diff --git "a/checkpoint-2518560/trainer_state.json" "b/checkpoint-2518560/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2518560/trainer_state.json" @@ -0,0 +1,29803 @@ +{ + "best_metric": 3.84253191947937, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-sent-neg/transformer/3/checkpoints/checkpoint-915840", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2518560, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.9229, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.813, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1836, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9693, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.812, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7004, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.593, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5226, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4468, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3948, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3465, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3025, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2616, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.1959, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1686, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1276, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1029, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0731, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0475, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0133, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0054, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9729, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.945, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.928, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9194, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8879, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8669, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.852, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8289, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8228, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8053, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740117521192533e-05, + "loss": 4.8013, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731731573682013e-05, + "loss": 4.7728, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7671, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.756, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7449, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.728, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.6968, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 4.7008, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6774, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6812, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6665, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6621, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6468, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.6443, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.64, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6244, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6271, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.9597605549924894e-05, + "loss": 4.5973, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.5894, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.5987, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.5874, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.578, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5525, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5685, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5454, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 4.5681, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5238, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5404, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5223, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949702331620985e-05, + "loss": 4.5074, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948863736869932e-05, + "loss": 4.5171, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5028, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4831, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946349590497149e-05, + "loss": 4.4879, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945510995746097e-05, + "loss": 4.5034, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4783, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4734, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.9429968493733145e-05, + "loss": 4.4682, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421598925026354e-05, + "loss": 4.4548, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941321297751584e-05, + "loss": 4.4675, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940482703000532e-05, + "loss": 4.4642, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396441082494794e-05, + "loss": 4.455, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388055134984274e-05, + "loss": 4.4647, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.4507, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4469, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.4278, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.4327, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4277, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.414, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4148, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4214, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4195, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.4113, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.3874, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.4021, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.4047, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.4035, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926231505873767e-05, + "loss": 4.3864, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3962, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924555954252036e-05, + "loss": 4.3849, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923717359500984e-05, + "loss": 4.3747, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.3747, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3734, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3641, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3758, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3533, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3509, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917848834123993e-05, + "loss": 4.3493, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.3585, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.3551, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3363, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914496093000158e-05, + "loss": 4.3392, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913657498249106e-05, + "loss": 4.3282, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912818903498054e-05, + "loss": 4.3393, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911981946627375e-05, + "loss": 4.313, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111449897566966e-05, + "loss": 4.3261, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9103063950056446e-05, + "loss": 4.3245, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.9094678002545926e-05, + "loss": 4.3195, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.9086292055035406e-05, + "loss": 4.3241, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.9077906107524886e-05, + "loss": 4.3181, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.9069520160014366e-05, + "loss": 4.3021, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.9061150591307575e-05, + "loss": 4.312, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052764643797055e-05, + "loss": 4.3135, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.9044378696286535e-05, + "loss": 4.3082, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.9035992748776015e-05, + "loss": 4.3088, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027606801265495e-05, + "loss": 4.3061, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019237232558704e-05, + "loss": 4.299, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010851285048184e-05, + "loss": 4.2901, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900246533753767e-05, + "loss": 4.2926, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899407939002715e-05, + "loss": 4.2907, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985693442516624e-05, + "loss": 4.2803, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977307495006104e-05, + "loss": 4.2821, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968921547495584e-05, + "loss": 4.2813, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2881, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.895216603127827e-05, + "loss": 4.2694, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.894378008376775e-05, + "loss": 4.2752, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893539413625723e-05, + "loss": 4.266, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892702456755045e-05, + "loss": 4.274, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891863862003992e-05, + "loss": 4.2606, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891025267252941e-05, + "loss": 4.2796, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890186672501889e-05, + "loss": 4.264, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889348077750837e-05, + "loss": 4.2575, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888509482999785e-05, + "loss": 4.2606, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887672526129106e-05, + "loss": 4.2603, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886833931378054e-05, + "loss": 4.2641, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885995336627002e-05, + "loss": 4.2656, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515674187595e-05, + "loss": 4.2563, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2562, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2543, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2468, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.238, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.8809654060010626e-05, + "loss": 4.2437, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.8801268112500106e-05, + "loss": 4.2367, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879289854379332e-05, + "loss": 4.2294, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.87845125962828e-05, + "loss": 4.2353, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877612664877228e-05, + "loss": 4.2298, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876774070126176e-05, + "loss": 4.2351, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875935475375124e-05, + "loss": 4.2348, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875096880624072e-05, + "loss": 4.2262, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.195621490478516, + "eval_runtime": 336.5361, + "eval_samples_per_second": 1133.879, + "eval_steps_per_second": 35.435, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.87425828587302e-05, + "loss": 4.211, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873419691121968e-05, + "loss": 4.2112, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872582734251289e-05, + "loss": 4.2249, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871744139500237e-05, + "loss": 4.216, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870905544749185e-05, + "loss": 4.2174, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870066949998133e-05, + "loss": 4.2055, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692316310078276e-05, + "loss": 4.2005, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683930362567756e-05, + "loss": 4.2007, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675544415057236e-05, + "loss": 4.2084, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667158467546716e-05, + "loss": 4.2059, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658772520036196e-05, + "loss": 4.2006, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.8650386572525676e-05, + "loss": 4.209, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642017003818885e-05, + "loss": 4.1806, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633631056308365e-05, + "loss": 4.1876, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.8625245108797845e-05, + "loss": 4.185, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.8616859161287324e-05, + "loss": 4.1747, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608489592580534e-05, + "loss": 4.1903, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.8600103645070014e-05, + "loss": 4.1804, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591717697559493e-05, + "loss": 4.1765, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858333175004898e-05, + "loss": 4.2044, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857494580253846e-05, + "loss": 4.1807, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856657623383167e-05, + "loss": 4.1783, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.855819028632115e-05, + "loss": 4.1774, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854980433881063e-05, + "loss": 4.1874, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854141839130011e-05, + "loss": 4.1684, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853303244378958e-05, + "loss": 4.1668, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852464649627906e-05, + "loss": 4.1698, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851626054876854e-05, + "loss": 4.1656, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850789098006175e-05, + "loss": 4.1637, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849950503255123e-05, + "loss": 4.1584, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849113546384445e-05, + "loss": 4.176, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.8482749516333934e-05, + "loss": 4.163, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847436356882341e-05, + "loss": 4.1601, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846597762131289e-05, + "loss": 4.1592, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845759167380237e-05, + "loss": 4.1613, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844922210509558e-05, + "loss": 4.1564, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.8440836157585056e-05, + "loss": 4.1411, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.8432450210074536e-05, + "loss": 4.1433, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.8424064262564016e-05, + "loss": 4.1326, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.8415694693857225e-05, + "loss": 4.1483, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.8407308746346705e-05, + "loss": 4.1369, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398922798836185e-05, + "loss": 4.1459, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839053685132567e-05, + "loss": 4.1359, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838215090381515e-05, + "loss": 4.1396, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837376495630463e-05, + "loss": 4.1449, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836537900879411e-05, + "loss": 4.1335, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835700944008732e-05, + "loss": 4.1398, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.83486234925768e-05, + "loss": 4.126, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834023754506628e-05, + "loss": 4.1233, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833185159755576e-05, + "loss": 4.1326, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832346565004524e-05, + "loss": 4.1285, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831509608133845e-05, + "loss": 4.1326, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830671013382793e-05, + "loss": 4.1054, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829832418631741e-05, + "loss": 4.1286, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828993823880689e-05, + "loss": 4.1079, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281568670100105e-05, + "loss": 4.1361, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273182722589585e-05, + "loss": 4.1053, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264796775079065e-05, + "loss": 4.1224, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256410827568545e-05, + "loss": 4.1146, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248024880058025e-05, + "loss": 4.101, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239655311351234e-05, + "loss": 4.1092, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.8231269363840714e-05, + "loss": 4.1086, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222883416330194e-05, + "loss": 4.0914, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214497468819674e-05, + "loss": 4.0975, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820612790011288e-05, + "loss": 4.1126, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819774195260236e-05, + "loss": 4.1011, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818935600509184e-05, + "loss": 4.0979, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818097005758132e-05, + "loss": 4.0952, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817258411007081e-05, + "loss": 4.0853, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816421454136402e-05, + "loss": 4.1025, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.81558285938535e-05, + "loss": 4.1017, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814744264634298e-05, + "loss": 4.0995, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813905669883246e-05, + "loss": 4.1089, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813068713012567e-05, + "loss": 4.101, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812230118261515e-05, + "loss": 4.1013, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811391523510463e-05, + "loss": 4.0804, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810552928759411e-05, + "loss": 4.0949, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809714334008359e-05, + "loss": 4.087, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.80887737713768e-05, + "loss": 4.0792, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808038782386628e-05, + "loss": 4.0864, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807200187635576e-05, + "loss": 4.0917, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.8063615928845243e-05, + "loss": 4.0963, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805524636013845e-05, + "loss": 4.09, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804686041262793e-05, + "loss": 4.069, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803847446511741e-05, + "loss": 4.0768, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.8030088517606886e-05, + "loss": 4.0935, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.80217189489001e-05, + "loss": 4.0873, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801333300138958e-05, + "loss": 4.0796, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800494705387906e-05, + "loss": 4.0868, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996561106368535e-05, + "loss": 4.0834, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988175158858015e-05, + "loss": 4.0681, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797980559015123e-05, + "loss": 4.0748, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797141964264071e-05, + "loss": 4.0787, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796303369513019e-05, + "loss": 4.0696, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795464774761967e-05, + "loss": 4.0861, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946278178912886e-05, + "loss": 4.0628, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793789223140236e-05, + "loss": 4.063, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792950628389184e-05, + "loss": 4.0657, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792112033638132e-05, + "loss": 4.0742, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912750767674535e-05, + "loss": 4.074, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790436482016401e-05, + "loss": 4.0605, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789597887265349e-05, + "loss": 4.0599, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788759292514297e-05, + "loss": 4.0529, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879223356436184e-05, + "loss": 4.0736, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870837408925664e-05, + "loss": 4.0432, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786246784021888e-05, + "loss": 4.0514, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785408189270836e-05, + "loss": 4.0653, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784569594519783e-05, + "loss": 4.0556, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783730999768731e-05, + "loss": 4.0537, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782892405017679e-05, + "loss": 4.0569, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782053810266627e-05, + "loss": 4.0476, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781215215515575e-05, + "loss": 4.0592, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780376620764523e-05, + "loss": 4.0511, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779539663893844e-05, + "loss": 4.055, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778701069142792e-05, + "loss": 4.0569, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.77786247439174e-05, + "loss": 4.0598, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777025517521062e-05, + "loss": 4.049, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.77618692277001e-05, + "loss": 4.042, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775348328018958e-05, + "loss": 4.0494, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774509733267906e-05, + "loss": 4.0451, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773671138516854e-05, + "loss": 4.0365, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772832543765802e-05, + "loss": 