972216e-05, + "loss": 3.4799, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5657576212211644e-05, + "loss": 3.4857, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5649206643504853e-05, + "loss": 3.4792, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5640820695994333e-05, + "loss": 3.4871, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5632434748483813e-05, + "loss": 3.4936, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624048800973293e-05, + "loss": 3.465, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5615662853462773e-05, + "loss": 3.4818, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5607293284755986e-05, + "loss": 3.4867, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5598907337245466e-05, + "loss": 3.4672, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5590521389734946e-05, + "loss": 3.4964, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5582135442224425e-05, + "loss": 3.488, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5573765873517635e-05, + "loss": 3.4887, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5565379926007115e-05, + "loss": 3.4946, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5556993978496594e-05, + "loss": 3.471, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5548608030986078e-05, + "loss": 3.4739, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5540238462279287e-05, + "loss": 3.4801, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5531852514768767e-05, + "loss": 3.487, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5523466567258247e-05, + "loss": 3.4786, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5515080619747727e-05, + "loss": 3.4793, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.550671105104094e-05, + "loss": 3.4785, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.549832510353042e-05, + "loss": 3.489, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.54899391560199e-05, + "loss": 3.47, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.548155320850938e-05, + "loss": 3.4765, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.547316726099886e-05, + "loss": 3.4868, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5464797692292068e-05, + "loss": 3.4918, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5456411744781548e-05, + "loss": 3.4846, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.544802579727103e-05, + "loss": 3.4659, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.543963984976051e-05, + "loss": 3.4795, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.543127028105372e-05, + "loss": 3.4822, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.54228843335432e-05, + "loss": 3.4851, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.541449838603268e-05, + "loss": 3.4825, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.540611243852216e-05, + "loss": 3.4782, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5397742869815373e-05, + "loss": 3.4655, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5389356922304853e-05, + "loss": 3.4823, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5380970974794333e-05, + "loss": 3.4684, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5372585027283813e-05, + "loss": 3.4779, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5364199079773293e-05, + "loss": 3.4683, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5355829511066502e-05, + "loss": 3.4833, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5347443563555985e-05, + "loss": 3.4683, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5339057616045465e-05, + "loss": 3.4855, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5330671668534945e-05, + "loss": 3.4713, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5322302099828154e-05, + "loss": 3.4746, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5313916152317634e-05, + "loss": 3.4757, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5305530204807114e-05, + "loss": 3.4744, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5297144257296594e-05, + "loss": 3.4802, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5288774688589807e-05, + "loss": 3.4887, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5280388741079286e-05, + "loss": 3.4802, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5272002793568766e-05, + "loss": 3.475, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.5263616846058246e-05, + "loss": 3.4842, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5255247277351455e-05, + "loss": 3.4822, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.524686132984094e-05, + "loss": 3.4649, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.523847538233042e-05, + "loss": 3.4861, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.52300894348199e-05, + "loss": 3.4741, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.522170348730938e-05, + "loss": 3.4824, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5213333918602588e-05, + "loss": 3.4744, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5204947971092068e-05, + "loss": 3.4784, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5196562023581548e-05, + "loss": 3.4639, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.518817607607103e-05, + "loss": 3.4766, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.517980650736424e-05, + "loss": 3.4733, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.517142055985372e-05, + "loss": 3.4793, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.51630346123432e-05, + "loss": 3.4868, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.515464866483268e-05, + "loss": 3.4808, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146279096125892e-05, + "loss": 3.4707, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5137893148615372e-05, + "loss": 3.4797, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5129507201104852e-05, + "loss": 3.4837, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5121121253594332e-05, + "loss": 3.4841, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.511275168488754e-05, + "loss": 3.4822, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.510436573737702e-05, + "loss": 3.4764, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.50959797898665e-05, + "loss": 3.4776, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5087593842355985e-05, + "loss": 3.4863, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5079207894845465e-05, + "loss": 3.4741, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5070838326138674e-05, + "loss": 3.4821, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5062452378628154e-05, + "loss": 3.4722, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5054066431117634e-05, + "loss": 3.477, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.504568048360711e-05, + "loss": 3.4912, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5037310914900326e-05, + "loss": 3.4823, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5028924967389806e-05, + "loss": 3.4728, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5020539019879286e-05, + "loss": 3.4699, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.501215307236876e-05, + "loss": 3.4736, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.8532137870788574, + "eval_runtime": 302.6504, + "eval_samples_per_second": 1260.831, + "eval_steps_per_second": 39.402, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500376712485824e-05, + "loss": 3.4606, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.4995381177347723e-05, + "loss": 3.4785, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4986995229837202e-05, + "loss": 3.4858, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4978609282326682e-05, + "loss": 3.4785, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970239713619895e-05, + "loss": 3.4933, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4961853766109375e-05, + "loss": 3.4722, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.495346781859885e-05, + "loss": 3.4772, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494508187108833e-05, + "loss": 3.4665, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4936712302381547e-05, + "loss": 3.4762, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928326354871024e-05, + "loss": 3.4784, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4919940407360504e-05, + "loss": 3.474, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911554459849984e-05, + "loss": 3.4858, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903184891143196e-05, + "loss": 3.4706, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4894798943632676e-05, + "loss": 3.466, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886412996122156e-05, + "loss": 3.4686, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878027048611636e-05, + "loss": 3.4726, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.486965747990485e-05, + "loss": 3.4794, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861271532394325e-05, + "loss": 3.4687, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4852885584883805e-05, + "loss": 3.477, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844499637373285e-05, + "loss": 3.496, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836130068666498e-05, + "loss": 3.4798, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4827744121155977e-05, + "loss": 3.4739, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819358173645457e-05, + "loss": 3.4748, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4810972226134937e-05, + "loss": 3.4813, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802602657428146e-05, + "loss": 3.4678, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794216709917626e-05, + "loss": 3.4764, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.478583076240711e-05, + "loss": 3.4752, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.477744481489659e-05, + "loss": 3.4725, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.476905886738607e-05, + "loss": 3.4637, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.476068929867928e-05, + "loss": 3.4678, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.475230335116876e-05, + "loss": 3.4736, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.474391740365824e-05, + "loss": 3.475, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.473553145614772e-05, + "loss": 3.4889, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727145508637202e-05, + "loss": 3.4767, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.471877593993041e-05, + "loss": 3.4612, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.471038999241989e-05, + "loss": 3.4778, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.470200404490937e-05, + "loss": 3.4769, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469361809739885e-05, + "loss": 3.4604, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685248528692063e-05, + "loss": 3.461, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4676862581181543e-05, + "loss": 3.4716, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668476633671023e-05, + "loss": 3.4618, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660090686160503e-05, + "loss": 3.4878, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4651721117453712e-05, + "loss": 3.4705, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4643335169943192e-05, + "loss": 3.4717, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4634949222432672e-05, + "loss": 3.4748, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4626563274922152e-05, + "loss": 3.4767, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618177327411632e-05, + "loss": 3.4699, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4609807758704845e-05, + "loss": 3.4608, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601421811194325e-05, + "loss": 3.4488, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.45930358636838e-05, + "loss": 3.4885, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4584649916173285e-05, + "loss": 3.4675, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576280347466497e-05, + "loss": 3.471, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4567894399955977e-05, + "loss": 3.467, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559508452445454e-05, + "loss": 3.4623, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551122504934934e-05, + "loss": 3.4553, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4542752936228146e-05, + "loss": 3.4706, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534366988717626e-05, + "loss": 3.4713, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4525981041207106e-05, + "loss": 3.4668, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517595093696586e-05, + "loss": 3.4819, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.45092255249898e-05, + "loss": 3.4588, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4500839577479275e-05, + "loss": 3.4559, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492453629968755e-05, + "loss": 3.4788, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484067682458235e-05, + "loss": 3.4499, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4475681734947718e-05, + "loss": 3.4554, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467312166240927e-05, + "loss": 3.4754, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4458926218730407e-05, + "loss": 3.4765, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450540271219887e-05, + "loss": 3.4573, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442154323709367e-05, + "loss": 3.469, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.443378475500258e-05, + "loss": 3.4544, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.442539880749206e-05, + "loss": 3.469, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.441701285998154e-05, + "loss": 3.4653, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440862691247102e-05, + "loss": 3.471, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.44002409649605e-05, + "loss": 3.4658, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439187139625371e-05, + "loss": 3.4749, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.438348544874319e-05, + "loss": 3.4812, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375099501232672e-05, + "loss": 3.4596, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4366713553722152e-05, + "loss": 3.4676, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435834398501536e-05, + "loss": 3.4767, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.434995803750484e-05, + "loss": 3.4563, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.434157208999432e-05, + "loss": 3.4804, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.43331861424838e-05, + "loss": 3.4798, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4324816573777013e-05, + "loss": 3.4782, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316430626266493e-05, + "loss": 3.4806, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308044678755973e-05, + "loss": 3.4635, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4299658731245453e-05, + "loss": 3.4584, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291289162538662e-05, + "loss": 3.47, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4282903215028142e-05, + "loss": 3.478, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4274517267517626e-05, + "loss": 3.469, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266131320007102e-05, + "loss": 3.4644, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4257761751300315e-05, + "loss": 3.4661, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249375803789795e-05, + "loss": 3.4762, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4240989856279275e-05, + "loss": 3.4621, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4232603908768754e-05, + "loss": 3.4635, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4224217961258234e-05, + "loss": 3.4706, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4215848392551447e-05, + "loss": 3.4816, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207462445040927e-05, + "loss": 3.4736, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199076497530403e-05, + "loss": 3.4547, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4190690550019883e-05, + "loss": 3.4661, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182320981313096e-05, + "loss": 3.4683, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4173935033802576e-05, + "loss": 3.4742, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4165549086292056e-05, + "loss": 3.4683, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157163138781536e-05, + "loss": 3.4686, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4148793570074748e-05, + "loss": 3.4536, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140407622564225e-05, + "loss": 3.4651, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132021675053708e-05, + "loss": 3.4572, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4123635727543188e-05, + "loss": 3.4697, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115249780032668e-05, + "loss": 3.4502, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4106880211325877e-05, + "loss": 3.4783, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4098494263815357e-05, + "loss": 3.4588, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090108316304837e-05, + "loss": 3.4677, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4081722368794317e-05, + "loss": 3.462, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.407335280008753e-05, + "loss": 3.4642, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.406496685257701e-05, + "loss": 3.4639, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.405658090506649e-05, + "loss": 3.4642, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404819495755597e-05, + "loss": 3.4688, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.403982538884918e-05, + "loss": 3.4764, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.403143944133866e-05, + "loss": 3.4666, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023053493828142e-05, + "loss": 3.4666, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4014667546317622e-05, + "loss": 3.47, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.400629797761083e-05, + "loss": 3.4743, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.399791203010031e-05, + "loss": 3.4494, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.398952608258979e-05, + "loss": 3.4738, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.398114013507927e-05, + "loss": 3.4606, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3972770566372483e-05, + "loss": 3.4716, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964384618861963e-05, + "loss": 3.4628, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3955998671351443e-05, + "loss": 3.4677, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3947612723840923e-05, + "loss": 3.4562, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939226776330403e-05, + "loss": 3.4618, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3930857207623612e-05, + "loss": 3.4656, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3922471260113095e-05, + "loss": 3.465, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914085312602575e-05, + "loss": 3.4704, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3905699365092055e-05, + "loss": 3.4733, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897329796385264e-05, + "loss": 3.4584, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3888943848874744e-05, + "loss": 3.4667, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3880557901364224e-05, + "loss": 3.474, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872171953853704e-05, + "loss": 3.4719, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3863802385146917e-05, + "loss": 3.4658, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855416437636397e-05, + "loss": 3.4692, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847030490125877e-05, + "loss": 3.4627, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3838644542615353e-05, + "loss": 3.4766, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830274973908566e-05, + "loss": 3.459, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.382188902639805e-05, + "loss": 3.4708, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381350307888753e-05, + "loss": 3.4629, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3805117131377006e-05, + "loss": 3.463, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3796747562670218e-05, + "loss": 3.4792, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788361615159698e-05, + "loss": 3.4713, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3779975667649178e-05, + "loss": 3.4635, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3771589720138658e-05, + "loss": 3.4551, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.376322015143187e-05, + "loss": 3.4635, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.853109359741211, + "eval_runtime": 303.8822, + "eval_samples_per_second": 1255.72, + "eval_steps_per_second": 39.242, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.375483420392135e-05, + "loss": 3.4518, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3746448256410827e-05, + "loss": 3.4615, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3738062308900307e-05, + "loss": 3.4759, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3729676361389787e-05, + "loss": 3.4698, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3721306792683e-05, + "loss": 3.4818, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.371292084517248e-05, + "loss": 3.4617, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.370453489766196e-05, + "loss": 3.4607, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.369614895015144e-05, + "loss": 3.4606, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.368777938144465e-05, + "loss": 3.4599, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.367939343393413e-05, + "loss": 3.4664, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.367100748642361e-05, + "loss": 3.4662, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.366262153891309e-05, + "loss": 3.4694, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.36542519702063e-05, + "loss": 3.4651, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.364586602269578e-05, + "loss": 3.4528, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.363748007518526e-05, + "loss": 3.4565, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.362909412767474e-05, + "loss": 3.4572, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3620724558967953e-05, + "loss": 3.4671, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3612338611457433e-05, + "loss": 3.4606, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3603952663946913e-05, + "loss": 3.4643, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3595566716436393e-05, + "loss": 3.481, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3587197147729602e-05, + "loss": 3.4717, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3578811200219082e-05, + "loss": 3.4584, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3570425252708565e-05, + "loss": 3.4666, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3562039305198045e-05, + "loss": 3.4669, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3553653357687525e-05, + "loss": 3.4573, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3545283788980734e-05, + "loss": 3.4685, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3536897841470214e-05, + "loss": 3.462, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3528511893959694e-05, + "loss": 3.4619, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3520125946449174e-05, + "loss": 3.457, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.3511739998938654e-05, + "loss": 3.4524, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.3503354051428134e-05, + "loss": 3.4619, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3494984482721347e-05, + "loss": 3.4615, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3486598535210827e-05, + "loss": 3.4713, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3478212587700303e-05, + "loss": 3.4669, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3469826640189786e-05, + "loss": 3.4524, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3461457071483e-05, + "loss": 3.4678, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.345307112397248e-05, + "loss": 3.4643, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3444685176461955e-05, + "loss": 3.4462, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3436299228951435e-05, + "loss": 3.4576, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3427929660244648e-05, + "loss": 3.4576, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3419543712734128e-05, + "loss": 3.4536, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3411157765223608e-05, + "loss": 3.4734, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3402771817713088e-05, + "loss": 3.4589, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.33944022490063e-05, + "loss": 3.4603, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3386016301495777e-05, + "loss": 3.4616, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3377630353985257e-05, + "loss": 3.4629, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.336924440647474e-05, + "loss": 3.4628, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3360874837767953e-05, + "loss": 3.448, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.335248889025743e-05, + "loss": 3.4351, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.334410294274691e-05, + "loss": 3.4777, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.333571699523639e-05, + "loss": 3.4557, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.33273474265296e-05, + "loss": 3.4666, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.331896147901908e-05, + "loss": 3.4511, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.331057553150856e-05, + "loss": 3.4518, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.330218958399804e-05, + "loss": 3.4451, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.329380363648752e-05, + "loss": 3.4563, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.328543406778073e-05, + "loss": 3.463, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.327704812027021e-05, + "loss": 3.4523, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.326866217275969e-05, + "loss": 3.4726, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3260276225249174e-05, + "loss": 3.4495, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3251906656542383e-05, + "loss": 3.4428, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3243520709031863e-05, + "loss": 3.4659, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3235134761521343e-05, + "loss": 3.443, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.3226748814010823e-05, + "loss": 3.4413, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.3218379245304035e-05, + "loss": 3.4639, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.3209993297793515e-05, + "loss": 3.4611, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3201607350282995e-05, + "loss": 3.4502, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3193221402772475e-05, + "loss": 3.4559, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3184835455261955e-05, + "loss": 3.4427, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.3176465886555164e-05, + "loss": 3.4595, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.3168079939044644e-05, + "loss": 3.4518, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3159693991534127e-05, + "loss": 3.4635, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3151308044023607e-05, + "loss": 3.4548, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3142938475316816e-05, + "loss": 3.4631, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3134552527806296e-05, + "loss": 3.469, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3126166580295776e-05, + "loss": 3.4459, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3117780632785256e-05, + "loss": 3.4584, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.310941106407847e-05, + "loss": 3.4626, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.310102511656795e-05, + "loss": 3.4436, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.309263916905743e-05, + "loss": 3.4683, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084253221546905e-05, + "loss": 3.4692, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3075883652840118e-05, + "loss": 3.464, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3067497705329598e-05, + "loss": 3.4743, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059111757819078e-05, + "loss": 3.45, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3050725810308558e-05, + "loss": 3.4464, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.304235624160177e-05, + "loss": 3.459, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.303397029409125e-05, + "loss": 3.4624, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3025584346580727e-05, + "loss": 3.4624, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.301719839907021e-05, + "loss": 3.4533, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3008828830363422e-05, + "loss": 3.4511, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.3000442882852902e-05, + "loss": 3.4647, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.299205693534238e-05, + "loss": 3.45, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.298367098783186e-05, + "loss": 3.4523, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.297530141912507e-05, + "loss": 3.4587, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.296691547161455e-05, + "loss": 3.4717, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.295852952410403e-05, + "loss": 3.4637, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.295014357659351e-05, + "loss": 3.4429, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2941774007886724e-05, + "loss": 3.4538, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.29333880603762e-05, + "loss": 3.4584, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.292500211286568e-05, + "loss": 3.4603, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2916616165355164e-05, + "loss": 3.4598, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2908246596648376e-05, + "loss": 3.4576, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2899860649137853e-05, + "loss": 3.4417, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2891474701627333e-05, + "loss": 3.4496, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2883088754116813e-05, + "loss": 