4.0433, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.77199394901475e-05, + "loss": 4.0412, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771155354263698e-05, + "loss": 4.0488, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.7703183973930186e-05, + "loss": 4.0349, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.7694798026419666e-05, + "loss": 4.0429, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.7686412078909146e-05, + "loss": 4.0252, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.7678026131398626e-05, + "loss": 4.0437, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766965656269184e-05, + "loss": 4.0321, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766127061518132e-05, + "loss": 4.0491, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.76528846676708e-05, + "loss": 4.0397, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764449872016028e-05, + "loss": 4.0347, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763612915145349e-05, + "loss": 4.0277, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762774320394297e-05, + "loss": 4.0345, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761935725643245e-05, + "loss": 4.044, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761097130892193e-05, + "loss": 4.047, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760260174021514e-05, + "loss": 4.0378, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759421579270462e-05, + "loss": 4.038, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.75858298451941e-05, + "loss": 4.0312, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757744389768358e-05, + "loss": 4.0336, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569074328976796e-05, + "loss": 4.0246, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560688381466276e-05, + "loss": 4.0291, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552302433955756e-05, + "loss": 4.0267, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543932865248965e-05, + "loss": 4.017, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535546917738445e-05, + "loss": 4.0268, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527160970227925e-05, + "loss": 4.0229, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518775022717405e-05, + "loss": 4.0275, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510389075206885e-05, + "loss": 4.0251, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7502003127696365e-05, + "loss": 4.0223, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.025752067565918, + "eval_runtime": 314.6731, + "eval_samples_per_second": 1212.658, + "eval_steps_per_second": 37.896, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493617180185845e-05, + "loss": 4.0062, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748523123267532e-05, + "loss": 4.0125, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.74768452851648e-05, + "loss": 4.0217, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746845933765428e-05, + "loss": 4.0179, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460073390143764e-05, + "loss": 4.0216, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451687442633244e-05, + "loss": 4.0027, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443301495122724e-05, + "loss": 4.0096, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434915547612204e-05, + "loss": 4.0032, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426545978905413e-05, + "loss": 4.0139, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741816003139489e-05, + "loss": 4.0144, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740977408388437e-05, + "loss": 4.0108, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740138813637385e-05, + "loss": 4.0134, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739301856766706e-05, + "loss": 3.9926, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738463262015654e-05, + "loss": 3.9992, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737624667264602e-05, + "loss": 4.0018, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.73678607251355e-05, + "loss": 3.9931, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735947477762498e-05, + "loss": 4.002, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735108883011446e-05, + "loss": 3.9972, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734270288260394e-05, + "loss": 3.9943, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733431693509343e-05, + "loss": 4.0261, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732593098758291e-05, + "loss": 3.9969, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731756141887612e-05, + "loss": 4.0038, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.73091754713656e-05, + "loss": 4.001, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730078952385508e-05, + "loss": 4.0107, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729240357634456e-05, + "loss": 3.9901, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728401762883403e-05, + "loss": 3.9908, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727563168132351e-05, + "loss": 3.9972, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726724573381299e-05, + "loss": 3.9945, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725885978630247e-05, + "loss": 3.9848, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725049021759568e-05, + "loss": 3.9891, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724210427008517e-05, + "loss": 4.0029, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233718322574647e-05, + "loss": 3.9933, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225332375064127e-05, + "loss": 3.9909, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216962806357336e-05, + "loss": 3.9948, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208576858846816e-05, + "loss": 3.9909, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200190911336296e-05, + "loss": 3.9894, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191804963825775e-05, + "loss": 3.9755, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183435395118985e-05, + "loss": 3.9848, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175049447608465e-05, + "loss": 3.9686, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166663500097945e-05, + "loss": 3.983, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158277552587424e-05, + "loss": 3.9759, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149907983880634e-05, + "loss": 3.987, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714152203637012e-05, + "loss": 3.9794, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.71331360888596e-05, + "loss": 3.9782, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712475014134908e-05, + "loss": 3.9835, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711638057264229e-05, + "loss": 3.9804, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710799462513177e-05, + "loss": 3.9825, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709962505642498e-05, + "loss": 3.969, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709123910891446e-05, + "loss": 3.9645, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708285316140394e-05, + "loss": 3.9805, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707446721389342e-05, + "loss": 3.973, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.70660812663829e-05, + "loss": 3.9745, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705769531887238e-05, + "loss": 3.9558, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704930937136186e-05, + "loss": 3.9773, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704092342385134e-05, + "loss": 3.9541, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032553855144554e-05, + "loss": 3.9837, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024167907634034e-05, + "loss": 3.9519, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015781960123514e-05, + "loss": 3.974, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007396012612994e-05, + "loss": 3.9649, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.69990264439062e-05, + "loss": 3.9594, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699064049639568e-05, + "loss": 3.9594, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698225454888516e-05, + "loss": 3.9624, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697386860137464e-05, + "loss": 3.9444, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696549903266785e-05, + "loss": 3.9545, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695711308515733e-05, + "loss": 3.9643, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694872713764681e-05, + "loss": 3.9631, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694034119013629e-05, + "loss": 3.9519, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693197162142951e-05, + "loss": 3.9532, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692358567391899e-05, + "loss": 3.9486, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691519972640847e-05, + "loss": 3.9559, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690681377889795e-05, + "loss": 3.9581, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898444210191157e-05, + "loss": 3.9579, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890058262680636e-05, + "loss": 3.9689, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881672315170116e-05, + "loss": 3.9645, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873302746463326e-05, + "loss": 3.9613, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864916798952806e-05, + "loss": 3.9425, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856547230246015e-05, + "loss": 3.956, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848161282735495e-05, + "loss": 3.9547, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683977533522498e-05, + "loss": 3.9421, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683138938771446e-05, + "loss": 3.9522, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682300344020394e-05, + "loss": 3.9553, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681463387149715e-05, + "loss": 3.9601, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680624792398663e-05, + "loss": 3.9535, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679786197647611e-05, + "loss": 3.9339, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678947602896559e-05, + "loss": 3.9468, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678109008145507e-05, + "loss": 3.9555, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677270413394455e-05, + "loss": 3.955, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676431818643403e-05, + "loss": 3.9495, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675593223892351e-05, + "loss": 3.9545, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674756267021672e-05, + "loss": 3.9561, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.67391767227062e-05, + "loss": 3.9343, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673079077519568e-05, + "loss": 3.9487, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672240482768516e-05, + "loss": 3.9454, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6714035258978375e-05, + "loss": 3.9398, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705649311467855e-05, + "loss": 3.9614, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697263363957335e-05, + "loss": 3.9377, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688877416446815e-05, + "loss": 3.9322, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680507847740024e-05, + "loss": 3.9404, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6672121900229504e-05, + "loss": 3.9494, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663735952718984e-05, + "loss": 3.9464, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665535000520846e-05, + "loss": 3.9372, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664698043650167e-05, + "loss": 3.9315, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663859448899115e-05, + "loss": 3.9278, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663020854148063e-05, + "loss": 3.9491, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662182259397011e-05, + "loss": 3.9202, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661345302526333e-05, + "loss": 3.9333, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660508345655654e-05, + "loss": 3.9417, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659669750904602e-05, + "loss": 3.9323, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.65883115615355e-05, + "loss": 3.9292, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657992561402498e-05, + "loss": 3.9362, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657153966651446e-05, + "loss": 3.9286, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656315371900393e-05, + "loss": 3.9369, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.6554784150297146e-05, + "loss": 3.9309, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546398202786626e-05, + "loss": 3.9331, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6538012255276106e-05, + "loss": 3.9386, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529626307765586e-05, + "loss": 3.9386, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.65212567390588e-05, + "loss": 3.9357, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651287079154828e-05, + "loss": 3.9232, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650448484403776e-05, + "loss": 3.9301, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6496098896527235e-05, + "loss": 3.9271, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487712949016715e-05, + "loss": 3.9188, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479327001506195e-05, + "loss": 3.9309, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470941053995675e-05, + "loss": 3.9198, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462555106485155e-05, + "loss": 3.9342, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454185537778364e-05, + "loss": 3.9205, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445799590267844e-05, + "loss": 3.9271, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437413642757324e-05, + "loss": 3.9132, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429027695246804e-05, + "loss": 3.9257, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642065812654002e-05, + "loss": 3.9153, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.64122721790295e-05, + "loss": 3.9351, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640388623151898e-05, + "loss": 3.9293, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639551666281219e-05, + "loss": 3.9219, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638713071530167e-05, + "loss": 3.913, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637874476779115e-05, + "loss": 3.924, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637035882028063e-05, + "loss": 3.9298, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636197287277011e-05, + "loss": 3.9356, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635360330406332e-05, + "loss": 3.9225, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.63452173565528e-05, + "loss": 3.929, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633683140904228e-05, + "loss": 3.9209, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632844546153176e-05, + "loss": 3.9246, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320059514021244e-05, + "loss": 3.9149, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311689945314454e-05, + "loss": 3.9161, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303303997803934e-05, + "loss": 3.9212, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294918050293413e-05, + "loss": 3.9104, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286532102782893e-05, + "loss": 3.9174, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.62781625340761e-05, + "loss": 3.9195, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626977658656558e-05, + "loss": 3.9135, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626139063905506e-05, + "loss": 3.9161, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625300469154454e-05, + "loss": 3.9126, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9506185054779053, + "eval_runtime": 347.5218, + "eval_samples_per_second": 1098.035, + "eval_steps_per_second": 34.314, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624461874403402e-05, + "loss": 3.9093, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623624917532723e-05, + "loss": 3.9043, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622786322781671e-05, + "loss": 3.9199, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.62194772803062e-05, + "loss": 3.9091, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621109133279568e-05, + "loss": 3.9188, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620270538528516e-05, + "loss": 3.8959, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619433581657837e-05, + "loss": 3.9079, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618594986906785e-05, + "loss": 3.8975, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617756392155733e-05, + "loss": 3.9136, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616917797404681e-05, + "loss": 3.911, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160808405340016e-05, + "loss": 3.9075, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.6152422457829496e-05, + "loss": 3.909, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6144052889122705e-05, + "loss": 3.8918, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135666941612185e-05, + "loss": 3.8988, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127280994101665e-05, + "loss": 3.8999, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611889504659115e-05, + "loss": 3.894, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611050909908063e-05, + "loss": 3.898, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610212315157011e-05, + "loss": 3.8998, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609373720405959e-05, + "loss": 3.8923, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085351256549065e-05, + "loss": 3.9288, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076965309038545e-05, + "loss": 3.8973, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606859574033176e-05, + "loss": 3.9019, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606020979282124e-05, + "loss": 3.9044, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051823845310714e-05, + "loss": 3.9073, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043437897800194e-05, + "loss": 3.8905, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.6035051950289674e-05, + "loss": 3.8993, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602668238158289e-05, + "loss": 3.8956, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601829643407237e-05, + "loss": 3.8966, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600991048656185e-05, + "loss": 3.8856, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600152453905133e-05, + "loss": 3.8941, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599315497034454e-05, + "loss": 3.905, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598476902283402e-05, + "loss": 3.8989, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.59763830753235e-05, + "loss": 3.8996, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596799712781298e-05, + "loss": 3.8985, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595962755910619e-05, + "loss": 3.891, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595124161159567e-05, + "loss": 3.8988, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594285566408515e-05, + "loss": 3.8784, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593446971657463e-05, + "loss": 3.8908, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592608376906411e-05, + "loss": 3.8728, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591771420035732e-05, + "loss": 3.89, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.59093282528468e-05, + "loss": 3.883, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590094230533628e-05, + "loss": 3.8945, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589255635782576e-05, + "loss": 3.8877, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588417041031524e-05, + "loss": 3.8846, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587580084160845e-05, + "loss": 3.8912, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586741489409793e-05, + "loss": 3.8882, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585902894658741e-05, + "loss": 3.8866, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585064299907689e-05, + "loss": 3.881, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.58422734303701e-05, + "loss": 3.8696, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583388748285958e-05, + "loss": 3.8894, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582550153534906e-05, + "loss": 3.8809, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581711558783854e-05, + "loss": 3.8842, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580872964032802e-05, + "loss": 3.8694, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580036007162124e-05, + "loss": 3.8893, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579197412411072e-05, + "loss": 3.8601, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.57835881766002e-05, + "loss": 3.894, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577520222908968e-05, + "loss": 3.8655, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576681628157916e-05, + "loss": 3.8806, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758446712872366e-05, + "loss": 3.875, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5750060765361846e-05, + "loss": 3.8721, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741674817851326e-05, + "loss": 3.8686, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733288870340806e-05, + "loss": 3.8801, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724919301634015e-05, + "loss": 3.8568, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716533354123495e-05, + "loss": 3.8617, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5708147406612975e-05, + "loss": 3.8799, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569976145910246e-05, + "loss": 3.8743, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569139189039567e-05, + "loss": 