3.4517, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.2874719185410025e-05, + "loss": 3.4571, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.2866333237899505e-05, + "loss": 3.4393, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.2857947290388985e-05, + "loss": 3.4697, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.2849561342878465e-05, + "loss": 3.4474, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2841191774171674e-05, + "loss": 3.4554, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2832805826661154e-05, + "loss": 3.4451, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2824419879150634e-05, + "loss": 3.459, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2816033931640114e-05, + "loss": 3.4525, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.2807664362933326e-05, + "loss": 3.4498, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.2799278415422806e-05, + "loss": 3.4584, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2790892467912286e-05, + "loss": 3.4669, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2782506520401766e-05, + "loss": 3.4513, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.277413695169498e-05, + "loss": 3.4623, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.276575100418446e-05, + "loss": 3.4513, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.275736505667394e-05, + "loss": 3.4641, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.274897910916342e-05, + "loss": 3.443, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.27405931616529e-05, + "loss": 3.4623, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2732223592946108e-05, + "loss": 3.4479, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2723837645435588e-05, + "loss": 3.4589, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2715451697925068e-05, + "loss": 3.4532, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.270706575041455e-05, + "loss": 3.4553, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.269869618170776e-05, + "loss": 3.4408, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.269031023419724e-05, + "loss": 3.4512, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.268192428668672e-05, + "loss": 3.4542, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.26735383391762e-05, + "loss": 3.4576, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2665168770469412e-05, + "loss": 3.4523, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2656782822958892e-05, + "loss": 3.4628, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2648396875448372e-05, + "loss": 3.4499, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2640010927937852e-05, + "loss": 3.4578, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.263162498042733e-05, + "loss": 3.4597, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.262325541172054e-05, + "loss": 3.4638, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.261486946421002e-05, + "loss": 3.4539, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2606483516699505e-05, + "loss": 3.4557, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598113947992714e-05, + "loss": 3.4481, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2589728000482194e-05, + "loss": 3.468, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2581342052971674e-05, + "loss": 3.4468, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.257295610546115e-05, + "loss": 3.4595, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2564586536754366e-05, + "loss": 3.4507, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2556200589243846e-05, + "loss": 3.4556, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2547814641733326e-05, + "loss": 3.4638, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2539428694222803e-05, + "loss": 3.4571, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2531042746712282e-05, + "loss": 3.4567, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2522673178005495e-05, + "loss": 3.4403, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2514287230494975e-05, + "loss": 3.4539, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.8541321754455566, + "eval_runtime": 307.9284, + "eval_samples_per_second": 1239.22, + "eval_steps_per_second": 38.727, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2505901282984455e-05, + "loss": 3.4471, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2497515335473935e-05, + "loss": 3.4467, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2489145766767147e-05, + "loss": 3.4625, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2480759819256624e-05, + "loss": 3.46, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2472373871746104e-05, + "loss": 3.4692, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2463987924235587e-05, + "loss": 3.4489, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.24556183555288e-05, + "loss": 3.4496, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.2447232408018276e-05, + "loss": 3.4492, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.2438846460507756e-05, + "loss": 3.4498, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2430460512997236e-05, + "loss": 3.457, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.242209094429045e-05, + "loss": 3.4524, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.241370499677993e-05, + "loss": 3.4561, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.240533542807314e-05, + "loss": 3.4533, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.239694948056262e-05, + "loss": 3.4427, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.2388563533052098e-05, + "loss": 3.4475, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.2380177585541578e-05, + "loss": 3.443, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2371791638031058e-05, + "loss": 3.4563, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2363405690520537e-05, + "loss": 3.4499, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.235501974301002e-05, + "loss": 3.4507, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.23466337954995e-05, + "loss": 3.4684, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.233826422679271e-05, + "loss": 3.4636, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.232987827928219e-05, + "loss": 3.4506, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.232149233177167e-05, + "loss": 3.4493, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.231310638426115e-05, + "loss": 3.4556, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2304736815554362e-05, + "loss": 3.4511, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2296350868043842e-05, + "loss": 3.4551, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2287964920533322e-05, + "loss": 3.4514, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2279578973022802e-05, + "loss": 3.4518, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.227120940431601e-05, + "loss": 3.4447, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.226282345680549e-05, + "loss": 3.4422, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2254437509294974e-05, + "loss": 3.4433, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2246051561784454e-05, + "loss": 3.4533, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2237681993077664e-05, + "loss": 3.4608, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2229296045567143e-05, + "loss": 3.4588, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.2220910098056623e-05, + "loss": 3.4408, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.2212524150546103e-05, + "loss": 3.4525, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.2204154581839316e-05, + "loss": 3.4535, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2195768634328796e-05, + "loss": 3.4377, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2187382686818276e-05, + "loss": 3.4466, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2178996739307752e-05, + "loss": 3.4457, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2170627170600965e-05, + "loss": 3.4382, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.2162241223090445e-05, + "loss": 3.4587, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.2153855275579928e-05, + "loss": 3.448, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.2145469328069405e-05, + "loss": 3.4516, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.2137099759362617e-05, + "loss": 3.4496, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.2128713811852097e-05, + "loss": 3.4481, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.2120327864341574e-05, + "loss": 3.4521, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2111941916831057e-05, + "loss": 3.4389, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.210357234812427e-05, + "loss": 3.4197, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.209518640061375e-05, + "loss": 3.4658, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.2086800453103226e-05, + "loss": 3.4452, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2078414505592706e-05, + "loss": 3.4542, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.207004493688592e-05, + "loss": 3.442, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.20616589893754e-05, + "loss": 3.4401, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.205327304186488e-05, + "loss": 3.43, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.204488709435436e-05, + "loss": 3.4456, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.203651752564757e-05, + "loss": 3.4526, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2028131578137047e-05, + "loss": 3.4414, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.2019745630626527e-05, + "loss": 3.4586, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.201135968311601e-05, + "loss": 3.4427, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2002990114409223e-05, + "loss": 3.4331, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.19946041668987e-05, + "loss": 3.4491, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.198621821938818e-05, + "loss": 3.4355, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.197783227187766e-05, + "loss": 3.4292, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.1969462703170872e-05, + "loss": 3.4545, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1961076755660352e-05, + "loss": 3.452, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1952690808149832e-05, + "loss": 3.4382, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1944304860639312e-05, + "loss": 3.4413, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.1935918913128792e-05, + "loss": 3.4347, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1927549344422e-05, + "loss": 3.4464, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.191916339691148e-05, + "loss": 3.4444, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.191077744940096e-05, + "loss": 3.4477, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1902391501890444e-05, + "loss": 3.4468, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1894021933183653e-05, + "loss": 3.4486, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1885635985673133e-05, + "loss": 3.4589, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1877250038162613e-05, + "loss": 3.4349, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1868864090652093e-05, + "loss": 3.4493, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1860494521945306e-05, + "loss": 3.45, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1852108574434786e-05, + "loss": 3.4369, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1843722626924266e-05, + "loss": 3.4551, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1835336679413746e-05, + "loss": 3.462, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1826967110706955e-05, + "loss": 3.4504, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1818581163196435e-05, + "loss": 3.464, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1810195215685915e-05, + "loss": 3.4371, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.1801809268175398e-05, + "loss": 3.4354, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.1793439699468607e-05, + "loss": 3.4474, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.1785053751958087e-05, + "loss": 3.4551, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1776667804447567e-05, + "loss": 3.4439, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1768281856937047e-05, + "loss": 3.4446, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.175991228823026e-05, + "loss": 3.4434, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.175152634071974e-05, + "loss": 3.454, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.174314039320922e-05, + "loss": 3.439, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.17347544456987e-05, + "loss": 3.445, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.172638487699191e-05, + "loss": 3.4465, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.171799892948139e-05, + "loss": 3.4586, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.170961298197087e-05, + "loss": 3.4514, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.170122703446035e-05, + "loss": 3.4295, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.169285746575356e-05, + "loss": 3.4486, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.168447151824304e-05, + "loss": 3.4437, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.167608557073252e-05, + "loss": 3.4514, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.1667699623221997e-05, + "loss": 3.4446, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1659330054515213e-05, + "loss": 3.4451, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1650944107004693e-05, + "loss": 3.4355, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1642558159494173e-05, + "loss": 3.4353, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.163417221198365e-05, + "loss": 3.445, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.1625802643276862e-05, + "loss": 3.4435, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.1617416695766342e-05, + "loss": 3.4276, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.1609030748255822e-05, + "loss": 3.4586, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.1600644800745302e-05, + "loss": 3.4353, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1592275232038514e-05, + "loss": 3.4403, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1583889284527994e-05, + "loss": 3.4372, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.157550333701747e-05, + "loss": 3.4413, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.156711738950695e-05, + "loss": 3.4462, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.1558747820800167e-05, + "loss": 3.4371, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.1550361873289647e-05, + "loss": 3.4468, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1541975925779123e-05, + "loss": 3.4532, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1533589978268603e-05, + "loss": 3.4447, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.1525220409561816e-05, + "loss": 3.4514, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.1516834462051296e-05, + "loss": 3.4401, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1508448514540776e-05, + "loss": 3.4508, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.1500062567030256e-05, + "loss": 3.4331, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.1491692998323468e-05, + "loss": 3.4504, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1483307050812945e-05, + "loss": 3.4399, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1474921103302425e-05, + "loss": 3.4456, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1466535155791905e-05, + "loss": 3.4443, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.145816558708512e-05, + "loss": 3.4427, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.1449779639574597e-05, + "loss": 3.4339, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1441393692064077e-05, + "loss": 3.4365, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.1433007744553557e-05, + "loss": 3.44, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1424621797043037e-05, + "loss": 3.4498, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1416252228336246e-05, + "loss": 3.4393, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.140786628082573e-05, + "loss": 3.4545, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.139948033331521e-05, + "loss": 3.4356, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.139111076460842e-05, + "loss": 3.4466, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.13827248170979e-05, + "loss": 3.4476, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.137433886958738e-05, + "loss": 3.4517, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.1365952922076858e-05, + "loss": 3.4442, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.135758335337007e-05, + "loss": 3.4456, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.134919740585955e-05, + "loss": 3.4349, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.134081145834903e-05, + "loss": 3.4573, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.133242551083851e-05, + "loss": 3.4352, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.132405594213172e-05, + "loss": 3.4476, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.13156699946212e-05, + "loss": 3.4401, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1307284047110683e-05, + "loss": 3.4484, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1298898099600163e-05, + "loss": 3.4483, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1290528530893372e-05, + "loss": 3.4441, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.1282142583382852e-05, + "loss": 3.4469, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.1273756635872332e-05, + "loss": 3.4317, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.1265370688361812e-05, + "loss": 3.4447, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.857224941253662, + "eval_runtime": 304.9787, + "eval_samples_per_second": 1251.205, + "eval_steps_per_second": 39.101, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1256984740851292e-05, + "loss": 3.4393, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1248598793340775e-05, + "loss": 3.4331, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1240212845830252e-05, + "loss": 3.4495, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1231826898319732e-05, + "loss": 3.4478, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1223457329612944e-05, + "loss": 3.4574, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215071382102424e-05, + "loss": 3.4432, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1206685434591904e-05, + "loss": 3.4412, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1198299487081384e-05, + "loss": 3.4421, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1189929918374597e-05, + "loss": 3.4387, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1181543970864073e-05, + "loss": 3.4445, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173158023353553e-05, + "loss": 3.4378, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1164772075843033e-05, + "loss": 3.4458, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1156402507136246e-05, + "loss": 3.4474, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.1148016559625726e-05, + "loss": 3.4327, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1139630612115205e-05, + "loss": 3.4333, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1131244664604685e-05, + "loss": 3.434, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1122858717094165e-05, + "loss": 3.4467, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1114472769583645e-05, + "loss": 3.4409, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1106086822073125e-05, + "loss": 3.4364, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1097700874562605e-05, + "loss": 3.4582, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1089331305855818e-05, + "loss": 3.4506, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1080945358345298e-05, + "loss": 3.4424, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1072559410834778e-05, + "loss": 3.4422, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1064173463324254e-05, + "loss": 3.4381, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1055803894617467e-05, + "loss": 3.4404, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1047417947106947e-05, + "loss": 3.4437, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.103903199959643e-05, + "loss": 3.4416, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1030646052085907e-05, + "loss": 3.4446, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.102227648337912e-05, + "loss": 3.4321, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.10138905358686e-05, + "loss": 3.4325, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.1005504588358076e-05, + "loss": 3.428, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.099711864084756e-05, + "loss": 3.4449, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.098874907214077e-05, + "loss": 3.4496, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.098036312463025e-05, + "loss": 3.4467, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0971977177119728e-05, + "loss": 3.4352, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0963591229609208e-05, + "loss": 3.4333, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.095522166090242e-05, + "loss": 3.4446, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.09468357133919e-05, + "loss": 3.4314, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.093844976588138e-05, + "loss": 3.4301, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.093006381837086e-05, + "loss": 3.4346, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0921694249664073e-05, + "loss": 3.4327, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.091330830215355e-05, + "loss": 3.4438, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.090492235464303e-05, + "loss": 3.4406, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0896536407132513e-05, + "loss": 3.4408, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0888166838425725e-05, + "loss": 3.4348, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.08797808909152e-05, + "loss": 3.4424, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.087139494340468e-05, + "loss": 3.4421, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.086300899589416e-05, + "loss": 3.4289, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0854639427187374e-05, + "loss": 3.4083, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0846253479676854e-05, + "loss": 3.4523, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0837867532166334e-05, + "loss": 3.4323, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0829481584655814e-05, + "loss": 3.4465, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0821112015949023e-05, + "loss": 3.431, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0812726068438503e-05, + "loss": 3.4312, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0804340120927983e-05, + "loss": 3.4166, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0795954173417463e-05, + "loss": 3.4342, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0787584604710675e-05, + "loss": 3.4447, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0779198657200155e-05, + "loss": 3.4268, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0770812709689635e-05, + "loss": 3.4526, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0762426762179115e-05, + "loss": 3.4325, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754057193472328e-05, + "loss": 3.4231, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0745671245961808e-05, + "loss": 3.4328, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0737285298451288e-05, + "loss": 3.4256, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.0728899350940768e-05, + "loss": 3.4208, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0720529782233977e-05, + "loss": 3.4395, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0712143834723457e-05, + "loss": 3.4409, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.070377426601667e-05, + "loss": 3.4268, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.069538831850615e-05, + "loss": 3.4348, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.068700237099563e-05, + "loss": 3.4196, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.067861642348511e-05, + "loss": 3.4406, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.067023047597459e-05, + "loss": 3.4289, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.066184452846407e-05, + "loss": 3.4351, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.065345858095355e-05, + "loss": 3.4404, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.064507263344303e-05, + "loss": 3.4329, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.063670306473624e-05, + "loss": 3.453, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.062831711722572e-05, + "loss": 3.425, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.06199311697152e-05, + "loss": 3.4369, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0611545222204678e-05, + "loss": 3.4361, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.060317565349789e-05, + "loss": 3.4261, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.059478970598737e-05, + "loss": 3.4438, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0586403758476854e-05, + "loss": 3.4481, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.057801781096633e-05, + "loss": 3.4401, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0569648242259543e-05, + "loss": 3.4524, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0561262294749023e-05, + "loss": 3.4294, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0552876347238502e-05, + "loss": 3.4234, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0544490399727982e-05, + "loss": 3.4348, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0536120831021195e-05, + "loss": 3.4474, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0527734883510675e-05, + "loss": 3.4287, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.051934893600015e-05, + "loss": 3.4386, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.051096298848963e-05, + "loss": 3.4319, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0502593419782844e-05, + "loss": 3.4403, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.0494207472272324e-05, + "loss": 3.4318, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0485821524761804e-05, + "loss": 3.431, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0477435577251284e-05, + "loss": 3.4347, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0469066008544496e-05, + "loss": 3.4499, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0460680061033973e-05, + "loss": 3.4403, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0452294113523453e-05, + "loss": 3.419, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0443908166012936e-05, + "loss": 3.4357, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.043553859730615e-05, + "loss": 3.4343, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.0427152649795625e-05, + "loss": 3.4454, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0418766702285105e-05, + "loss": 3.4375, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0410380754774585e-05, + "loss": 3.4318, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402011186067798e-05, + "loss": 3.4249, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0393625238557278e-05, + "loss": 3.4212, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0385239291046757e-05, + "loss": 3.434, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.0376853343536237e-05, + "loss": 3.4316, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.0368483774829447e-05, + "loss": 3.4198, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0360097827318926e-05, + "loss": 3.4427, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0351711879808406e-05, + "loss": 3.4296, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0343325932297886e-05, + "loss": 3.4288, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.03349563635911e-05, + "loss": 3.4289, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.032657041608058e-05, + "loss": 3.4279, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.031818446857006e-05, + "loss": 3.4362, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.030979852105954e-05, + "loss": 3.4274, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.030141257354902e-05, + "loss": 3.439, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.029304300484223e-05, + "loss": 3.4424, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.028465705733171e-05, + "loss": 3.4303, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.027627110982119e-05, + "loss": 3.4403, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.026788516231067e-05, + "loss": 3.4297, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.025951559360388e-05, + "loss": 3.4417, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.025112964609336e-05, + "loss": 3.4263, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.024274369858284e-05, + "loss": 3.433, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0234357751072323e-05, + "loss": 3.4305, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0225988182365533e-05, + "loss": 3.4369, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0217602234855012e-05, + "loss": 3.4377, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0209216287344492e-05, + "loss": 3.4315, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.02008467186377e-05, + "loss": 3.4185, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0192460771127185e-05, + "loss": 3.4315, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0184074823616665e-05, + "loss": 3.4273, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0175688876106145e-05, + "loss": 3.4355, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0167302928595625e-05, + "loss": 3.4307, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0158933359888834e-05, + "loss": 3.4407, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0150547412378314e-05, + "loss": 3.423, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0142161464867794e-05, + "loss": 3.4414, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0133791896161006e-05, + "loss": 3.4328, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0125405948650486e-05, + "loss": 3.4436, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0117020001139966e-05, + "loss": 