3.8663, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568300594288515e-05, + "loss": 3.867, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567461999537463e-05, + "loss": 3.8576, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566623404786411e-05, + "loss": 3.8686, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565786447915732e-05, + "loss": 3.8739, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.56494785316468e-05, + "loss": 3.8718, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564109258413628e-05, + "loss": 3.8841, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563270663662576e-05, + "loss": 3.8777, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562433706791897e-05, + "loss": 3.8773, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561595112040845e-05, + "loss": 3.8575, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560756517289793e-05, + "loss": 3.8702, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.5599179225387415e-05, + "loss": 3.8725, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590793277876895e-05, + "loss": 3.8561, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.5582423709170104e-05, + "loss": 3.8713, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.5574037761659584e-05, + "loss": 3.8703, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.5565651814149064e-05, + "loss": 3.8742, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557265866638544e-05, + "loss": 3.8698, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554889629793175e-05, + "loss": 3.8539, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554051035042123e-05, + "loss": 3.8642, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553212440291071e-05, + "loss": 3.8689, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552373845540019e-05, + "loss": 3.8727, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.5515352507889666e-05, + "loss": 3.8659, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550698293918288e-05, + "loss": 3.868, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549859699167237e-05, + "loss": 3.876, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549021104416185e-05, + "loss": 3.8519, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548182509665132e-05, + "loss": 3.8676, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547345552794454e-05, + "loss": 3.861, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546506958043402e-05, + "loss": 3.8633, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.54566836329235e-05, + "loss": 3.878, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544829768541297e-05, + "loss": 3.8598, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543992811670619e-05, + "loss": 3.8507, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431542169195667e-05, + "loss": 3.8597, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542315622168514e-05, + "loss": 3.8664, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541477027417462e-05, + "loss": 3.8676, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406384326664106e-05, + "loss": 3.8576, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5397998379153586e-05, + "loss": 3.8523, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389628810446796e-05, + "loss": 3.8496, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5381242862936275e-05, + "loss": 3.8683, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372856915425755e-05, + "loss": 3.8414, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364470967915235e-05, + "loss": 3.8527, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5356101399208444e-05, + "loss": 3.8619, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347715451697924e-05, + "loss": 3.8579, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339329504187404e-05, + "loss": 3.8475, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330943556676884e-05, + "loss": 3.8598, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322557609166364e-05, + "loss": 3.8526, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314188040459573e-05, + "loss": 3.8559, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530580209294906e-05, + "loss": 3.8553, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529741614543854e-05, + "loss": 3.8534, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528903019792802e-05, + "loss": 3.8667, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528066062922123e-05, + "loss": 3.8568, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.5272291060514445e-05, + "loss": 3.8595, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526390511300392e-05, + "loss": 3.8459, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.52555191654934e-05, + "loss": 3.8537, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524713321798288e-05, + "loss": 3.8523, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523874727047236e-05, + "loss": 3.8423, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523036132296184e-05, + "loss": 3.8542, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522197537545132e-05, + "loss": 3.8462, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.52135894279408e-05, + "loss": 3.8551, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520521985923401e-05, + "loss": 3.8451, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.5196833911723494e-05, + "loss": 3.8535, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188447964212974e-05, + "loss": 3.8329, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.5180062016702454e-05, + "loss": 3.8532, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171676069191934e-05, + "loss": 3.8442, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516330650048514e-05, + "loss": 3.8577, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515492055297462e-05, + "loss": 3.852, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.51465346054641e-05, + "loss": 3.8515, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513814865795358e-05, + "loss": 3.8363, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512977908924679e-05, + "loss": 3.8515, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512139314173627e-05, + "loss": 3.8531, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511300719422575e-05, + "loss": 3.8597, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510462124671523e-05, + "loss": 3.8508, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509625167800845e-05, + "loss": 3.8519, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508786573049793e-05, + "loss": 3.8487, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507947978298741e-05, + "loss": 3.8548, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507109383547689e-05, + "loss": 3.8397, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.5062724266770096e-05, + "loss": 3.8451, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054338319259576e-05, + "loss": 3.8457, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.5045952371749056e-05, + "loss": 3.8387, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.5037566424238536e-05, + "loss": 3.8441, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.5029196855531745e-05, + "loss": 3.8484, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.5020810908021225e-05, + "loss": 3.8419, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012424960510705e-05, + "loss": 3.8412, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.5004039013000185e-05, + "loss": 3.848, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.910633087158203, + "eval_runtime": 329.2898, + "eval_samples_per_second": 1158.83, + "eval_steps_per_second": 36.214, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995653065489665e-05, + "loss": 3.827, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987267117979145e-05, + "loss": 3.8347, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497888117046863e-05, + "loss": 3.8462, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970495222958105e-05, + "loss": 3.8392, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4962109275447585e-05, + "loss": 3.8498, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953723327937065e-05, + "loss": 3.826, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945337380426545e-05, + "loss": 3.8358, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936951432916025e-05, + "loss": 3.8261, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928581864209234e-05, + "loss": 3.8434, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920195916698714e-05, + "loss": 3.8429, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911809969188194e-05, + "loss": 3.8299, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903424021677674e-05, + "loss": 3.8464, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489505445297088e-05, + "loss": 3.8178, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488666850546037e-05, + "loss": 3.83, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487828255794985e-05, + "loss": 3.8325, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486989661043933e-05, + "loss": 3.8248, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486152704173254e-05, + "loss": 3.8293, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485314109422202e-05, + "loss": 3.8306, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.48447551467115e-05, + "loss": 3.8265, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483636919920098e-05, + "loss": 3.8571, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482799963049419e-05, + "loss": 3.8298, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481961368298367e-05, + "loss": 3.8313, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481122773547315e-05, + "loss": 3.8383, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480284178796263e-05, + "loss": 3.8395, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.4794472219255837e-05, + "loss": 3.8222, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478608627174532e-05, + "loss": 3.833, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.47777003242348e-05, + "loss": 3.8276, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476931437672428e-05, + "loss": 3.8287, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476094480801749e-05, + "loss": 3.8172, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475255886050697e-05, + "loss": 3.8263, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474417291299645e-05, + "loss": 3.8407, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473578696548593e-05, + "loss": 3.8302, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472741739677914e-05, + "loss": 3.8327, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471903144926862e-05, + "loss": 3.8313, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.47106455017581e-05, + "loss": 3.8267, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470225955424758e-05, + "loss": 3.8316, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469388998554079e-05, + "loss": 3.8149, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468550403803028e-05, + "loss": 3.8247, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467711809051976e-05, + "loss": 3.8133, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466873214300924e-05, + "loss": 3.8206, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4660362574302446e-05, + "loss": 3.8202, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651976626791926e-05, + "loss": 3.8311, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.4643590679281406e-05, + "loss": 3.8221, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4635204731770886e-05, + "loss": 3.8217, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626835163064095e-05, + "loss": 3.826, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618449215553575e-05, + "loss": 3.8209, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4610063268043055e-05, + "loss": 3.8225, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601677320532535e-05, + "loss": 3.8182, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593291373022015e-05, + "loss": 3.8062, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584921804315224e-05, + "loss": 3.8286, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457653585680471e-05, + "loss": 3.8158, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456814990929419e-05, + "loss": 3.8222, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455976396178367e-05, + "loss": 3.8103, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455139439307688e-05, + "loss": 3.8216, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454300844556636e-05, + "loss": 3.7997, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453462249805584e-05, + "loss": 3.8287, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452623655054532e-05, + "loss": 3.8019, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451786698183853e-05, + "loss": 3.813, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450948103432801e-05, + "loss": 3.8169, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450109508681749e-05, + "loss": 3.8075, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449270913930697e-05, + "loss": 3.8097, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448433957060018e-05, + "loss": 3.8125, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475953623089664e-05, + "loss": 3.8034, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.4467567675579144e-05, + "loss": 3.7969, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445919810687235e-05, + "loss": 3.8143, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445081215936183e-05, + "loss": 3.8132, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444242621185131e-05, + "loss": 3.8015, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443404026434079e-05, + "loss": 3.8087, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442565431683027e-05, + "loss": 3.7946, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441728474812348e-05, + "loss": 3.8073, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440889880061296e-05, + "loss": 3.8134, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440051285310244e-05, + "loss": 3.8106, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439212690559192e-05, + "loss": 3.8206, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438375733688513e-05, + "loss": 3.8142, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437537138937462e-05, + "loss": 3.8228, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.43669854418641e-05, + "loss": 3.7965, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435859949435358e-05, + "loss": 3.809, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435022992564679e-05, + "loss": 3.8109, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434184397813627e-05, + "loss": 3.7939, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433345803062575e-05, + "loss": 3.8134, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432507208311523e-05, + "loss": 3.8101, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316702514408436e-05, + "loss": 3.8119, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308316566897916e-05, + "loss": 3.8104, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299930619387396e-05, + "loss": 3.7939, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291544671876876e-05, + "loss": 3.8069, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283175103170085e-05, + "loss": 3.8072, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427478915565957e-05, + "loss": 3.8125, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426640320814905e-05, + "loss": 3.8063, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425801726063853e-05, + "loss": 3.8123, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424964769193174e-05, + "loss": 3.8116, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424126174442122e-05, + "loss": 3.7975, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.42328757969107e-05, + "loss": 3.8078, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422448984940018e-05, + "loss": 3.7991, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421612028069339e-05, + "loss": 3.8108, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420773433318287e-05, + "loss": 3.8187, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419934838567235e-05, + "loss": 3.7999, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419096243816182e-05, + "loss": 3.7959, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418259286945504e-05, + "loss": 3.798, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174206921944525e-05, + "loss": 3.8057, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165820974434005e-05, + "loss": 3.8146, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415743502692348e-05, + "loss": 3.7982, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4149065458216694e-05, + "loss": 3.7951, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140679510706174e-05, + "loss": 3.7918, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132293563195654e-05, + "loss": 3.8102, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412390761568513e-05, + "loss": 3.7849, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411553804697834e-05, + "loss": 3.7968, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410715209946782e-05, + "loss": 3.8042, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098766151957296e-05, + "loss": 3.7988, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4090380204446776e-05, + "loss": 3.7929, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408201063573999e-05, + "loss": 3.8046, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407362468822948e-05, + "loss": 3.7956, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406523874071895e-05, + "loss": 3.7943, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405686917201217e-05, + "loss": 3.8007, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404848322450165e-05, + "loss": 3.8, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404009727699113e-05, + "loss": 3.8075, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.40317113294806e-05, + "loss": 3.8028, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402334176077382e-05, + "loss": 3.8003, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.40149558132633e-05, + "loss": 3.7895, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400656986575277e-05, + "loss": 3.7988, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399818391824225e-05, + "loss": 3.7955, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398979797073173e-05, + "loss": 3.7841, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398141202322122e-05, + "loss": 3.7993, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.39730260757107e-05, + "loss": 3.7877, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396464012820018e-05, + "loss": 3.8005, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956270559493386e-05, + "loss": 3.7929, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.3947884611982866e-05, + "loss": 3.798, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939498664472346e-05, + "loss": 3.7785, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3931112716961826e-05, + "loss": 3.7941, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922743148255035e-05, + "loss": 3.7942, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914357200744515e-05, + "loss": 3.7965, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905971253233995e-05, + "loss": 3.796, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897585305723475e-05, + "loss": 3.7998, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889215737016684e-05, + "loss": 3.7788, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388082978950617e-05, + "loss": 3.7983, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387244384199565e-05, + "loss": 3.8021, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386405789448513e-05, + "loss": 3.8022, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385568832577834e-05, + "loss": 3.7974, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384730237826782e-05, + "loss": 3.8003, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.38389164307573e-05, + "loss": 3.7931, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383053048324678e-05, + "loss": 3.7997, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382216091453999e-05, + "loss": 3.7826, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381377496702947e-05, + "loss": 3.7939, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380538901951895e-05, + "loss": 3.7873, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379700307200843e-05, + "loss": 3.7885, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378864988210537e-05, + "loss": 3.7911, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378026393459485e-05, + "loss": 3.7879, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377187798708433e-05, + "loss": 3.7922, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376349203957381e-05, + "loss": 3.7817, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375510609206329e-05, + "loss": 3.7971, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8853719234466553, + "eval_runtime": 303.7347, + "eval_samples_per_second": 1256.33, + "eval_steps_per_second": 39.261, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374672014455277e-05, + "loss": 3.7824, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373833419704225e-05, + "loss": 3.7787, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372994824953173e-05, + "loss": 3.7907, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372157868082494e-05, + "loss": 3.7904, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371319273331442e-05, + "loss": 3.7913, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.37048067858039e-05, + "loss": 3.7799, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369642083829338e-05, + "loss": 3.7783, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368805126958659e-05, + "loss": 3.7765, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367966532207607e-05, + "loss": 3.7851, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367127937456556e-05, + "loss": 3.7922, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366289342705504e-05, + "loss": 