3.4331, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0108634053629446e-05, + "loss": 3.4296, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0100264484922655e-05, + "loss": 3.4295, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.009187853741214e-05, + "loss": 3.4464, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.008349258990162e-05, + "loss": 3.4232, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.00751066423911e-05, + "loss": 3.436, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0066737073684308e-05, + "loss": 3.4331, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0058351126173787e-05, + "loss": 3.4338, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0049965178663267e-05, + "loss": 3.4364, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0041579231152747e-05, + "loss": 3.4374, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.003320966244596e-05, + "loss": 3.4323, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.002482371493544e-05, + "loss": 3.424, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.001643776742492e-05, + "loss": 3.4313, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.8587112426757812, + "eval_runtime": 304.5832, + "eval_samples_per_second": 1252.83, + "eval_steps_per_second": 39.152, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.00080518199144e-05, + "loss": 3.4221, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9999665872403876e-05, + "loss": 3.4256, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.999127992489336e-05, + "loss": 3.4348, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.998289397738284e-05, + "loss": 3.435, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.997452440867605e-05, + "loss": 3.4492, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.996613846116553e-05, + "loss": 3.4273, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.995775251365501e-05, + "loss": 3.4318, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.994936656614449e-05, + "loss": 3.4316, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.99409969974377e-05, + "loss": 3.4255, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.993261104992718e-05, + "loss": 3.4381, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.992422510241666e-05, + "loss": 3.4274, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.991583915490614e-05, + "loss": 3.4327, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.990746958619935e-05, + "loss": 3.4443, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.989908363868883e-05, + "loss": 3.4151, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.989069769117831e-05, + "loss": 3.4233, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9882311743667793e-05, + "loss": 3.4207, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9873942174961002e-05, + "loss": 3.4379, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9865556227450482e-05, + "loss": 3.427, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.9857170279939962e-05, + "loss": 3.4253, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.9848784332429442e-05, + "loss": 3.4434, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9840414763722655e-05, + "loss": 3.4404, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9832028816212135e-05, + "loss": 3.4313, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9823642868701615e-05, + "loss": 3.4325, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9815256921191095e-05, + "loss": 3.429, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9806887352484304e-05, + "loss": 3.4324, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9798501404973784e-05, + "loss": 3.4303, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.9790115457463264e-05, + "loss": 3.4265, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9781729509952747e-05, + "loss": 3.4368, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9773359941245956e-05, + "loss": 3.4202, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9764973993735436e-05, + "loss": 3.419, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9756588046224916e-05, + "loss": 3.4246, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9748202098714396e-05, + "loss": 3.4285, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.973983253000761e-05, + "loss": 3.4325, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.973144658249709e-05, + "loss": 3.4423, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.972306063498657e-05, + "loss": 3.4221, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.9714674687476048e-05, + "loss": 3.4272, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.9706305118769257e-05, + "loss": 3.4362, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.9697919171258737e-05, + "loss": 3.4177, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9689533223748217e-05, + "loss": 3.42, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.96811472762377e-05, + "loss": 3.4271, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.967277770753091e-05, + "loss": 3.4175, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.966439176002039e-05, + "loss": 3.4302, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.965600581250987e-05, + "loss": 3.431, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.964761986499935e-05, + "loss": 3.4325, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9639250296292562e-05, + "loss": 3.424, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9630864348782042e-05, + "loss": 3.4323, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.9622478401271522e-05, + "loss": 3.4293, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.9614092453761e-05, + "loss": 3.4229, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.960572288505421e-05, + "loss": 3.399, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.959733693754369e-05, + "loss": 3.4372, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.958895099003317e-05, + "loss": 3.421, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.958056504252265e-05, + "loss": 3.4319, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.9572195473815863e-05, + "loss": 3.4228, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9563809526305343e-05, + "loss": 3.4174, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.9555423578794823e-05, + "loss": 3.4108, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.95470376312843e-05, + "loss": 3.4223, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.9538668062577516e-05, + "loss": 3.4373, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9530282115066996e-05, + "loss": 3.4123, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9521896167556472e-05, + "loss": 3.4456, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9513510220045952e-05, + "loss": 3.4237, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.9505140651339165e-05, + "loss": 3.409, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.9496754703828645e-05, + "loss": 3.4263, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9488368756318125e-05, + "loss": 3.4154, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9479982808807605e-05, + "loss": 3.4142, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9471613240100817e-05, + "loss": 3.4252, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9463227292590297e-05, + "loss": 3.4314, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9454857723883506e-05, + "loss": 3.4132, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9446471776372986e-05, + "loss": 3.4273, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.943808582886247e-05, + "loss": 3.4078, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.9429699881351946e-05, + "loss": 3.4265, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9421313933841426e-05, + "loss": 3.4228, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9412927986330906e-05, + "loss": 3.4239, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9404542038820386e-05, + "loss": 3.4291, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9396156091309866e-05, + "loss": 3.4257, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9387786522603078e-05, + "loss": 3.4403, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9379400575092558e-05, + "loss": 3.4163, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9371014627582038e-05, + "loss": 3.4253, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9362628680071518e-05, + "loss": 3.4231, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9354259111364727e-05, + "loss": 3.4164, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9345873163854207e-05, + "loss": 3.4327, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9337487216343687e-05, + "loss": 3.4338, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.932910126883317e-05, + "loss": 3.434, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.932073170012638e-05, + "loss": 3.4423, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.931234575261586e-05, + "loss": 3.4211, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.930395980510534e-05, + "loss": 3.4111, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.929557385759482e-05, + "loss": 3.4204, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9287204288888032e-05, + "loss": 3.436, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9278818341377512e-05, + "loss": 3.4176, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9270432393866992e-05, + "loss": 3.4243, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.9262046446356472e-05, + "loss": 3.4262, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.925367687764968e-05, + "loss": 3.4263, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.924529093013916e-05, + "loss": 3.4248, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.923690498262864e-05, + "loss": 3.4178, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.9228519035118124e-05, + "loss": 3.4263, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.9220149466411333e-05, + "loss": 3.4377, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.9211763518900813e-05, + "loss": 3.431, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.9203377571390293e-05, + "loss": 3.4122, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.9194991623879773e-05, + "loss": 3.4247, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9186622055172986e-05, + "loss": 3.4226, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.9178236107662466e-05, + "loss": 3.4283, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9169850160151946e-05, + "loss": 3.4287, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9161464212641422e-05, + "loss": 3.4216, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9153094643934635e-05, + "loss": 3.4176, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9144708696424115e-05, + "loss": 3.4112, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.9136322748913594e-05, + "loss": 3.4234, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.9127936801403074e-05, + "loss": 3.4232, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9119567232696287e-05, + "loss": 3.4131, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.9111181285185767e-05, + "loss": 3.4286, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9102795337675247e-05, + "loss": 3.4188, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.9094409390164723e-05, + "loss": 3.4193, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.908603982145794e-05, + "loss": 3.4146, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.907765387394742e-05, + "loss": 3.4163, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9069267926436896e-05, + "loss": 3.4281, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9060881978926376e-05, + "loss": 3.4137, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9052512410219588e-05, + "loss": 3.429, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9044126462709068e-05, + "loss": 3.4311, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9035740515198548e-05, + "loss": 3.4217, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9027354567688028e-05, + "loss": 3.4281, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.901898499898124e-05, + "loss": 3.4201, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.901059905147072e-05, + "loss": 3.4308, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.9002213103960197e-05, + "loss": 3.4195, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8993827156449677e-05, + "loss": 3.4235, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8985457587742893e-05, + "loss": 3.4188, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.897707164023237e-05, + "loss": 3.4239, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.896868569272185e-05, + "loss": 3.4297, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.896029974521133e-05, + "loss": 3.4175, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.8951930176504542e-05, + "loss": 3.4097, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.894354422899402e-05, + "loss": 3.4166, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8935158281483502e-05, + "loss": 3.4185, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8926772333972982e-05, + "loss": 3.4267, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8918402765266194e-05, + "loss": 3.4202, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.891001681775567e-05, + "loss": 3.4294, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.890163087024515e-05, + "loss": 3.4127, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.889324492273463e-05, + "loss": 3.4356, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.8884875354027843e-05, + "loss": 3.4195, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.8876489406517323e-05, + "loss": 3.4297, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8868103459006803e-05, + "loss": 3.4236, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8859717511496283e-05, + "loss": 3.4176, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8851347942789492e-05, + "loss": 3.4176, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.8842961995278972e-05, + "loss": 3.4358, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.8834576047768455e-05, + "loss": 3.4136, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8826190100257935e-05, + "loss": 3.4251, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8817820531551145e-05, + "loss": 3.4242, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8809434584040624e-05, + "loss": 3.421, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8801048636530104e-05, + "loss": 3.4263, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8792662689019584e-05, + "loss": 3.4263, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8784293120312797e-05, + "loss": 3.4196, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8775907172802277e-05, + "loss": 3.4226, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8767521225291757e-05, + "loss": 3.4182, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.8596272468566895, + "eval_runtime": 303.7386, + "eval_samples_per_second": 1256.314, + "eval_steps_per_second": 39.261, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8759135277781237e-05, + "loss": 3.4111, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.8750765709074446e-05, + "loss": 3.4128, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.8742379761563926e-05, + "loss": 3.4256, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.873401019285714e-05, + "loss": 3.4294, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.8725624245346618e-05, + "loss": 3.4373, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.8717238297836098e-05, + "loss": 3.413, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.8708852350325578e-05, + "loss": 3.4209, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.8700466402815058e-05, + "loss": 3.4222, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.8692080455304538e-05, + "loss": 3.4125, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.8683694507794018e-05, + "loss": 3.4279, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.8675308560283498e-05, + "loss": 3.4156, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.866693899157671e-05, + "loss": 3.4209, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.865856942286992e-05, + "loss": 3.4363, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.86501834753594e-05, + "loss": 3.4065, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.864179752784888e-05, + "loss": 3.4098, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.8633411580338363e-05, + "loss": 3.4115, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.8625025632827843e-05, + "loss": 3.426, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.8616639685317323e-05, + "loss": 3.4246, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.86082537378068e-05, + "loss": 3.4094, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.859986779029628e-05, + "loss": 3.4317, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.8591498221589492e-05, + "loss": 3.432, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8583112274078972e-05, + "loss": 3.42, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.857472632656845e-05, + "loss": 3.4209, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.856634037905793e-05, + "loss": 3.4184, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8557970810351144e-05, + "loss": 3.4233, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.854958486284062e-05, + "loss": 3.4168, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.85411989153301e-05, + "loss": 3.4136, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.853281296781958e-05, + "loss": 3.4264, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.8524443399112793e-05, + "loss": 3.4115, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8516057451602273e-05, + "loss": 3.4071, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.8507671504091753e-05, + "loss": 3.4166, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.8499285556581233e-05, + "loss": 3.4168, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.8490915987874442e-05, + "loss": 3.4186, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.8482530040363925e-05, + "loss": 3.4336, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.8474144092853405e-05, + "loss": 3.415, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.8465758145342885e-05, + "loss": 3.4139, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8457388576636094e-05, + "loss": 3.4273, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.8449002629125574e-05, + "loss": 3.4023, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8440616681615054e-05, + "loss": 3.412, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.8432230734104534e-05, + "loss": 3.416, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.8423861165397747e-05, + "loss": 3.4092, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.8415475217887227e-05, + "loss": 3.4145, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.8407089270376707e-05, + "loss": 3.4219, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.8398703322866187e-05, + "loss": 3.4234, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.8390333754159396e-05, + "loss": 3.4111, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.838194780664888e-05, + "loss": 3.4215, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.837356185913836e-05, + "loss": 3.4179, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.836517591162784e-05, + "loss": 3.4127, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.8356806342921048e-05, + "loss": 3.3935, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.8348420395410528e-05, + "loss": 3.4245, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.8340034447900008e-05, + "loss": 3.4124, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8331648500389488e-05, + "loss": 3.4267, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.83232789316827e-05, + "loss": 3.4059, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.831489298417218e-05, + "loss": 3.408, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.830650703666166e-05, + "loss": 3.4001, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.829812108915114e-05, + "loss": 3.4099, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.828975152044435e-05, + "loss": 3.4282, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8281365572933833e-05, + "loss": 3.4041, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8272979625423313e-05, + "loss": 3.4296, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.8264593677912793e-05, + "loss": 3.414, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.8256224109206002e-05, + "loss": 3.3976, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.824783816169548e-05, + "loss": 3.4121, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.823945221418496e-05, + "loss": 3.4008, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.823106626667444e-05, + "loss": 3.4082, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.8222696697967654e-05, + "loss": 3.4132, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.8214310750457134e-05, + "loss": 3.4224, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.8205941181750343e-05, + "loss": 3.4044, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.8197555234239823e-05, + "loss": 3.416, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.8189169286729303e-05, + "loss": 3.3987, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.8180783339218786e-05, + "loss": 3.4158, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.8172397391708266e-05, + "loss": 3.4123, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.8164011444197746e-05, + "loss": 3.4161, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.8155625496687223e-05, + "loss": 3.413, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.8147239549176703e-05, + "loss": 3.4141, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.8138869980469915e-05, + "loss": 3.4312, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.8130484032959395e-05, + "loss": 3.4056, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.8122098085448875e-05, + "loss": 3.4174, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.8113712137938355e-05, + "loss": 3.4129, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.8105342569231568e-05, + "loss": 3.4042, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.8096956621721044e-05, + "loss": 3.4204, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.8088570674210524e-05, + "loss": 3.4234, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.8080184726700004e-05, + "loss": 3.4216, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.807181515799322e-05, + "loss": 3.4333, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.8063429210482697e-05, + "loss": 3.4125, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.8055043262972177e-05, + "loss": 3.3996, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.8046657315461656e-05, + "loss": 3.4128, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.8038287746754866e-05, + "loss": 3.4221, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.802990179924435e-05, + "loss": 3.4106, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.802151585173383e-05, + "loss": 3.4143, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.801312990422331e-05, + "loss": 3.4135, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.8004760335516518e-05, + "loss": 3.4205, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.7996374388005998e-05, + "loss": 3.4128, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.7987988440495478e-05, + "loss": 3.4071, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7979602492984958e-05, + "loss": 3.4148, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.797123292427817e-05, + "loss": 3.4293, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.796284697676765e-05, + "loss": 3.4205, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.795446102925713e-05, + "loss": 3.3987, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.794607508174661e-05, + "loss": 3.4149, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.793770551303982e-05, + "loss": 3.4134, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.7929319565529303e-05, + "loss": 3.4193, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7920933618018783e-05, + "loss": 3.4169, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.7912547670508262e-05, + "loss": 3.4085, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.790417810180147e-05, + "loss": 3.4061, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.789579215429095e-05, + "loss": 3.4003, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.788740620678043e-05, + "loss": 3.4128, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.787902025926991e-05, + "loss": 3.4097, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.7870650690563124e-05, + "loss": 3.4045, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.7862264743052604e-05, + "loss": 3.4133, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.7853878795542084e-05, + "loss": 3.4112, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.7845492848031564e-05, + "loss": 3.4075, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.7837123279324773e-05, + "loss": 3.4058, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.7828737331814256e-05, + "loss": 3.4051, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.7820351384303736e-05, + "loss": 3.4188, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7811965436793216e-05, + "loss": 3.4016, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7803595868086425e-05, + "loss": 3.4171, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.7795209920575905e-05, + "loss": 3.4216, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.7786823973065385e-05, + "loss": 3.4104, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.7778438025554865e-05, + "loss": 3.4159, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.7770068456848078e-05, + "loss": 3.413, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.7761682509337558e-05, + "loss": 3.419, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.7753296561827038e-05, + "loss": 3.4111, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.7744910614316517e-05, + "loss": 3.4116, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.7736541045609727e-05, + "loss": 3.4118, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.772815509809921e-05, + "loss": 3.4109, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.771976915058869e-05, + "loss": 3.4152, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.771138320307817e-05, + "loss": 3.4121, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.770301363437138e-05, + "loss": 3.4009, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.769462768686086e-05, + "loss": 3.4105, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.768624173935034e-05, + "loss": 3.4033, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.767785579183982e-05, + "loss": 3.4183, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.766948622313303e-05, + "loss": 3.4101, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.766110027562251e-05, + "loss": 3.4176, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.765271432811199e-05, + "loss": 3.4023, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.76443447594052e-05, + "loss": 3.4245, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.763595881189468e-05, + "loss": 3.4089, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.7627572864384164e-05, + "loss": 3.4238, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.7619186916873644e-05, + "loss": 3.4144, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.761080096936312e-05, + "loss": 3.4084, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.7602431400656333e-05, + "loss": 3.404, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.7594045453145813e-05, + "loss": 3.429, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.758565950563529e-05, + "loss": 3.4013, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.7577289936928505e-05, + "loss": 3.4184, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7568903989417985e-05, + "loss": 3.4111, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7560518041907465e-05, + "loss": 3.4105, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.755213209439694e-05, + "loss": 3.4157, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.7543762525690154e-05, + "loss": 3.4111, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.7535376578179634e-05, + "loss": 3.412, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.7526990630669117e-05, + "loss": 3.4137, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.7518604683158594e-05, + "loss": 3.4054, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.8608524799346924, + "eval_runtime": 303.5835, + "eval_samples_per_second": 1256.956, + "eval_steps_per_second": 39.281, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.7510218735648074e-05, + "loss": 3.3976, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7501832788137554e-05, + "loss": 3.4035, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.7493446840627034e-05, + "loss": 3.4157, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7485060893116514e-05, + "loss": 3.4185, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7476691324409726e-05, + "loss": 3.4285, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7468305376899206e-05, + "loss": 3.4053, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7459919429388686e-05, + "loss": 3.4096, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7451533481878166e-05, + "loss": 3.4166, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.7443147534367646e-05, + "loss": 3.4026, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.7434761586857123e-05, + "loss": 3.4104, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.7426375639346602e-05, + "loss": 3.4116, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.741800607063982e-05, + "loss": 3.412, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.7409636501933027e-05, + "loss": 3.4236, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.7401250554422507e-05, + "loss": 3.396, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.7392864606911987e-05, + "loss": 3.398, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.7384478659401467e-05, + "loss": 3.3982, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.7376092711890947e-05, + "loss": 3.421, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.7367706764380427e-05, + "loss": 3.4105, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.7359320816869907e-05, + "loss": 3.4007, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.7350934869359387e-05, + "loss": 3.4189, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.7342565300652596e-05, + "loss": 3.4202, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.7334179353142076e-05, + "loss": 3.4108, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.7325793405631556e-05, + "loss": 3.41, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.7317407458121036e-05, + "loss": 3.4065, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.730903788941425e-05, + "loss": 3.4185, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.730065194190373e-05, + "loss": 3.4064, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.729226599439321e-05, + "loss": 3.4023, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.728388004688269e-05, + "loss": 3.418, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7275510478175898e-05, + "loss": 3.4008, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.726712453066538e-05, + "loss": 3.3964, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.725873858315486e-05, + "loss": 3.4092, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.725035263564434e-05, + "loss": 3.4058, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.724198306693755e-05, + "loss": 3.412, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.723359711942703e-05, + "loss": 3.4215, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.722521117191651e-05, + "loss": 3.4006, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.721682522440599e-05, + "loss": 3.4063, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.7208455655699202e-05, + "loss": 3.4167, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.7200069708188682e-05, + "loss": 3.3919, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.7191683760678162e-05, + "loss": 3.4045, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.7183297813167642e-05, + "loss": 3.406, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.717492824446085e-05, + "loss": 3.3985, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.7166542296950335e-05, + "loss": 3.4048, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.7158156349439814e-05, + "loss": 3.4108, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7149770401929294e-05, + "loss": 3.4133, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.7141400833222504e-05, + "loss": 3.402, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.7133014885711984e-05, + "loss": 3.407, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.7124628938201463e-05, + "loss": 3.4068, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.7116242990690943e-05, + "loss": 3.4016, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.7107873421984156e-05, + "loss": 3.3846, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.7099487474473636e-05, + "loss": 3.4141, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.7091101526963116e-05, + "loss": 3.404, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.7082715579452596e-05, + "loss": 3.4142, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.7074346010745805e-05, + "loss": 3.4016, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.7065960063235288e-05, + "loss": 3.3923, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7057574115724768e-05, + "loss": 3.3925, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.7049188168214248e-05, + "loss": 3.4001, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.7040818599507457e-05, + "loss": 3.4159, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.7032432651996937e-05, + "loss": 3.3936, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.7024046704486417e-05, + "loss": 3.4171, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.701567713577963e-05, + "loss": 3.4075, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.700729118826911e-05, + "loss": 3.3883, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.699890524075859e-05, + "loss": 3.4043, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.699051929324807e-05, + "loss": 3.3912, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.698214972454128e-05, + "loss": 3.3959, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.697376377703076e-05, + "loss": 3.3994, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.6965377829520242e-05, + "loss": 3.4152, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.695700826081345e-05, + "loss": 3.394, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.694862231330293e-05, + "loss": 3.4026, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.694023636579241e-05, + "loss": 3.3897, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.693185041828189e-05, + "loss": 3.4028, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6923464470771367e-05, + "loss": 3.4038, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.691507852326085e-05, + "loss": 3.4067, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.690669257575033e-05, + "loss": 3.4026, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.689830662823981e-05, + "loss": 3.4017, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.688993705953302e-05, + "loss": 3.4212, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.68815511120225e-05, + "loss": 3.3971, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.687316516451198e-05, + "loss": 3.4038, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.686477921700146e-05, + "loss": 3.4029, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.6856409648294672e-05, + "loss": 3.3996, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.6848023700784152e-05, + "loss": 3.4128, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.6839637753273632e-05, + "loss": 3.406, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.6831251805763112e-05, + "loss": 3.4129, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.682288223705632e-05, + "loss": 3.4218, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.6814496289545804e-05, + "loss": 3.4106, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.6806110342035284e-05, + "loss": 3.3871, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.6797724394524764e-05, + "loss": 3.398, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789371204621706e-05, + "loss": 3.4126, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.6780985257111186e-05, + "loss": 3.4023, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.6772599309600666e-05, + "loss": 3.4044, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6764213362090146e-05, + "loss": 3.4037, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.6755827414579626e-05, + "loss": 3.4071, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.6747441467069106e-05, + "loss": 3.4039, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.6739055519558586e-05, + "loss": 3.3971, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.6730669572048066e-05, + "loss": 3.4073, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.6722300003341275e-05, + "loss": 3.4156, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.6713914055830758e-05, + "loss": 3.4086, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.6705528108320238e-05, + "loss": 3.3867, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.6697142160809718e-05, + "loss": 3.4043, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.6688772592102927e-05, + "loss": 3.4059, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.6680386644592407e-05, + "loss": 3.4082, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.6672000697081887e-05, + "loss": 3.4086, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.6663614749571367e-05, + "loss": 3.3969, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.665524518086458e-05, + "loss": 3.3954, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.664685923335406e-05, + "loss": 3.3908, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.663847328584354e-05, + "loss": 3.4017, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.663008733833302e-05, + "loss": 3.4008, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.662171776962623e-05, + "loss": 3.395, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.6613331822115712e-05, + "loss": 3.4072, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.6604945874605192e-05, + "loss": 3.3995, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.659655992709467e-05, + "loss": 3.3977, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.658819035838788e-05, + "loss": 3.397, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.657980441087736e-05, + "loss": 3.3908, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.657141846336684e-05, + "loss": 3.4069, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.656303251585632e-05, + "loss": 3.3961, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.6554662947149533e-05, + "loss": 3.4016, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.6546276999639013e-05, + "loss": 3.4099, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.6537907430932222e-05, + "loss": 3.4027, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.6529521483421702e-05, + "loss": 3.4036, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.6521135535911182e-05, + "loss": 3.4059, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.6512749588400665e-05, + "loss": 3.4055, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.6504363640890145e-05, + "loss": 3.4066, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.6495977693379622e-05, + "loss": 3.3979, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.6487591745869102e-05, + "loss": 3.4004, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.6479205798358582e-05, + "loss": 3.4, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.647083622965179e-05, + "loss": 3.4056, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.6462450282141274e-05, + "loss": 3.3998, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.6454064334630754e-05, + "loss": 3.393, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.6445678387120234e-05, + "loss": 3.3972, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.6437308818413443e-05, + "loss": 3.3939, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.6428922870902923e-05, + "loss": 3.4093, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.6420536923392403e-05, + "loss": 3.3993, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.6412150975881883e-05, + "loss": 3.4076, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.6403781407175096e-05, + "loss": 3.3944, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.6395395459664576e-05, + "loss": 3.4085, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.6387009512154056e-05, + "loss": 3.3994, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.6378623564643536e-05, + "loss": 3.4159, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.637027037474048e-05, + "loss": 3.4025, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.636188442722996e-05, + "loss": 3.3989, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.635349847971944e-05, + "loss": 3.397, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6345112532208917e-05, + "loss": 3.4162, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.6336726584698397e-05, + "loss": 3.3938, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.6328340637187877e-05, + "loss": 3.4035, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.6319954689677357e-05, + "loss": 3.4034, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.6311568742166837e-05, + "loss": 3.4014, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.630319917346005e-05, + "loss": 3.4045, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.629481322594953e-05, + "loss": 3.402, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.628642727843901e-05, + "loss": 3.403, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.627804133092849e-05, + "loss": 3.4041, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.6269671762221698e-05, + "loss": 3.3944, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.8623785972595215, + "eval_runtime": 304.1155, + "eval_samples_per_second": 1254.757, + "eval_steps_per_second": 39.212, + "step": 2060640 + }, + { + "epoch": 1.0, + "learning_rate": 1.626128581471118e-05, + "loss": 3.3899, + "step": 2060800 + }, + { + "epoch": 1.0, + "learning_rate": 1.625291624600439e-05, + "loss": 3.3917, + "step": 2061312 + }, + { + "epoch": 1.0, + "learning_rate": 1.624453029849387e-05, + "loss": 3.4045, + "step": 2061824 + }, + { + "epoch": 1.0, + "learning_rate": 1.623614435098335e-05, + "loss": 3.4061, + "step": 2062336 + }, + { + "epoch": 1.0, + "learning_rate": 1.622775840347283e-05, + "loss": 3.4169, + "step": 2062848 + }, + { + "epoch": 1.0, + "learning_rate": 1.621937245596231e-05, + "loss": 3.3935, + "step": 2063360 + }, + { + "epoch": 1.0, + "learning_rate": 1.621098650845179e-05, + "loss": 3.3987, + "step": 2063872 + }, + { + "epoch": 1.0, + "learning_rate": 1.6202600560941274e-05, + "loss": 3.4048, + "step": 2064384 + }, + { + "epoch": 1.0, + "learning_rate": 1.619421461343075e-05, + "loss": 3.3956, + "step": 2064896 + }, + { + "epoch": 1.0, + "learning_rate": 1.6185845044723963e-05, + "loss": 3.3963, + "step": 2065408 + }, + { + "epoch": 1.0, + "learning_rate": 1.6177459097213443e-05, + "loss": 3.4053, + "step": 2065920 + }, + { + "epoch": 1.0, + "learning_rate": 1.616907314970292e-05, + "loss": 3.4006, + "step": 2066432 + }, + { + "epoch": 1.0, + "learning_rate": 1.6160703580996135e-05, + "loss": 3.4142, + "step": 2066944 + }, + { + "epoch": 1.0, + "learning_rate": 1.6152317633485615e-05, + "loss": 3.3877, + "step": 2067456 + }, + { + "epoch": 1.0, + "learning_rate": 1.6143931685975095e-05, + "loss": 3.3873, + "step": 2067968 + }, + { + "epoch": 1.0, + "learning_rate": 1.6135545738464572e-05, + "loss": 3.3899, + "step": 2068480 + }, + { + "epoch": 1.0, + "learning_rate": 1.6127159790954052e-05, + "loss": 3.407, + "step": 2068992 + }, + { + "epoch": 1.0, + "learning_rate": 1.611877384344353e-05, + "loss": 3.4042, + "step": 2069504 + }, + { + "epoch": 1.0, + "learning_rate": 1.611038789593301e-05, + "loss": 3.3891, + "step": 2070016 + }, + { + "epoch": 1.0, + "learning_rate": 1.610200194842249e-05, + "loss": 3.4059, + "step": 2070528 + }, + { + "epoch": 1.0, + "learning_rate": 1.6093632379715704e-05, + "loss": 3.4149, + "step": 2071040 + }, + { + "epoch": 1.0, + "learning_rate": 1.6085246432205184e-05, + "loss": 3.3982, + "step": 2071552 + }, + { + "epoch": 1.0, + "learning_rate": 1.6076860484694664e-05, + "loss": 3.402, + "step": 2072064 + }, + { + "epoch": 1.0, + "learning_rate": 1.6068474537184144e-05, + "loss": 3.3967, + "step": 2072576 + }, + { + "epoch": 1.0, + "learning_rate": 1.6060104968477353e-05, + "loss": 3.4108, + "step": 2073088 + }, + { + "epoch": 1.0, + "learning_rate": 1.6051719020966836e-05, + "loss": 3.3931, + "step": 2073600 + }, + { + "epoch": 1.0, + "learning_rate": 1.6043333073456316e-05, + "loss": 3.3932, + "step": 2074112 + }, + { + "epoch": 1.0, + "learning_rate": 1.6034947125945796e-05, + "loss": 3.4118, + "step": 2074624 + }, + { + "epoch": 1.0, + "learning_rate": 1.6026577557239005e-05, + "loss": 3.3879, + "step": 2075136 + }, + { + "epoch": 1.0, + "learning_rate": 1.6018191609728485e-05, + "loss": 3.386, + "step": 2075648 + }, + { + "epoch": 1.01, + "learning_rate": 1.6009805662217965e-05, + "loss": 3.3943, + "step": 2076160 + }, + { + "epoch": 1.01, + "learning_rate": 1.6001419714707445e-05, + "loss": 3.3935, + "step": 2076672 + }, + { + "epoch": 1.01, + "learning_rate": 1.5993050146000658e-05, + "loss": 3.4036, + "step": 2077184 + }, + { + "epoch": 1.01, + "learning_rate": 1.5984664198490138e-05, + "loss": 3.4132, + "step": 2077696 + }, + { + "epoch": 1.01, + "learning_rate": 1.5976278250979618e-05, + "loss": 3.3887, + "step": 2078208 + }, + { + "epoch": 1.01, + "learning_rate": 1.5967892303469098e-05, + "loss": 3.3991, + "step": 2078720 + }, + { + "epoch": 1.01, + "learning_rate": 1.5959522734762307e-05, + "loss": 3.4065, + "step": 2079232 + }, + { + "epoch": 1.01, + "learning_rate": 1.595113678725179e-05, + "loss": 3.3822, + "step": 2079744 + }, + { + "epoch": 1.01, + "learning_rate": 1.594275083974127e-05, + "loss": 3.3918, + "step": 2080256 + }, + { + "epoch": 1.01, + "learning_rate": 1.593436489223075e-05, + "loss": 3.398, + "step": 2080768 + }, + { + "epoch": 1.01, + "learning_rate": 1.592599532352396e-05, + "loss": 3.3852, + "step": 2081280 + }, + { + "epoch": 1.01, + "learning_rate": 1.591760937601344e-05, + "loss": 3.3965, + "step": 2081792 + }, + { + "epoch": 1.01, + "learning_rate": 1.590922342850292e-05, + "loss": 3.4043, + "step": 2082304 + }, + { + "epoch": 1.01, + "learning_rate": 1.59008374809924e-05, + "loss": 3.4004, + "step": 2082816 + }, + { + "epoch": 1.01, + "learning_rate": 1.589246791228561e-05, + "loss": 3.3923, + "step": 2083328 + }, + { + "epoch": 1.01, + "learning_rate": 1.588408196477509e-05, + "loss": 3.3984, + "step": 2083840 + }, + { + "epoch": 1.01, + "learning_rate": 1.587569601726457e-05, + "loss": 3.3954, + "step": 2084352 + }, + { + "epoch": 1.01, + "learning_rate": 1.5867310069754048e-05, + "loss": 3.3945, + "step": 2084864 + }, + { + "epoch": 1.01, + "learning_rate": 1.585894050104726e-05, + "loss": 3.3732, + "step": 2085376 + }, + { + "epoch": 1.01, + "learning_rate": 1.5850554553536744e-05, + "loss": 3.4016, + "step": 2085888 + }, + { + "epoch": 1.01, + "learning_rate": 1.5842168606026224e-05, + "loss": 3.3987, + "step": 2086400 + }, + { + "epoch": 1.01, + "learning_rate": 1.58337826585157e-05, + "loss": 3.4003, + "step": 2086912 + }, + { + "epoch": 1.01, + "learning_rate": 1.5825413089808913e-05, + "loss": 3.3889, + "step": 2087424 + }, + { + "epoch": 1.01, + "learning_rate": 1.5817027142298393e-05, + "loss": 3.3839, + "step": 2087936 + }, + { + "epoch": 1.01, + "learning_rate": 1.5808641194787873e-05, + "loss": 3.3824, + "step": 2088448 + }, + { + "epoch": 1.01, + "learning_rate": 1.5800255247277353e-05, + "loss": 3.3859, + "step": 2088960 + }, + { + "epoch": 1.01, + "learning_rate": 1.5791885678570565e-05, + "loss": 3.4078, + "step": 2089472 + }, + { + "epoch": 1.01, + "learning_rate": 1.5783499731060045e-05, + "loss": 3.3854, + "step": 2089984 + }, + { + "epoch": 1.01, + "learning_rate": 1.577511378354952e-05, + "loss": 3.3993, + "step": 2090496 + }, + { + "epoch": 1.01, + "learning_rate": 1.5766727836039e-05, + "loss": 3.3984, + "step": 2091008 + }, + { + "epoch": 1.01, + "learning_rate": 1.5758358267332214e-05, + "loss": 3.3816, + "step": 2091520 + }, + { + "epoch": 1.01, + "learning_rate": 1.5749972319821697e-05, + "loss": 3.3901, + "step": 2092032 + }, + { + "epoch": 1.01, + "learning_rate": 1.5741586372311174e-05, + "loss": 3.383, + "step": 2092544 + }, + { + "epoch": 1.01, + "learning_rate": 1.5733216803604386e-05, + "loss": 3.3887, + "step": 2093056 + }, + { + "epoch": 1.01, + "learning_rate": 1.5724830856093866e-05, + "loss": 3.3846, + "step": 2093568 + }, + { + "epoch": 1.01, + "learning_rate": 1.5716444908583343e-05, + "loss": 3.4068, + "step": 2094080 + }, + { + "epoch": 1.01, + "learning_rate": 1.570807533987656e-05, + "loss": 3.3884, + "step": 2094592 + }, + { + "epoch": 1.01, + "learning_rate": 1.569968939236604e-05, + "loss": 3.3868, + "step": 2095104 + }, + { + "epoch": 1.01, + "learning_rate": 1.569130344485552e-05, + "loss": 3.3841, + "step": 2095616 + }, + { + "epoch": 1.01, + "learning_rate": 1.5682917497344995e-05, + "loss": 3.3914, + "step": 2096128 + }, + { + "epoch": 1.01, + "learning_rate": 1.5674531549834475e-05, + "loss": 3.3931, + "step": 2096640 + }, + { + "epoch": 1.01, + "learning_rate": 1.5666145602323955e-05, + "loss": 3.3933, + "step": 2097152 + }, + { + "epoch": 1.01, + "learning_rate": 1.5657759654813435e-05, + "loss": 3.397, + "step": 2097664 + }, + { + "epoch": 1.01, + "learning_rate": 1.5649373707302915e-05, + "loss": 3.3943, + "step": 2098176 + }, + { + "epoch": 1.01, + "learning_rate": 1.5641004138596128e-05, + "loss": 3.4064, + "step": 2098688 + }, + { + "epoch": 1.01, + "learning_rate": 1.5632618191085608e-05, + "loss": 3.3867, + "step": 2099200 + }, + { + "epoch": 1.01, + "learning_rate": 1.5624232243575088e-05, + "loss": 3.396, + "step": 2099712 + }, + { + "epoch": 1.01, + "learning_rate": 1.5615846296064567e-05, + "loss": 3.3928, + "step": 2100224 + }, + { + "epoch": 1.01, + "learning_rate": 1.5607476727357777e-05, + "loss": 3.3883, + "step": 2100736 + }, + { + "epoch": 1.01, + "learning_rate": 1.559909077984726e-05, + "loss": 3.4015, + "step": 2101248 + }, + { + "epoch": 1.01, + "learning_rate": 1.559070483233674e-05, + "loss": 3.3956, + "step": 2101760 + }, + { + "epoch": 1.01, + "learning_rate": 1.558231888482622e-05, + "loss": 3.4055, + "step": 2102272 + }, + { + "epoch": 1.01, + "learning_rate": 1.557394931611943e-05, + "loss": 3.4079, + "step": 2102784 + }, + { + "epoch": 1.01, + "learning_rate": 1.556556336860891e-05, + "loss": 3.4032, + "step": 2103296 + }, + { + "epoch": 1.01, + "learning_rate": 1.555717742109839e-05, + "loss": 3.3776, + "step": 2103808 + }, + { + "epoch": 1.01, + "learning_rate": 1.554879147358787e-05, + "loss": 3.3899, + "step": 2104320 + }, + { + "epoch": 1.01, + "learning_rate": 1.554042190488108e-05, + "loss": 3.4012, + "step": 2104832 + }, + { + "epoch": 1.01, + "learning_rate": 1.553205233617429e-05, + "loss": 3.3969, + "step": 2105344 + }, + { + "epoch": 1.01, + "learning_rate": 1.552366638866377e-05, + "loss": 3.3915, + "step": 2105856 + }, + { + "epoch": 1.01, + "learning_rate": 1.551528044115325e-05, + "loss": 3.3959, + "step": 2106368 + }, + { + "epoch": 1.02, + "learning_rate": 1.550689449364273e-05, + "loss": 3.3974, + "step": 2106880 + }, + { + "epoch": 1.02, + "learning_rate": 1.5498508546132214e-05, + "loss": 3.3903, + "step": 2107392 + }, + { + "epoch": 1.02, + "learning_rate": 1.5490122598621694e-05, + "loss": 3.3879, + "step": 2107904 + }, + { + "epoch": 1.02, + "learning_rate": 1.5481736651111174e-05, + "loss": 3.3977, + "step": 2108416 + }, + { + "epoch": 1.02, + "learning_rate": 1.5473367082404383e-05, + "loss": 3.4001, + "step": 2108928 + }, + { + "epoch": 1.02, + "learning_rate": 1.5464981134893863e-05, + "loss": 3.4033, + "step": 2109440 + }, + { + "epoch": 1.02, + "learning_rate": 1.5456595187383343e-05, + "loss": 3.3774, + "step": 2109952 + }, + { + "epoch": 1.02, + "learning_rate": 1.5448209239872822e-05, + "loss": 3.3938, + "step": 2110464 + }, + { + "epoch": 1.02, + "learning_rate": 1.5439839671166035e-05, + "loss": 3.3964, + "step": 2110976 + }, + { + "epoch": 1.02, + "learning_rate": 1.5431453723655515e-05, + "loss": 3.3978, + "step": 2111488 + }, + { + "epoch": 1.02, + "learning_rate": 1.5423067776144995e-05, + "loss": 3.3966, + "step": 2112000 + }, + { + "epoch": 1.02, + "learning_rate": 1.541468182863447e-05, + "loss": 3.3877, + "step": 2112512 + }, + { + "epoch": 1.02, + "learning_rate": 1.5406312259927684e-05, + "loss": 3.3879, + "step": 2113024 + }, + { + "epoch": 1.02, + "learning_rate": 1.5397926312417167e-05, + "loss": 3.3782, + "step": 2113536 + }, + { + "epoch": 1.02, + "learning_rate": 1.5389540364906647e-05, + "loss": 3.3945, + "step": 2114048 + }, + { + "epoch": 1.02, + "learning_rate": 1.5381154417396124e-05, + "loss": 3.3874, + "step": 2114560 + }, + { + "epoch": 1.02, + "learning_rate": 1.5372784848689336e-05, + "loss": 3.3837, + "step": 2115072 + }, + { + "epoch": 1.02, + "learning_rate": 1.5364398901178816e-05, + "loss": 3.3951, + "step": 2115584 + }, + { + "epoch": 1.02, + "learning_rate": 1.5356012953668296e-05, + "loss": 3.3906, + "step": 2116096 + }, + { + "epoch": 1.02, + "learning_rate": 1.5347627006157776e-05, + "loss": 3.3845, + "step": 2116608 + }, + { + "epoch": 1.02, + "learning_rate": 1.533925743745099e-05, + "loss": 3.3909, + "step": 2117120 + }, + { + "epoch": 1.02, + "learning_rate": 1.533087148994047e-05, + "loss": 3.3807, + "step": 2117632 + }, + { + "epoch": 1.02, + "learning_rate": 1.5322485542429945e-05, + "loss": 3.4017, + "step": 2118144 + }, + { + "epoch": 1.02, + "learning_rate": 1.5314099594919425e-05, + "loss": 3.3814, + "step": 2118656 + }, + { + "epoch": 1.02, + "learning_rate": 1.5305730026212638e-05, + "loss": 3.3963, + "step": 2119168 + }, + { + "epoch": 1.02, + "learning_rate": 1.529734407870212e-05, + "loss": 3.3913, + "step": 2119680 + }, + { + "epoch": 1.02, + "learning_rate": 1.5288958131191597e-05, + "loss": 3.3963, + "step": 2120192 + }, + { + "epoch": 1.02, + "learning_rate": 1.5280572183681077e-05, + "loss": 3.3915, + "step": 2120704 + }, + { + "epoch": 1.02, + "learning_rate": 1.527220261497429e-05, + "loss": 3.3942, + "step": 2121216 + }, + { + "epoch": 1.02, + "learning_rate": 1.5263816667463767e-05, + "loss": 3.4003, + "step": 2121728 + }, + { + "epoch": 1.02, + "learning_rate": 1.5255430719953248e-05, + "loss": 3.3954, + "step": 2122240 + }, + { + "epoch": 1.02, + "learning_rate": 1.5247044772442728e-05, + "loss": 3.3881, + "step": 2122752 + }, + { + "epoch": 1.02, + "learning_rate": 1.5238675203735942e-05, + "loss": 3.3906, + "step": 2123264 + }, + { + "epoch": 1.02, + "learning_rate": 1.5230289256225419e-05, + "loss": 3.3883, + "step": 2123776 + }, + { + "epoch": 1.02, + "learning_rate": 1.5221903308714899e-05, + "loss": 3.3971, + "step": 2124288 + }, + { + "epoch": 1.02, + "learning_rate": 1.521351736120438e-05, + "loss": 3.3896, + "step": 2124800 + }, + { + "epoch": 1.02, + "learning_rate": 1.5205147792497593e-05, + "loss": 3.3835, + "step": 2125312 + }, + { + "epoch": 1.02, + "learning_rate": 1.519676184498707e-05, + "loss": 3.3846, + "step": 2125824 + }, + { + "epoch": 1.02, + "learning_rate": 1.5188375897476551e-05, + "loss": 3.3858, + "step": 2126336 + }, + { + "epoch": 1.02, + "learning_rate": 1.5179989949966031e-05, + "loss": 3.3961, + "step": 2126848 + }, + { + "epoch": 1.02, + "learning_rate": 1.5171620381259242e-05, + "loss": 3.3888, + "step": 2127360 + }, + { + "epoch": 1.02, + "learning_rate": 1.5163234433748722e-05, + "loss": 3.4028, + "step": 2127872 + }, + { + "epoch": 1.02, + "learning_rate": 1.5154848486238202e-05, + "loss": 3.3814, + "step": 2128384 + }, + { + "epoch": 1.02, + "learning_rate": 1.5146462538727682e-05, + "loss": 3.4013, + "step": 2128896 + }, + { + "epoch": 1.02, + "learning_rate": 1.5138092970020893e-05, + "loss": 3.3902, + "step": 2129408 + }, + { + "epoch": 1.02, + "learning_rate": 1.5129707022510373e-05, + "loss": 3.3991, + "step": 2129920 + }, + { + "epoch": 1.02, + "learning_rate": 1.5121321074999852e-05, + "loss": 3.3934, + "step": 2130432 + }, + { + "epoch": 1.02, + "learning_rate": 1.5112935127489332e-05, + "loss": 3.3875, + "step": 2130944 + }, + { + "epoch": 1.02, + "learning_rate": 1.5104565558782543e-05, + "loss": 3.3873, + "step": 2131456 + }, + { + "epoch": 1.02, + "learning_rate": 1.5096179611272023e-05, + "loss": 3.4033, + "step": 2131968 + }, + { + "epoch": 1.02, + "learning_rate": 1.5087793663761505e-05, + "loss": 3.3897, + "step": 2132480 + }, + { + "epoch": 1.02, + "learning_rate": 1.5079407716250985e-05, + "loss": 3.3893, + "step": 2132992 + }, + { + "epoch": 1.02, + "learning_rate": 1.5071038147544196e-05, + "loss": 3.3963, + "step": 2133504 + }, + { + "epoch": 1.02, + "learning_rate": 1.5062652200033676e-05, + "loss": 3.3902, + "step": 2134016 + }, + { + "epoch": 1.02, + "learning_rate": 1.5054282631326888e-05, + "loss": 3.3896, + "step": 2134528 + }, + { + "epoch": 1.02, + "learning_rate": 1.5045896683816366e-05, + "loss": 3.3991, + "step": 2135040 + }, + { + "epoch": 1.02, + "learning_rate": 1.5037510736305846e-05, + "loss": 3.3866, + "step": 2135552 + }, + { + "epoch": 1.02, + "learning_rate": 1.5029124788795326e-05, + "loss": 3.3935, + "step": 2136064 + }, + { + "epoch": 1.02, + "learning_rate": 1.5020738841284806e-05, + "loss": 3.3856, + "step": 2136576 + }, + { + "epoch": 1.03, + "eval_loss": 3.8638458251953125, + "eval_runtime": 304.4643, + "eval_samples_per_second": 1253.319, + "eval_steps_per_second": 39.167, + "step": 2136960 + }, + { + "epoch": 0.0, + "learning_rate": 1.5012352893774286e-05, + "loss": 3.3911, + "step": 2137088 + }, + { + "epoch": 0.0, + "learning_rate": 1.5003983325067497e-05, + "loss": 3.3774, + "step": 2137600 + }, + { + "epoch": 0.0, + "learning_rate": 1.4995597377556977e-05, + "loss": 3.3975, + "step": 2138112 + }, + { + "epoch": 0.0, + "learning_rate": 1.4987211430046458e-05, + "loss": 3.3994, + "step": 2138624 + }, + { + "epoch": 0.0, + "learning_rate": 1.4978825482535938e-05, + "loss": 3.401, + "step": 2139136 + }, + { + "epoch": 0.0, + "learning_rate": 1.4970439535025418e-05, + "loss": 3.3882, + "step": 2139648 + }, + { + "epoch": 0.0, + "learning_rate": 1.4962053587514897e-05, + "loss": 3.3902, + "step": 2140160 + }, + { + "epoch": 0.0, + "learning_rate": 1.4953667640004377e-05, + "loss": 3.3925, + "step": 2140672 + }, + { + "epoch": 0.0, + "learning_rate": 1.4945281692493857e-05, + "loss": 3.3828, + "step": 2141184 + }, + { + "epoch": 0.0, + "learning_rate": 1.4936912123787069e-05, + "loss": 3.3886, + "step": 2141696 + }, + { + "epoch": 0.0, + "learning_rate": 1.4928526176276547e-05, + "loss": 3.3904, + "step": 2142208 + }, + { + "epoch": 0.0, + "learning_rate": 1.4920140228766027e-05, + "loss": 3.3908, + "step": 2142720 + }, + { + "epoch": 0.0, + "learning_rate": 1.491177066005924e-05, + "loss": 3.4069, + "step": 2143232 + }, + { + "epoch": 0.0, + "learning_rate": 1.4903384712548721e-05, + "loss": 3.377, + "step": 2143744 + }, + { + "epoch": 0.0, + "learning_rate": 1.4894998765038198e-05, + "loss": 3.3752, + "step": 2144256 + }, + { + "epoch": 0.0, + "learning_rate": 1.4886612817527678e-05, + "loss": 3.378, + "step": 2144768 + }, + { + "epoch": 0.0, + "learning_rate": 1.487822687001716e-05, + "loss": 3.4012, + "step": 2145280 + }, + { + "epoch": 0.0, + "learning_rate": 1.486984092250664e-05, + "loss": 3.3901, + "step": 2145792 + }, + { + "epoch": 0.0, + "learning_rate": 1.486145497499612e-05, + "loss": 3.3821, + "step": 2146304 + }, + { + "epoch": 0.0, + "learning_rate": 1.48530690274856e-05, + "loss": 3.3962, + "step": 2146816 + }, + { + "epoch": 0.0, + "learning_rate": 1.484469945877881e-05, + "loss": 3.4014, + "step": 2147328 + }, + { + "epoch": 0.0, + "learning_rate": 1.483631351126829e-05, + "loss": 3.3899, + "step": 2147840 + }, + { + "epoch": 0.0, + "learning_rate": 1.482792756375777e-05, + "loss": 3.3903, + "step": 2148352 + }, + { + "epoch": 0.0, + "learning_rate": 1.4819541616247252e-05, + "loss": 3.3877, + "step": 2148864 + }, + { + "epoch": 0.0, + "learning_rate": 1.4811172047540461e-05, + "loss": 3.4041, + "step": 2149376 + }, + { + "epoch": 0.0, + "learning_rate": 1.4802786100029941e-05, + "loss": 3.3831, + "step": 2149888 + }, + { + "epoch": 0.0, + "learning_rate": 