3.7772, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365452385834825e-05, + "loss": 3.7918, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.3646154289641456e-05, + "loss": 3.77, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.3637768342130936e-05, + "loss": 3.778, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.3629382394620416e-05, + "loss": 3.7802, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.3620996447109896e-05, + "loss": 3.7704, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.3612610499599376e-05, + "loss": 3.7773, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.3604224552088856e-05, + "loss": 3.78, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.3595838604578336e-05, + "loss": 3.7727, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.3587452657067816e-05, + "loss": 3.8021, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.3579083088361025e-05, + "loss": 3.7831, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357069714085051e-05, + "loss": 3.7832, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356231119333999e-05, + "loss": 3.7858, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355392524582947e-05, + "loss": 3.7889, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354555567712268e-05, + "loss": 3.771, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353716972961216e-05, + "loss": 3.7809, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352878378210164e-05, + "loss": 3.7805, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352039783459112e-05, + "loss": 3.7736, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351202826588433e-05, + "loss": 3.7653, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350364231837381e-05, + "loss": 3.7776, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349525637086329e-05, + "loss": 3.7915, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.34868868021565e-05, + "loss": 3.7805, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347850085464598e-05, + "loss": 3.7856, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3470114907135465e-05, + "loss": 3.7775, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461728959624945e-05, + "loss": 3.7742, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.3453359390918154e-05, + "loss": 3.7796, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444973443407634e-05, + "loss": 3.7716, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436587495897114e-05, + "loss": 3.7699, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3428201548386594e-05, + "loss": 3.7628, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.34198319796798e-05, + "loss": 3.7696, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341144603216928e-05, + "loss": 3.7716, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340306008465876e-05, + "loss": 3.7797, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339467413714824e-05, + "loss": 3.7722, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338630456844145e-05, + "loss": 3.7737, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337791862093093e-05, + "loss": 3.7775, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336953267342042e-05, + "loss": 3.7729, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.33611467259099e-05, + "loss": 3.7753, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335277715720311e-05, + "loss": 3.7694, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334439120969259e-05, + "loss": 3.7558, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333600526218207e-05, + "loss": 3.7787, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332761931467155e-05, + "loss": 3.767, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331924974596476e-05, + "loss": 3.7741, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331086379845424e-05, + "loss": 3.7617, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.3302477850943717e-05, + "loss": 3.7704, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3294091903433197e-05, + "loss": 3.7511, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.3285722334726406e-05, + "loss": 3.7776, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.3277336387215886e-05, + "loss": 3.7556, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326895043970537e-05, + "loss": 3.7671, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326056449219485e-05, + "loss": 3.7704, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325219492348806e-05, + "loss": 3.757, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324380897597754e-05, + "loss": 3.7597, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323542302846702e-05, + "loss": 3.7718, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.32270370809565e-05, + "loss": 3.7524, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321866751224971e-05, + "loss": 3.7481, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321028156473919e-05, + "loss": 3.7681, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320189561722867e-05, + "loss": 3.7679, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319350966971815e-05, + "loss": 3.7523, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318514010101136e-05, + "loss": 3.7635, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317675415350084e-05, + "loss": 3.7469, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3168368205990326e-05, + "loss": 3.7572, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.31599822584798e-05, + "loss": 3.7661, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151612689773015e-05, + "loss": 3.7628, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.3143226742262495e-05, + "loss": 3.7697, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.3134840794751975e-05, + "loss": 3.7666, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312645484724145e-05, + "loss": 3.7781, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.3118085278534664e-05, + "loss": 3.7485, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109699331024144e-05, + "loss": 3.7655, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310131338351362e-05, + "loss": 3.7646, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.30929274360031e-05, + "loss": 3.7442, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308455786729631e-05, + "loss": 3.7659, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307617191978579e-05, + "loss": 3.7638, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306778597227527e-05, + "loss": 3.7652, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305940002476475e-05, + "loss": 3.7629, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305103045605797e-05, + "loss": 3.7509, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304264450854745e-05, + "loss": 3.7536, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303425856103692e-05, + "loss": 3.7618, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.30258726135264e-05, + "loss": 3.7695, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301750304481962e-05, + "loss": 3.7563, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300911709730909e-05, + "loss": 3.7676, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300073114979857e-05, + "loss": 3.77, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299234520228805e-05, + "loss": 3.7515, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298397563358127e-05, + "loss": 3.7605, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297558968607075e-05, + "loss": 3.7511, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2967203738560227e-05, + "loss": 3.7637, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958817791049707e-05, + "loss": 3.7775, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295044822234292e-05, + "loss": 3.7483, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.2942062274832396e-05, + "loss": 3.7543, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.2933676327321876e-05, + "loss": 3.7491, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.2925290379811355e-05, + "loss": 3.7602, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.2916920811104565e-05, + "loss": 3.7705, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.2908534863594045e-05, + "loss": 3.7529, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.2900148916083525e-05, + "loss": 3.7511, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289177934737674e-05, + "loss": 3.7424, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288339339986622e-05, + "loss": 3.7661, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.28750074523557e-05, + "loss": 3.7381, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286662150484518e-05, + "loss": 3.7554, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858251936138396e-05, + "loss": 3.7548, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284986598862787e-05, + "loss": 3.7571, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284148004111735e-05, + "loss": 3.7465, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283309409360683e-05, + "loss": 3.757, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282472452490004e-05, + "loss": 3.7542, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281633857738952e-05, + "loss": 3.749, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807969008682734e-05, + "loss": 3.7572, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799583061172214e-05, + "loss": 3.7552, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2791197113661694e-05, + "loss": 3.761, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782811166151174e-05, + "loss": 3.7625, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277444159744439e-05, + "loss": 3.7544, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276605564993387e-05, + "loss": 3.7475, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275766970242334e-05, + "loss": 3.7528, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274928375491282e-05, + "loss": 3.7543, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.27408978074023e-05, + "loss": 3.7411, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273251185989178e-05, + "loss": 3.7516, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272412591238126e-05, + "loss": 3.742, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271573996487074e-05, + "loss": 3.7557, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270737039616395e-05, + "loss": 3.7484, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269898444865343e-05, + "loss": 3.753, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269059850114291e-05, + "loss": 3.7414, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268221255363239e-05, + "loss": 3.746, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267384298492561e-05, + "loss": 3.7517, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266545703741509e-05, + "loss": 3.7569, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265707108990457e-05, + "loss": 3.7478, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264868514239405e-05, + "loss": 3.7532, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.2640315573687257e-05, + "loss": 3.7402, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631929626176737e-05, + "loss": 3.7538, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623543678666216e-05, + "loss": 3.7588, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2615157731155696e-05, + "loss": 3.7577, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606788162448906e-05, + "loss": 3.7524, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2598402214938386e-05, + "loss": 3.7606, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2590016267427865e-05, + "loss": 3.7459, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581630319917345e-05, + "loss": 3.7589, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257326075121056e-05, + "loss": 3.7389, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256487480370004e-05, + "loss": 3.7492, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255648885618952e-05, + "loss": 3.7436, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.2548102908679e-05, + "loss": 3.7457, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253973333997221e-05, + "loss": 3.7494, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253134739246169e-05, + "loss": 3.7412, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252296144495117e-05, + "loss": 3.7559, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251457549744065e-05, + "loss": 3.7321, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250618954993013e-05, + "loss": 3.757, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.86928129196167, + "eval_runtime": 302.9976, + "eval_samples_per_second": 1259.386, + "eval_steps_per_second": 39.357, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249780360241961e-05, + "loss": 3.7352, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248941765490909e-05, + "loss": 3.7377, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248103170739857e-05, + "loss": 3.7486, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247264575988805e-05, + "loss": 3.7465, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246425981237753e-05, + "loss": 3.7491, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245587386486701e-05, + "loss": 3.7373, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244748791735649e-05, + "loss": 3.7322, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243910196984597e-05, + "loss": 3.7389, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243073240113918e-05, + "loss": 3.7431, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242234645362866e-05, + "loss": 3.7499, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241396050611814e-05, + "loss": 3.7394, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240557455860762e-05, + "loss": 3.7458, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.2397221368704564e-05, + "loss": 3.7315, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388835421194044e-05, + "loss": 3.7333, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380449473683524e-05, + "loss": 3.7386, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2372063526173004e-05, + "loss": 3.7293, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363677578662484e-05, + "loss": 3.7337, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355291631151963e-05, + "loss": 3.7403, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346905683641443e-05, + "loss": 3.7315, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233851973613092e-05, + "loss": 3.7577, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233015016742413e-05, + "loss": 3.7441, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232176421991361e-05, + "loss": 3.7373, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231337827240309e-05, + "loss": 3.7429, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230499232489257e-05, + "loss": 3.7498, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229663913498952e-05, + "loss": 3.728, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2288253187479e-05, + "loss": 3.7428, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227986723996847e-05, + "loss": 3.735, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227148129245796e-05, + "loss": 3.7347, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226309534494744e-05, + "loss": 3.7274, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225470939743692e-05, + "loss": 3.7369, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.22463234499264e-05, + "loss": 3.7497, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223793750241588e-05, + "loss": 3.7382, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2229567933709086e-05, + "loss": 3.7474, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2221181986198566e-05, + "loss": 3.7406, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212796038688046e-05, + "loss": 3.7321, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2204410091177526e-05, + "loss": 3.739, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2196040522470735e-05, + "loss": 3.7334, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187654574960215e-05, + "loss": 3.7272, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2179268627449695e-05, + "loss": 3.7238, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170882679939175e-05, + "loss": 3.7286, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216251311123239e-05, + "loss": 3.7327, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215412716372187e-05, + "loss": 3.7401, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214574121621135e-05, + "loss": 3.7312, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213735526870083e-05, + "loss": 3.7313, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212898569999404e-05, + "loss": 3.7394, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212059975248352e-05, + "loss": 3.7298, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112213804973e-05, + "loss": 3.7364, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210382785746248e-05, + "loss": 3.7295, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209545828875569e-05, + "loss": 3.7114, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208707234124517e-05, + "loss": 3.7416, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207868639373465e-05, + "loss": 3.7275, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070316825027865e-05, + "loss": 3.7369, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061930877517345e-05, + "loss": 3.7267, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2053544930006824e-05, + "loss": 3.7256, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045158982496304e-05, + "loss": 3.7157, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036789413789514e-05, + "loss": 3.7341, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028403466278993e-05, + "loss": 3.7198, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2020017518768473e-05, + "loss": 3.7235, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011631571257953e-05, + "loss": 3.7367, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200326200255116e-05, + "loss": 3.7125, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199487605504064e-05, + "loss": 3.7176, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198649010753012e-05, + "loss": 3.7394, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.19781041600196e-05, + "loss": 3.7072, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196973459131281e-05, + "loss": 3.7095, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.19613486438023e-05, + "loss": 3.7278, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195296269629178e-05, + "loss": 3.7259, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194457674878126e-05, + "loss": 3.7156, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193620718007447e-05, + "loss": 3.7267, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192782123256395e-05, + "loss": 3.7094, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191943528505343e-05, + "loss": 3.7174, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191104933754291e-05, + "loss": 3.7281, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902679768836116e-05, + "loss": 3.7246, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1894293821325596e-05, + "loss": 3.7305, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885907873815076e-05, + "loss": 3.7291, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1877521926304556e-05, + "loss": 3.7381, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1869135978794036e-05, + "loss": 3.7123, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860750031283516e-05, + "loss": 3.7251, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.1852364083772996e-05, + "loss": 3.7273, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184397813626248e-05, + "loss": 3.7077, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183560856755569e-05, + "loss": 3.7292, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182722262004517e-05, + "loss": 3.7258, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181883667253465e-05, + "loss": 3.7282, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181045072502413e-05, + "loss": 3.724, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180208115631734e-05, + "loss": 3.7156, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179369520880682e-05, + "loss": 3.7128, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.17853092612963e-05, + "loss": 3.7246, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177693969258951e-05, + "loss": 3.7288, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176855374507899e-05, + "loss": 3.7209, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.176016779756847e-05, + "loss": 3.7293, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175178185005795e-05, + "loss": 3.7308, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743412281351165e-05, + "loss": 3.7172, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1735026333840645e-05, + "loss": 3.721, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726656765133854e-05, + "loss": 3.713, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1718270817623334e-05, + "loss": 3.7294, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.1709884870112814e-05, + "loss": 3.7344, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1701498922602294e-05, + "loss": 3.7151, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693112975091774e-05, + "loss": 3.7145, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168472702758125e-05, + "loss": 3.7093, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167634108007073e-05, + "loss": 3.7256, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166795513256021e-05, + "loss": 3.7298, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165958556385342e-05, + "loss": 3.7168, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.16511996163429e-05, + "loss": 3.7174, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164281366883238e-05, + "loss": 3.7083, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163442772132186e-05, + "loss": 3.7253, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162605815261508e-05, + "loss": 