1.4794400152519423e-05, + "loss": 3.3798, + "step": 2150400 + }, + { + "epoch": 0.0, + "learning_rate": 1.4786014205008902e-05, + "loss": 3.4035, + "step": 2150912 + }, + { + "epoch": 0.0, + "learning_rate": 1.4777644636302113e-05, + "loss": 3.3727, + "step": 2151424 + }, + { + "epoch": 0.0, + "learning_rate": 1.4769258688791593e-05, + "loss": 3.3784, + "step": 2151936 + }, + { + "epoch": 0.01, + "learning_rate": 1.4760872741281073e-05, + "loss": 3.3846, + "step": 2152448 + }, + { + "epoch": 0.01, + "learning_rate": 1.4752486793770551e-05, + "loss": 3.3836, + "step": 2152960 + }, + { + "epoch": 0.01, + "learning_rate": 1.4744117225063764e-05, + "loss": 3.395, + "step": 2153472 + }, + { + "epoch": 0.01, + "learning_rate": 1.4735731277553244e-05, + "loss": 3.3995, + "step": 2153984 + }, + { + "epoch": 0.01, + "learning_rate": 1.4727345330042724e-05, + "loss": 3.3842, + "step": 2154496 + }, + { + "epoch": 0.01, + "learning_rate": 1.4718959382532202e-05, + "loss": 3.3855, + "step": 2155008 + }, + { + "epoch": 0.01, + "learning_rate": 1.4710589813825415e-05, + "loss": 3.3959, + "step": 2155520 + }, + { + "epoch": 0.01, + "learning_rate": 1.4702203866314895e-05, + "loss": 3.3736, + "step": 2156032 + }, + { + "epoch": 0.01, + "learning_rate": 1.4693817918804373e-05, + "loss": 3.3857, + "step": 2156544 + }, + { + "epoch": 0.01, + "learning_rate": 1.4685431971293853e-05, + "loss": 3.3829, + "step": 2157056 + }, + { + "epoch": 0.01, + "learning_rate": 1.4677062402587067e-05, + "loss": 3.3753, + "step": 2157568 + }, + { + "epoch": 0.01, + "learning_rate": 1.4668676455076547e-05, + "loss": 3.3837, + "step": 2158080 + }, + { + "epoch": 0.01, + "learning_rate": 1.4660290507566023e-05, + "loss": 3.3974, + "step": 2158592 + }, + { + "epoch": 0.01, + "learning_rate": 1.4651904560055505e-05, + "loss": 3.3883, + "step": 2159104 + }, + { + "epoch": 0.01, + "learning_rate": 1.4643534991348718e-05, + "loss": 3.3824, + "step": 2159616 + }, + { + "epoch": 0.01, + "learning_rate": 1.4635149043838198e-05, + "loss": 3.3953, + "step": 2160128 + }, + { + "epoch": 0.01, + "learning_rate": 1.4626763096327676e-05, + "loss": 3.3829, + "step": 2160640 + }, + { + "epoch": 0.01, + "learning_rate": 1.4618377148817156e-05, + "loss": 3.3857, + "step": 2161152 + }, + { + "epoch": 0.01, + "learning_rate": 1.4610007580110368e-05, + "loss": 3.3616, + "step": 2161664 + }, + { + "epoch": 0.01, + "learning_rate": 1.4601621632599847e-05, + "loss": 3.3884, + "step": 2162176 + }, + { + "epoch": 0.01, + "learning_rate": 1.4593235685089326e-05, + "loss": 3.3923, + "step": 2162688 + }, + { + "epoch": 0.01, + "learning_rate": 1.4584849737578806e-05, + "loss": 3.39, + "step": 2163200 + }, + { + "epoch": 0.01, + "learning_rate": 1.457648016887202e-05, + "loss": 3.3774, + "step": 2163712 + }, + { + "epoch": 0.01, + "learning_rate": 1.4568094221361497e-05, + "loss": 3.3764, + "step": 2164224 + }, + { + "epoch": 0.01, + "learning_rate": 1.4559708273850977e-05, + "loss": 3.3711, + "step": 2164736 + }, + { + "epoch": 0.01, + "learning_rate": 1.4551322326340459e-05, + "loss": 3.3735, + "step": 2165248 + }, + { + "epoch": 0.01, + "learning_rate": 1.4542952757633671e-05, + "loss": 3.4021, + "step": 2165760 + }, + { + "epoch": 0.01, + "learning_rate": 1.4534566810123148e-05, + "loss": 3.3786, + "step": 2166272 + }, + { + "epoch": 0.01, + "learning_rate": 1.452618086261263e-05, + "loss": 3.3872, + "step": 2166784 + }, + { + "epoch": 0.01, + "learning_rate": 1.451779491510211e-05, + "loss": 3.3889, + "step": 2167296 + }, + { + "epoch": 0.01, + "learning_rate": 1.450942534639532e-05, + "loss": 3.3724, + "step": 2167808 + }, + { + "epoch": 0.01, + "learning_rate": 1.45010393988848e-05, + "loss": 3.3802, + "step": 2168320 + }, + { + "epoch": 0.01, + "learning_rate": 1.449265345137428e-05, + "loss": 3.3744, + "step": 2168832 + }, + { + "epoch": 0.01, + "learning_rate": 1.4484283882667493e-05, + "loss": 3.3777, + "step": 2169344 + }, + { + "epoch": 0.01, + "learning_rate": 1.4475897935156971e-05, + "loss": 3.3763, + "step": 2169856 + }, + { + "epoch": 0.01, + "learning_rate": 1.446751198764645e-05, + "loss": 3.3939, + "step": 2170368 + }, + { + "epoch": 0.01, + "learning_rate": 1.4459142418939663e-05, + "loss": 3.385, + "step": 2170880 + }, + { + "epoch": 0.01, + "learning_rate": 1.4450756471429145e-05, + "loss": 3.3749, + "step": 2171392 + }, + { + "epoch": 0.01, + "learning_rate": 1.4442370523918622e-05, + "loss": 3.3716, + "step": 2171904 + }, + { + "epoch": 0.01, + "learning_rate": 1.4433984576408101e-05, + "loss": 3.3806, + "step": 2172416 + }, + { + "epoch": 0.01, + "learning_rate": 1.4425598628897583e-05, + "loss": 3.3841, + "step": 2172928 + }, + { + "epoch": 0.01, + "learning_rate": 1.4417212681387063e-05, + "loss": 3.3873, + "step": 2173440 + }, + { + "epoch": 0.01, + "learning_rate": 1.4408826733876543e-05, + "loss": 3.3842, + "step": 2173952 + }, + { + "epoch": 0.01, + "learning_rate": 1.4400440786366023e-05, + "loss": 3.3824, + "step": 2174464 + }, + { + "epoch": 0.01, + "learning_rate": 1.4392071217659234e-05, + "loss": 3.3976, + "step": 2174976 + }, + { + "epoch": 0.01, + "learning_rate": 1.4383685270148714e-05, + "loss": 3.3792, + "step": 2175488 + }, + { + "epoch": 0.01, + "learning_rate": 1.4375299322638194e-05, + "loss": 3.3807, + "step": 2176000 + }, + { + "epoch": 0.01, + "learning_rate": 1.4366913375127675e-05, + "loss": 3.387, + "step": 2176512 + }, + { + "epoch": 0.01, + "learning_rate": 1.4358543806420884e-05, + "loss": 3.3807, + "step": 2177024 + }, + { + "epoch": 0.01, + "learning_rate": 1.4350157858910364e-05, + "loss": 3.3895, + "step": 2177536 + }, + { + "epoch": 0.01, + "learning_rate": 1.4341771911399846e-05, + "loss": 3.3875, + "step": 2178048 + }, + { + "epoch": 0.01, + "learning_rate": 1.4333385963889326e-05, + "loss": 3.3904, + "step": 2178560 + }, + { + "epoch": 0.01, + "learning_rate": 1.4325016395182537e-05, + "loss": 3.4029, + "step": 2179072 + }, + { + "epoch": 0.01, + "learning_rate": 1.4316630447672017e-05, + "loss": 3.3907, + "step": 2179584 + }, + { + "epoch": 0.01, + "learning_rate": 1.4308244500161497e-05, + "loss": 3.3678, + "step": 2180096 + }, + { + "epoch": 0.01, + "learning_rate": 1.4299858552650975e-05, + "loss": 3.3783, + "step": 2180608 + }, + { + "epoch": 0.01, + "learning_rate": 1.4291488983944187e-05, + "loss": 3.3911, + "step": 2181120 + }, + { + "epoch": 0.01, + "learning_rate": 1.4283119415237398e-05, + "loss": 3.3886, + "step": 2181632 + }, + { + "epoch": 0.01, + "learning_rate": 1.4274733467726878e-05, + "loss": 3.3787, + "step": 2182144 + }, + { + "epoch": 0.01, + "learning_rate": 1.4266347520216358e-05, + "loss": 3.3876, + "step": 2182656 + }, + { + "epoch": 0.02, + "learning_rate": 1.4257961572705838e-05, + "loss": 3.3891, + "step": 2183168 + }, + { + "epoch": 0.02, + "learning_rate": 1.4249575625195318e-05, + "loss": 3.3786, + "step": 2183680 + }, + { + "epoch": 0.02, + "learning_rate": 1.42411896776848e-05, + "loss": 3.3776, + "step": 2184192 + }, + { + "epoch": 0.02, + "learning_rate": 1.4232803730174276e-05, + "loss": 3.3873, + "step": 2184704 + }, + { + "epoch": 0.02, + "learning_rate": 1.422443416146749e-05, + "loss": 3.3855, + "step": 2185216 + }, + { + "epoch": 0.02, + "learning_rate": 1.421604821395697e-05, + "loss": 3.3939, + "step": 2185728 + }, + { + "epoch": 0.02, + "learning_rate": 1.4207662266446447e-05, + "loss": 3.3753, + "step": 2186240 + }, + { + "epoch": 0.02, + "learning_rate": 1.4199276318935929e-05, + "loss": 3.3795, + "step": 2186752 + }, + { + "epoch": 0.02, + "learning_rate": 1.4190906750229141e-05, + "loss": 3.39, + "step": 2187264 + }, + { + "epoch": 0.02, + "learning_rate": 1.4182520802718621e-05, + "loss": 3.3844, + "step": 2187776 + }, + { + "epoch": 0.02, + "learning_rate": 1.41741348552081e-05, + "loss": 3.3872, + "step": 2188288 + }, + { + "epoch": 0.02, + "learning_rate": 1.416574890769758e-05, + "loss": 3.3768, + "step": 2188800 + }, + { + "epoch": 0.02, + "learning_rate": 1.4157379338990792e-05, + "loss": 3.3761, + "step": 2189312 + }, + { + "epoch": 0.02, + "learning_rate": 1.4148993391480272e-05, + "loss": 3.3693, + "step": 2189824 + }, + { + "epoch": 0.02, + "learning_rate": 1.414060744396975e-05, + "loss": 3.385, + "step": 2190336 + }, + { + "epoch": 0.02, + "learning_rate": 1.413222149645923e-05, + "loss": 3.3771, + "step": 2190848 + }, + { + "epoch": 0.02, + "learning_rate": 1.4123851927752444e-05, + "loss": 3.3766, + "step": 2191360 + }, + { + "epoch": 0.02, + "learning_rate": 1.411546598024192e-05, + "loss": 3.3831, + "step": 2191872 + }, + { + "epoch": 0.02, + "learning_rate": 1.41070800327314e-05, + "loss": 3.3792, + "step": 2192384 + }, + { + "epoch": 0.02, + "learning_rate": 1.4098694085220882e-05, + "loss": 3.3804, + "step": 2192896 + }, + { + "epoch": 0.02, + "learning_rate": 1.4090324516514095e-05, + "loss": 3.383, + "step": 2193408 + }, + { + "epoch": 0.02, + "learning_rate": 1.4081938569003571e-05, + "loss": 3.3674, + "step": 2193920 + }, + { + "epoch": 0.02, + "learning_rate": 1.4073552621493053e-05, + "loss": 3.3882, + "step": 2194432 + }, + { + "epoch": 0.02, + "learning_rate": 1.4065166673982533e-05, + "loss": 3.3753, + "step": 2194944 + }, + { + "epoch": 0.02, + "learning_rate": 1.4056797105275744e-05, + "loss": 3.381, + "step": 2195456 + }, + { + "epoch": 0.02, + "learning_rate": 1.4048411157765224e-05, + "loss": 3.3863, + "step": 2195968 + }, + { + "epoch": 0.02, + "learning_rate": 1.4040025210254704e-05, + "loss": 3.3896, + "step": 2196480 + }, + { + "epoch": 0.02, + "learning_rate": 1.4031639262744184e-05, + "loss": 3.3813, + "step": 2196992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4023269694037394e-05, + "loss": 3.3847, + "step": 2197504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4014883746526874e-05, + "loss": 3.3887, + "step": 2198016 + }, + { + "epoch": 0.02, + "learning_rate": 1.4006497799016354e-05, + "loss": 3.3822, + "step": 2198528 + }, + { + "epoch": 0.02, + "learning_rate": 1.3998111851505836e-05, + "loss": 3.377, + "step": 2199040 + }, + { + "epoch": 0.02, + "learning_rate": 1.3989742282799045e-05, + "loss": 3.3845, + "step": 2199552 + }, + { + "epoch": 0.02, + "learning_rate": 1.3981356335288525e-05, + "loss": 3.3757, + "step": 2200064 + }, + { + "epoch": 0.02, + "learning_rate": 1.3972970387778007e-05, + "loss": 3.3876, + "step": 2200576 + }, + { + "epoch": 0.02, + "learning_rate": 1.3964584440267487e-05, + "loss": 3.3744, + "step": 2201088 + }, + { + "epoch": 0.02, + "learning_rate": 1.3956214871560697e-05, + "loss": 3.3795, + "step": 2201600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3947828924050177e-05, + "loss": 3.3717, + "step": 2202112 + }, + { + "epoch": 0.02, + "learning_rate": 1.3939442976539657e-05, + "loss": 3.3774, + "step": 2202624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3931057029029137e-05, + "loss": 3.3885, + "step": 2203136 + }, + { + "epoch": 0.02, + "learning_rate": 1.3922687460322348e-05, + "loss": 3.3782, + "step": 2203648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3914301512811828e-05, + "loss": 3.3929, + "step": 2204160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3905915565301308e-05, + "loss": 3.3756, + "step": 2204672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3897529617790788e-05, + "loss": 3.3881, + "step": 2205184 + }, + { + "epoch": 0.02, + "learning_rate": 1.3889160049083999e-05, + "loss": 3.3826, + "step": 2205696 + }, + { + "epoch": 0.02, + "learning_rate": 1.3880774101573479e-05, + "loss": 3.3879, + "step": 2206208 + }, + { + "epoch": 0.02, + "learning_rate": 1.387238815406296e-05, + "loss": 3.3807, + "step": 2206720 + }, + { + "epoch": 0.02, + "learning_rate": 1.386401858535617e-05, + "loss": 3.3809, + "step": 2207232 + }, + { + "epoch": 0.02, + "learning_rate": 1.3855632637845651e-05, + "loss": 3.3795, + "step": 2207744 + }, + { + "epoch": 0.02, + "learning_rate": 1.3847246690335131e-05, + "loss": 3.3908, + "step": 2208256 + }, + { + "epoch": 0.02, + "learning_rate": 1.3838860742824611e-05, + "loss": 3.3794, + "step": 2208768 + }, + { + "epoch": 0.02, + "learning_rate": 1.3830474795314091e-05, + "loss": 3.3812, + "step": 2209280 + }, + { + "epoch": 0.02, + "learning_rate": 1.3822088847803571e-05, + "loss": 3.3864, + "step": 2209792 + }, + { + "epoch": 0.02, + "learning_rate": 1.381370290029305e-05, + "loss": 3.3789, + "step": 2210304 + }, + { + "epoch": 0.02, + "learning_rate": 1.3805333331586262e-05, + "loss": 3.3787, + "step": 2210816 + }, + { + "epoch": 0.02, + "learning_rate": 1.3796947384075742e-05, + "loss": 3.3905, + "step": 2211328 + }, + { + "epoch": 0.02, + "learning_rate": 1.3788561436565223e-05, + "loss": 3.3776, + "step": 2211840 + }, + { + "epoch": 0.02, + "learning_rate": 1.37801754890547e-05, + "loss": 3.3848, + "step": 2212352 + }, + { + "epoch": 0.02, + "learning_rate": 1.377178954154418e-05, + "loss": 3.3773, + "step": 2212864 + }, + { + "epoch": 0.03, + "eval_loss": 3.864529609680176, + "eval_runtime": 310.0639, + "eval_samples_per_second": 1230.685, + "eval_steps_per_second": 38.46, + "step": 2213280 + }, + { + "epoch": 1.0, + "learning_rate": 1.3763403594033661e-05, + "loss": 3.3739, + "step": 2213376 + }, + { + "epoch": 1.0, + "learning_rate": 1.375503402532687e-05, + "loss": 3.3676, + "step": 2213888 + }, + { + "epoch": 1.0, + "learning_rate": 1.3746648077816352e-05, + "loss": 3.3861, + "step": 2214400 + }, + { + "epoch": 1.0, + "learning_rate": 1.3738262130305832e-05, + "loss": 3.3949, + "step": 2214912 + }, + { + "epoch": 1.0, + "learning_rate": 1.3729876182795312e-05, + "loss": 3.3862, + "step": 2215424 + }, + { + "epoch": 1.0, + "learning_rate": 1.3721490235284792e-05, + "loss": 3.3842, + "step": 2215936 + }, + { + "epoch": 1.0, + "learning_rate": 1.3713104287774272e-05, + "loss": 3.3742, + "step": 2216448 + }, + { + "epoch": 1.0, + "learning_rate": 1.3704718340263754e-05, + "loss": 3.3838, + "step": 2216960 + }, + { + "epoch": 1.0, + "learning_rate": 1.369633239275323e-05, + "loss": 3.3741, + "step": 2217472 + }, + { + "epoch": 1.0, + "learning_rate": 1.3687962824046444e-05, + "loss": 3.3833, + "step": 2217984 + }, + { + "epoch": 1.0, + "learning_rate": 1.3679576876535924e-05, + "loss": 3.3781, + "step": 2218496 + }, + { + "epoch": 1.0, + "learning_rate": 1.3671190929025404e-05, + "loss": 3.3819, + "step": 2219008 + }, + { + "epoch": 1.0, + "learning_rate": 1.3662821360318615e-05, + "loss": 3.3951, + "step": 2219520 + }, + { + "epoch": 1.0, + "learning_rate": 1.3654435412808095e-05, + "loss": 3.368, + "step": 2220032 + }, + { + "epoch": 1.0, + "learning_rate": 1.3646049465297575e-05, + "loss": 3.3669, + "step": 2220544 + }, + { + "epoch": 1.0, + "learning_rate": 1.3637663517787053e-05, + "loss": 3.3717, + "step": 2221056 + }, + { + "epoch": 1.0, + "learning_rate": 1.3629277570276533e-05, + "loss": 3.391, + "step": 2221568 + }, + { + "epoch": 1.0, + "learning_rate": 1.3620891622766013e-05, + "loss": 3.3782, + "step": 2222080 + }, + { + "epoch": 1.0, + "learning_rate": 1.3612505675255493e-05, + "loss": 3.3748, + "step": 2222592 + }, + { + "epoch": 1.0, + "learning_rate": 1.3604119727744973e-05, + "loss": 3.3846, + "step": 2223104 + }, + { + "epoch": 1.0, + "learning_rate": 1.3595750159038184e-05, + "loss": 3.3951, + "step": 2223616 + }, + { + "epoch": 1.0, + "learning_rate": 1.3587364211527664e-05, + "loss": 3.3811, + "step": 2224128 + }, + { + "epoch": 1.0, + "learning_rate": 1.3578978264017145e-05, + "loss": 3.376, + "step": 2224640 + }, + { + "epoch": 1.0, + "learning_rate": 1.3570592316506625e-05, + "loss": 3.3786, + "step": 2225152 + }, + { + "epoch": 1.0, + "learning_rate": 1.3562222747799835e-05, + "loss": 3.3933, + "step": 2225664 + }, + { + "epoch": 1.0, + "learning_rate": 1.3553836800289316e-05, + "loss": 3.3736, + "step": 2226176 + }, + { + "epoch": 1.0, + "learning_rate": 1.3545450852778796e-05, + "loss": 3.3705, + "step": 2226688 + }, + { + "epoch": 1.0, + "learning_rate": 1.3537064905268276e-05, + "loss": 3.3947, + "step": 2227200 + }, + { + "epoch": 1.0, + "learning_rate": 1.3528695336561487e-05, + "loss": 3.3629, + "step": 2227712 + }, + { + "epoch": 1.0, + "learning_rate": 1.3520309389050967e-05, + "loss": 3.3692, + "step": 2228224 + }, + { + "epoch": 1.01, + "learning_rate": 1.3511923441540447e-05, + "loss": 3.3731, + "step": 2228736 + }, + { + "epoch": 1.01, + "learning_rate": 1.3503537494029927e-05, + "loss": 3.3756, + "step": 2229248 + }, + { + "epoch": 1.01, + "learning_rate": 1.3495167925323138e-05, + "loss": 3.3826, + "step": 2229760 + }, + { + "epoch": 1.01, + "learning_rate": 1.3486781977812618e-05, + "loss": 3.3909, + "step": 2230272 + }, + { + "epoch": 1.01, + "learning_rate": 1.34783960303021e-05, + "loss": 3.3743, + "step": 2230784 + }, + { + "epoch": 1.01, + "learning_rate": 1.3470010082791579e-05, + "loss": 3.3735, + "step": 2231296 + }, + { + "epoch": 1.01, + "learning_rate": 1.3461640514084788e-05, + "loss": 3.3843, + "step": 2231808 + }, + { + "epoch": 1.01, + "learning_rate": 1.345325456657427e-05, + "loss": 3.3638, + "step": 2232320 + }, + { + "epoch": 1.01, + "learning_rate": 1.344486861906375e-05, + "loss": 3.3755, + "step": 2232832 + }, + { + "epoch": 1.01, + "learning_rate": 1.343648267155323e-05, + "loss": 3.3711, + "step": 2233344 + }, + { + "epoch": 1.01, + "learning_rate": 1.342811310284644e-05, + "loss": 3.3739, + "step": 2233856 + }, + { + "epoch": 1.01, + "learning_rate": 1.341972715533592e-05, + "loss": 3.3683, + "step": 2234368 + }, + { + "epoch": 1.01, + "learning_rate": 1.34113412078254e-05, + "loss": 3.3901, + "step": 2234880 + }, + { + "epoch": 1.01, + "learning_rate": 1.340295526031488e-05, + "loss": 3.374, + "step": 2235392 + }, + { + "epoch": 1.01, + "learning_rate": 1.3394585691608091e-05, + "loss": 3.3768, + "step": 2235904 + }, + { + "epoch": 1.01, + "learning_rate": 1.3386199744097571e-05, + "loss": 3.3819, + "step": 2236416 + }, + { + "epoch": 1.01, + "learning_rate": 1.3377813796587053e-05, + "loss": 3.3764, + "step": 2236928 + }, + { + "epoch": 1.01, + "learning_rate": 1.336942784907653e-05, + "loss": 3.3734, + "step": 2237440 + }, + { + "epoch": 1.01, + "learning_rate": 1.3361058280369742e-05, + "loss": 3.3547, + "step": 2237952 + }, + { + "epoch": 1.01, + "learning_rate": 1.3352672332859224e-05, + "loss": 3.373, + "step": 2238464 + }, + { + "epoch": 1.01, + "learning_rate": 1.3344286385348703e-05, + "loss": 3.3847, + "step": 2238976 + }, + { + "epoch": 1.01, + "learning_rate": 1.333590043783818e-05, + "loss": 3.3836, + "step": 2239488 + }, + { + "epoch": 1.01, + "learning_rate": 1.3327530869131394e-05, + "loss": 3.365, + "step": 2240000 + }, + { + "epoch": 1.01, + "learning_rate": 1.3319144921620874e-05, + "loss": 3.3649, + "step": 2240512 + }, + { + "epoch": 1.01, + "learning_rate": 1.3310758974110354e-05, + "loss": 3.3673, + "step": 2241024 + }, + { + "epoch": 1.01, + "learning_rate": 1.3302373026599832e-05, + "loss": 3.3604, + "step": 2241536 + }, + { + "epoch": 1.01, + "learning_rate": 1.3294003457893045e-05, + "loss": 3.3926, + "step": 2242048 + }, + { + "epoch": 1.01, + "learning_rate": 1.3285617510382525e-05, + "loss": 3.3653, + "step": 2242560 + }, + { + "epoch": 1.01, + "learning_rate": 1.3277231562872003e-05, + "loss": 3.3818, + "step": 2243072 + }, + { + "epoch": 1.01, + "learning_rate": 1.3268861994165216e-05, + "loss": 3.3801, + "step": 2243584 + }, + { + "epoch": 1.01, + "learning_rate": 1.3260476046654696e-05, + "loss": 3.3618, + "step": 2244096 + }, + { + "epoch": 1.01, + "learning_rate": 1.3252090099144177e-05, + "loss": 3.3712, + "step": 2244608 + }, + { + "epoch": 1.01, + "learning_rate": 1.3243704151633654e-05, + "loss": 3.3634, + "step": 2245120 + }, + { + "epoch": 1.01, + "learning_rate": 1.3235334582926868e-05, + "loss": 3.3674, + "step": 2245632 + }, + { + "epoch": 1.01, + "learning_rate": 1.3226948635416348e-05, + "loss": 3.3647, + "step": 2246144 + }, + { + "epoch": 1.01, + "learning_rate": 1.3218562687905828e-05, + "loss": 3.3838, + "step": 2246656 + }, + { + "epoch": 1.01, + "learning_rate": 1.3210193119199039e-05, + "loss": 3.3778, + "step": 2247168 + }, + { + "epoch": 1.01, + "learning_rate": 1.3201807171688519e-05, + "loss": 3.3682, + "step": 2247680 + }, + { + "epoch": 1.01, + "learning_rate": 1.3193421224177999e-05, + "loss": 3.3627, + "step": 2248192 + }, + { + "epoch": 1.01, + "learning_rate": 1.3185035276667477e-05, + "loss": 3.3695, + "step": 2248704 + }, + { + "epoch": 1.01, + "learning_rate": 1.3176649329156957e-05, + "loss": 3.3757, + "step": 2249216 + }, + { + "epoch": 1.01, + "learning_rate": 1.3168263381646437e-05, + "loss": 3.3766, + "step": 2249728 + }, + { + "epoch": 1.01, + "learning_rate": 1.3159877434135917e-05, + "loss": 3.3727, + "step": 2250240 + }, + { + "epoch": 1.01, + "learning_rate": 1.3151491486625397e-05, + "loss": 3.3759, + "step": 2250752 + }, + { + "epoch": 1.01, + "learning_rate": 1.3143121917918607e-05, + "loss": 3.387, + "step": 2251264 + }, + { + "epoch": 1.01, + "learning_rate": 1.3134735970408087e-05, + "loss": 3.3701, + "step": 2251776 + }, + { + "epoch": 1.01, + "learning_rate": 1.3126350022897569e-05, + "loss": 3.3701, + "step": 2252288 + }, + { + "epoch": 1.01, + "learning_rate": 1.3117964075387049e-05, + "loss": 3.372, + "step": 2252800 + }, + { + "epoch": 1.01, + "learning_rate": 1.3109594506680258e-05, + "loss": 3.3745, + "step": 2253312 + }, + { + "epoch": 1.01, + "learning_rate": 1.310120855916974e-05, + "loss": 3.3801, + "step": 2253824 + }, + { + "epoch": 1.01, + "learning_rate": 1.309282261165922e-05, + "loss": 3.3789, + "step": 2254336 + }, + { + "epoch": 1.01, + "learning_rate": 1.30844366641487e-05, + "loss": 3.3834, + "step": 2254848 + }, + { + "epoch": 1.01, + "learning_rate": 1.307606709544191e-05, + "loss": 3.3886, + "step": 2255360 + }, + { + "epoch": 1.01, + "learning_rate": 1.3067697526735123e-05, + "loss": 3.3804, + "step": 2255872 + }, + { + "epoch": 1.01, + "learning_rate": 1.3059311579224601e-05, + "loss": 3.3594, + "step": 2256384 + }, + { + "epoch": 1.01, + "learning_rate": 1.3050925631714081e-05, + "loss": 3.3668, + "step": 2256896 + }, + { + "epoch": 1.01, + "learning_rate": 1.3042539684203561e-05, + "loss": 3.3825, + "step": 2257408 + }, + { + "epoch": 1.01, + "learning_rate": 1.3034153736693041e-05, + "loss": 3.3802, + "step": 2257920 + }, + { + "epoch": 1.01, + "learning_rate": 1.3025767789182523e-05, + "loss": 3.372, + "step": 2258432 + }, + { + "epoch": 1.01, + "learning_rate": 1.3017381841672003e-05, + "loss": 3.3736, + "step": 2258944 + }, + { + "epoch": 1.02, + "learning_rate": 1.3008995894161483e-05, + "loss": 3.3843, + "step": 2259456 + }, + { + "epoch": 1.02, + "learning_rate": 1.3000626325454693e-05, + "loss": 3.3675, + "step": 2259968 + }, + { + "epoch": 1.02, + "learning_rate": 1.2992240377944173e-05, + "loss": 3.3691, + "step": 2260480 + }, + { + "epoch": 1.02, + "learning_rate": 1.2983854430433653e-05, + "loss": 3.3796, + "step": 2260992 + }, + { + "epoch": 1.02, + "learning_rate": 1.2975468482923132e-05, + "loss": 3.3733, + "step": 2261504 + }, + { + "epoch": 1.02, + "learning_rate": 1.2967098914216344e-05, + "loss": 3.3878, + "step": 2262016 + }, + { + "epoch": 1.02, + "learning_rate": 1.2958712966705824e-05, + "loss": 3.3644, + "step": 2262528 + }, + { + "epoch": 1.02, + "learning_rate": 1.2950327019195304e-05, + "loss": 3.3707, + "step": 2263040 + }, + { + "epoch": 1.02, + "learning_rate": 1.2941941071684782e-05, + "loss": 3.3796, + "step": 2263552 + }, + { + "epoch": 1.02, + "learning_rate": 1.2933571502977995e-05, + "loss": 3.3773, + "step": 2264064 + }, + { + "epoch": 1.02, + "learning_rate": 1.2925185555467476e-05, + "loss": 3.38, + "step": 2264576 + }, + { + "epoch": 1.02, + "learning_rate": 1.2916799607956956e-05, + "loss": 3.3694, + "step": 2265088 + }, + { + "epoch": 1.02, + "learning_rate": 1.2908413660446433e-05, + "loss": 3.366, + "step": 2265600 + }, + { + "epoch": 1.02, + "learning_rate": 1.2900044091739647e-05, + "loss": 3.359, + "step": 2266112 + }, + { + "epoch": 1.02, + "learning_rate": 1.2891658144229127e-05, + "loss": 3.377, + "step": 2266624 + }, + { + "epoch": 1.02, + "learning_rate": 1.2883272196718604e-05, + "loss": 3.3643, + "step": 2267136 + }, + { + "epoch": 1.02, + "learning_rate": 1.2874886249208085e-05, + "loss": 3.3676, + "step": 2267648 + }, + { + "epoch": 1.02, + "learning_rate": 1.2866516680501298e-05, + "loss": 3.3789, + "step": 2268160 + }, + { + "epoch": 1.02, + "learning_rate": 1.2858130732990778e-05, + "loss": 3.3696, + "step": 2268672 + }, + { + "epoch": 1.02, + "learning_rate": 1.2849744785480256e-05, + "loss": 3.3644, + "step": 2269184 + }, + { + "epoch": 1.02, + "learning_rate": 1.2841375216773468e-05, + "loss": 3.3771, + "step": 2269696 + }, + { + "epoch": 1.02, + "learning_rate": 1.2832989269262948e-05, + "loss": 3.3585, + "step": 2270208 + }, + { + "epoch": 1.02, + "learning_rate": 1.2824603321752427e-05, + "loss": 3.376, + "step": 2270720 + }, + { + "epoch": 1.02, + "learning_rate": 1.2816217374241907e-05, + "loss": 3.3685, + "step": 2271232 + }, + { + "epoch": 1.02, + "learning_rate": 1.2807847805535119e-05, + "loss": 3.3718, + "step": 2271744 + }, + { + "epoch": 1.02, + "learning_rate": 1.27994618580246e-05, + "loss": 3.3763, + "step": 2272256 + }, + { + "epoch": 1.02, + "learning_rate": 1.2791075910514077e-05, + "loss": 3.3761, + "step": 2272768 + }, + { + "epoch": 1.02, + "learning_rate": 1.2782689963003557e-05, + "loss": 3.3697, + "step": 2273280 + }, + { + "epoch": 1.02, + "learning_rate": 1.2774320394296771e-05, + "loss": 3.375, + "step": 2273792 + }, + { + "epoch": 1.02, + "learning_rate": 1.2765934446786251e-05, + "loss": 3.3826, + "step": 2274304 + }, + { + "epoch": 1.02, + "learning_rate": 1.275754849927573e-05, + "loss": 3.3691, + "step": 2274816 + }, + { + "epoch": 1.02, + "learning_rate": 1.274916255176521e-05, + "loss": 3.3681, + "step": 2275328 + }, + { + "epoch": 1.02, + "learning_rate": 1.2740792983058422e-05, + "loss": 3.373, + "step": 2275840 + }, + { + "epoch": 1.02, + "learning_rate": 1.27324070355479e-05, + "loss": 3.372, + "step": 2276352 + }, + { + "epoch": 1.02, + "learning_rate": 1.272402108803738e-05, + "loss": 3.375, + "step": 2276864 + }, + { + "epoch": 1.02, + "learning_rate": 1.271563514052686e-05, + "loss": 3.3671, + "step": 2277376 + }, + { + "epoch": 1.02, + "learning_rate": 1.2707265571820073e-05, + "loss": 3.3684, + "step": 2277888 + }, + { + "epoch": 1.02, + "learning_rate": 1.2698879624309551e-05, + "loss": 3.3659, + "step": 2278400 + }, + { + "epoch": 1.02, + "learning_rate": 1.2690493676799031e-05, + "loss": 3.3648, + "step": 2278912 + }, + { + "epoch": 1.02, + "learning_rate": 1.2682107729288511e-05, + "loss": 3.3775, + "step": 2279424 + }, + { + "epoch": 1.02, + "learning_rate": 1.2673738160581725e-05, + "loss": 3.3733, + "step": 2279936 + }, + { + "epoch": 1.02, + "learning_rate": 1.2665352213071202e-05, + "loss": 3.3804, + "step": 2280448 + }, + { + "epoch": 1.02, + "learning_rate": 1.2656966265560682e-05, + "loss": 3.366, + "step": 2280960 + }, + { + "epoch": 1.02, + "learning_rate": 1.2648580318050163e-05, + "loss": 3.381, + "step": 2281472 + }, + { + "epoch": 1.02, + "learning_rate": 1.2640210749343372e-05, + "loss": 3.3713, + "step": 2281984 + }, + { + "epoch": 1.02, + "learning_rate": 1.2631824801832854e-05, + "loss": 3.3822, + "step": 2282496 + }, + { + "epoch": 1.02, + "learning_rate": 1.2623438854322334e-05, + "loss": 3.3677, + "step": 2283008 + }, + { + "epoch": 1.02, + "learning_rate": 1.2615052906811814e-05, + "loss": 3.3722, + "step": 2283520 + }, + { + "epoch": 1.02, + "learning_rate": 1.2606683338105025e-05, + "loss": 3.3705, + "step": 2284032 + }, + { + "epoch": 1.02, + "learning_rate": 1.2598297390594505e-05, + "loss": 3.3823, + "step": 2284544 + }, + { + "epoch": 1.02, + "learning_rate": 1.2589911443083985e-05, + "loss": 3.372, + "step": 2285056 + }, + { + "epoch": 1.02, + "learning_rate": 1.2581525495573465e-05, + "loss": 3.3681, + "step": 2285568 + }, + { + "epoch": 1.02, + "learning_rate": 1.2573155926866675e-05, + "loss": 3.3775, + "step": 2286080 + }, + { + "epoch": 1.02, + "learning_rate": 1.2564769979356155e-05, + "loss": 3.3702, + "step": 2286592 + }, + { + "epoch": 1.02, + "learning_rate": 1.255640041064937e-05, + "loss": 3.3674, + "step": 2287104 + }, + { + "epoch": 1.02, + "learning_rate": 1.2548014463138846e-05, + "loss": 3.3826, + "step": 2287616 + }, + { + "epoch": 1.02, + "learning_rate": 1.2539628515628326e-05, + "loss": 3.3638, + "step": 2288128 + }, + { + "epoch": 1.02, + "learning_rate": 1.2531242568117808e-05, + "loss": 3.3779, + "step": 2288640 + }, + { + "epoch": 1.02, + "learning_rate": 1.2522856620607288e-05, + "loss": 3.3645, + "step": 2289152 + }, + { + "epoch": 1.03, + "eval_loss": 3.865164279937744, + "eval_runtime": 303.1105, + "eval_samples_per_second": 1258.917, + "eval_steps_per_second": 39.342, + "step": 2289600 + }, + { + "epoch": 0.0, + "learning_rate": 1.2514470673096768e-05, + "loss": 3.3677, + "step": 2289664 + }, + { + "epoch": 0.0, + "learning_rate": 1.2506101104389978e-05, + "loss": 3.361, + "step": 2290176 + }, + { + "epoch": 0.0, + "learning_rate": 1.2497715156879458e-05, + "loss": 3.3747, + "step": 2290688 + }, + { + "epoch": 0.0, + "learning_rate": 1.2489329209368938e-05, + "loss": 3.3831, + "step": 2291200 + }, + { + "epoch": 0.0, + "learning_rate": 1.2480943261858418e-05, + "loss": 3.3774, + "step": 2291712 + }, + { + "epoch": 0.0, + "learning_rate": 1.2472557314347898e-05, + "loss": 3.3743, + "step": 2292224 + }, + { + "epoch": 0.0, + "learning_rate": 1.2464171366837378e-05, + "loss": 3.3606, + "step": 2292736 + }, + { + "epoch": 0.0, + "learning_rate": 1.2455785419326858e-05, + "loss": 3.3759, + "step": 2293248 + }, + { + "epoch": 0.0, + "learning_rate": 1.2447399471816338e-05, + "loss": 3.3684, + "step": 2293760 + }, + { + "epoch": 0.0, + "learning_rate": 1.2439029903109549e-05, + "loss": 3.3708, + "step": 2294272 + }, + { + "epoch": 0.0, + "learning_rate": 1.2430643955599029e-05, + "loss": 3.3695, + "step": 2294784 + }, + { + "epoch": 0.0, + "learning_rate": 1.2422258008088509e-05, + "loss": 3.3717, + "step": 2295296 + }, + { + "epoch": 0.0, + "learning_rate": 1.241388843938172e-05, + "loss": 3.3858, + "step": 2295808 + }, + { + "epoch": 0.0, + "learning_rate": 1.24055024918712e-05, + "loss": 3.3603, + "step": 2296320 + }, + { + "epoch": 0.0, + "learning_rate": 1.2397116544360681e-05, + "loss": 3.3553, + "step": 2296832 + }, + { + "epoch": 0.0, + "learning_rate": 1.2388730596850161e-05, + "loss": 3.362, + "step": 2297344 + }, + { + "epoch": 0.0, + "learning_rate": 1.238034464933964e-05, + "loss": 3.3775, + "step": 2297856 + }, + { + "epoch": 0.0, + "learning_rate": 1.237195870182912e-05, + "loss": 3.3711, + "step": 2298368 + }, + { + "epoch": 0.0, + "learning_rate": 1.2363572754318601e-05, + "loss": 3.3665, + "step": 