3.7047, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161767220510455e-05, + "loss": 3.7185, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160928625759403e-05, + "loss": 3.7088, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160091668888725e-05, + "loss": 3.7244, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159253074137672e-05, + "loss": 3.71, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.15841447938662e-05, + "loss": 3.72, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157575884635568e-05, + "loss": 3.7196, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.15673892776489e-05, + "loss": 3.7107, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155901970894211e-05, + "loss": 3.7229, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155063376143159e-05, + "loss": 3.7158, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154224781392107e-05, + "loss": 3.7235, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153386186641055e-05, + "loss": 3.7241, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152549229770376e-05, + "loss": 3.7129, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151710635019324e-05, + "loss": 3.7184, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150872040268272e-05, + "loss": 3.7115, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1500334455172195e-05, + "loss": 3.7194, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.1491948507661675e-05, + "loss": 3.7134, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1483562560151155e-05, + "loss": 3.7119, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1475176612640635e-05, + "loss": 3.7037, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466790665130115e-05, + "loss": 3.7192, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145842109642333e-05, + "loss": 3.7103, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.145003514891281e-05, + "loss": 3.7189, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144164920140229e-05, + "loss": 3.7022, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143326325389177e-05, + "loss": 3.7132, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142489368518498e-05, + "loss": 3.712, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141650773767446e-05, + "loss": 3.7228, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140812179016394e-05, + "loss": 3.7102, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139973584265342e-05, + "loss": 3.7183, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139136627394663e-05, + "loss": 3.7028, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138298032643611e-05, + "loss": 3.7192, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137459437892559e-05, + "loss": 3.7211, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136620843141507e-05, + "loss": 3.7203, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357838862708284e-05, + "loss": 3.7164, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349452915197764e-05, + "loss": 3.7239, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1341066967687244e-05, + "loss": 3.7124, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1332681020176724e-05, + "loss": 3.7238, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132431145146993e-05, + "loss": 3.7045, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131592550395941e-05, + "loss": 3.7154, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130753955644889e-05, + "loss": 3.7071, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129915360893837e-05, + "loss": 3.7126, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129078404023158e-05, + "loss": 3.7084, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128239809272106e-05, + "loss": 3.7048, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127401214521054e-05, + "loss": 3.7181, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126562619770002e-05, + "loss": 3.6998, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.12572402501895e-05, + "loss": 3.7273, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.8582229614257812, + "eval_runtime": 304.3065, + "eval_samples_per_second": 1253.969, + "eval_steps_per_second": 39.187, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124885430267898e-05, + "loss": 3.7034, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.124046835516847e-05, + "loss": 3.6999, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123209878646168e-05, + "loss": 3.7119, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122371283895116e-05, + "loss": 3.7126, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121532689144064e-05, + "loss": 3.7094, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120694094393012e-05, + "loss": 3.7061, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.11985549964196e-05, + "loss": 3.7008, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119016904890908e-05, + "loss": 3.7018, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118178310139856e-05, + "loss": 3.7104, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117339715388803e-05, + "loss": 3.7142, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.1165027585181247e-05, + "loss": 3.7062, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1156641637670727e-05, + "loss": 3.7073, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1148272068963936e-05, + "loss": 3.7021, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113988612145342e-05, + "loss": 3.6989, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.11315001739429e-05, + "loss": 3.7011, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112311422643238e-05, + "loss": 3.6936, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111474465772559e-05, + "loss": 3.7007, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110635871021507e-05, + "loss": 3.7052, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109797276270455e-05, + "loss": 3.6954, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108958681519403e-05, + "loss": 3.7209, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.1081200867683504e-05, + "loss": 3.7146, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.1072814920172984e-05, + "loss": 3.7039, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.1064428972662464e-05, + "loss": 3.7095, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1056043025151944e-05, + "loss": 3.7127, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104768983524889e-05, + "loss": 3.694, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.1039303887738376e-05, + "loss": 3.7092, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030917940227856e-05, + "loss": 3.7034, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102253199271733e-05, + "loss": 3.6985, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101414604520681e-05, + "loss": 3.6913, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100576009769629e-05, + "loss": 3.7058, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099737415018577e-05, + "loss": 3.7118, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098898820267525e-05, + "loss": 3.707, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.098061863396846e-05, + "loss": 3.7128, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097223268645794e-05, + "loss": 3.7008, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096384673894742e-05, + "loss": 3.6988, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.09554607914369e-05, + "loss": 3.707, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0947091222730114e-05, + "loss": 3.7012, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0938705275219594e-05, + "loss": 3.691, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930319327709074e-05, + "loss": 3.6905, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921933380198554e-05, + "loss": 3.6951, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091356381149176e-05, + "loss": 3.6973, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090519424278498e-05, + "loss": 3.7058, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089680829527445e-05, + "loss": 3.7005, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088842234776393e-05, + "loss": 3.6964, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.088003640025341e-05, + "loss": 3.7054, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087165045274289e-05, + "loss": 3.7016, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086326450523237e-05, + "loss": 3.7001, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085487855772185e-05, + "loss": 3.698, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084650898901507e-05, + "loss": 3.674, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083812304150455e-05, + "loss": 3.7113, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082973709399403e-05, + "loss": 3.6921, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082135114648351e-05, + "loss": 3.704, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.0812981577776716e-05, + "loss": 3.6917, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.0804595630266196e-05, + "loss": 3.6951, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.0796209682755676e-05, + "loss": 3.6839, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.0787840114048885e-05, + "loss": 3.6985, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.0779454166538365e-05, + "loss": 3.6877, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0771068219027845e-05, + "loss": 3.6903, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0762682271517325e-05, + "loss": 3.7057, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0754296324006805e-05, + "loss": 3.6834, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745910376496285e-05, + "loss": 3.6825, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0737524428985765e-05, + "loss": 3.7039, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072913848147525e-05, + "loss": 3.6789, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072076891276846e-05, + "loss": 3.6757, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071238296525794e-05, + "loss": 3.6947, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070399701774742e-05, + "loss": 3.6921, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.06956110702369e-05, + "loss": 3.6848, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068724150153011e-05, + "loss": 3.6942, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067885555401959e-05, + "loss": 3.6736, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067046960650907e-05, + "loss": 3.6872, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066208365899855e-05, + "loss": 3.6958, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065371409029176e-05, + "loss": 3.6903, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064532814278124e-05, + "loss": 3.7, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063694219527072e-05, + "loss": 3.695, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.06285562477602e-05, + "loss": 3.7026, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620186679053415e-05, + "loss": 3.6791, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611800731542895e-05, + "loss": 3.6955, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0603414784032375e-05, + "loss": 3.6914, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0595028836521855e-05, + "loss": 3.678, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0586642889011335e-05, + "loss": 3.6934, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578256941500814e-05, + "loss": 3.6942, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569887372794024e-05, + "loss": 3.6942, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0561501425283504e-05, + "loss": 3.6991, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0553115477772983e-05, + "loss": 3.68, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054472953026246e-05, + "loss": 3.6816, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053634358275194e-05, + "loss": 3.6933, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052795763524142e-05, + "loss": 3.6958, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.05195716877309e-05, + "loss": 3.6919, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051118574022038e-05, + "loss": 3.6929, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050281617151359e-05, + "loss": 3.6978, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049444660280681e-05, + "loss": 3.6907, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048606065529629e-05, + "loss": 3.6877, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047767470778576e-05, + "loss": 3.6824, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046928876027524e-05, + "loss": 3.696, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046090281276472e-05, + "loss": 3.6998, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045253324405793e-05, + "loss": 3.6861, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044414729654741e-05, + "loss": 3.6813, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043576134903689e-05, + "loss": 3.6808, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042737540152638e-05, + "loss": 3.6892, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041898945401586e-05, + "loss": 3.7014, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.041060350650534e-05, + "loss": 3.6839, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040221755899482e-05, + "loss": 3.6855, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.03938316114843e-05, + "loss": 3.6794, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.0385462042777506e-05, + "loss": 3.6869, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.0377076095266986e-05, + "loss": 3.6779, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.0368690147756466e-05, + "loss": 3.688, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.0360304200245946e-05, + "loss": 3.6737, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.0351934631539155e-05, + "loss": 3.693, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0343548684028635e-05, + "loss": 3.683, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.0335162736518115e-05, + "loss": 3.6848, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.0326776789007595e-05, + "loss": 3.6859, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031840722030081e-05, + "loss": 3.6866, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.031003765159402e-05, + "loss": 3.6873, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.03016517040835e-05, + "loss": 3.6856, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029326575657298e-05, + "loss": 3.689, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028487980906246e-05, + "loss": 3.6965, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027651024035567e-05, + "loss": 3.6832, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026812429284515e-05, + "loss": 3.6866, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025973834533463e-05, + "loss": 3.6818, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025135239782411e-05, + "loss": 3.685, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024296645031359e-05, + "loss": 3.6822, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.02345968816068e-05, + "loss": 3.6819, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0226210934096284e-05, + "loss": 3.674, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217824986585764e-05, + "loss": 3.6863, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0209439039075244e-05, + "loss": 3.6828, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0201053091564724e-05, + "loss": 3.6862, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0192667144054204e-05, + "loss": 3.6691, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0184281196543684e-05, + "loss": 3.686, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175895249033164e-05, + "loss": 3.6795, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016752568032637e-05, + "loss": 3.6916, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015913973281585e-05, + "loss": 3.6814, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015077016410906e-05, + "loss": 3.6877, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014238421659854e-05, + "loss": 3.6718, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013399826908802e-05, + "loss": 3.6907, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.01256123215775e-05, + "loss": 3.6916, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011722637406698e-05, + "loss": 3.6903, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010884042655647e-05, + "loss": 3.6886, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010045447904595e-05, + "loss": 3.6901, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009206853153542e-05, + "loss": 3.6812, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008369896282864e-05, + "loss": 3.6932, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007532939412185e-05, + "loss": 3.6742, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006694344661133e-05, + "loss": 3.6869, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005855749910081e-05, + "loss": 3.6745, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005017155159029e-05, + "loss": 3.6865, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.0041801982883496e-05, + "loss": 3.6759, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0033416035372976e-05, + "loss": 3.6754, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0025030087862456e-05, + "loss": 3.6841, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0016644140351936e-05, + "loss": 3.6717, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000825819284142e-05, + "loss": 3.6964, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.851386070251465, + "eval_runtime": 304.0939, + "eval_samples_per_second": 1254.846, + "eval_steps_per_second": 39.215, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.9999872245330896e-05, + "loss": 3.6693, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.9991486297820376e-05, + "loss": 3.6729, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.9983100350309856e-05, + "loss": 3.6783, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9974714402799336e-05, + "loss": 3.6828, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.9966328455288815e-05, + "loss": 3.6839, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.9957942507778295e-05, + "loss": 3.6727, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.9949556560267775e-05, + "loss": 3.6767, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.9941170612757255e-05, + "loss": 3.6724, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.9932801044050464e-05, + "loss": 3.6749, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.9924431475343674e-05, + "loss": 3.6875, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991604552783316e-05, + "loss": 3.6732, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990765958032264e-05, + "loss": 3.6765, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989927363281212e-05, + "loss": 3.673, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.98908876853016e-05, + "loss": 3.6666, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988251811659481e-05, + "loss": 3.6746, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987413216908429e-05, + "loss": 3.6638, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986574622157377e-05, + "loss": 3.6723, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985736027406325e-05, + "loss": 3.6768, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984897432655273e-05, + "loss": 3.6644, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984058837904221e-05, + "loss": 3.6889, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983220243153169e-05, + "loss": 3.6867, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.98238328628249e-05, + "loss": 3.6762, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981544691531438e-05, + "loss": 3.6744, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980706096780386e-05, + "loss": 3.6838, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979867502029334e-05, + "loss": 3.6704, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9790289072782825e-05, + "loss": 3.6738, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781919504076034e-05, + "loss": 3.6745, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9773533556565514e-05, + "loss": 3.6722, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9765147609054994e-05, + "loss": 3.6677, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9756761661544474e-05, + "loss": 3.6717, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748375714033954e-05, + "loss": 3.6787, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973998976652343e-05, + "loss": 3.6819, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973160381901291e-05, + "loss": 3.6827, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972323425030612e-05, + "loss": 3.6742, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.97148483027956e-05, + "loss": 3.6682, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9706462355285076e-05, + "loss": 3.6806, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969807640777456e-05, + "loss": 3.6731, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968969046026404e-05, + "loss": 3.6621, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968132089155726e-05, + "loss": 3.6642, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967293494404673e-05, + "loss": 3.6633, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966454899653621e-05, + "loss": 3.6676, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965616304902569e-05, + "loss": 3.6753, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964777710151517e-05, + "loss": 3.6756, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963939115400465e-05, + "loss": 3.6708, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963100520649413e-05, + "loss": 3.6718, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962263563778734e-05, + "loss": 3.6738, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961424969027682e-05, + "loss": 3.6689, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.96058637427663e-05, + "loss": 3.6729, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959747779525578e-05, + "loss": 3.6449, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.9589108226548996e-05, + "loss": 3.6802, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.9580738657842205e-05, + "loss": 3.6645, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.9572352710331685e-05, + "loss": 3.6778, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.9563966762821165e-05, + "loss": 3.6636, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9555580815310645e-05, + "loss": 3.6636, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9547194867800125e-05, + "loss": 3.6548, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.9538825299093334e-05, + "loss": 3.6707, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.9530439351582814e-05, + "loss": 3.6632, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.9522053404072294e-05, + "loss": 3.6617, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.9513667456561774e-05, + "loss": 3.6719, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.9505281509051254e-05, + "loss": 3.658, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949691194034447e-05, + "loss": 3.6519, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948852599283395e-05, + "loss": 3.6765, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.948014004532343e-05, + "loss": 3.6518, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947175409781291e-05, + "loss": 3.646, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946336815030239e-05, + "loss": 3.6667, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.94549985815956e-05, + "loss": 3.6648, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944661263408508e-05, + "loss": 3.6573, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943822668657456e-05, + "loss": 3.6639, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942984073906404e-05, + "loss": 3.6474, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942145479155352e-05, + "loss": 3.6593, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941308522284673e-05, + "loss": 3.6677, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940469927533621e-05, + "loss": 3.6625, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939631332782569e-05, + "loss": 3.6742, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938792738031517e-05, + "loss": 3.6635, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937954143280465e-05, + "loss": 3.6756, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937117186409786e-05, + "loss": 3.6509, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936278591658734e-05, + "loss": 3.6695, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935439996907682e-05, + "loss": 3.659, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.93460140215663e-05, + "loss": 3.6517, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933762807405578e-05, + "loss": 3.6665, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932924212654526e-05, + "loss": 3.67, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932087255783847e-05, + "loss": 3.6643, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931248661032795e-05, + "loss": 3.6734, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930410066281743e-05, + "loss": 3.6487, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929571471530691e-05, + "loss": 3.6517, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9287328767796385e-05, + "loss": 3.6683, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.92789591990896e-05, + "loss": 3.6673, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927057325157909e-05, + "loss": 3.6636, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926218730406856e-05, + "loss": 3.6673, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925380135655804e-05, + "loss": 3.6651, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924543178785126e-05, + "loss": 3.6645, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923704584034074e-05, + "loss": 3.6592, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922865989283021e-05, + "loss": 3.6558, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922027394531969e-05, + "loss": 3.6698, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921188799780917e-05, + "loss": 3.6687, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9203518429102386e-05, + "loss": 3.6613, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919513248159186e-05, + "loss": 3.6559, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918674653408134e-05, + "loss": 3.6525, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178360586570826e-05, + "loss": 3.6583, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169974639060306e-05, + "loss": 3.6733, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161588691549786e-05, + "loss": 3.6586, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9153202744039265e-05, + "loss": 3.6596, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144833175332475e-05, + "loss": 3.6523, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9136447227821955e-05, + "loss": 3.6564, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.9128061280311434e-05, + "loss": 3.6561, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.9119675332800914e-05, + "loss": 3.6553, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.9111289385290394e-05, + "loss": 3.6484, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.9102919816583604e-05, + "loss": 3.6673, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9094533869073083e-05, + "loss": 3.6578, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9086147921562563e-05, + "loss": 3.6565, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907776197405204e-05, + "loss": 3.6534, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906939240534526e-05, + "loss": 3.6622, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906100645783474e-05, + "loss": 3.6619, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905262051032422e-05, + "loss": 3.6595, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.90442345628137e-05, + "loss": 3.6625, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903584861530318e-05, + "loss": 3.6693, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902746266779266e-05, + "loss": 3.6532, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901909309908587e-05, + "loss": 3.6638, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901070715157535e-05, + "loss": 3.6502, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900232120406483e-05, + "loss": 3.66, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899393525655431e-05, + "loss": 3.656, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898554930904379e-05, + "loss": 3.6529, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8977179740337e-05, + "loss": 3.6509, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896879379282648e-05, + "loss": 3.6585, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8960407845315964e-05, + "loss": 3.6578, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8952021897805444e-05, + "loss": 3.6592, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894365232909865e-05, + "loss": 3.6442, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893526638158813e-05, + "loss": 3.6567, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892688043407761e-05, + "loss": 3.6526, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891849448656709e-05, + "loss": 3.6631, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891010853905657e-05, + "loss": 3.6576, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890173897034978e-05, + "loss": 3.6569, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889335302283926e-05, + "loss": 3.6471, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888496707532874e-05, + "loss": 3.6627, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887658112781822e-05, + "loss": 3.6636, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.88681951803077e-05, + "loss": 3.6631, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885980923279718e-05, + "loss": 3.6617, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885142328528666e-05, + "loss": 3.6621, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884303733777614e-05, + "loss": 3.6563, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883466776906935e-05, + "loss": 3.6664, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882628182155883e-05, + "loss": 3.6481, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881789587404831e-05, + "loss": 3.6593, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880950992653779e-05, + "loss": 3.6518, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8801140357831e-05, + "loss": 3.6572, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879275441032048e-05, + "loss": 3.6486, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878436846280996e-05, + "loss": 3.6487, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877598251529944e-05, + "loss": 3.6579, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876759656778892e-05, + "loss": 3.6533, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8759226999082135e-05, + "loss": 3.6653, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8471181392669678, + "eval_runtime": 303.5207, + "eval_samples_per_second": 1257.216, + "eval_steps_per_second": 39.289, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750841051571615e-05, + "loss": 3.6422, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742455104061095e-05, + "loss": 3.6462, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8734069156550575e-05, + "loss": 3.6486, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.8725683209040055e-05, + "loss": 3.6612, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.8717297261529535e-05, + "loss": 3.6572, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.8708927692822744e-05, + "loss": 3.6446, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.8700541745312224e-05, + "loss": 3.6515, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.8692155797801704e-05, + "loss": 3.6435, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.8683769850291184e-05, + "loss": 3.6478, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8675383902780664e-05, + "loss": 3.663, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866701433407387e-05, + "loss": 3.6468, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865862838656335e-05, + "loss": 3.6473, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865025881785657e-05, + "loss": 3.6579, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864187287034605e-05, + "loss": 3.6356, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863348692283553e-05, + "loss": 3.6464, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862510097532501e-05, + "loss": 3.6387, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861671502781449e-05, + "loss": 3.6474, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860832908030397e-05, + "loss": 3.6493, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859994313279345e-05, + "loss": 3.6358, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859155718528293e-05, + "loss": 3.6611, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858317123777241e-05, + "loss": 3.6607, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857480166906562e-05, + "loss": 3.6518, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.85664157215551e-05, + "loss": 3.6544, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855802977404458e-05, + "loss": 3.6531, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854964382653406e-05, + "loss": 3.647, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854127425782727e-05, + "loss": 3.6448, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853288831031675e-05, + "loss": 3.6529, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852450236280623e-05, + "loss": 3.6485, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.8516116415295706e-05, + "loss": 3.6377, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8507730467785186e-05, + "loss": 3.6454, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.8499344520274666e-05, + "loss": 3.6513, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.8490958572764146e-05, + "loss": 3.6595, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.8482572625253626e-05, + "loss": 3.6551, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.8474203056546835e-05, + "loss": 3.6507, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.8465817109036315e-05, + "loss": 3.6429, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8457431161525795e-05, + "loss": 3.6473, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.8449045214015275e-05, + "loss": 3.6532, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.844067564530849e-05, + "loss": 3.6388, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843228969779797e-05, + "loss": 3.6366, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842390375028745e-05, + "loss": 3.6382, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841551780277693e-05, + "loss": 3.6439, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840713185526641e-05, + "loss": 3.6464, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839876228655962e-05, + "loss": 3.6506, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.83903763390491e-05, + "loss": 3.6475, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838199039153858e-05, + "loss": 3.6475, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837360444402806e-05, + "loss": 3.6464, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836521849651754e-05, + "loss": 3.6429, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835683254900702e-05, + "loss": 3.6527, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834846298030023e-05, + "loss": 3.6182, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.834007703278971e-05, + "loss": 3.6517, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331691085279195e-05, + "loss": 3.6394, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8323305137768675e-05, + "loss": 3.6555, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.8314919190258155e-05, + "loss": 3.6393, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8306533242747635e-05, + "loss": 3.6402, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8298147295237115e-05, + "loss": 3.6273, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8289777726530324e-05, + "loss": 3.6439, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.8281391779019804e-05, + "loss": 3.644, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.8273005831509284e-05, + "loss": 3.6316, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.8264619883998764e-05, + "loss": 3.6497, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.8256233936488244e-05, + "loss": 3.6373, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824786436778145e-05, + "loss": 3.6207, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823947842027093e-05, + "loss": 3.6507, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823109247276041e-05, + "loss": 3.6301, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822270652524989e-05, + "loss": 3.6219, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821433695654311e-05, + "loss": 3.64, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820595100903259e-05, + "loss": 3.6393, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819756506152207e-05, + "loss": 3.6262, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818917911401154e-05, + "loss": 3.6449, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818079316650102e-05, + "loss": 3.624, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.81724072189905e-05, + "loss": 3.6301, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816402127147998e-05, + "loss": 3.6433, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815565170277319e-05, + "loss": 3.6353, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814726575526267e-05, + "loss": 3.6501, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813887980775215e-05, + "loss": 3.6366, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.813049386024163e-05, + "loss": 3.6499, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812212429153485e-05, + "loss": 3.6291, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811373834402433e-05, + "loss": 3.6489, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810535239651381e-05, + "loss": 3.631, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809696644900329e-05, + "loss": 3.6333, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808858050149277e-05, + "loss": 3.6395, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808019455398225e-05, + "loss": 3.6421, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071824985275456e-05, + "loss": 3.6393, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.8063439037764936e-05, + "loss": 3.648, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.8055053090254416e-05, + "loss": 3.622, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.8046667142743896e-05, + "loss": 3.6268, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8038297574037105e-05, + "loss": 3.6415, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029911626526585e-05, + "loss": 3.6457, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8021525679016065e-05, + "loss": 3.6363, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801313973150555e-05, + "loss": 3.6445, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800475378399503e-05, + "loss": 3.6396, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799638421528824e-05, + "loss": 3.6404, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798799826777772e-05, + "loss": 3.6375, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.79796123202672e-05, + "loss": 3.6315, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797122637275668e-05, + "loss": 3.6439, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796285680404989e-05, + "loss": 3.6462, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795447085653937e-05, + "loss": 3.6354, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794608490902885e-05, + "loss": 3.6344, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793769896151833e-05, + "loss": 3.622, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792932939281154e-05, + "loss": 3.6367, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792094344530102e-05, + "loss": 3.6482, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7912557497790505e-05, + "loss": 3.6354, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7904171550279985e-05, + "loss": 3.6384, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895785602769465e-05, + "loss": 3.6287, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.7887416034062674e-05, + "loss": 3.6293, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7879030086552154e-05, + "loss": 3.6355, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.7870644139041634e-05, + "loss": 3.629, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.7862258191531114e-05, + "loss": 3.6248, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785388862282432e-05, + "loss": 3.6436, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.78455026753138e-05, + "loss": 3.6394, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783711672780328e-05, + "loss": 3.6283, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782873078029276e-05, + "loss": 3.6338, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782034483278224e-05, + "loss": 3.6326, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781197526407546e-05, + "loss": 3.6401, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780358931656494e-05, + "loss": 3.6317, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779520336905442e-05, + "loss": 3.6422, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.77868174215439e-05, + "loss": 3.6422, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777843147403338e-05, + "loss": 3.6277, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777006190532659e-05, + "loss": 3.6372, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776167595781607e-05, + "loss": 3.6297, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775329001030555e-05, + "loss": 3.6346, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774490406279502e-05, + "loss": 3.6354, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.77365181152845e-05, + "loss": 3.6268, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.7728148546577716e-05, + "loss": 3.6261, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719762599067196e-05, + "loss": 3.635, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.7711376651556676e-05, + "loss": 3.6336, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.7702990704046156e-05, + "loss": 3.6347, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769462113533937e-05, + "loss": 3.6204, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768623518782885e-05, + "loss": 3.63, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.7677849240318325e-05, + "loss": 3.6273, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.7669463292807805e-05, + "loss": 3.639, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.7661077345297285e-05, + "loss": 3.6358, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.7652707776590494e-05, + "loss": 3.6353, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.7644321829079974e-05, + "loss": 3.6191, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.7635935881569454e-05, + "loss": 3.6439, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.7627549934058934e-05, + "loss": 3.6361, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761918036535215e-05, + "loss": 3.6416, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.761079441784163e-05, + "loss": 3.6346, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760240847033111e-05, + "loss": 3.6374, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759402252282059e-05, + "loss": 3.6326, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758563657531007e-05, + "loss": 3.6474, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757726700660328e-05, + "loss": 3.619, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756888105909276e-05, + "loss": 3.639, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756049511158224e-05, + "loss": 