2298880 + }, + { + "epoch": 0.0, + "learning_rate": 1.235518680680808e-05, + "loss": 3.3728, + "step": 2299392 + }, + { + "epoch": 0.0, + "learning_rate": 1.234681723810129e-05, + "loss": 3.3847, + "step": 2299904 + }, + { + "epoch": 0.0, + "learning_rate": 1.2338431290590772e-05, + "loss": 3.3687, + "step": 2300416 + }, + { + "epoch": 0.0, + "learning_rate": 1.2330045343080252e-05, + "loss": 3.3662, + "step": 2300928 + }, + { + "epoch": 0.0, + "learning_rate": 1.232165939556973e-05, + "loss": 3.371, + "step": 2301440 + }, + { + "epoch": 0.0, + "learning_rate": 1.2313289826862942e-05, + "loss": 3.3827, + "step": 2301952 + }, + { + "epoch": 0.0, + "learning_rate": 1.2304903879352422e-05, + "loss": 3.3613, + "step": 2302464 + }, + { + "epoch": 0.0, + "learning_rate": 1.22965179318419e-05, + "loss": 3.3654, + "step": 2302976 + }, + { + "epoch": 0.0, + "learning_rate": 1.2288131984331382e-05, + "loss": 3.3803, + "step": 2303488 + }, + { + "epoch": 0.0, + "learning_rate": 1.2279762415624593e-05, + "loss": 3.3579, + "step": 2304000 + }, + { + "epoch": 0.0, + "learning_rate": 1.2271376468114073e-05, + "loss": 3.3582, + "step": 2304512 + }, + { + "epoch": 0.01, + "learning_rate": 1.2262990520603553e-05, + "loss": 3.359, + "step": 2305024 + }, + { + "epoch": 0.01, + "learning_rate": 1.2254604573093033e-05, + "loss": 3.3697, + "step": 2305536 + }, + { + "epoch": 0.01, + "learning_rate": 1.2246235004386244e-05, + "loss": 3.3732, + "step": 2306048 + }, + { + "epoch": 0.01, + "learning_rate": 1.2237865435679456e-05, + "loss": 3.3785, + "step": 2306560 + }, + { + "epoch": 0.01, + "learning_rate": 1.2229479488168934e-05, + "loss": 3.3687, + "step": 2307072 + }, + { + "epoch": 0.01, + "learning_rate": 1.2221093540658416e-05, + "loss": 3.364, + "step": 2307584 + }, + { + "epoch": 0.01, + "learning_rate": 1.2212707593147896e-05, + "loss": 3.3757, + "step": 2308096 + }, + { + "epoch": 0.01, + "learning_rate": 1.2204321645637374e-05, + "loss": 3.3533, + "step": 2308608 + }, + { + "epoch": 0.01, + "learning_rate": 1.2195935698126854e-05, + "loss": 3.3641, + "step": 2309120 + }, + { + "epoch": 0.01, + "learning_rate": 1.2187549750616336e-05, + "loss": 3.3621, + "step": 2309632 + }, + { + "epoch": 0.01, + "learning_rate": 1.2179163803105814e-05, + "loss": 3.3652, + "step": 2310144 + }, + { + "epoch": 0.01, + "learning_rate": 1.2170794234399025e-05, + "loss": 3.3574, + "step": 2310656 + }, + { + "epoch": 0.01, + "learning_rate": 1.2162408286888507e-05, + "loss": 3.3809, + "step": 2311168 + }, + { + "epoch": 0.01, + "learning_rate": 1.2154022339377987e-05, + "loss": 3.3643, + "step": 2311680 + }, + { + "epoch": 0.01, + "learning_rate": 1.2145636391867465e-05, + "loss": 3.3712, + "step": 2312192 + }, + { + "epoch": 0.01, + "learning_rate": 1.2137266823160677e-05, + "loss": 3.3697, + "step": 2312704 + }, + { + "epoch": 0.01, + "learning_rate": 1.2128880875650157e-05, + "loss": 3.3646, + "step": 2313216 + }, + { + "epoch": 0.01, + "learning_rate": 1.2120494928139637e-05, + "loss": 3.3631, + "step": 2313728 + }, + { + "epoch": 0.01, + "learning_rate": 1.2112108980629117e-05, + "loss": 3.3483, + "step": 2314240 + }, + { + "epoch": 0.01, + "learning_rate": 1.2103739411922328e-05, + "loss": 3.3652, + "step": 2314752 + }, + { + "epoch": 0.01, + "learning_rate": 1.2095353464411808e-05, + "loss": 3.3728, + "step": 2315264 + }, + { + "epoch": 0.01, + "learning_rate": 1.2086967516901288e-05, + "loss": 3.3678, + "step": 2315776 + }, + { + "epoch": 0.01, + "learning_rate": 1.2078597948194499e-05, + "loss": 3.3586, + "step": 2316288 + }, + { + "epoch": 0.01, + "learning_rate": 1.2070212000683979e-05, + "loss": 3.3524, + "step": 2316800 + }, + { + "epoch": 0.01, + "learning_rate": 1.206182605317346e-05, + "loss": 3.3619, + "step": 2317312 + }, + { + "epoch": 0.01, + "learning_rate": 1.2053440105662939e-05, + "loss": 3.3473, + "step": 2317824 + }, + { + "epoch": 0.01, + "learning_rate": 1.2045070536956151e-05, + "loss": 3.382, + "step": 2318336 + }, + { + "epoch": 0.01, + "learning_rate": 1.2036684589445631e-05, + "loss": 3.3608, + "step": 2318848 + }, + { + "epoch": 0.01, + "learning_rate": 1.2028298641935111e-05, + "loss": 3.3682, + "step": 2319360 + }, + { + "epoch": 0.01, + "learning_rate": 1.201991269442459e-05, + "loss": 3.373, + "step": 2319872 + }, + { + "epoch": 0.01, + "learning_rate": 1.2011543125717802e-05, + "loss": 3.3541, + "step": 2320384 + }, + { + "epoch": 0.01, + "learning_rate": 1.2003157178207282e-05, + "loss": 3.3593, + "step": 2320896 + }, + { + "epoch": 0.01, + "learning_rate": 1.1994771230696762e-05, + "loss": 3.3578, + "step": 2321408 + }, + { + "epoch": 0.01, + "learning_rate": 1.1986385283186242e-05, + "loss": 3.3533, + "step": 2321920 + }, + { + "epoch": 0.01, + "learning_rate": 1.1978015714479452e-05, + "loss": 3.3532, + "step": 2322432 + }, + { + "epoch": 0.01, + "learning_rate": 1.1969629766968932e-05, + "loss": 3.3751, + "step": 2322944 + }, + { + "epoch": 0.01, + "learning_rate": 1.1961260198262143e-05, + "loss": 3.368, + "step": 2323456 + }, + { + "epoch": 0.01, + "learning_rate": 1.1952874250751623e-05, + "loss": 3.3582, + "step": 2323968 + }, + { + "epoch": 0.01, + "learning_rate": 1.1944488303241105e-05, + "loss": 3.3527, + "step": 2324480 + }, + { + "epoch": 0.01, + "learning_rate": 1.1936102355730585e-05, + "loss": 3.3598, + "step": 2324992 + }, + { + "epoch": 0.01, + "learning_rate": 1.1927716408220063e-05, + "loss": 3.365, + "step": 2325504 + }, + { + "epoch": 0.01, + "learning_rate": 1.1919330460709543e-05, + "loss": 3.369, + "step": 2326016 + }, + { + "epoch": 0.01, + "learning_rate": 1.1910944513199025e-05, + "loss": 3.3627, + "step": 2326528 + }, + { + "epoch": 0.01, + "learning_rate": 1.1902558565688503e-05, + "loss": 3.3677, + "step": 2327040 + }, + { + "epoch": 0.01, + "learning_rate": 1.1894188996981714e-05, + "loss": 3.3748, + "step": 2327552 + }, + { + "epoch": 0.01, + "learning_rate": 1.1885803049471195e-05, + "loss": 3.3656, + "step": 2328064 + }, + { + "epoch": 0.01, + "learning_rate": 1.1877417101960675e-05, + "loss": 3.3573, + "step": 2328576 + }, + { + "epoch": 0.01, + "learning_rate": 1.1869031154450153e-05, + "loss": 3.3658, + "step": 2329088 + }, + { + "epoch": 0.01, + "learning_rate": 1.1860661585743366e-05, + "loss": 3.3654, + "step": 2329600 + }, + { + "epoch": 0.01, + "learning_rate": 1.1852275638232846e-05, + "loss": 3.3695, + "step": 2330112 + }, + { + "epoch": 0.01, + "learning_rate": 1.1843889690722324e-05, + "loss": 3.3711, + "step": 2330624 + }, + { + "epoch": 0.01, + "learning_rate": 1.1835503743211806e-05, + "loss": 3.3719, + "step": 2331136 + }, + { + "epoch": 0.01, + "learning_rate": 1.1827134174505017e-05, + "loss": 3.3798, + "step": 2331648 + }, + { + "epoch": 0.01, + "learning_rate": 1.1818748226994497e-05, + "loss": 3.369, + "step": 2332160 + }, + { + "epoch": 0.01, + "learning_rate": 1.1810362279483977e-05, + "loss": 3.3504, + "step": 2332672 + }, + { + "epoch": 0.01, + "learning_rate": 1.1801976331973456e-05, + "loss": 3.3576, + "step": 2333184 + }, + { + "epoch": 0.01, + "learning_rate": 1.1793606763266667e-05, + "loss": 3.3741, + "step": 2333696 + }, + { + "epoch": 0.01, + "learning_rate": 1.1785220815756149e-05, + "loss": 3.3688, + "step": 2334208 + }, + { + "epoch": 0.01, + "learning_rate": 1.1776834868245627e-05, + "loss": 3.3611, + "step": 2334720 + }, + { + "epoch": 0.01, + "learning_rate": 1.1768448920735107e-05, + "loss": 3.3642, + "step": 2335232 + }, + { + "epoch": 0.02, + "learning_rate": 1.176007935202832e-05, + "loss": 3.3719, + "step": 2335744 + }, + { + "epoch": 0.02, + "learning_rate": 1.1751693404517798e-05, + "loss": 3.36, + "step": 2336256 + }, + { + "epoch": 0.02, + "learning_rate": 1.1743307457007278e-05, + "loss": 3.3646, + "step": 2336768 + }, + { + "epoch": 0.02, + "learning_rate": 1.173492150949676e-05, + "loss": 3.3607, + "step": 2337280 + }, + { + "epoch": 0.02, + "learning_rate": 1.172655194078997e-05, + "loss": 3.3669, + "step": 2337792 + }, + { + "epoch": 0.02, + "learning_rate": 1.1718165993279449e-05, + "loss": 3.3725, + "step": 2338304 + }, + { + "epoch": 0.02, + "learning_rate": 1.170978004576893e-05, + "loss": 3.3675, + "step": 2338816 + }, + { + "epoch": 0.02, + "learning_rate": 1.170139409825841e-05, + "loss": 3.3529, + "step": 2339328 + }, + { + "epoch": 0.02, + "learning_rate": 1.1693024529551621e-05, + "loss": 3.37, + "step": 2339840 + }, + { + "epoch": 0.02, + "learning_rate": 1.1684638582041101e-05, + "loss": 3.3648, + "step": 2340352 + }, + { + "epoch": 0.02, + "learning_rate": 1.167625263453058e-05, + "loss": 3.3686, + "step": 2340864 + }, + { + "epoch": 0.02, + "learning_rate": 1.166786668702006e-05, + "loss": 3.3616, + "step": 2341376 + }, + { + "epoch": 0.02, + "learning_rate": 1.1659497118313272e-05, + "loss": 3.3559, + "step": 2341888 + }, + { + "epoch": 0.02, + "learning_rate": 1.1651111170802752e-05, + "loss": 3.3517, + "step": 2342400 + }, + { + "epoch": 0.02, + "learning_rate": 1.1642725223292232e-05, + "loss": 3.3661, + "step": 2342912 + }, + { + "epoch": 0.02, + "learning_rate": 1.1634339275781713e-05, + "loss": 3.356, + "step": 2343424 + }, + { + "epoch": 0.02, + "learning_rate": 1.1625969707074922e-05, + "loss": 3.3582, + "step": 2343936 + }, + { + "epoch": 0.02, + "learning_rate": 1.1617583759564402e-05, + "loss": 3.3672, + "step": 2344448 + }, + { + "epoch": 0.02, + "learning_rate": 1.1609197812053884e-05, + "loss": 3.3636, + "step": 2344960 + }, + { + "epoch": 0.02, + "learning_rate": 1.1600811864543362e-05, + "loss": 3.354, + "step": 2345472 + }, + { + "epoch": 0.02, + "learning_rate": 1.1592442295836575e-05, + "loss": 3.3639, + "step": 2345984 + }, + { + "epoch": 0.02, + "learning_rate": 1.1584056348326055e-05, + "loss": 3.3507, + "step": 2346496 + }, + { + "epoch": 0.02, + "learning_rate": 1.1575670400815535e-05, + "loss": 3.3655, + "step": 2347008 + }, + { + "epoch": 0.02, + "learning_rate": 1.1567284453305013e-05, + "loss": 3.3573, + "step": 2347520 + }, + { + "epoch": 0.02, + "learning_rate": 1.1558914884598225e-05, + "loss": 3.3652, + "step": 2348032 + }, + { + "epoch": 0.02, + "learning_rate": 1.1550528937087705e-05, + "loss": 3.3647, + "step": 2348544 + }, + { + "epoch": 0.02, + "learning_rate": 1.1542142989577183e-05, + "loss": 3.3713, + "step": 2349056 + }, + { + "epoch": 0.02, + "learning_rate": 1.1533773420870396e-05, + "loss": 3.3593, + "step": 2349568 + }, + { + "epoch": 0.02, + "learning_rate": 1.1525387473359876e-05, + "loss": 3.3659, + "step": 2350080 + }, + { + "epoch": 0.02, + "learning_rate": 1.1517001525849356e-05, + "loss": 3.3711, + "step": 2350592 + }, + { + "epoch": 0.02, + "learning_rate": 1.1508615578338836e-05, + "loss": 3.3601, + "step": 2351104 + }, + { + "epoch": 0.02, + "learning_rate": 1.1500246009632047e-05, + "loss": 3.3542, + "step": 2351616 + }, + { + "epoch": 0.02, + "learning_rate": 1.1491860062121528e-05, + "loss": 3.3679, + "step": 2352128 + }, + { + "epoch": 0.02, + "learning_rate": 1.1483474114611008e-05, + "loss": 3.3591, + "step": 2352640 + }, + { + "epoch": 0.02, + "learning_rate": 1.1475088167100486e-05, + "loss": 3.3698, + "step": 2353152 + }, + { + "epoch": 0.02, + "learning_rate": 1.1466718598393699e-05, + "loss": 3.3568, + "step": 2353664 + }, + { + "epoch": 0.02, + "learning_rate": 1.1458332650883179e-05, + "loss": 3.3577, + "step": 2354176 + }, + { + "epoch": 0.02, + "learning_rate": 1.1449946703372657e-05, + "loss": 3.3571, + "step": 2354688 + }, + { + "epoch": 0.02, + "learning_rate": 1.1441560755862137e-05, + "loss": 3.3611, + "step": 2355200 + }, + { + "epoch": 0.02, + "learning_rate": 1.143319118715535e-05, + "loss": 3.3592, + "step": 2355712 + }, + { + "epoch": 0.02, + "learning_rate": 1.142480523964483e-05, + "loss": 3.3662, + "step": 2356224 + }, + { + "epoch": 0.02, + "learning_rate": 1.141641929213431e-05, + "loss": 3.3709, + "step": 2356736 + }, + { + "epoch": 0.02, + "learning_rate": 1.140803334462379e-05, + "loss": 3.3568, + "step": 2357248 + }, + { + "epoch": 0.02, + "learning_rate": 1.1399663775917e-05, + "loss": 3.3688, + "step": 2357760 + }, + { + "epoch": 0.02, + "learning_rate": 1.1391277828406482e-05, + "loss": 3.3635, + "step": 2358272 + }, + { + "epoch": 0.02, + "learning_rate": 1.138289188089596e-05, + "loss": 3.3737, + "step": 2358784 + }, + { + "epoch": 0.02, + "learning_rate": 1.137450593338544e-05, + "loss": 3.3567, + "step": 2359296 + }, + { + "epoch": 0.02, + "learning_rate": 1.1366136364678653e-05, + "loss": 3.3623, + "step": 2359808 + }, + { + "epoch": 0.02, + "learning_rate": 1.1357750417168131e-05, + "loss": 3.3645, + "step": 2360320 + }, + { + "epoch": 0.02, + "learning_rate": 1.1349364469657611e-05, + "loss": 3.3686, + "step": 2360832 + }, + { + "epoch": 0.02, + "learning_rate": 1.134097852214709e-05, + "loss": 3.3598, + "step": 2361344 + }, + { + "epoch": 0.02, + "learning_rate": 1.1332608953440303e-05, + "loss": 3.3595, + "step": 2361856 + }, + { + "epoch": 0.02, + "learning_rate": 1.1324223005929782e-05, + "loss": 3.3651, + "step": 2362368 + }, + { + "epoch": 0.02, + "learning_rate": 1.1315837058419263e-05, + "loss": 3.3588, + "step": 2362880 + }, + { + "epoch": 0.02, + "learning_rate": 1.1307451110908743e-05, + "loss": 3.3577, + "step": 2363392 + }, + { + "epoch": 0.02, + "learning_rate": 1.1299081542201954e-05, + "loss": 3.3742, + "step": 2363904 + }, + { + "epoch": 0.02, + "learning_rate": 1.1290695594691434e-05, + "loss": 3.3574, + "step": 2364416 + }, + { + "epoch": 0.02, + "learning_rate": 1.1282309647180914e-05, + "loss": 3.3663, + "step": 2364928 + }, + { + "epoch": 0.02, + "learning_rate": 1.1273923699670394e-05, + "loss": 3.3559, + "step": 2365440 + }, + { + "epoch": 0.03, + "eval_loss": 3.865949869155884, + "eval_runtime": 316.7209, + "eval_samples_per_second": 1204.818, + "eval_steps_per_second": 37.651, + "step": 2365920 + }, + { + "epoch": 1.0, + "learning_rate": 1.1265537752159872e-05, + "loss": 3.3557, + "step": 2365952 + }, + { + "epoch": 1.0, + "learning_rate": 1.1257168183453085e-05, + "loss": 3.3524, + "step": 2366464 + }, + { + "epoch": 1.0, + "learning_rate": 1.1248782235942565e-05, + "loss": 3.3625, + "step": 2366976 + }, + { + "epoch": 1.0, + "learning_rate": 1.1240396288432044e-05, + "loss": 3.3729, + "step": 2367488 + }, + { + "epoch": 1.0, + "learning_rate": 1.1232010340921524e-05, + "loss": 3.3654, + "step": 2368000 + }, + { + "epoch": 1.0, + "learning_rate": 1.1223624393411004e-05, + "loss": 3.3677, + "step": 2368512 + }, + { + "epoch": 1.0, + "learning_rate": 1.1215238445900484e-05, + "loss": 3.3545, + "step": 2369024 + }, + { + "epoch": 1.0, + "learning_rate": 1.1206852498389964e-05, + "loss": 3.3648, + "step": 2369536 + }, + { + "epoch": 1.0, + "learning_rate": 1.1198466550879444e-05, + "loss": 3.3557, + "step": 2370048 + }, + { + "epoch": 1.0, + "learning_rate": 1.1190096982172655e-05, + "loss": 3.364, + "step": 2370560 + }, + { + "epoch": 1.0, + "learning_rate": 1.1181711034662137e-05, + "loss": 3.3583, + "step": 2371072 + }, + { + "epoch": 1.0, + "learning_rate": 1.1173325087151615e-05, + "loss": 3.366, + "step": 2371584 + }, + { + "epoch": 1.0, + "learning_rate": 1.1164955518444826e-05, + "loss": 3.379, + "step": 2372096 + }, + { + "epoch": 1.0, + "learning_rate": 1.1156569570934307e-05, + "loss": 3.3513, + "step": 2372608 + }, + { + "epoch": 1.0, + "learning_rate": 1.1148183623423786e-05, + "loss": 3.3431, + "step": 2373120 + }, + { + "epoch": 1.0, + "learning_rate": 1.1139797675913266e-05, + "loss": 3.348, + "step": 2373632 + }, + { + "epoch": 1.0, + "learning_rate": 1.1131411728402746e-05, + "loss": 3.3646, + "step": 2374144 + }, + { + "epoch": 1.0, + "learning_rate": 1.1123025780892227e-05, + "loss": 3.3645, + "step": 2374656 + }, + { + "epoch": 1.0, + "learning_rate": 1.1114639833381705e-05, + "loss": 3.3592, + "step": 2375168 + }, + { + "epoch": 1.0, + "learning_rate": 1.1106253885871185e-05, + "loss": 3.3574, + "step": 2375680 + }, + { + "epoch": 1.0, + "learning_rate": 1.1097884317164398e-05, + "loss": 3.3831, + "step": 2376192 + }, + { + "epoch": 1.0, + "learning_rate": 1.1089498369653876e-05, + "loss": 3.3586, + "step": 2376704 + }, + { + "epoch": 1.0, + "learning_rate": 1.1081112422143356e-05, + "loss": 3.3567, + "step": 2377216 + }, + { + "epoch": 1.0, + "learning_rate": 1.1072726474632838e-05, + "loss": 3.3622, + "step": 2377728 + }, + { + "epoch": 1.0, + "learning_rate": 1.1064356905926049e-05, + "loss": 3.3752, + "step": 2378240 + }, + { + "epoch": 1.0, + "learning_rate": 1.1055970958415529e-05, + "loss": 3.3486, + "step": 2378752 + }, + { + "epoch": 1.0, + "learning_rate": 1.1047585010905008e-05, + "loss": 3.3585, + "step": 2379264 + }, + { + "epoch": 1.0, + "learning_rate": 1.1039199063394488e-05, + "loss": 3.3679, + "step": 2379776 + }, + { + "epoch": 1.0, + "learning_rate": 1.10308294946877e-05, + "loss": 3.3553, + "step": 2380288 + }, + { + "epoch": 1.0, + "learning_rate": 1.102244354717718e-05, + "loss": 3.3491, + "step": 2380800 + }, + { + "epoch": 1.01, + "learning_rate": 1.1014057599666659e-05, + "loss": 3.3483, + "step": 2381312 + }, + { + "epoch": 1.01, + "learning_rate": 1.1005671652156139e-05, + "loss": 3.3572, + "step": 2381824 + }, + { + "epoch": 1.01, + "learning_rate": 1.099730208344935e-05, + "loss": 3.3673, + "step": 2382336 + }, + { + "epoch": 1.01, + "learning_rate": 1.098893251474256e-05, + "loss": 3.3641, + "step": 2382848 + }, + { + "epoch": 1.01, + "learning_rate": 1.0980546567232042e-05, + "loss": 3.3634, + "step": 2383360 + }, + { + "epoch": 1.01, + "learning_rate": 1.0972160619721522e-05, + "loss": 3.3519, + "step": 2383872 + }, + { + "epoch": 1.01, + "learning_rate": 1.0963774672211e-05, + "loss": 3.3659, + "step": 2384384 + }, + { + "epoch": 1.01, + "learning_rate": 1.095538872470048e-05, + "loss": 3.3481, + "step": 2384896 + }, + { + "epoch": 1.01, + "learning_rate": 1.0947002777189962e-05, + "loss": 3.3576, + "step": 2385408 + }, + { + "epoch": 1.01, + "learning_rate": 1.093861682967944e-05, + "loss": 3.3511, + "step": 2385920 + }, + { + "epoch": 1.01, + "learning_rate": 1.093023088216892e-05, + "loss": 3.3556, + "step": 2386432 + }, + { + "epoch": 1.01, + "learning_rate": 1.0921861313462133e-05, + "loss": 3.3476, + "step": 2386944 + }, + { + "epoch": 1.01, + "learning_rate": 1.0913475365951613e-05, + "loss": 3.3706, + "step": 2387456 + }, + { + "epoch": 1.01, + "learning_rate": 1.0905089418441091e-05, + "loss": 3.3532, + "step": 2387968 + }, + { + "epoch": 1.01, + "learning_rate": 1.0896703470930573e-05, + "loss": 3.3598, + "step": 2388480 + }, + { + "epoch": 1.01, + "learning_rate": 1.0888333902223784e-05, + "loss": 3.3637, + "step": 2388992 + }, + { + "epoch": 1.01, + "learning_rate": 1.0879947954713263e-05, + "loss": 3.3547, + "step": 2389504 + }, + { + "epoch": 1.01, + "learning_rate": 1.0871562007202743e-05, + "loss": 3.3545, + "step": 2390016 + }, + { + "epoch": 1.01, + "learning_rate": 1.0863176059692223e-05, + "loss": 3.3405, + "step": 2390528 + }, + { + "epoch": 1.01, + "learning_rate": 1.0854790112181703e-05, + "loss": 3.3523, + "step": 2391040 + }, + { + "epoch": 1.01, + "learning_rate": 1.0846404164671183e-05, + "loss": 3.3642, + "step": 2391552 + }, + { + "epoch": 1.01, + "learning_rate": 1.0838018217160663e-05, + "loss": 3.3601, + "step": 2392064 + }, + { + "epoch": 1.01, + "learning_rate": 1.0829648648453874e-05, + "loss": 3.3497, + "step": 2392576 + }, + { + "epoch": 1.01, + "learning_rate": 1.0821262700943354e-05, + "loss": 3.3429, + "step": 2393088 + }, + { + "epoch": 1.01, + "learning_rate": 1.0812876753432834e-05, + "loss": 3.3493, + "step": 2393600 + }, + { + "epoch": 1.01, + "learning_rate": 1.0804490805922314e-05, + "loss": 3.3419, + "step": 2394112 + }, + { + "epoch": 1.01, + "learning_rate": 1.0796121237215526e-05, + "loss": 3.3693, + "step": 2394624 + }, + { + "epoch": 1.01, + "learning_rate": 1.0787735289705005e-05, + "loss": 3.3502, + "step": 2395136 + }, + { + "epoch": 1.01, + "learning_rate": 1.0779349342194485e-05, + "loss": 3.3579, + "step": 2395648 + }, + { + "epoch": 1.01, + "learning_rate": 1.0770963394683965e-05, + "loss": 3.367, + "step": 2396160 + }, + { + "epoch": 1.01, + "learning_rate": 1.0762593825977177e-05, + "loss": 3.3422, + "step": 2396672 + }, + { + "epoch": 1.01, + "learning_rate": 1.0754207878466655e-05, + "loss": 3.3485, + "step": 2397184 + }, + { + "epoch": 1.01, + "learning_rate": 1.0745821930956137e-05, + "loss": 3.3497, + "step": 2397696 + }, + { + "epoch": 1.01, + "learning_rate": 1.0737435983445617e-05, + "loss": 3.3432, + "step": 2398208 + }, + { + "epoch": 1.01, + "learning_rate": 1.0729066414738826e-05, + "loss": 3.3464, + "step": 2398720 + }, + { + "epoch": 1.01, + "learning_rate": 1.0720680467228308e-05, + "loss": 3.3589, + "step": 2399232 + }, + { + "epoch": 1.01, + "learning_rate": 1.0712310898521518e-05, + "loss": 3.3632, + "step": 2399744 + }, + { + "epoch": 1.01, + "learning_rate": 1.0703924951010998e-05, + "loss": 3.3475, + "step": 2400256 + }, + { + "epoch": 1.01, + "learning_rate": 1.0695539003500478e-05, + "loss": 3.3408, + "step": 2400768 + }, + { + "epoch": 1.01, + "learning_rate": 1.0687153055989958e-05, + "loss": 3.3513, + "step": 2401280 + }, + { + "epoch": 1.01, + "learning_rate": 1.0678767108479438e-05, + "loss": 3.3555, + "step": 2401792 + }, + { + "epoch": 1.01, + "learning_rate": 1.0670381160968918e-05, + "loss": 3.3564, + "step": 2402304 + }, + { + "epoch": 1.01, + "learning_rate": 1.0661995213458398e-05, + "loss": 3.3558, + "step": 2402816 + }, + { + "epoch": 1.01, + "learning_rate": 1.0653609265947878e-05, + "loss": 3.3569, + "step": 2403328 + }, + { + "epoch": 1.01, + "learning_rate": 1.0645239697241089e-05, + "loss": 3.3662, + "step": 2403840 + }, + { + "epoch": 1.01, + "learning_rate": 1.0636853749730569e-05, + "loss": 3.3598, + "step": 2404352 + }, + { + "epoch": 1.01, + "learning_rate": 1.0628467802220049e-05, + "loss": 3.3428, + "step": 2404864 + }, + { + "epoch": 1.01, + "learning_rate": 1.0620081854709529e-05, + "loss": 3.3588, + "step": 2405376 + }, + { + "epoch": 1.01, + "learning_rate": 1.0611712286002741e-05, + "loss": 3.3557, + "step": 2405888 + }, + { + "epoch": 1.01, + "learning_rate": 1.060332633849222e-05, + "loss": 3.353, + "step": 2406400 + }, + { + "epoch": 1.01, + "learning_rate": 1.05949403909817e-05, + "loss": 3.3655, + "step": 2406912 + }, + { + "epoch": 1.01, + "learning_rate": 1.0586554443471181e-05, + "loss": 3.3613, + "step": 2407424 + }, + { + "epoch": 1.01, + "learning_rate": 1.057818487476439e-05, + "loss": 3.3701, + "step": 2407936 + }, + { + "epoch": 1.01, + "learning_rate": 1.0569815306057603e-05, + "loss": 3.3604, + "step": 2408448 + }, + { + "epoch": 1.01, + "learning_rate": 1.0561429358547083e-05, + "loss": 3.3444, + "step": 2408960 + }, + { + "epoch": 1.01, + "learning_rate": 1.0553043411036563e-05, + "loss": 3.3471, + "step": 2409472 + }, + { + "epoch": 1.01, + "learning_rate": 1.0544657463526043e-05, + "loss": 3.3595, + "step": 2409984 + }, + { + "epoch": 1.01, + "learning_rate": 1.0536271516015523e-05, + "loss": 3.362, + "step": 2410496 + }, + { + "epoch": 1.01, + "learning_rate": 1.0527885568505003e-05, + "loss": 3.3554, + "step": 2411008 + }, + { + "epoch": 1.01, + "learning_rate": 1.051949962099448e-05, + "loss": 3.3544, + "step": 2411520 + }, + { + "epoch": 1.02, + "learning_rate": 1.0511113673483962e-05, + "loss": 3.3628, + "step": 2412032 + }, + { + "epoch": 1.02, + "learning_rate": 1.0502744104777173e-05, + "loss": 3.3504, + "step": 2412544 + }, + { + "epoch": 1.02, + "learning_rate": 1.0494358157266653e-05, + "loss": 3.3535, + "step": 2413056 + }, + { + "epoch": 1.02, + "learning_rate": 1.0485972209756133e-05, + "loss": 3.352, + "step": 2413568 + }, + { + "epoch": 1.02, + "learning_rate": 1.0477586262245613e-05, + "loss": 3.3569, + "step": 2414080 + }, + { + "epoch": 1.02, + "learning_rate": 1.0469216693538826e-05, + "loss": 3.3674, + "step": 2414592 + }, + { + "epoch": 1.02, + "learning_rate": 1.0460830746028306e-05, + "loss": 3.3541, + "step": 2415104 + }, + { + "epoch": 1.02, + "learning_rate": 1.0452444798517784e-05, + "loss": 3.3435, + "step": 2415616 + }, + { + "epoch": 1.02, + "learning_rate": 1.0444058851007264e-05, + "loss": 3.358, + "step": 2416128 + }, + { + "epoch": 1.02, + "learning_rate": 1.0435689282300476e-05, + "loss": 3.3558, + "step": 2416640 + }, + { + "epoch": 1.02, + "learning_rate": 1.0427303334789954e-05, + "loss": 3.3592, + "step": 2417152 + }, + { + "epoch": 1.02, + "learning_rate": 1.0418917387279434e-05, + "loss": 3.3517, + "step": 2417664 + }, + { + "epoch": 1.02, + "learning_rate": 1.0410531439768916e-05, + "loss": 3.3492, + "step": 2418176 + }, + { + "epoch": 1.02, + "learning_rate": 1.0402161871062127e-05, + "loss": 3.3408, + "step": 2418688 + }, + { + "epoch": 1.02, + "learning_rate": 1.0393775923551607e-05, + "loss": 3.3608, + "step": 2419200 + }, + { + "epoch": 1.02, + "learning_rate": 1.0385389976041087e-05, + "loss": 3.3445, + "step": 2419712 + }, + { + "epoch": 1.02, + "learning_rate": 1.0377004028530567e-05, + "loss": 3.3523, + "step": 2420224 + }, + { + "epoch": 1.02, + "learning_rate": 1.0368634459823778e-05, + "loss": 3.3574, + "step": 2420736 + }, + { + "epoch": 1.02, + "learning_rate": 1.0360248512313257e-05, + "loss": 3.3471, + "step": 2421248 + }, + { + "epoch": 1.02, + "learning_rate": 1.0351862564802737e-05, + "loss": 3.3459, + "step": 2421760 + }, + { + "epoch": 1.02, + "learning_rate": 1.0343476617292217e-05, + "loss": 3.3507, + "step": 2422272 + }, + { + "epoch": 1.02, + "learning_rate": 1.0335107048585428e-05, + "loss": 3.3449, + "step": 2422784 + }, + { + "epoch": 1.02, + "learning_rate": 1.0326721101074908e-05, + "loss": 3.358, + "step": 2423296 + }, + { + "epoch": 1.02, + "learning_rate": 1.0318335153564388e-05, + "loss": 3.3487, + "step": 2423808 + }, + { + "epoch": 1.02, + "learning_rate": 1.030994920605387e-05, + "loss": 3.3541, + "step": 2424320 + }, + { + "epoch": 1.02, + "learning_rate": 1.0301579637347079e-05, + "loss": 3.3516, + "step": 2424832 + }, + { + "epoch": 1.02, + "learning_rate": 1.0293210068640291e-05, + "loss": 3.3632, + "step": 2425344 + }, + { + "epoch": 1.02, + "learning_rate": 1.0284824121129771e-05, + "loss": 3.3509, + "step": 2425856 + }, + { + "epoch": 1.02, + "learning_rate": 1.0276438173619251e-05, + "loss": 3.3572, + "step": 2426368 + }, + { + "epoch": 1.02, + "learning_rate": 1.0268052226108731e-05, + "loss": 3.3605, + "step": 2426880 + }, + { + "epoch": 1.02, + "learning_rate": 1.0259666278598211e-05, + "loss": 3.3535, + "step": 2427392 + }, + { + "epoch": 1.02, + "learning_rate": 1.0251280331087691e-05, + "loss": 3.3401, + "step": 2427904 + }, + { + "epoch": 1.02, + "learning_rate": 1.024289438357717e-05, + "loss": 3.3602, + "step": 2428416 + }, + { + "epoch": 1.02, + "learning_rate": 1.0234508436066651e-05, + "loss": 3.3518, + "step": 2428928 + }, + { + "epoch": 1.02, + "learning_rate": 1.0226138867359862e-05, + "loss": 3.3607, + "step": 2429440 + }, + { + "epoch": 1.02, + "learning_rate": 1.0217752919849342e-05, + "loss": 3.3452, + "step": 2429952 + }, + { + "epoch": 1.02, + "learning_rate": 1.0209366972338822e-05, + "loss": 3.3492, + "step": 2430464 + }, + { + "epoch": 1.02, + "learning_rate": 1.0200981024828302e-05, + "loss": 3.347, + "step": 2430976 + }, + { + "epoch": 1.02, + "learning_rate": 1.0192611456121512e-05, + "loss": 3.3479, + "step": 2431488 + }, + { + "epoch": 1.02, + "learning_rate": 1.0184225508610992e-05, + "loss": 3.3492, + "step": 2432000 + }, + { + "epoch": 1.02, + "learning_rate": 1.0175839561100472e-05, + "loss": 3.358, + "step": 2432512 + }, + { + "epoch": 1.02, + "learning_rate": 1.0167453613589952e-05, + "loss": 3.3628, + "step": 2433024 + }, + { + "epoch": 1.02, + "learning_rate": 1.0159084044883165e-05, + "loss": 3.3489, + "step": 2433536 + }, + { + "epoch": 1.02, + "learning_rate": 1.0150698097372643e-05, + "loss": 3.3551, + "step": 2434048 + }, + { + "epoch": 1.02, + "learning_rate": 1.0142312149862123e-05, + "loss": 3.3532, + "step": 2434560 + }, + { + "epoch": 1.02, + "learning_rate": 1.0133926202351605e-05, + "loss": 3.3632, + "step": 2435072 + }, + { + "epoch": 1.02, + "learning_rate": 1.0125556633644814e-05, + "loss": 3.3555, + "step": 2435584 + }, + { + "epoch": 1.02, + "learning_rate": 1.0117170686134295e-05, + "loss": 3.3507, + "step": 2436096 + }, + { + "epoch": 1.02, + "learning_rate": 1.0108784738623775e-05, + "loss": 3.3577, + "step": 2436608 + }, + { + "epoch": 1.02, + "learning_rate": 1.0100398791113255e-05, + "loss": 3.3556, + "step": 2437120 + }, + { + "epoch": 1.02, + "learning_rate": 1.0092029222406466e-05, + "loss": 3.353, + "step": 2437632 + }, + { + "epoch": 1.02, + "learning_rate": 1.0083643274895946e-05, + "loss": 3.3505, + "step": 2438144 + }, + { + "epoch": 1.02, + "learning_rate": 1.0075257327385426e-05, + "loss": 3.3577, + "step": 2438656 + }, + { + "epoch": 1.02, + "learning_rate": 1.0066871379874904e-05, + "loss": 3.3505, + "step": 2439168 + }, + { + "epoch": 1.02, + "learning_rate": 1.0058501811168117e-05, + "loss": 3.3455, + "step": 2439680 + }, + { + "epoch": 1.02, + "learning_rate": 1.0050132242461328e-05, + "loss": 3.3673, + "step": 2440192 + }, + { + "epoch": 1.02, + "learning_rate": 1.004174629495081e-05, + "loss": 3.3499, + "step": 2440704 + }, + { + "epoch": 1.02, + "learning_rate": 1.0033360347440288e-05, + "loss": 3.3565, + "step": 2441216 + }, + { + "epoch": 1.02, + "learning_rate": 1.0024974399929767e-05, + "loss": 3.3481, + "step": 2441728 + }, + { + "epoch": 1.03, + "learning_rate": 1.0016588452419247e-05, + "loss": 3.3475, + "step": 2442240 + }, + { + "epoch": 1.03, + "eval_loss": 3.867100715637207, + "eval_runtime": 307.341, + "eval_samples_per_second": 1241.588, + "eval_steps_per_second": 38.801, + "step": 2442240 + }, + { + "epoch": 0.0, + "learning_rate": 1.0008202504908729e-05, + "loss": 3.3382, + "step": 2442752 + }, + { + "epoch": 0.0, + "learning_rate": 9.999816557398207e-06, + "loss": 3.3552, + "step": 2443264 + }, + { + "epoch": 0.0, + "learning_rate": 9.991430609887687e-06, + "loss": 3.3653, + "step": 2443776 + }, + { + "epoch": 0.0, + "learning_rate": 9.9830610411809e-06, + "loss": 3.3573, + "step": 2444288 + }, + { + "epoch": 0.0, + "learning_rate": 9.974675093670378e-06, + "loss": 3.3614, + "step": 2444800 + }, + { + "epoch": 0.0, + "learning_rate": 9.966289146159858e-06, + "loss": 3.3458, + "step": 2445312 + }, + { + "epoch": 0.0, + "learning_rate": 9.95790319864934e-06, + "loss": 3.3532, + "step": 2445824 + }, + { + "epoch": 0.0, + "learning_rate": 9.94951725113882e-06, + "loss": 3.345, + "step": 2446336 + }, + { + "epoch": 0.0, + "learning_rate": 9.941131303628298e-06, + "loss": 3.3546, + "step": 2446848 + }, + { + "epoch": 0.0, + "learning_rate": 9.932745356117778e-06, + "loss": 3.3513, + "step": 2447360 + }, + { + "epoch": 0.0, + "learning_rate": 9.92435940860726e-06, + "loss": 