3.6263, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755210916407172e-05, + "loss": 3.6316, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754373959536493e-05, + "loss": 3.6266, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753535364785441e-05, + "loss": 3.6274, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752696770034389e-05, + "loss": 3.6321, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751858175283337e-05, + "loss": 3.6295, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.7510212184126584e-05, + "loss": 3.6391, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.84498929977417, + "eval_runtime": 303.5093, + "eval_samples_per_second": 1257.263, + "eval_steps_per_second": 39.29, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.7501826236616064e-05, + "loss": 3.6229, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.7493440289105544e-05, + "loss": 3.6228, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7485054341595024e-05, + "loss": 3.6246, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7476668394084504e-05, + "loss": 3.6377, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746829882537771e-05, + "loss": 3.6372, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745991287786719e-05, + "loss": 3.6197, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745152693035667e-05, + "loss": 3.6257, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744314098284615e-05, + "loss": 3.6208, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743475503533563e-05, + "loss": 3.6273, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742638546662884e-05, + "loss": 3.637, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741799951911832e-05, + "loss": 3.6227, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.74096135716078e-05, + "loss": 3.6257, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740122762409728e-05, + "loss": 3.6342, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739284167658677e-05, + "loss": 3.6138, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738447210787998e-05, + "loss": 3.6218, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737608616036946e-05, + "loss": 3.6123, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736770021285894e-05, + "loss": 3.6244, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735931426534842e-05, + "loss": 3.6272, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.7350944696641626e-05, + "loss": 3.6148, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7342558749131106e-05, + "loss": 3.6343, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7334172801620586e-05, + "loss": 3.6383, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7325786854110066e-05, + "loss": 3.6286, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7317417285403275e-05, + "loss": 3.6298, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7309031337892755e-05, + "loss": 3.6288, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.7300645390382235e-05, + "loss": 3.6279, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729225944287172e-05, + "loss": 3.6223, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728388987416493e-05, + "loss": 3.6246, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727550392665441e-05, + "loss": 3.6302, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726711797914389e-05, + "loss": 3.6149, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725873203163337e-05, + "loss": 3.6226, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725036246292658e-05, + "loss": 3.6306, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724197651541606e-05, + "loss": 3.6298, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723359056790554e-05, + "loss": 3.6386, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722520462039502e-05, + "loss": 3.6264, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.72168186728845e-05, + "loss": 3.6207, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720844910417771e-05, + "loss": 3.6239, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.720006315666719e-05, + "loss": 3.6301, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191677209156676e-05, + "loss": 3.614, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7183291261646155e-05, + "loss": 3.616, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174921692939365e-05, + "loss": 3.619, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7166535745428845e-05, + "loss": 3.617, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.7158149797918324e-05, + "loss": 3.6257, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7149763850407804e-05, + "loss": 3.6266, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.7141394281701014e-05, + "loss": 3.6255, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.7133008334190493e-05, + "loss": 3.6192, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.7124622386679973e-05, + "loss": 3.6279, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7116236439169453e-05, + "loss": 3.6192, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7107850491658927e-05, + "loss": 3.6303, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709948092295214e-05, + "loss": 3.5981, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709109497544163e-05, + "loss": 3.626, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.70827090279311e-05, + "loss": 3.6181, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707432308042058e-05, + "loss": 3.6317, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.70659535117138e-05, + "loss": 3.6161, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705756756420328e-05, + "loss": 3.6157, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704918161669275e-05, + "loss": 3.6091, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704079566918223e-05, + "loss": 3.6181, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703242610047545e-05, + "loss": 3.6265, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702404015296493e-05, + "loss": 3.6053, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.70156542054544e-05, + "loss": 3.6306, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700726825794388e-05, + "loss": 3.6147, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699888231043337e-05, + "loss": 3.596, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6990512741726576e-05, + "loss": 3.6298, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6982126794216056e-05, + "loss": 3.6095, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6973740846705536e-05, + "loss": 3.5994, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.6965354899195016e-05, + "loss": 3.6204, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6956985330488225e-05, + "loss": 3.6186, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.6948599382977705e-05, + "loss": 3.6022, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.6940213435467185e-05, + "loss": 3.6245, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.6931827487956665e-05, + "loss": 3.6008, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923441540446145e-05, + "loss": 3.6076, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.6915071971739354e-05, + "loss": 3.6194, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6906686024228834e-05, + "loss": 3.6159, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689830007671832e-05, + "loss": 3.6231, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.68899141292078e-05, + "loss": 3.6163, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688154456050101e-05, + "loss": 3.6268, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687315861299049e-05, + "loss": 3.6102, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686477266547997e-05, + "loss": 3.6261, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685638671796945e-05, + "loss": 3.6072, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684801714926266e-05, + "loss": 3.6089, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683963120175214e-05, + "loss": 3.6188, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683124525424162e-05, + "loss": 3.6164, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.68228593067311e-05, + "loss": 3.6213, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681448973802431e-05, + "loss": 3.6251, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680610379051379e-05, + "loss": 3.6057, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.6797717843003274e-05, + "loss": 3.6051, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.6789331895492754e-05, + "loss": 3.6165, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678096232678596e-05, + "loss": 3.6255, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677257637927544e-05, + "loss": 3.6118, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676419043176492e-05, + "loss": 3.6228, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.67558044842544e-05, + "loss": 3.6189, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674743491554761e-05, + "loss": 3.6187, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673904896803709e-05, + "loss": 3.6156, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673066302052657e-05, + "loss": 3.6086, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672227707301605e-05, + "loss": 3.6218, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671390750430926e-05, + "loss": 3.622, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670552155679874e-05, + "loss": 3.6185, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669713560928822e-05, + "loss": 3.6082, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668874966177771e-05, + "loss": 3.6005, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668038009307092e-05, + "loss": 3.6153, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.66719941455604e-05, + "loss": 3.6235, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666360819804988e-05, + "loss": 3.6148, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665522225053936e-05, + "loss": 3.6148, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664683630302884e-05, + "loss": 3.6087, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6638466734322046e-05, + "loss": 3.6064, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6630080786811526e-05, + "loss": 3.6171, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6621694839301006e-05, + "loss": 3.6032, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6613308891790486e-05, + "loss": 3.605, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604939323083695e-05, + "loss": 3.6197, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6596553375573175e-05, + "loss": 3.6179, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658816742806266e-05, + "loss": 3.6097, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657978148055214e-05, + "loss": 3.6089, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657139553304162e-05, + "loss": 3.6069, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656302596433483e-05, + "loss": 3.622, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655464001682431e-05, + "loss": 3.6095, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654625406931379e-05, + "loss": 3.6216, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653786812180327e-05, + "loss": 3.6192, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652948217429275e-05, + "loss": 3.6097, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652111260558596e-05, + "loss": 3.6125, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651272665807544e-05, + "loss": 3.6121, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650434071056492e-05, + "loss": 3.6116, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.64959547630544e-05, + "loss": 3.617, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.6487585194347615e-05, + "loss": 3.6021, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6479199246837095e-05, + "loss": 3.6042, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6470813299326575e-05, + "loss": 3.6122, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6462427351816055e-05, + "loss": 3.6127, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6454057783109264e-05, + "loss": 3.6117, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6445671835598744e-05, + "loss": 3.6015, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.6437285888088224e-05, + "loss": 3.6092, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6428899940577704e-05, + "loss": 3.6029, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642051399306718e-05, + "loss": 3.6209, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641214442436039e-05, + "loss": 3.6102, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640375847684987e-05, + "loss": 3.6153, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639537252933935e-05, + "loss": 3.5988, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638698658182883e-05, + "loss": 3.6217, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637861701312205e-05, + "loss": 3.6121, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637023106561153e-05, + "loss": 3.6209, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636184511810101e-05, + "loss": 3.6186, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635345917059048e-05, + "loss": 3.6132, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.63450896018837e-05, + "loss": 3.6098, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633670365437318e-05, + "loss": 3.6263, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632831770686265e-05, + "loss": 3.599, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631993175935213e-05, + "loss": 3.6154, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631154581184161e-05, + "loss": 3.6064, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630317624313483e-05, + "loss": 3.6116, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629479029562431e-05, + "loss": 3.605, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628640434811379e-05, + "loss": 3.6046, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627801840060327e-05, + "loss": 3.6071, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6269632453092747e-05, + "loss": 3.6145, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6261262884385956e-05, + "loss": 3.6146, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8437137603759766, + "eval_runtime": 307.4998, + "eval_samples_per_second": 1240.947, + "eval_steps_per_second": 38.781, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6252876936875436e-05, + "loss": 3.6047, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6244490989364916e-05, + "loss": 3.5985, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6236105041854396e-05, + "loss": 3.6014, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.6227735473147605e-05, + "loss": 3.6178, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.6219349525637085e-05, + "loss": 3.6154, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.6210963578126565e-05, + "loss": 3.5991, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.6202577630616045e-05, + "loss": 3.6056, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.6194191683105524e-05, + "loss": 3.6009, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618582211439874e-05, + "loss": 3.6069, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617743616688822e-05, + "loss": 3.6121, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.61690502193777e-05, + "loss": 3.608, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616066427186718e-05, + "loss": 3.6037, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615229470316039e-05, + "loss": 3.6143, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614390875564987e-05, + "loss": 3.5925, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613552280813935e-05, + "loss": 3.6025, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612713686062883e-05, + "loss": 3.5898, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611875091311831e-05, + "loss": 3.6088, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611038134441152e-05, + "loss": 3.6096, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.6101995396901e-05, + "loss": 3.5901, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609360944939048e-05, + "loss": 3.6124, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608522350187996e-05, + "loss": 3.6192, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.6076853933173174e-05, + "loss": 3.6065, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6068467985662654e-05, + "loss": 3.6115, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.6060082038152134e-05, + "loss": 3.6091, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051696090641614e-05, + "loss": 3.6064, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604332652193482e-05, + "loss": 3.6014, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.60349405744243e-05, + "loss": 3.6016, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602655462691378e-05, + "loss": 3.6072, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601816867940326e-05, + "loss": 3.5951, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600979911069647e-05, + "loss": 3.603, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600141316318595e-05, + "loss": 3.6101, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599302721567543e-05, + "loss": 3.6127, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598464126816491e-05, + "loss": 3.6076, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597627169945813e-05, + "loss": 3.6156, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596788575194761e-05, + "loss": 3.5964, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595949980443709e-05, + "loss": 3.6061, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595111385692657e-05, + "loss": 3.6119, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.5942744288219777e-05, + "loss": 3.5905, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5934358340709257e-05, + "loss": 3.5982, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.5925972393198737e-05, + "loss": 3.5966, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.5917586445688216e-05, + "loss": 3.5968, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5909200498177696e-05, + "loss": 3.6014, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5900830929470906e-05, + "loss": 3.6085, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892444981960385e-05, + "loss": 3.6043, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5884059034449865e-05, + "loss": 3.6024, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5875673086939345e-05, + "loss": 3.6055, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586730351823256e-05, + "loss": 3.5975, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585891757072204e-05, + "loss": 3.6089, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.585053162321152e-05, + "loss": 3.5835, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5842145675701e-05, + "loss": 3.6029, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583377610699421e-05, + "loss": 3.5961, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582539015948369e-05, + "loss": 3.6102, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581700421197317e-05, + "loss": 3.5988, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580861826446265e-05, + "loss": 3.5941, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580023231695213e-05, + "loss": 3.5887, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579186274824534e-05, + "loss": 3.5988, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578347680073482e-05, + "loss": 3.6066, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.57750908532243e-05, + "loss": 3.5834, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5766704905713786e-05, + "loss": 3.6087, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.5758335337006995e-05, + "loss": 3.5987, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.5749949389496475e-05, + "loss": 3.5734, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.5741563441985955e-05, + "loss": 3.6086, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5733177494475435e-05, + "loss": 3.5881, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572479154696491e-05, + "loss": 3.581, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.5716421978258124e-05, + "loss": 3.5959, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.5708036030747604e-05, + "loss": 3.5976, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.5699650083237084e-05, + "loss": 3.5861, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569126413572656e-05, + "loss": 3.6048, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568289456701977e-05, + "loss": 3.5771, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567450861950925e-05, + "loss": 3.5869, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566612267199873e-05, + "loss": 3.6005, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565773672448821e-05, + "loss": 3.6002, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564936715578143e-05, + "loss": 3.5998, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564098120827091e-05, + "loss": 3.5986, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563259526076038e-05, + "loss": 3.6039, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562420931324986e-05, + "loss": 3.5907, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561583974454308e-05, + "loss": 3.6053, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560745379703255e-05, + "loss": 3.5893, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559906784952203e-05, + "loss": 3.5865, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559068190201151e-05, + "loss": 3.5953, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5582312333304726e-05, + "loss": 3.5991, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5573926385794206e-05, + "loss": 3.6, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.5565540438283686e-05, + "loss": 3.6056, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5557154490773166e-05, + "loss": 3.5885, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.5548768543262646e-05, + "loss": 3.5821, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.5540398974555855e-05, + "loss": 3.5991, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.5532013027045335e-05, + "loss": 