3.3569, + "step": 2447872 + }, + { + "epoch": 0.0, + "learning_rate": 9.915989839900469e-06, + "loss": 3.3588, + "step": 2448384 + }, + { + "epoch": 0.0, + "learning_rate": 9.907620271193681e-06, + "loss": 3.3519, + "step": 2448896 + }, + { + "epoch": 0.0, + "learning_rate": 9.899234323683161e-06, + "loss": 3.3359, + "step": 2449408 + }, + { + "epoch": 0.0, + "learning_rate": 9.890848376172641e-06, + "loss": 3.346, + "step": 2449920 + }, + { + "epoch": 0.0, + "learning_rate": 9.882462428662121e-06, + "loss": 3.349, + "step": 2450432 + }, + { + "epoch": 0.0, + "learning_rate": 9.874076481151601e-06, + "loss": 3.3542, + "step": 2450944 + }, + { + "epoch": 0.0, + "learning_rate": 9.86569053364108e-06, + "loss": 3.345, + "step": 2451456 + }, + { + "epoch": 0.0, + "learning_rate": 9.857304586130559e-06, + "loss": 3.3511, + "step": 2451968 + }, + { + "epoch": 0.0, + "learning_rate": 9.848935017423772e-06, + "loss": 3.3765, + "step": 2452480 + }, + { + "epoch": 0.0, + "learning_rate": 9.840549069913252e-06, + "loss": 3.35, + "step": 2452992 + }, + { + "epoch": 0.0, + "learning_rate": 9.832163122402731e-06, + "loss": 3.3488, + "step": 2453504 + }, + { + "epoch": 0.0, + "learning_rate": 9.823777174892211e-06, + "loss": 3.3516, + "step": 2454016 + }, + { + "epoch": 0.0, + "learning_rate": 9.815407606185422e-06, + "loss": 3.3653, + "step": 2454528 + }, + { + "epoch": 0.0, + "learning_rate": 9.807021658674904e-06, + "loss": 3.3403, + "step": 2455040 + }, + { + "epoch": 0.0, + "learning_rate": 9.798635711164384e-06, + "loss": 3.3467, + "step": 2455552 + }, + { + "epoch": 0.0, + "learning_rate": 9.790249763653862e-06, + "loss": 3.3615, + "step": 2456064 + }, + { + "epoch": 0.0, + "learning_rate": 9.781880194947075e-06, + "loss": 3.348, + "step": 2456576 + }, + { + "epoch": 0.0, + "learning_rate": 9.773494247436555e-06, + "loss": 3.3363, + "step": 2457088 + }, + { + "epoch": 0.01, + "learning_rate": 9.765108299926033e-06, + "loss": 3.3404, + "step": 2457600 + }, + { + "epoch": 0.01, + "learning_rate": 9.756722352415513e-06, + "loss": 3.3512, + "step": 2458112 + }, + { + "epoch": 0.01, + "learning_rate": 9.748352783708725e-06, + "loss": 3.3554, + "step": 2458624 + }, + { + "epoch": 0.01, + "learning_rate": 9.739966836198205e-06, + "loss": 3.362, + "step": 2459136 + }, + { + "epoch": 0.01, + "learning_rate": 9.731580888687685e-06, + "loss": 3.3488, + "step": 2459648 + }, + { + "epoch": 0.01, + "learning_rate": 9.723194941177165e-06, + "loss": 3.3416, + "step": 2460160 + }, + { + "epoch": 0.01, + "learning_rate": 9.714825372470376e-06, + "loss": 3.3561, + "step": 2460672 + }, + { + "epoch": 0.01, + "learning_rate": 9.706439424959858e-06, + "loss": 3.338, + "step": 2461184 + }, + { + "epoch": 0.01, + "learning_rate": 9.698053477449336e-06, + "loss": 3.3473, + "step": 2461696 + }, + { + "epoch": 0.01, + "learning_rate": 9.689667529938816e-06, + "loss": 3.3403, + "step": 2462208 + }, + { + "epoch": 0.01, + "learning_rate": 9.681297961232028e-06, + "loss": 3.3477, + "step": 2462720 + }, + { + "epoch": 0.01, + "learning_rate": 9.672912013721506e-06, + "loss": 3.3373, + "step": 2463232 + }, + { + "epoch": 0.01, + "learning_rate": 9.664526066210986e-06, + "loss": 3.3642, + "step": 2463744 + }, + { + "epoch": 0.01, + "learning_rate": 9.656140118700466e-06, + "loss": 3.3434, + "step": 2464256 + }, + { + "epoch": 0.01, + "learning_rate": 9.647770549993679e-06, + "loss": 3.3472, + "step": 2464768 + }, + { + "epoch": 0.01, + "learning_rate": 9.639384602483157e-06, + "loss": 3.3548, + "step": 2465280 + }, + { + "epoch": 0.01, + "learning_rate": 9.630998654972639e-06, + "loss": 3.3497, + "step": 2465792 + }, + { + "epoch": 0.01, + "learning_rate": 9.622612707462119e-06, + "loss": 3.3443, + "step": 2466304 + }, + { + "epoch": 0.01, + "learning_rate": 9.614243138755328e-06, + "loss": 3.3336, + "step": 2466816 + }, + { + "epoch": 0.01, + "learning_rate": 9.60585719124481e-06, + "loss": 3.3392, + "step": 2467328 + }, + { + "epoch": 0.01, + "learning_rate": 9.59747124373429e-06, + "loss": 3.3563, + "step": 2467840 + }, + { + "epoch": 0.01, + "learning_rate": 9.58908529622377e-06, + "loss": 3.3496, + "step": 2468352 + }, + { + "epoch": 0.01, + "learning_rate": 9.58071572751698e-06, + "loss": 3.3397, + "step": 2468864 + }, + { + "epoch": 0.01, + "learning_rate": 9.57232978000646e-06, + "loss": 3.3357, + "step": 2469376 + }, + { + "epoch": 0.01, + "learning_rate": 9.56394383249594e-06, + "loss": 3.3444, + "step": 2469888 + }, + { + "epoch": 0.01, + "learning_rate": 9.55555788498542e-06, + "loss": 3.3319, + "step": 2470400 + }, + { + "epoch": 0.01, + "learning_rate": 9.547188316278631e-06, + "loss": 3.3561, + "step": 2470912 + }, + { + "epoch": 0.01, + "learning_rate": 9.53880236876811e-06, + "loss": 3.3442, + "step": 2471424 + }, + { + "epoch": 0.01, + "learning_rate": 9.530416421257592e-06, + "loss": 3.3464, + "step": 2471936 + }, + { + "epoch": 0.01, + "learning_rate": 9.52203047374707e-06, + "loss": 3.3535, + "step": 2472448 + }, + { + "epoch": 0.01, + "learning_rate": 9.513660905040282e-06, + "loss": 3.3427, + "step": 2472960 + }, + { + "epoch": 0.01, + "learning_rate": 9.505274957529763e-06, + "loss": 3.3359, + "step": 2473472 + }, + { + "epoch": 0.01, + "learning_rate": 9.496889010019243e-06, + "loss": 3.3428, + "step": 2473984 + }, + { + "epoch": 0.01, + "learning_rate": 9.488503062508721e-06, + "loss": 3.3336, + "step": 2474496 + }, + { + "epoch": 0.01, + "learning_rate": 9.480133493801934e-06, + "loss": 3.3384, + "step": 2475008 + }, + { + "epoch": 0.01, + "learning_rate": 9.471747546291414e-06, + "loss": 3.3491, + "step": 2475520 + }, + { + "epoch": 0.01, + "learning_rate": 9.463361598780892e-06, + "loss": 3.3536, + "step": 2476032 + }, + { + "epoch": 0.01, + "learning_rate": 9.454992030074105e-06, + "loss": 3.3385, + "step": 2476544 + }, + { + "epoch": 0.01, + "learning_rate": 9.446606082563585e-06, + "loss": 3.3374, + "step": 2477056 + }, + { + "epoch": 0.01, + "learning_rate": 9.438220135053064e-06, + "loss": 3.3377, + "step": 2477568 + }, + { + "epoch": 0.01, + "learning_rate": 9.429834187542544e-06, + "loss": 3.3448, + "step": 2478080 + }, + { + "epoch": 0.01, + "learning_rate": 9.421448240032024e-06, + "loss": 3.3454, + "step": 2478592 + }, + { + "epoch": 0.01, + "learning_rate": 9.413062292521504e-06, + "loss": 3.3482, + "step": 2479104 + }, + { + "epoch": 0.01, + "learning_rate": 9.404676345010983e-06, + "loss": 3.3485, + "step": 2479616 + }, + { + "epoch": 0.01, + "learning_rate": 9.396306776304195e-06, + "loss": 3.3529, + "step": 2480128 + }, + { + "epoch": 0.01, + "learning_rate": 9.387920828793675e-06, + "loss": 3.3533, + "step": 2480640 + }, + { + "epoch": 0.01, + "learning_rate": 9.379534881283155e-06, + "loss": 3.3321, + "step": 2481152 + }, + { + "epoch": 0.01, + "learning_rate": 9.371148933772635e-06, + "loss": 3.3478, + "step": 2481664 + }, + { + "epoch": 0.01, + "learning_rate": 9.362779365065846e-06, + "loss": 3.3511, + "step": 2482176 + }, + { + "epoch": 0.01, + "learning_rate": 9.354393417555327e-06, + "loss": 3.342, + "step": 2482688 + }, + { + "epoch": 0.01, + "learning_rate": 9.346007470044807e-06, + "loss": 3.3557, + "step": 2483200 + }, + { + "epoch": 0.01, + "learning_rate": 9.337621522534286e-06, + "loss": 3.353, + "step": 2483712 + }, + { + "epoch": 0.01, + "learning_rate": 9.329251953827498e-06, + "loss": 3.3623, + "step": 2484224 + }, + { + "epoch": 0.01, + "learning_rate": 9.320882385120709e-06, + "loss": 3.3535, + "step": 2484736 + }, + { + "epoch": 0.01, + "learning_rate": 9.312496437610189e-06, + "loss": 3.3331, + "step": 2485248 + }, + { + "epoch": 0.01, + "learning_rate": 9.304110490099669e-06, + "loss": 3.3387, + "step": 2485760 + }, + { + "epoch": 0.01, + "learning_rate": 9.295724542589149e-06, + "loss": 3.3496, + "step": 2486272 + }, + { + "epoch": 0.01, + "learning_rate": 9.287338595078629e-06, + "loss": 3.3503, + "step": 2486784 + }, + { + "epoch": 0.01, + "learning_rate": 9.278952647568109e-06, + "loss": 3.3458, + "step": 2487296 + }, + { + "epoch": 0.01, + "learning_rate": 9.270566700057589e-06, + "loss": 3.3445, + "step": 2487808 + }, + { + "epoch": 0.02, + "learning_rate": 9.262180752547069e-06, + "loss": 3.3509, + "step": 2488320 + }, + { + "epoch": 0.02, + "learning_rate": 9.253811183840281e-06, + "loss": 3.3443, + "step": 2488832 + }, + { + "epoch": 0.02, + "learning_rate": 9.24542523632976e-06, + "loss": 3.34, + "step": 2489344 + }, + { + "epoch": 0.02, + "learning_rate": 9.23703928881924e-06, + "loss": 3.3446, + "step": 2489856 + }, + { + "epoch": 0.02, + "learning_rate": 9.22865334130872e-06, + "loss": 3.3493, + "step": 2490368 + }, + { + "epoch": 0.02, + "learning_rate": 9.22028377260193e-06, + "loss": 3.3613, + "step": 2490880 + }, + { + "epoch": 0.02, + "learning_rate": 9.21189782509141e-06, + "loss": 3.343, + "step": 2491392 + }, + { + "epoch": 0.02, + "learning_rate": 9.20351187758089e-06, + "loss": 3.3375, + "step": 2491904 + }, + { + "epoch": 0.02, + "learning_rate": 9.195125930070372e-06, + "loss": 3.3456, + "step": 2492416 + }, + { + "epoch": 0.02, + "learning_rate": 9.18675636136358e-06, + "loss": 3.3474, + "step": 2492928 + }, + { + "epoch": 0.02, + "learning_rate": 9.178370413853062e-06, + "loss": 3.351, + "step": 2493440 + }, + { + "epoch": 0.02, + "learning_rate": 9.169984466342542e-06, + "loss": 3.342, + "step": 2493952 + }, + { + "epoch": 0.02, + "learning_rate": 9.16159851883202e-06, + "loss": 3.3454, + "step": 2494464 + }, + { + "epoch": 0.02, + "learning_rate": 9.153228950125233e-06, + "loss": 3.326, + "step": 2494976 + }, + { + "epoch": 0.02, + "learning_rate": 9.144843002614713e-06, + "loss": 3.3475, + "step": 2495488 + }, + { + "epoch": 0.02, + "learning_rate": 9.136457055104193e-06, + "loss": 3.3409, + "step": 2496000 + }, + { + "epoch": 0.02, + "learning_rate": 9.128071107593671e-06, + "loss": 3.3412, + "step": 2496512 + }, + { + "epoch": 0.02, + "learning_rate": 9.119701538886884e-06, + "loss": 3.3441, + "step": 2497024 + }, + { + "epoch": 0.02, + "learning_rate": 9.111315591376364e-06, + "loss": 3.3443, + "step": 2497536 + }, + { + "epoch": 0.02, + "learning_rate": 9.102929643865844e-06, + "loss": 3.3366, + "step": 2498048 + }, + { + "epoch": 0.02, + "learning_rate": 9.094543696355324e-06, + "loss": 3.3427, + "step": 2498560 + }, + { + "epoch": 0.02, + "learning_rate": 9.086174127648534e-06, + "loss": 3.3382, + "step": 2499072 + }, + { + "epoch": 0.02, + "learning_rate": 9.077788180138016e-06, + "loss": 3.348, + "step": 2499584 + }, + { + "epoch": 0.02, + "learning_rate": 9.069402232627494e-06, + "loss": 3.337, + "step": 2500096 + }, + { + "epoch": 0.02, + "learning_rate": 9.061016285116974e-06, + "loss": 3.3443, + "step": 2500608 + }, + { + "epoch": 0.02, + "learning_rate": 9.052646716410187e-06, + "loss": 3.3453, + "step": 2501120 + }, + { + "epoch": 0.02, + "learning_rate": 9.044260768899667e-06, + "loss": 3.352, + "step": 2501632 + }, + { + "epoch": 0.02, + "learning_rate": 9.035874821389145e-06, + "loss": 3.3432, + "step": 2502144 + }, + { + "epoch": 0.02, + "learning_rate": 9.027505252682357e-06, + "loss": 3.3471, + "step": 2502656 + }, + { + "epoch": 0.02, + "learning_rate": 9.019119305171837e-06, + "loss": 3.3503, + "step": 2503168 + }, + { + "epoch": 0.02, + "learning_rate": 9.010733357661317e-06, + "loss": 3.3426, + "step": 2503680 + }, + { + "epoch": 0.02, + "learning_rate": 9.002347410150797e-06, + "loss": 3.3324, + "step": 2504192 + }, + { + "epoch": 0.02, + "learning_rate": 8.993977841444008e-06, + "loss": 3.3518, + "step": 2504704 + }, + { + "epoch": 0.02, + "learning_rate": 8.985591893933488e-06, + "loss": 3.3431, + "step": 2505216 + }, + { + "epoch": 0.02, + "learning_rate": 8.977205946422968e-06, + "loss": 3.3486, + "step": 2505728 + }, + { + "epoch": 0.02, + "learning_rate": 8.968819998912448e-06, + "loss": 3.3395, + "step": 2506240 + }, + { + "epoch": 0.02, + "learning_rate": 8.960450430205659e-06, + "loss": 3.3398, + "step": 2506752 + }, + { + "epoch": 0.02, + "learning_rate": 8.95206448269514e-06, + "loss": 3.3344, + "step": 2507264 + }, + { + "epoch": 0.02, + "learning_rate": 8.943678535184619e-06, + "loss": 3.3411, + "step": 2507776 + }, + { + "epoch": 0.02, + "learning_rate": 8.935292587674099e-06, + "loss": 3.3389, + "step": 2508288 + }, + { + "epoch": 0.02, + "learning_rate": 8.926923018967311e-06, + "loss": 3.3491, + "step": 2508800 + }, + { + "epoch": 0.02, + "learning_rate": 8.91853707145679e-06, + "loss": 3.3538, + "step": 2509312 + }, + { + "epoch": 0.02, + "learning_rate": 8.91015112394627e-06, + "loss": 3.3398, + "step": 2509824 + }, + { + "epoch": 0.02, + "learning_rate": 8.901765176435751e-06, + "loss": 3.3425, + "step": 2510336 + }, + { + "epoch": 0.02, + "learning_rate": 8.893395607728962e-06, + "loss": 3.3435, + "step": 2510848 + }, + { + "epoch": 0.02, + "learning_rate": 8.88500966021844e-06, + "loss": 3.3507, + "step": 2511360 + }, + { + "epoch": 0.02, + "learning_rate": 8.876640091511652e-06, + "loss": 3.3468, + "step": 2511872 + }, + { + "epoch": 0.02, + "learning_rate": 8.868254144001132e-06, + "loss": 3.3467, + "step": 2512384 + }, + { + "epoch": 0.02, + "learning_rate": 8.859868196490612e-06, + "loss": 3.3427, + "step": 2512896 + }, + { + "epoch": 0.02, + "learning_rate": 8.851482248980092e-06, + "loss": 3.3434, + "step": 2513408 + }, + { + "epoch": 0.02, + "learning_rate": 8.843096301469572e-06, + "loss": 3.3431, + "step": 2513920 + }, + { + "epoch": 0.02, + "learning_rate": 8.834710353959052e-06, + "loss": 3.343, + "step": 2514432 + }, + { + "epoch": 0.02, + "learning_rate": 8.826324406448532e-06, + "loss": 3.3493, + "step": 2514944 + }, + { + "epoch": 0.02, + "learning_rate": 8.817938458938012e-06, + "loss": 3.3437, + "step": 2515456 + }, + { + "epoch": 0.02, + "learning_rate": 8.809568890231223e-06, + "loss": 3.3313, + "step": 2515968 + }, + { + "epoch": 0.02, + "learning_rate": 8.801199321524435e-06, + "loss": 3.3625, + "step": 2516480 + }, + { + "epoch": 0.02, + "learning_rate": 8.792813374013914e-06, + "loss": 3.3415, + "step": 2516992 + }, + { + "epoch": 0.02, + "learning_rate": 8.784427426503394e-06, + "loss": 3.3443, + "step": 2517504 + }, + { + "epoch": 0.02, + "learning_rate": 8.776041478992875e-06, + "loss": 3.3398, + "step": 2518016 + }, + { + "epoch": 0.02, + "learning_rate": 8.767655531482354e-06, + "loss": 3.3376, + "step": 2518528 + }, + { + "epoch": 0.03, + "eval_loss": 3.867447853088379, + "eval_runtime": 306.8717, + "eval_samples_per_second": 1243.487, + "eval_steps_per_second": 38.86, + "step": 2518560 + }, + { + "epoch": 1.0, + "learning_rate": 8.759269583971834e-06, + "loss": 3.3299, + "step": 2519040 + }, + { + "epoch": 1.0, + "learning_rate": 8.750900015265046e-06, + "loss": 3.3495, + "step": 2519552 + }, + { + "epoch": 1.0, + "learning_rate": 8.742514067754526e-06, + "loss": 3.3544, + "step": 2520064 + }, + { + "epoch": 1.0, + "learning_rate": 8.734128120244004e-06, + "loss": 3.3397, + "step": 2520576 + }, + { + "epoch": 1.0, + "learning_rate": 8.725742172733486e-06, + "loss": 3.3594, + "step": 2521088 + }, + { + "epoch": 1.0, + "learning_rate": 8.717356225222966e-06, + "loss": 3.3326, + "step": 2521600 + }, + { + "epoch": 1.0, + "learning_rate": 8.708970277712444e-06, + "loss": 3.3444, + "step": 2522112 + }, + { + "epoch": 1.0, + "learning_rate": 8.700584330201924e-06, + "loss": 3.3359, + "step": 2522624 + }, + { + "epoch": 1.0, + "learning_rate": 8.692214761495137e-06, + "loss": 3.346, + "step": 2523136 + }, + { + "epoch": 1.0, + "learning_rate": 8.683828813984617e-06, + "loss": 3.342, + "step": 2523648 + }, + { + "epoch": 1.0, + "learning_rate": 8.675442866474095e-06, + "loss": 3.3418, + "step": 2524160 + }, + { + "epoch": 1.0, + "learning_rate": 8.667056918963576e-06, + "loss": 3.3504, + "step": 2524672 + }, + { + "epoch": 1.0, + "learning_rate": 8.658687350256787e-06, + "loss": 3.3416, + "step": 2525184 + }, + { + "epoch": 1.0, + "learning_rate": 8.650301402746267e-06, + "loss": 3.3302, + "step": 2525696 + }, + { + "epoch": 1.0, + "learning_rate": 8.641915455235747e-06, + "loss": 3.3353, + "step": 2526208 + }, + { + "epoch": 1.0, + "learning_rate": 8.633529507725227e-06, + "loss": 3.3403, + "step": 2526720 + }, + { + "epoch": 1.0, + "learning_rate": 8.625143560214707e-06, + "loss": 3.3452, + "step": 2527232 + }, + { + "epoch": 1.0, + "learning_rate": 8.616757612704187e-06, + "loss": 3.3369, + "step": 2527744 + }, + { + "epoch": 1.0, + "learning_rate": 8.608371665193667e-06, + "loss": 3.3439, + "step": 2528256 + }, + { + "epoch": 1.0, + "learning_rate": 8.600002096486878e-06, + "loss": 3.3671, + "step": 2528768 + }, + { + "epoch": 1.0, + "learning_rate": 8.59161614897636e-06, + "loss": 3.3431, + "step": 2529280 + }, + { + "epoch": 1.0, + "learning_rate": 8.583230201465838e-06, + "loss": 3.3381, + "step": 2529792 + }, + { + "epoch": 1.0, + "learning_rate": 8.574844253955318e-06, + "loss": 3.3434, + "step": 2530304 + }, + { + "epoch": 1.0, + "learning_rate": 8.56647468524853e-06, + "loss": 3.3531, + "step": 2530816 + }, + { + "epoch": 1.0, + "learning_rate": 8.558088737738008e-06, + "loss": 3.3319, + "step": 2531328 + }, + { + "epoch": 1.0, + "learning_rate": 8.549702790227488e-06, + "loss": 3.3405, + "step": 2531840 + }, + { + "epoch": 1.0, + "learning_rate": 8.541316842716968e-06, + "loss": 3.3473, + "step": 2532352 + }, + { + "epoch": 1.0, + "learning_rate": 8.53294727401018e-06, + "loss": 3.3398, + "step": 2532864 + }, + { + "epoch": 1.0, + "learning_rate": 8.524561326499659e-06, + "loss": 3.325, + "step": 2533376 + }, + { + "epoch": 1.01, + "learning_rate": 8.51617537898914e-06, + "loss": 3.3346, + "step": 2533888 + }, + { + "epoch": 1.01, + "learning_rate": 8.50778943147862e-06, + "loss": 3.3388, + "step": 2534400 + }, + { + "epoch": 1.01, + "learning_rate": 8.499403483968099e-06, + "loss": 3.3458, + "step": 2534912 + }, + { + "epoch": 1.01, + "learning_rate": 8.491017536457579e-06, + "loss": 3.3528, + "step": 2535424 + }, + { + "epoch": 1.01, + "learning_rate": 8.48263158894706e-06, + "loss": 3.3394, + "step": 2535936 + }, + { + "epoch": 1.01, + "learning_rate": 8.47424564143654e-06, + "loss": 3.3331, + "step": 2536448 + }, + { + "epoch": 1.01, + "learning_rate": 8.46587607272975e-06, + "loss": 3.3471, + "step": 2536960 + }, + { + "epoch": 1.01, + "learning_rate": 8.457490125219231e-06, + "loss": 3.3278, + "step": 2537472 + }, + { + "epoch": 1.01, + "learning_rate": 8.449104177708711e-06, + "loss": 3.3413, + "step": 2537984 + }, + { + "epoch": 1.01, + "learning_rate": 8.44071823019819e-06, + "loss": 3.3288, + "step": 2538496 + }, + { + "epoch": 1.01, + "learning_rate": 8.432348661491402e-06, + "loss": 3.3389, + "step": 2539008 + }, + { + "epoch": 1.01, + "learning_rate": 8.423962713980882e-06, + "loss": 3.3281, + "step": 2539520 + }, + { + "epoch": 1.01, + "learning_rate": 8.415576766470362e-06, + "loss": 3.3541, + "step": 2540032 + }, + { + "epoch": 1.01, + "learning_rate": 8.407190818959842e-06, + "loss": 3.3372, + "step": 2540544 + }, + { + "epoch": 1.01, + "learning_rate": 8.398821250253053e-06, + "loss": 3.3391, + "step": 2541056 + }, + { + "epoch": 1.01, + "learning_rate": 8.390451681546265e-06, + "loss": 3.341, + "step": 2541568 + }, + { + "epoch": 1.01, + "learning_rate": 8.382065734035745e-06, + "loss": 3.3419, + "step": 2542080 + }, + { + "epoch": 1.01, + "learning_rate": 8.373679786525223e-06, + "loss": 3.3322, + "step": 2542592 + }, + { + "epoch": 1.01, + "learning_rate": 8.365293839014703e-06, + "loss": 3.3301, + "step": 2543104 + }, + { + "epoch": 1.01, + "learning_rate": 8.356907891504185e-06, + "loss": 3.3282, + "step": 2543616 + }, + { + "epoch": 1.01, + "learning_rate": 8.348521943993663e-06, + "loss": 3.3464, + "step": 2544128 + }, + { + "epoch": 1.01, + "learning_rate": 8.340135996483143e-06, + "loss": 3.3375, + "step": 2544640 + }, + { + "epoch": 1.01, + "learning_rate": 8.331750048972623e-06, + "loss": 3.3301, + "step": 2545152 + }, + { + "epoch": 1.01, + "learning_rate": 8.323380480265835e-06, + "loss": 3.3291, + "step": 2545664 + }, + { + "epoch": 1.01, + "learning_rate": 8.314994532755314e-06, + "loss": 3.3348, + "step": 2546176 + }, + { + "epoch": 1.01, + "learning_rate": 8.306608585244795e-06, + "loss": 3.3228, + "step": 2546688 + }, + { + "epoch": 1.01, + "learning_rate": 8.298239016538006e-06, + "loss": 3.346, + "step": 2547200 + }, + { + "epoch": 1.01, + "learning_rate": 8.289853069027486e-06, + "loss": 3.3345, + "step": 2547712 + }, + { + "epoch": 1.01, + "learning_rate": 8.281467121516966e-06, + "loss": 3.3365, + "step": 2548224 + }, + { + "epoch": 1.01, + "learning_rate": 8.273081174006446e-06, + "loss": 3.3476, + "step": 2548736 + }, + { + "epoch": 1.01, + "learning_rate": 8.264711605299657e-06, + "loss": 3.3276, + "step": 2549248 + }, + { + "epoch": 1.01, + "learning_rate": 8.256325657789137e-06, + "loss": 3.33, + "step": 2549760 + }, + { + "epoch": 1.01, + "learning_rate": 8.247939710278617e-06, + "loss": 3.3371, + "step": 2550272 + }, + { + "epoch": 1.01, + "learning_rate": 8.239553762768097e-06, + "loss": 3.3232, + "step": 2550784 + }, + { + "epoch": 1.01, + "learning_rate": 8.23118419406131e-06, + "loss": 3.3288, + "step": 2551296 + }, + { + "epoch": 1.01, + "learning_rate": 8.222798246550787e-06, + "loss": 3.3388, + "step": 2551808 + }, + { + "epoch": 1.01, + "learning_rate": 8.214412299040267e-06, + "loss": 3.3457, + "step": 2552320 + }, + { + "epoch": 1.01, + "learning_rate": 8.20604273033348e-06, + "loss": 3.3308, + "step": 2552832 + }, + { + "epoch": 1.01, + "learning_rate": 8.197656782822958e-06, + "loss": 3.3305, + "step": 2553344 + }, + { + "epoch": 1.01, + "learning_rate": 8.189270835312438e-06, + "loss": 3.3247, + "step": 2553856 + }, + { + "epoch": 1.01, + "learning_rate": 8.18088488780192e-06, + "loss": 3.3362, + "step": 2554368 + }, + { + "epoch": 1.01, + "learning_rate": 8.1724989402914e-06, + "loss": 3.3354, + "step": 2554880 + }, + { + "epoch": 1.01, + "learning_rate": 8.164112992780878e-06, + "loss": 3.3383, + "step": 2555392 + }, + { + "epoch": 1.01, + "learning_rate": 8.15572704527036e-06, + "loss": 3.3399, + "step": 2555904 + }, + { + "epoch": 1.01, + "learning_rate": 8.14735747656357e-06, + "loss": 3.343, + "step": 2556416 + }, + { + "epoch": 1.01, + "learning_rate": 8.138971529053049e-06, + "loss": 3.3459, + "step": 2556928 + }, + { + "epoch": 1.01, + "learning_rate": 8.13058558154253e-06, + "loss": 3.3226, + "step": 2557440 + }, + { + "epoch": 1.01, + "learning_rate": 8.12219963403201e-06, + "loss": 3.3381, + "step": 2557952 + }, + { + "epoch": 1.01, + "learning_rate": 8.113830065325221e-06, + "loss": 3.3413, + "step": 2558464 + }, + { + "epoch": 1.01, + "learning_rate": 8.105460496618432e-06, + "loss": 3.3281, + "step": 2558976 + }, + { + "epoch": 1.01, + "learning_rate": 8.097074549107912e-06, + "loss": 3.3527, + "step": 2559488 + }, + { + "epoch": 1.01, + "learning_rate": 8.088688601597392e-06, + "loss": 3.3446, + "step": 2560000 + }, + { + "epoch": 1.01, + "learning_rate": 8.080302654086873e-06, + "loss": 3.3495, + "step": 2560512 + }, + { + "epoch": 1.01, + "learning_rate": 8.071916706576352e-06, + "loss": 3.3462, + "step": 2561024 + }, + { + "epoch": 1.01, + "learning_rate": 8.063530759065832e-06, + "loss": 3.3217, + "step": 2561536 + }, + { + "epoch": 1.01, + "learning_rate": 8.055144811555312e-06, + "loss": 3.3338, + "step": 2562048 + }, + { + "epoch": 1.01, + "learning_rate": 8.046758864044792e-06, + "loss": 3.3364, + "step": 2562560 + }, + { + "epoch": 1.01, + "learning_rate": 8.038389295338002e-06, + "loss": 3.3413, + "step": 2563072 + }, + { + "epoch": 1.01, + "learning_rate": 8.030003347827484e-06, + "loss": 3.3384, + "step": 2563584 + }, + { + "epoch": 1.01, + "learning_rate": 8.021617400316964e-06, + "loss": 3.334, + "step": 2564096 + }, + { + "epoch": 1.02, + "learning_rate": 8.013231452806442e-06, + "loss": 3.3433, + "step": 2564608 + }, + { + "epoch": 1.02, + "learning_rate": 8.004845505295922e-06, + "loss": 3.3375, + "step": 2565120 + }, + { + "epoch": 1.02, + "learning_rate": 7.996459557785404e-06, + "loss": 3.3271, + "step": 2565632 + }, + { + "epoch": 1.02, + "learning_rate": 7.988073610274882e-06, + "loss": 3.3333, + "step": 2566144 + }, + { + "epoch": 1.02, + "learning_rate": 7.979687662764362e-06, + "loss": 3.3422, + "step": 2566656 + }, + { + "epoch": 1.02, + "learning_rate": 7.971318094057575e-06, + "loss": 3.3517, + "step": 2567168 + }, + { + "epoch": 1.02, + "learning_rate": 7.962932146547054e-06, + "loss": 3.3348, + "step": 2567680 + }, + { + "epoch": 1.02, + "learning_rate": 7.954546199036533e-06, + "loss": 3.3248, + "step": 2568192 + }, + { + "epoch": 1.02, + "learning_rate": 7.946160251526014e-06, + "loss": 3.3378, + "step": 2568704 + }, + { + "epoch": 1.02, + "learning_rate": 7.937790682819225e-06, + "loss": 3.3381, + "step": 2569216 + }, + { + "epoch": 1.02, + "learning_rate": 7.929404735308703e-06, + "loss": 3.3425, + "step": 2569728 + }, + { + "epoch": 1.02, + "learning_rate": 7.921018787798185e-06, + "loss": 3.3349, + "step": 2570240 + }, + { + "epoch": 1.02, + "learning_rate": 7.912632840287665e-06, + "loss": 3.3315, + "step": 2570752 + }, + { + "epoch": 1.02, + "learning_rate": 7.904263271580876e-06, + "loss": 3.3221, + "step": 2571264 + }, + { + "epoch": 1.02, + "learning_rate": 7.895877324070356e-06, + "loss": 3.3381, + "step": 2571776 + }, + { + "epoch": 1.02, + "learning_rate": 7.887491376559836e-06, + "loss": 3.3283, + "step": 2572288 + }, + { + "epoch": 1.02, + "learning_rate": 7.879105429049316e-06, + "loss": 3.3339, + "step": 2572800 + }, + { + "epoch": 1.02, + "learning_rate": 7.870735860342528e-06, + "loss": 3.3329, + "step": 2573312 + }, + { + "epoch": 1.02, + "learning_rate": 7.862349912832006e-06, + "loss": 3.335, + "step": 2573824 + }, + { + "epoch": 1.02, + "learning_rate": 7.853963965321486e-06, + "loss": 3.3289, + "step": 2574336 + }, + { + "epoch": 1.02, + "learning_rate": 7.845594396614699e-06, + "loss": 3.3358, + "step": 2574848 + }, + { + "epoch": 1.02, + "learning_rate": 7.837208449104177e-06, + "loss": 3.3292, + "step": 2575360 + }, + { + "epoch": 1.02, + "learning_rate": 7.828822501593657e-06, + "loss": 3.3336, + "step": 2575872 + }, + { + "epoch": 1.02, + "learning_rate": 7.820436554083139e-06, + "loss": 3.3286, + "step": 2576384 + }, + { + "epoch": 1.02, + "learning_rate": 7.81206698537635e-06, + "loss": 3.3306, + "step": 2576896 + }, + { + "epoch": 1.02, + "learning_rate": 7.80368103786583e-06, + "loss": 3.3386, + "step": 2577408 + }, + { + "epoch": 1.02, + "learning_rate": 7.79529509035531e-06, + "loss": 3.3439, + "step": 2577920 + }, + { + "epoch": 1.02, + "learning_rate": 7.78692552164852e-06, + "loss": 3.3342, + "step": 2578432 + }, + { + "epoch": 1.02, + "learning_rate": 7.778539574138e-06, + "loss": 3.3353, + "step": 2578944 + }, + { + "epoch": 1.02, + "learning_rate": 7.77015362662748e-06, + "loss": 3.3433, + "step": 2579456 + }, + { + "epoch": 1.02, + "learning_rate": 7.76176767911696e-06, + "loss": 3.3346, + "step": 2579968 + }, + { + "epoch": 1.02, + "learning_rate": 7.75338173160644e-06, + "loss": 3.3246, + "step": 2580480 + }, + { + "epoch": 1.02, + "learning_rate": 7.74499578409592e-06, + "loss": 3.3436, + "step": 2580992 + }, + { + "epoch": 1.02, + "learning_rate": 7.7366098365854e-06, + "loss": 3.3339, + "step": 2581504 + }, + { + "epoch": 1.02, + "learning_rate": 7.72824026787861e-06, + "loss": 3.3411, + "step": 2582016 + }, + { + "epoch": 1.02, + "learning_rate": 7.71985432036809e-06, + "loss": 3.3286, + "step": 2582528 + }, + { + "epoch": 1.02, + "learning_rate": 7.71146837285757e-06, + "loss": 3.3327, + "step": 2583040 + }, + { + "epoch": 1.02, + "learning_rate": 7.70308242534705e-06, + "loss": 3.3254, + "step": 2583552 + }, + { + "epoch": 1.02, + "learning_rate": 7.694712856640263e-06, + "loss": 3.3275, + "step": 2584064 + }, + { + "epoch": 1.02, + "learning_rate": 7.686326909129741e-06, + "loss": 3.3299, + "step": 2584576 + }, + { + "epoch": 1.02, + "learning_rate": 7.677940961619221e-06, + "loss": 3.3406, + "step": 2585088 + }, + { + "epoch": 1.02, + "learning_rate": 7.669555014108703e-06, + "loss": 3.3475, + "step": 2585600 + }, + { + "epoch": 1.02, + "learning_rate": 7.661185445401914e-06, + "loss": 3.3358, + "step": 2586112 + }, + { + "epoch": 1.02, + "learning_rate": 7.652799497891392e-06, + "loss": 3.3274, + "step": 2586624 + }, + { + "epoch": 1.02, + "learning_rate": 7.644413550380874e-06, + "loss": 3.3376, + "step": 2587136 + }, + { + "epoch": 1.02, + "learning_rate": 7.636027602870354e-06, + "loss": 3.341, + "step": 2587648 + }, + { + "epoch": 1.02, + "learning_rate": 7.627658034163564e-06, + "loss": 3.3428, + "step": 2588160 + }, + { + "epoch": 1.02, + "learning_rate": 7.6192720866530436e-06, + "loss": 3.3353, + "step": 2588672 + }, + { + "epoch": 1.02, + "learning_rate": 7.610886139142524e-06, + "loss": 3.3373, + "step": 2589184 + }, + { + "epoch": 1.02, + "learning_rate": 7.602500191632004e-06, + "loss": 3.3295, + "step": 2589696 + }, + { + "epoch": 1.02, + "learning_rate": 7.594130622925215e-06, + "loss": 3.3406, + "step": 2590208 + }, + { + "epoch": 1.02, + "learning_rate": 7.585744675414695e-06, + "loss": 3.3339, + "step": 2590720 + }, + { + "epoch": 1.02, + "learning_rate": 7.577358727904176e-06, + "loss": 3.3361, + "step": 2591232 + }, + { + "epoch": 1.02, + "learning_rate": 7.568972780393654e-06, + "loss": 3.3377, + "step": 2591744 + }, + { + "epoch": 1.02, + "learning_rate": 7.560603211686866e-06, + "loss": 3.326, + "step": 2592256 + }, + { + "epoch": 1.02, + "learning_rate": 7.552233642980077e-06, + "loss": 3.351, + "step": 2592768 + }, + { + "epoch": 1.02, + "learning_rate": 7.543847695469558e-06, + "loss": 3.3334, + "step": 2593280 + }, + { + "epoch": 1.02, + "learning_rate": 7.535461747959037e-06, + "loss": 3.3346, + "step": 2593792 + }, + { + "epoch": 1.02, + "learning_rate": 7.527075800448517e-06, + "loss": 3.3299, + "step": 2594304 + }, + { + "epoch": 1.02, + "learning_rate": 7.518689852937997e-06, + "loss": 3.3262, + "step": 2594816 + }, + { + "epoch": 1.03, + "eval_loss": 3.8677029609680176, + "eval_runtime": 306.3411, + "eval_samples_per_second": 1245.641, + "eval_steps_per_second": 38.927, + "step": 2594880 + }, + { + "epoch": 0.0, + "learning_rate": 7.510303905427478e-06, + "loss": 3.3185, + "step": 2595328 + }, + { + "epoch": 0.0, + "learning_rate": 7.501934336720688e-06, + "loss": 3.3398, + "step": 2595840 + }, + { + "epoch": 0.0, + "learning_rate": 7.493548389210169e-06, + "loss": 3.3467, + "step": 2596352 + }, + { + "epoch": 0.0, + "learning_rate": 7.485162441699649e-06, + "loss": 3.3318, + "step": 2596864 + }, + { + "epoch": 0.0, + "learning_rate": 7.476776494189128e-06, + "loss": 3.3504, + "step": 2597376 + }, + { + "epoch": 0.0, + "learning_rate": 7.468390546678608e-06, + "loss": 3.3266, + "step": 2597888 + }, + { + "epoch": 0.0, + "learning_rate": 7.460004599168089e-06, + "loss": 3.3381, + "step": 2598400 + }, + { + "epoch": 0.0, + "learning_rate": 7.4516186516575686e-06, + "loss": 3.3232, + "step": 2598912 + }, + { + "epoch": 0.0, + "learning_rate": 7.443249082950779e-06, + "loss": 3.3363, + "step": 2599424 + }, + { + "epoch": 0.0, + "learning_rate": 7.434863135440259e-06, + "loss": 3.3332, + "step": 2599936 + }, + { + "epoch": 0.0, + "learning_rate": 7.426477187929739e-06, + "loss": 3.3307, + "step": 2600448 + }, + { + "epoch": 0.0, + "learning_rate": 7.418091240419218e-06, + "loss": 3.3439, + "step": 2600960 + }, + { + "epoch": 0.0, + "learning_rate": 7.40972167171243e-06, + "loss": 3.3319, + "step": 2601472 + }, + { + "epoch": 0.0, + "learning_rate": 7.401335724201911e-06, + "loss": 3.3207, + "step": 2601984 + }, + { + "epoch": 0.0, + "learning_rate": 7.392949776691391e-06, + "loss": 3.3241, + "step": 2602496 + }, + { + "epoch": 0.0, + "learning_rate": 7.38456382918087e-06, + "loss": 3.3327, + "step": 2603008 + }, + { + "epoch": 0.0, + "learning_rate": 7.37617788167035e-06, + "loss": 3.3355, + "step": 2603520 + }, + { + "epoch": 0.0, + "learning_rate": 7.367791934159831e-06, + "loss": 3.3302, + "step": 2604032 + }, + { + "epoch": 0.0, + "learning_rate": 7.359405986649309e-06, + "loss": 3.3319, + "step": 2604544 + }, + { + "epoch": 0.0, + "learning_rate": 7.35102003913879e-06, + "loss": 3.355, + "step": 2605056 + }, + { + "epoch": 0.0, + "learning_rate": 7.342650470432001e-06, + "loss": 3.3321, + "step": 2605568 + }, + { + "epoch": 0.0, + "learning_rate": 7.334264522921481e-06, + "loss": 3.3266, + "step": 2606080 + }, + { + "epoch": 0.0, + "learning_rate": 7.32587857541096e-06, + "loss": 3.3359, + "step": 2606592 + }, + { + "epoch": 0.0, + "learning_rate": 7.317509006704172e-06, + "loss": 3.3416, + "step": 2607104 + }, + { + "epoch": 0.0, + "learning_rate": 7.309123059193653e-06, + "loss": 3.3259, + "step": 2607616 + }, + { + "epoch": 0.0, + "learning_rate": 7.300737111683133e-06, + "loss": 3.3354, + "step": 2608128 + }, + { + "epoch": 0.0, + "learning_rate": 7.292351164172612e-06, + "loss": 3.3358, + "step": 2608640 + }, + { + "epoch": 0.0, + "learning_rate": 7.2839815954658235e-06, + "loss": 3.3292, + "step": 2609152 + }, + { + "epoch": 0.0, + "learning_rate": 7.2755956479553035e-06, + "loss": 3.3175, + "step": 2609664 + }, + { + "epoch": 0.01, + "learning_rate": 7.267209700444783e-06, + "loss": 3.3255, + "step": 2610176 + }, + { + "epoch": 0.01, + "learning_rate": 7.2588237529342626e-06, + "loss": 3.3305, + "step": 2610688 + }, + { + "epoch": 0.01, + "learning_rate": 7.250454184227474e-06, + "loss": 3.332, + "step": 2611200 + }, + { + "epoch": 0.01, + "learning_rate": 7.242084615520686e-06, + "loss": 3.3464, + "step": 2611712 + }, + { + "epoch": 0.01, + "learning_rate": 7.233698668010165e-06, + "loss": 3.3274, + "step": 2612224 + }, + { + "epoch": 0.01, + "learning_rate": 7.225312720499646e-06, + "loss": 3.3256, + "step": 2612736 + }, + { + "epoch": 0.01, + "learning_rate": 7.216926772989126e-06, + "loss": 3.3379, + "step": 2613248 + }, + { + "epoch": 0.01, + "learning_rate": 7.208540825478606e-06, + "loss": 3.3243, + "step": 2613760 + }, + { + "epoch": 0.01, + "learning_rate": 7.200154877968085e-06, + "loss": 3.3251, + "step": 2614272 + }, + { + "epoch": 0.01, + "learning_rate": 7.1917689304575656e-06, + "loss": 3.3205, + "step": 2614784 + }, + { + "epoch": 0.01, + "learning_rate": 7.1833829829470455e-06, + "loss": 3.3303, + "step": 2615296 + }, + { + "epoch": 0.01, + "learning_rate": 7.1750134142402555e-06, + "loss": 3.3186, + "step": 2615808 + }, + { + "epoch": 0.01, + "learning_rate": 7.166627466729736e-06, + "loss": 3.3468, + "step": 2616320 + }, + { + "epoch": 0.01, + "learning_rate": 7.158241519219216e-06, + "loss": 3.326, + "step": 2616832 + }, + { + "epoch": 0.01, + "learning_rate": 7.149855571708697e-06, + "loss": 3.3349, + "step": 2617344 + }, + { + "epoch": 0.01, + "learning_rate": 7.141486003001907e-06, + "loss": 3.3341, + "step": 2617856 + }, + { + "epoch": 0.01, + "learning_rate": 7.133100055491388e-06, + "loss": 3.3303, + "step": 2618368 + }, + { + "epoch": 0.01, + "learning_rate": 7.124714107980868e-06, + "loss": 3.3269, + "step": 2618880 + }, + { + "epoch": 0.01, + "learning_rate": 7.116328160470347e-06, + "loss": 3.3195, + "step": 2619392 + }, + { + "epoch": 0.01, + "learning_rate": 7.1079585917635585e-06, + "loss": 3.3172, + "step": 2619904 + }, + { + "epoch": 0.01, + "learning_rate": 7.0995726442530384e-06, + "loss": 3.3378, + "step": 2620416 + }, + { + "epoch": 0.01, + "learning_rate": 7.091186696742519e-06, + "loss": 3.3291, + "step": 2620928 + }, + { + "epoch": 0.01, + "learning_rate": 7.0828007492319975e-06, + "loss": 3.3224, + "step": 2621440 + }, + { + "epoch": 0.01, + "learning_rate": 7.074431180525209e-06, + "loss": 3.3232, + "step": 2621952 + }, + { + "epoch": 0.01, + "learning_rate": 7.06604523301469e-06, + "loss": 3.3282, + "step": 2622464 + }, + { + "epoch": 0.01, + "learning_rate": 7.057659285504169e-06, + "loss": 3.309, + "step": 2622976 + }, + { + "epoch": 0.01, + "learning_rate": 7.049273337993649e-06, + "loss": 3.3355, + "step": 2623488 + }, + { + "epoch": 0.01, + "learning_rate": 7.040903769286861e-06, + "loss": 3.326, + "step": 2624000 + }, + { + "epoch": 0.01, + "learning_rate": 7.032517821776341e-06, + "loss": 3.3263, + "step": 2624512 + }, + { + "epoch": 0.01, + "learning_rate": 7.02413187426582e-06, + "loss": 3.3386, + "step": 2625024 + }, + { + "epoch": 0.01, + "learning_rate": 7.0157459267553005e-06, + "loss": 3.3207, + "step": 2625536 + }, + { + "epoch": 0.01, + "learning_rate": 7.007376358048512e-06, + "loss": 3.3186, + "step": 2626048 + }, + { + "epoch": 0.01, + "learning_rate": 6.998990410537992e-06, + "loss": 3.3294, + "step": 2626560 + }, + { + "epoch": 0.01, + "learning_rate": 6.990604463027471e-06, + "loss": 3.3155, + "step": 2627072 + }, + { + "epoch": 0.01, + "learning_rate": 6.982218515516951e-06, + "loss": 3.3203, + "step": 2627584 + }, + { + "epoch": 0.01, + "learning_rate": 6.973848946810163e-06, + "loss": 3.3308, + "step": 2628096 + }, + { + "epoch": 0.01, + "learning_rate": 6.965462999299642e-06, + "loss": 3.3363, + "step": 2628608 + }, + { + "epoch": 0.01, + "learning_rate": 6.9570934305928536e-06, + "loss": 3.3191, + "step": 2629120 + }, + { + "epoch": 0.01, + "learning_rate": 6.948707483082334e-06, + "loss": 3.3222, + "step": 2629632 + }, + { + "epoch": 0.01, + "learning_rate": 6.940321535571814e-06, + "loss": 3.3153, + "step": 2630144 + }, + { + "epoch": 0.01, + "learning_rate": 6.931935588061293e-06, + "loss": 3.328, + "step": 2630656 + }, + { + "epoch": 0.01, + "learning_rate": 6.923549640550773e-06, + "loss": 3.3248, + "step": 2631168 + }, + { + "epoch": 0.01, + "learning_rate": 6.915163693040254e-06, + "loss": 3.3311, + "step": 2631680 + }, + { + "epoch": 0.01, + "learning_rate": 6.9067777455297324e-06, + "loss": 3.3292, + "step": 2632192 + }, + { + "epoch": 0.01, + "learning_rate": 6.898391798019213e-06, + "loss": 3.3308, + "step": 2632704 + }, + { + "epoch": 0.01, + "learning_rate": 6.890022229312425e-06, + "loss": 3.3407, + "step": 2633216 + }, + { + "epoch": 0.01, + "learning_rate": 6.881636281801905e-06, + "loss": 3.3145, + "step": 2633728 + }, + { + "epoch": 0.01, + "learning_rate": 6.873250334291384e-06, + "loss": 3.328, + "step": 2634240 + }, + { + "epoch": 0.01, + "learning_rate": 6.864880765584596e-06, + "loss": 3.3357, + "step": 2634752 + }, + { + "epoch": 0.01, + "learning_rate": 6.8564948180740755e-06, + "loss": 3.3211, + "step": 2635264 + }, + { + "epoch": 0.01, + "learning_rate": 6.848108870563556e-06, + "loss": 3.3405, + "step": 2635776 + }, + { + "epoch": 0.01, + "learning_rate": 6.8397229230530354e-06, + "loss": 3.3335, + "step": 2636288 + }, + { + "epoch": 0.01, + "learning_rate": 6.831353354346247e-06, + "loss": 3.3402, + "step": 2636800 + }, + { + "epoch": 0.01, + "learning_rate": 6.822967406835727e-06, + "loss": 3.3375, + "step": 2637312 + }, + { + "epoch": 0.01, + "learning_rate": 6.814581459325206e-06, + "loss": 3.3137, + "step": 2637824 + }, + { + "epoch": 0.01, + "learning_rate": 6.806195511814686e-06, + "loss": 3.3266, + "step": 2638336 + }, + { + "epoch": 0.01, + "learning_rate": 6.797825943107898e-06, + "loss": 3.3246, + "step": 2638848 + }, + { + "epoch": 0.01, + "learning_rate": 6.789456374401109e-06, + "loss": 3.3339, + "step": 2639360 + }, + { + "epoch": 0.01, + "learning_rate": 6.7810704268905885e-06, + "loss": 3.3276, + "step": 2639872 + }, + { + "epoch": 0.01, + "learning_rate": 6.772684479380069e-06, + "loss": 3.3241, + "step": 2640384 + }, + { + "epoch": 0.02, + "learning_rate": 6.764298531869549e-06, + "loss": 3.334, + "step": 2640896 + }, + { + "epoch": 0.02, + "learning_rate": 6.755912584359029e-06, + "loss": 3.3331, + "step": 2641408 + }, + { + "epoch": 0.02, + "learning_rate": 6.747526636848508e-06, + "loss": 3.3157, + "step": 2641920 + }, + { + "epoch": 0.02, + "learning_rate": 6.739140689337989e-06, + "loss": 3.3217, + "step": 2642432 + }, + { + "epoch": 0.02, + "learning_rate": 6.730754741827469e-06, + "loss": 3.3322, + "step": 2642944 + }, + { + "epoch": 0.02, + "learning_rate": 6.722385173120679e-06, + "loss": 3.3412, + "step": 2643456 + }, + { + "epoch": 0.02, + "learning_rate": 6.71399922561016e-06, + "loss": 3.3295, + "step": 2643968 + }, + { + "epoch": 0.02, + "learning_rate": 6.70561327809964e-06, + "loss": 3.3143, + "step": 2644480 + }, + { + "epoch": 0.02, + "learning_rate": 6.6972273305891206e-06, + "loss": 3.33, + "step": 2644992 + }, + { + "epoch": 0.02, + "learning_rate": 6.6888577618823305e-06, + "loss": 3.3291, + "step": 2645504 + }, + { + "epoch": 0.02, + "learning_rate": 6.680471814371811e-06, + "loss": 3.3301, + "step": 2646016 + }, + { + "epoch": 0.02, + "learning_rate": 6.672085866861291e-06, + "loss": 3.3248, + "step": 2646528 + }, + { + "epoch": 0.02, + "learning_rate": 6.66369991935077e-06, + "loss": 3.3249, + "step": 2647040 + }, + { + "epoch": 0.02, + "learning_rate": 6.655330350643982e-06, + "loss": 3.3127, + "step": 2647552 + }, + { + "epoch": 0.02, + "learning_rate": 6.646944403133462e-06, + "loss": 3.3303, + "step": 2648064 + }, + { + "epoch": 0.02, + "learning_rate": 6.638558455622943e-06, + "loss": 3.3141, + "step": 2648576 + }, + { + "epoch": 0.02, + "learning_rate": 6.630172508112421e-06, + "loss": 3.3274, + "step": 2649088 + }, + { + "epoch": 0.02, + "learning_rate": 6.621802939405633e-06, + "loss": 3.3177, + "step": 2649600 + }, + { + "epoch": 0.02, + "learning_rate": 6.6134169918951135e-06, + "loss": 3.3303, + "step": 2650112 + }, + { + "epoch": 0.02, + "learning_rate": 6.6050310443845934e-06, + "loss": 3.3161, + "step": 2650624 + }, + { + "epoch": 0.02, + "learning_rate": 6.5966450968740725e-06, + "loss": 3.3291, + "step": 2651136 + }, + { + "epoch": 0.02, + "learning_rate": 6.588275528167284e-06, + "loss": 3.3224, + "step": 2651648 + }, + { + "epoch": 0.02, + "learning_rate": 6.579889580656764e-06, + "loss": 3.3214, + "step": 2652160 + }, + { + "epoch": 0.02, + "learning_rate": 6.571503633146243e-06, + "loss": 3.3254, + "step": 2652672 + }, + { + "epoch": 0.02, + "learning_rate": 6.563134064439455e-06, + "loss": 3.3201, + "step": 2653184 + }, + { + "epoch": 0.02, + "learning_rate": 6.554748116928936e-06, + "loss": 3.3292, + "step": 2653696 + }, + { + "epoch": 0.02, + "learning_rate": 6.546362169418416e-06, + "loss": 3.3344, + "step": 2654208 + }, + { + "epoch": 0.02, + "learning_rate": 6.537976221907895e-06, + "loss": 3.328, + "step": 2654720 + }, + { + "epoch": 0.02, + "learning_rate": 6.529606653201106e-06, + "loss": 3.3254, + "step": 2655232 + }, + { + "epoch": 0.02, + "learning_rate": 6.521220705690586e-06, + "loss": 3.3306, + "step": 2655744 + }, + { + "epoch": 0.02, + "learning_rate": 6.512834758180067e-06, + "loss": 3.3294, + "step": 2656256 + }, + { + "epoch": 0.02, + "learning_rate": 6.504448810669546e-06, + "loss": 3.3134, + "step": 2656768 + }, + { + "epoch": 0.02, + "learning_rate": 6.496079241962758e-06, + "loss": 3.3345, + "step": 2657280 + }, + { + "epoch": 0.02, + "learning_rate": 6.487693294452238e-06, + "loss": 3.329, + "step": 2657792 + }, + { + "epoch": 0.02, + "learning_rate": 6.479307346941717e-06, + "loss": 3.3287, + "step": 2658304 + }, + { + "epoch": 0.02, + "learning_rate": 6.470921399431197e-06, + "loss": 3.322, + "step": 2658816 + }, + { + "epoch": 0.02, + "learning_rate": 6.4625518307244086e-06, + "loss": 3.3269, + "step": 2659328 + }, + { + "epoch": 0.02, + "learning_rate": 6.454165883213889e-06, + "loss": 3.3135, + "step": 2659840 + }, + { + "epoch": 0.02, + "learning_rate": 6.445779935703368e-06, + "loss": 3.3203, + "step": 2660352 + }, + { + "epoch": 0.02, + "learning_rate": 6.437393988192848e-06, + "loss": 3.3203, + "step": 2660864 + }, + { + "epoch": 0.02, + "learning_rate": 6.42902441948606e-06, + "loss": 3.3309, + "step": 2661376 + }, + { + "epoch": 0.02, + "learning_rate": 6.420638471975539e-06, + "loss": 3.339, + "step": 2661888 + }, + { + "epoch": 0.02, + "learning_rate": 6.412252524465019e-06, + "loss": 3.3269, + "step": 2662400 + }, + { + "epoch": 0.02, + "learning_rate": 6.403866576954499e-06, + "loss": 3.3186, + "step": 2662912 + }, + { + "epoch": 0.02, + "learning_rate": 6.3954970082477116e-06, + "loss": 3.3272, + "step": 2663424 + }, + { + "epoch": 0.02, + "learning_rate": 6.38711106073719e-06, + "loss": 3.3295, + "step": 2663936 + }, + { + "epoch": 0.02, + "learning_rate": 6.378725113226671e-06, + "loss": 3.3323, + "step": 2664448 + }, + { + "epoch": 0.02, + "learning_rate": 6.370339165716151e-06, + "loss": 3.3289, + "step": 2664960 + }, + { + "epoch": 0.02, + "learning_rate": 6.361969597009362e-06, + "loss": 3.3216, + "step": 2665472 + }, + { + "epoch": 0.02, + "learning_rate": 6.353583649498841e-06, + "loss": 3.3252, + "step": 2665984 + }, + { + "epoch": 0.02, + "learning_rate": 6.345197701988321e-06, + "loss": 3.3326, + "step": 2666496 + }, + { + "epoch": 0.02, + "learning_rate": 6.336811754477802e-06, + "loss": 3.3235, + "step": 2667008 + }, + { + "epoch": 0.02, + "learning_rate": 6.328442185771012e-06, + "loss": 3.3267, + "step": 2667520 + }, + { + "epoch": 0.02, + "learning_rate": 6.320056238260493e-06, + "loss": 3.3247, + "step": 2668032 + }, + { + "epoch": 0.02, + "learning_rate": 6.311670290749973e-06, + "loss": 3.3193, + "step": 2668544 + }, + { + "epoch": 0.02, + "learning_rate": 6.3033007220431844e-06, + "loss": 3.3391, + "step": 2669056 + }, + { + "epoch": 0.02, + "learning_rate": 6.2949147745326635e-06, + "loss": 3.3316, + "step": 2669568 + }, + { + "epoch": 0.02, + "learning_rate": 6.2865288270221435e-06, + "loss": 3.3227, + "step": 2670080 + }, + { + "epoch": 0.02, + "learning_rate": 6.278142879511624e-06, + "loss": 3.3218, + "step": 2670592 + }, + { + "epoch": 0.02, + "learning_rate": 6.2697569320011026e-06, + "loss": 3.316, + "step": 2671104 + }, + { + "epoch": 0.03, + "eval_loss": 3.8669540882110596, + "eval_runtime": 314.0443, + "eval_samples_per_second": 1215.087, + "eval_steps_per_second": 37.972, + "step": 2671200 + }, + { + "epoch": 0.0, + "learning_rate": 6.261370984490583e-06, + "loss": 3.3107, + "step": 2671616 + }, + { + "epoch": 0.0, + "learning_rate": 6.253001415783795e-06, + "loss": 3.329, + "step": 2672128 + }, + { + "epoch": 0.0, + "learning_rate": 6.244615468273274e-06, + "loss": 3.3376, + "step": 2672640 + }, + { + "epoch": 0.0, + "learning_rate": 6.236229520762755e-06, + "loss": 3.3239, + "step": 2673152 + }, + { + "epoch": 0.0, + "learning_rate": 6.227843573252235e-06, + "loss": 3.3446, + "step": 2673664 + }, + { + "epoch": 0.0, + "learning_rate": 6.219457625741715e-06, + "loss": 3.3158, + "step": 2674176 + }, + { + "epoch": 0.0, + "learning_rate": 6.211071678231195e-06, + "loss": 3.3315, + "step": 2674688 + }, + { + "epoch": 0.0, + "learning_rate": 6.202685730720674e-06, + "loss": 3.3123, + "step": 2675200 + }, + { + "epoch": 0.0, + "learning_rate": 6.194299783210155e-06, + "loss": 3.3271, + "step": 2675712 + }, + { + "epoch": 0.0, + "learning_rate": 6.1859302145033655e-06, + "loss": 3.326, + "step": 2676224 + }, + { + "epoch": 0.0, + "learning_rate": 6.1775442669928454e-06, + "loss": 3.3208, + "step": 2676736 + }, + { + "epoch": 0.0, + "learning_rate": 6.169158319482325e-06, + "loss": 3.3349, + "step": 2677248 + }, + { + "epoch": 0.0, + "learning_rate": 6.160788750775537e-06, + "loss": 3.3232, + "step": 2677760 + }, + { + "epoch": 0.0, + "learning_rate": 6.152402803265016e-06, + "loss": 3.3132, + "step": 2678272 + }, + { + "epoch": 0.0, + "learning_rate": 6.144016855754497e-06, + "loss": 3.3154, + "step": 2678784 + }, + { + "epoch": 0.0, + "learning_rate": 6.135630908243976e-06, + "loss": 3.323, + "step": 2679296 + }, + { + "epoch": 0.0, + "learning_rate": 6.127244960733456e-06, + "loss": 3.326, + "step": 2679808 + }, + { + "epoch": 0.0, + "learning_rate": 6.118859013222936e-06, + "loss": 3.3203, + "step": 2680320 + }, + { + "epoch": 0.0, + "learning_rate": 6.110473065712416e-06, + "loss": 3.3236, + "step": 2680832 + }, + { + "epoch": 0.0, + "learning_rate": 6.102087118201896e-06, + "loss": 3.3453, + "step": 2681344 + }, + { + "epoch": 0.0, + "learning_rate": 6.0937175494951075e-06, + "loss": 3.3253, + "step": 2681856 + }, + { + "epoch": 0.0, + "learning_rate": 6.085331601984587e-06, + "loss": 3.324, + "step": 2682368 + }, + { + "epoch": 0.0, + "learning_rate": 6.076945654474067e-06, + "loss": 3.3236, + "step": 2682880 + }, + { + "epoch": 0.0, + "learning_rate": 6.068576085767278e-06, + "loss": 3.3325, + "step": 2683392 + }, + { + "epoch": 0.0, + "learning_rate": 6.060190138256758e-06, + "loss": 3.3154, + "step": 2683904 + }, + { + "epoch": 0.0, + "learning_rate": 6.051804190746238e-06, + "loss": 3.3254, + "step": 2684416 + }, + { + "epoch": 0.0, + "learning_rate": 6.043418243235718e-06, + "loss": 3.3287, + "step": 2684928 + }, + { + "epoch": 0.0, + "learning_rate": 6.03504867452893e-06, + "loss": 3.3193, + "step": 2685440 + }, + { + "epoch": 0.0, + "learning_rate": 6.02666272701841e-06, + "loss": 3.3117, + "step": 2685952 + }, + { + "epoch": 0.01, + "learning_rate": 6.01827677950789e-06, + "loss": 3.3156, + "step": 2686464 + }, + { + "epoch": 0.01, + "learning_rate": 6.009890831997369e-06, + "loss": 3.3261, + "step": 2686976 + }, + { + "epoch": 0.01, + "learning_rate": 6.0015048844868495e-06, + "loss": 3.3207, + "step": 2687488 + }, + { + "epoch": 0.01, + "learning_rate": 5.993118936976329e-06, + "loss": 3.3374, + "step": 2688000 + }, + { + "epoch": 0.01, + "learning_rate": 5.9847329894658094e-06, + "loss": 3.3254, + "step": 2688512 + }, + { + "epoch": 0.01, + "learning_rate": 5.9763470419552886e-06, + "loss": 3.3109, + "step": 2689024 + }, + { + "epoch": 0.01, + "learning_rate": 5.9679774732485e-06, + "loss": 3.327, + "step": 2689536 + }, + { + "epoch": 0.01, + "learning_rate": 5.95959152573798e-06, + "loss": 3.3206, + "step": 2690048 + }, + { + "epoch": 0.01, + "learning_rate": 5.951205578227459e-06, + "loss": 3.3132, + "step": 2690560 + }, + { + "epoch": 0.01, + "learning_rate": 5.94281963071694e-06, + "loss": 3.314, + "step": 2691072 + }, + { + "epoch": 0.01, + "learning_rate": 5.934450062010151e-06, + "loss": 3.3181, + "step": 2691584 + }, + { + "epoch": 0.01, + "learning_rate": 5.926064114499631e-06, + "loss": 3.3123, + "step": 2692096 + }, + { + "epoch": 0.01, + "learning_rate": 5.917678166989111e-06, + "loss": 3.3334, + "step": 2692608 + }, + { + "epoch": 0.01, + "learning_rate": 5.9092922194785916e-06, + "loss": 3.3178, + "step": 2693120 + }, + { + "epoch": 0.01, + "learning_rate": 5.900922650771802e-06, + "loss": 3.3244, + "step": 2693632 + }, + { + "epoch": 0.01, + "learning_rate": 5.892553082065014e-06, + "loss": 3.3305, + "step": 2694144 + }, + { + "epoch": 0.01, + "learning_rate": 5.884167134554493e-06, + "loss": 3.3199, + "step": 2694656 + }, + { + "epoch": 0.01, + "learning_rate": 5.875781187043974e-06, + "loss": 3.321, + "step": 2695168 + }, + { + "epoch": 0.01, + "learning_rate": 5.867395239533453e-06, + "loss": 3.3072, + "step": 2695680 + }, + { + "epoch": 0.01, + "learning_rate": 5.859009292022933e-06, + "loss": 3.3026, + "step": 2696192 + }, + { + "epoch": 0.01, + "learning_rate": 5.850623344512413e-06, + "loss": 3.3348, + "step": 2696704 + }, + { + "epoch": 0.01, + "learning_rate": 5.842237397001893e-06, + "loss": 3.319, + "step": 2697216 + }, + { + "epoch": 0.01, + "learning_rate": 5.833851449491373e-06, + "loss": 3.3188, + "step": 2697728 + }, + { + "epoch": 0.01, + "learning_rate": 5.8254818807845845e-06, + "loss": 3.3139, + "step": 2698240 + }, + { + "epoch": 0.01, + "learning_rate": 5.8170959332740644e-06, + "loss": 3.3154, + "step": 2698752 + }, + { + "epoch": 0.01, + "learning_rate": 5.808709985763544e-06, + "loss": 3.3018, + "step": 2699264 + }, + { + "epoch": 0.01, + "learning_rate": 5.8003240382530235e-06, + "loss": 3.3251, + "step": 2699776 + }, + { + "epoch": 0.01, + "learning_rate": 5.791954469546235e-06, + "loss": 3.3222, + "step": 2700288 + }, + { + "epoch": 0.01, + "learning_rate": 5.783568522035715e-06, + "loss": 3.3159, + "step": 2700800 + }, + { + "epoch": 0.01, + "learning_rate": 5.775182574525195e-06, + "loss": 3.3284, + "step": 2701312 + }, + { + "epoch": 0.01, + "learning_rate": 5.766796627014675e-06, + "loss": 3.3099, + "step": 2701824 + }, + { + "epoch": 0.01, + "learning_rate": 5.758427058307887e-06, + "loss": 3.3109, + "step": 2702336 + }, + { + "epoch": 0.01, + "learning_rate": 5.750041110797367e-06, + "loss": 3.3239, + "step": 2702848 + }, + { + "epoch": 0.01, + "learning_rate": 5.7416551632868465e-06, + "loss": 3.3018, + "step": 2703360 + }, + { + "epoch": 0.01, + "learning_rate": 5.733285594580057e-06, + "loss": 3.3082, + "step": 2703872 + }, + { + "epoch": 0.01, + "learning_rate": 5.724899647069538e-06, + "loss": 3.3261, + "step": 2704384 + }, + { + "epoch": 0.01, + "learning_rate": 5.716513699559017e-06, + "loss": 3.325, + "step": 2704896 + }, + { + "epoch": 0.01, + "learning_rate": 5.708144130852229e-06, + "loss": 3.3089, + "step": 2705408 + }, + { + "epoch": 0.01, + "learning_rate": 5.699758183341709e-06, + "loss": 3.3191, + "step": 2705920 + }, + { + "epoch": 0.01, + "learning_rate": 5.691372235831188e-06, + "loss": 3.3044, + "step": 2706432 + }, + { + "epoch": 0.01, + "learning_rate": 5.682986288320669e-06, + "loss": 3.3222, + "step": 2706944 + }, + { + "epoch": 0.01, + "learning_rate": 5.674600340810148e-06, + "loss": 3.3154, + "step": 2707456 + }, + { + "epoch": 0.01, + "learning_rate": 5.666214393299629e-06, + "loss": 3.322, + "step": 2707968 + }, + { + "epoch": 0.01, + "learning_rate": 5.657828445789108e-06, + "loss": 3.3198, + "step": 2708480 + }, + { + "epoch": 0.01, + "learning_rate": 5.649442498278588e-06, + "loss": 3.3253, + "step": 2708992 + }, + { + "epoch": 0.01, + "learning_rate": 5.641072929571799e-06, + "loss": 3.3308, + "step": 2709504 + }, + { + "epoch": 0.01, + "learning_rate": 5.632686982061279e-06, + "loss": 3.3053, + "step": 2710016 + }, + { + "epoch": 0.01, + "learning_rate": 5.624301034550759e-06, + "loss": 3.3211, + "step": 2710528 + }, + { + "epoch": 0.01, + "learning_rate": 5.61593146584397e-06, + "loss": 3.3251, + "step": 2711040 + }, + { + "epoch": 0.01, + "learning_rate": 5.607545518333451e-06, + "loss": 3.3058, + "step": 2711552 + }, + { + "epoch": 0.01, + "learning_rate": 5.59915957082293e-06, + "loss": 3.3334, + "step": 2712064 + }, + { + "epoch": 0.01, + "learning_rate": 5.590773623312411e-06, + "loss": 3.3264, + "step": 2712576 + }, + { + "epoch": 0.01, + "learning_rate": 5.5824040546056216e-06, + "loss": 3.3275, + "step": 2713088 + }, + { + "epoch": 0.01, + "learning_rate": 5.5740181070951015e-06, + "loss": 3.3339, + "step": 2713600 + }, + { + "epoch": 0.01, + "learning_rate": 5.5656321595845815e-06, + "loss": 3.3101, + "step": 2714112 + }, + { + "epoch": 0.01, + "learning_rate": 5.5572462120740614e-06, + "loss": 3.3124, + "step": 2714624 + }, + { + "epoch": 0.01, + "learning_rate": 5.548876643367273e-06, + "loss": 3.3195, + "step": 2715136 + }, + { + "epoch": 0.01, + "learning_rate": 5.540507074660485e-06, + "loss": 3.3255, + "step": 2715648 + }, + { + "epoch": 0.01, + "learning_rate": 5.532121127149964e-06, + "loss": 3.3183, + "step": 2716160 + }, + { + "epoch": 0.01, + "learning_rate": 5.523735179639444e-06, + "loss": 3.3172, + "step": 2716672 + }, + { + "epoch": 0.02, + "learning_rate": 5.515349232128924e-06, + "loss": 3.3179, + "step": 2717184 + }, + { + "epoch": 0.02, + "learning_rate": 5.506963284618404e-06, + "loss": 3.3284, + "step": 2717696 + }, + { + "epoch": 0.02, + "learning_rate": 5.498577337107883e-06, + "loss": 3.3086, + "step": 2718208 + }, + { + "epoch": 0.02, + "learning_rate": 5.490191389597364e-06, + "loss": 3.3165, + "step": 2718720 + }, + { + "epoch": 0.02, + "learning_rate": 5.481805442086843e-06, + "loss": 3.3247, + "step": 2719232 + }, + { + "epoch": 0.02, + "learning_rate": 5.473435873380054e-06, + "loss": 3.3306, + "step": 2719744 + }, + { + "epoch": 0.02, + "learning_rate": 5.465049925869534e-06, + "loss": 3.3237, + "step": 2720256 + }, + { + "epoch": 0.02, + "learning_rate": 5.456663978359015e-06, + "loss": 3.3063, + "step": 2720768 + }, + { + "epoch": 0.02, + "learning_rate": 5.448278030848494e-06, + "loss": 3.3202, + "step": 2721280 + }, + { + "epoch": 0.02, + "learning_rate": 5.439908462141706e-06, + "loss": 3.3184, + "step": 2721792 + }, + { + "epoch": 0.02, + "learning_rate": 5.431522514631186e-06, + "loss": 3.322, + "step": 2722304 + }, + { + "epoch": 0.02, + "learning_rate": 5.423136567120665e-06, + "loss": 3.3186, + "step": 2722816 + }, + { + "epoch": 0.02, + "learning_rate": 5.414750619610146e-06, + "loss": 3.3154, + "step": 2723328 + }, + { + "epoch": 0.02, + "learning_rate": 5.4063810509033565e-06, + "loss": 3.3063, + "step": 2723840 + }, + { + "epoch": 0.02, + "learning_rate": 5.3979951033928365e-06, + "loss": 3.3189, + "step": 2724352 + }, + { + "epoch": 0.02, + "learning_rate": 5.389609155882316e-06, + "loss": 3.3086, + "step": 2724864 + }, + { + "epoch": 0.02, + "learning_rate": 5.381223208371796e-06, + "loss": 3.3182, + "step": 2725376 + }, + { + "epoch": 0.02, + "learning_rate": 5.372853639665008e-06, + "loss": 3.3073, + "step": 2725888 + }, + { + "epoch": 0.02, + "learning_rate": 5.364467692154488e-06, + "loss": 3.3213, + "step": 2726400 + }, + { + "epoch": 0.02, + "learning_rate": 5.356081744643968e-06, + "loss": 3.3083, + "step": 2726912 + }, + { + "epoch": 0.02, + "learning_rate": 5.347695797133447e-06, + "loss": 3.324, + "step": 2727424 + }, + { + "epoch": 0.02, + "learning_rate": 5.339326228426659e-06, + "loss": 3.3087, + "step": 2727936 + }, + { + "epoch": 0.02, + "learning_rate": 5.330940280916139e-06, + "loss": 3.3157, + "step": 2728448 + }, + { + "epoch": 0.02, + "learning_rate": 5.322554333405619e-06, + "loss": 3.315, + "step": 2728960 + }, + { + "epoch": 0.02, + "learning_rate": 5.314184764698829e-06, + "loss": 3.3148, + "step": 2729472 + }, + { + "epoch": 0.02, + "learning_rate": 5.30579881718831e-06, + "loss": 3.3178, + "step": 2729984 + }, + { + "epoch": 0.02, + "learning_rate": 5.29741286967779e-06, + "loss": 3.3317, + "step": 2730496 + }, + { + "epoch": 0.02, + "learning_rate": 5.28902692216727e-06, + "loss": 3.3164, + "step": 2731008 + }, + { + "epoch": 0.02, + "learning_rate": 5.280657353460481e-06, + "loss": 3.3157, + "step": 2731520 + }, + { + "epoch": 0.02, + "learning_rate": 5.272271405949962e-06, + "loss": 3.3209, + "step": 2732032 + }, + { + "epoch": 0.02, + "learning_rate": 5.263885458439441e-06, + "loss": 3.3214, + "step": 2732544 + }, + { + "epoch": 0.02, + "learning_rate": 5.255499510928921e-06, + "loss": 3.3071, + "step": 2733056 + }, + { + "epoch": 0.02, + "learning_rate": 5.247129942222132e-06, + "loss": 3.3227, + "step": 2733568 + }, + { + "epoch": 0.02, + "learning_rate": 5.2387439947116115e-06, + "loss": 3.3145, + "step": 2734080 + }, + { + "epoch": 0.02, + "learning_rate": 5.230358047201092e-06, + "loss": 3.3227, + "step": 2734592 + }, + { + "epoch": 0.02, + "learning_rate": 5.221972099690571e-06, + "loss": 3.3139, + "step": 2735104 + }, + { + "epoch": 0.02, + "learning_rate": 5.213602530983783e-06, + "loss": 3.319, + "step": 2735616 + }, + { + "epoch": 0.02, + "learning_rate": 5.205216583473263e-06, + "loss": 3.3054, + "step": 2736128 + }, + { + "epoch": 0.02, + "learning_rate": 5.196830635962743e-06, + "loss": 3.3154, + "step": 2736640 + }, + { + "epoch": 0.02, + "learning_rate": 5.188444688452223e-06, + "loss": 3.314, + "step": 2737152 + }, + { + "epoch": 0.02, + "learning_rate": 5.1800751197454345e-06, + "loss": 3.3167, + "step": 2737664 + }, + { + "epoch": 0.02, + "learning_rate": 5.1716891722349145e-06, + "loss": 3.3258, + "step": 2738176 + }, + { + "epoch": 0.02, + "learning_rate": 5.163303224724394e-06, + "loss": 3.3198, + "step": 2738688 + }, + { + "epoch": 0.02, + "learning_rate": 5.154917277213874e-06, + "loss": 3.3114, + "step": 2739200 + }, + { + "epoch": 0.02, + "learning_rate": 5.146547708507085e-06, + "loss": 3.3186, + "step": 2739712 + }, + { + "epoch": 0.02, + "learning_rate": 5.138161760996565e-06, + "loss": 3.3214, + "step": 2740224 + }, + { + "epoch": 0.02, + "learning_rate": 5.129775813486045e-06, + "loss": 3.3229, + "step": 2740736 + }, + { + "epoch": 0.02, + "learning_rate": 5.121406244779257e-06, + "loss": 3.3208, + "step": 2741248 + }, + { + "epoch": 0.02, + "learning_rate": 5.113020297268737e-06, + "loss": 3.315, + "step": 2741760 + }, + { + "epoch": 0.02, + "learning_rate": 5.104634349758217e-06, + "loss": 3.3154, + "step": 2742272 + }, + { + "epoch": 0.02, + "learning_rate": 5.096248402247697e-06, + "loss": 3.3257, + "step": 2742784 + }, + { + "epoch": 0.02, + "learning_rate": 5.087862454737176e-06, + "loss": 3.3115, + "step": 2743296 + }, + { + "epoch": 0.02, + "learning_rate": 5.0794765072266565e-06, + "loss": 3.3208, + "step": 2743808 + }, + { + "epoch": 0.02, + "learning_rate": 5.071090559716136e-06, + "loss": 3.3114, + "step": 2744320 + }, + { + "epoch": 0.02, + "learning_rate": 5.062720991009347e-06, + "loss": 3.3147, + "step": 2744832 + }, + { + "epoch": 0.02, + "learning_rate": 5.054351422302558e-06, + "loss": 3.3285, + "step": 2745344 + }, + { + "epoch": 0.02, + "learning_rate": 5.045965474792039e-06, + "loss": 3.3224, + "step": 2745856 + }, + { + "epoch": 0.02, + "learning_rate": 5.037579527281518e-06, + "loss": 3.3151, + "step": 2746368 + }, + { + "epoch": 0.02, + "learning_rate": 5.029193579770999e-06, + "loss": 3.3094, + "step": 2746880 + }, + { + "epoch": 0.02, + "learning_rate": 5.020807632260478e-06, + "loss": 3.3108, + "step": 2747392 + }, + { + "epoch": 0.03, + "eval_loss": 3.8680174350738525, + "eval_runtime": 304.0144, + "eval_samples_per_second": 1255.174, + "eval_steps_per_second": 39.225, + "step": 2747520 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.9043031216750428e+18, + "trial_name": null, + "trial_params": null +}