3.6063, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5523627079534815e-05, + "loss": 3.5915, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5515241132024295e-05, + "loss": 3.6014, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.5506871563317504e-05, + "loss": 3.6023, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.5498485615806984e-05, + "loss": 3.595, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.5490099668296464e-05, + "loss": 3.595, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.5481713720785944e-05, + "loss": 3.5898, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547334415207916e-05, + "loss": 3.6019, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546495820456864e-05, + "loss": 3.6025, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545657225705812e-05, + "loss": 3.5968, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.54481863095476e-05, + "loss": 3.5919, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543981674084081e-05, + "loss": 3.5806, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543143079333029e-05, + "loss": 3.5923, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542304484581977e-05, + "loss": 3.6044, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541465889830925e-05, + "loss": 3.5943, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540628932960246e-05, + "loss": 3.5955, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539790338209194e-05, + "loss": 3.5892, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538951743458142e-05, + "loss": 3.589, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.53811314870709e-05, + "loss": 3.5931, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.5372745539560385e-05, + "loss": 3.5895, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.5364375970853594e-05, + "loss": 3.5849, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.5355990023343074e-05, + "loss": 3.5994, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.5347604075832554e-05, + "loss": 3.5948, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.5339218128322034e-05, + "loss": 3.5902, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533084855961524e-05, + "loss": 3.5917, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532246261210472e-05, + "loss": 3.5857, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.53140766645942e-05, + "loss": 3.6006, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530569071708368e-05, + "loss": 3.5905, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529730476957316e-05, + "loss": 3.5997, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528893520086637e-05, + "loss": 3.5987, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528054925335585e-05, + "loss": 3.5911, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527217968464907e-05, + "loss": 3.5974, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526379373713855e-05, + "loss": 3.5937, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525540778962803e-05, + "loss": 3.5916, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524702184211751e-05, + "loss": 3.596, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523863589460699e-05, + "loss": 3.5848, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523024994709647e-05, + "loss": 3.586, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522186399958595e-05, + "loss": 3.5941, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521347805207543e-05, + "loss": 3.5912, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.5205108483368636e-05, + "loss": 3.592, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5196722535858116e-05, + "loss": 3.5831, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.5188336588347596e-05, + "loss": 3.5862, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.5179950640837076e-05, + "loss": 3.587, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.5171564693326556e-05, + "loss": 3.6034, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516319512461977e-05, + "loss": 3.588, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515480917710925e-05, + "loss": 3.5981, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514642322959873e-05, + "loss": 3.58, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513803728208821e-05, + "loss": 3.5969, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512966771338142e-05, + "loss": 3.5947, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.51212817658709e-05, + "loss": 3.6002, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511289581836038e-05, + "loss": 3.5995, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510450987084986e-05, + "loss": 3.5926, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509614030214307e-05, + "loss": 3.5945, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508775435463255e-05, + "loss": 3.6006, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507936840712203e-05, + "loss": 3.5847, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507098245961151e-05, + "loss": 3.5935, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.5062612890904726e-05, + "loss": 3.5899, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.5054226943394205e-05, + "loss": 3.5893, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.5045840995883685e-05, + "loss": 3.583, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.5037455048373165e-05, + "loss": 3.5883, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5029085479666374e-05, + "loss": 3.5866, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.5020699532155854e-05, + "loss": 3.5901, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.5012313584645334e-05, + "loss": 3.5942, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.84253191947937, + "eval_runtime": 306.957, + "eval_samples_per_second": 1243.141, + "eval_steps_per_second": 38.849, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500392763713481e-05, + "loss": 3.5996, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499554168962429e-05, + "loss": 3.5765, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498715574211377e-05, + "loss": 3.5863, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497876979460325e-05, + "loss": 3.5967, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.497040022589646e-05, + "loss": 3.592, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496201427838594e-05, + "loss": 3.5815, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495362833087542e-05, + "loss": 3.5906, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.49452423833649e-05, + "loss": 3.5819, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493687281465811e-05, + "loss": 3.5853, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492848686714759e-05, + "loss": 3.5896, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.492010091963707e-05, + "loss": 3.5934, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491171497212655e-05, + "loss": 3.5825, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490334540341976e-05, + "loss": 3.5965, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489495945590924e-05, + "loss": 3.5686, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488657350839872e-05, + "loss": 3.5854, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.48781875608882e-05, + "loss": 3.5717, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486980161337768e-05, + "loss": 3.5868, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.48614320446709e-05, + "loss": 3.5919, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485304609716038e-05, + "loss": 3.5717, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484466014964986e-05, + "loss": 3.5892, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483627420213934e-05, + "loss": 3.6002, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.4827904633432546e-05, + "loss": 3.5857, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.4819518685922026e-05, + "loss": 3.5936, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.4811132738411506e-05, + "loss": 3.5909, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.4802746790900986e-05, + "loss": 3.5898, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4794377222194195e-05, + "loss": 3.5851, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4785991274683675e-05, + "loss": 3.5803, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4777605327173155e-05, + "loss": 3.59, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4769219379662635e-05, + "loss": 3.5756, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.476084981095585e-05, + "loss": 3.582, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475246386344533e-05, + "loss": 3.5945, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474407791593481e-05, + "loss": 3.5902, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473569196842429e-05, + "loss": 3.5872, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.47273223997175e-05, + "loss": 3.5968, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471893645220698e-05, + "loss": 3.5784, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471055050469646e-05, + "loss": 3.5858, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470216455718594e-05, + "loss": 3.587, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469379498847915e-05, + "loss": 3.5739, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468540904096863e-05, + "loss": 3.5814, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467702309345811e-05, + "loss": 3.5792, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466863714594759e-05, + "loss": 3.5752, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466025119843707e-05, + "loss": 3.5824, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.4651881629730284e-05, + "loss": 3.5909, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.4643495682219764e-05, + "loss": 3.5845, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.4635109734709244e-05, + "loss": 3.584, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4626723787198724e-05, + "loss": 3.5877, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461835421849193e-05, + "loss": 3.5765, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460996827098141e-05, + "loss": 3.5879, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460158232347089e-05, + "loss": 3.568, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459319637596037e-05, + "loss": 3.5834, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458482680725358e-05, + "loss": 3.5771, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457644085974306e-05, + "loss": 3.5928, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456805491223254e-05, + "loss": 3.579, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455966896472202e-05, + "loss": 3.5735, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455129939601524e-05, + "loss": 3.5719, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454291344850472e-05, + "loss": 3.5778, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.45345275009942e-05, + "loss": 3.5889, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452614155348368e-05, + "loss": 3.5613, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451777198477689e-05, + "loss": 3.5909, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450938603726637e-05, + "loss": 3.579, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450100008975585e-05, + "loss": 3.5584, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449261414224533e-05, + "loss": 3.5886, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.4484244573538536e-05, + "loss": 3.5696, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.4475858626028016e-05, + "loss": 3.564, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.4467472678517496e-05, + "loss": 3.5722, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4459086731006976e-05, + "loss": 3.5815, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445071716230019e-05, + "loss": 3.5727, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444233121478967e-05, + "loss": 3.5774, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443394526727915e-05, + "loss": 3.5641, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442555931976863e-05, + "loss": 3.5665, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441718975106184e-05, + "loss": 3.5798, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440880380355132e-05, + "loss": 3.5845, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.44004178560408e-05, + "loss": 3.5814, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439203190853028e-05, + "loss": 3.5787, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438366233982349e-05, + "loss": 3.5863, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437527639231297e-05, + "loss": 3.5729, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436689044480245e-05, + "loss": 3.5838, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435850449729193e-05, + "loss": 3.5747, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.4350134928585145e-05, + "loss": 3.5701, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.4341748981074625e-05, + "loss": 3.5808, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.4333363033564105e-05, + "loss": 3.5725, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.4324977086053585e-05, + "loss": 3.5856, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.4316607517346794e-05, + "loss": 3.5888, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4308221569836274e-05, + "loss": 3.5743, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.4299835622325754e-05, + "loss": 3.5583, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4291449674815234e-05, + "loss": 3.5797, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428308010610844e-05, + "loss": 3.5835, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427469415859792e-05, + "loss": 3.5779, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.42663082110874e-05, + "loss": 3.5821, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425792226357688e-05, + "loss": 3.5852, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.42495526948701e-05, + "loss": 3.5747, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424116674735958e-05, + "loss": 3.5786, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423278079984906e-05, + "loss": 3.5698, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422439485233854e-05, + "loss": 3.5843, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421602528363175e-05, + "loss": 3.5842, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420763933612123e-05, + "loss": 3.5792, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419925338861071e-05, + "loss": 3.5733, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419086744110018e-05, + "loss": 3.5636, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.41824978723934e-05, + "loss": 3.574, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417411192488288e-05, + "loss": 3.5873, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416572597737236e-05, + "loss": 3.5791, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415734002986184e-05, + "loss": 3.571, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414897046115505e-05, + "loss": 3.5719, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414058451364453e-05, + "loss": 3.5712, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413219856613401e-05, + "loss": 3.5761, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4123812618623486e-05, + "loss": 3.5744, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.41154430499167e-05, + "loss": 3.568, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410705710240618e-05, + "loss": 3.577, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.4098671154895655e-05, + "loss": 3.577, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4090285207385135e-05, + "loss": 3.5724, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408191563867835e-05, + "loss": 3.5706, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407352969116783e-05, + "loss": 3.5701, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406514374365731e-05, + "loss": 3.5817, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405675779614679e-05, + "loss": 3.572, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404837184863627e-05, + "loss": 3.578, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4040002279929486e-05, + "loss": 3.5786, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403161633241896e-05, + "loss": 3.5766, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.4023246763712175e-05, + "loss": 3.5802, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.4014860816201655e-05, + "loss": 3.5726, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400647486869113e-05, + "loss": 3.5769, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399808892118061e-05, + "loss": 3.5766, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398970297367009e-05, + "loss": 3.5648, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398131702615957e-05, + "loss": 3.5721, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397293107864905e-05, + "loss": 3.5706, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396454513113853e-05, + "loss": 3.5726, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3956175562431744e-05, + "loss": 3.5762, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3947789614921224e-05, + "loss": 3.5662, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3939403667410704e-05, + "loss": 3.5649, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3931017719900184e-05, + "loss": 3.57, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392264815119339e-05, + "loss": 3.5847, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391426220368287e-05, + "loss": 3.5712, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390587625617235e-05, + "loss": 3.5777, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389749030866183e-05, + "loss": 3.5632, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388912073995504e-05, + "loss": 3.578, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388073479244452e-05, + "loss": 3.5787, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3872348844934e-05, + "loss": 3.5793, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386396289742348e-05, + "loss": 3.5795, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.38555933287167e-05, + "loss": 3.573, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384720738120618e-05, + "loss": 3.583, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383882143369566e-05, + "loss": 3.5856, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383043548618514e-05, + "loss": 3.5657, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382206591747835e-05, + "loss": 3.5756, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381367996996783e-05, + "loss": 3.5692, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.3805294022457307e-05, + "loss": 3.5731, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.3796908074946787e-05, + "loss": 3.5645, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788538506239996e-05, + "loss": 3.5727, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3780152558729476e-05, + "loss": 3.5682, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3771766611218956e-05, + "loss": 3.5722, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3763380663708435e-05, + "loss": 3.5746, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.8426942825317383, + "eval_runtime": 303.4119, + "eval_samples_per_second": 1257.667, + "eval_steps_per_second": 39.303, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375501109500165e-05, + "loss": 3.577, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374662514749113e-05, + "loss": 3.5589, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373823919998061e-05, + "loss": 3.5669, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372985325247009e-05, + "loss": 3.5802, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.37214836837633e-05, + "loss": 3.5729, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371309773625278e-05, + "loss": 3.5698, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370471178874226e-05, + "loss": 3.5701, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369632584123174e-05, + "loss": 3.562, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368795627252495e-05, + "loss": 3.5668, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367957032501443e-05, + "loss": 3.5764, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367118437750391e-05, + "loss": 3.5714, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366279842999339e-05, + "loss": 3.568, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.3654428861286605e-05, + "loss": 3.5823, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.3646042913776085e-05, + "loss": 3.5488, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3637656966265565e-05, + "loss": 3.566, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.3629271018755045e-05, + "loss": 3.5524, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.3620901450048254e-05, + "loss": 3.5738, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.3612515502537734e-05, + "loss": 3.5693, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.3604129555027214e-05, + "loss": 3.5577, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.3595743607516694e-05, + "loss": 3.5673, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.35873740388099e-05, + "loss": 3.5885, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357898809129938e-05, + "loss": 3.5687, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357060214378886e-05, + "loss": 3.5745, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356221619627834e-05, + "loss": 3.5773, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355384662757156e-05, + "loss": 3.5749, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354546068006104e-05, + "loss": 3.5623, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353707473255052e-05, + "loss": 3.5642, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352868878504e-05, + "loss": 3.5736, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.352031921633321e-05, + "loss": 3.5562, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351193326882269e-05, + "loss": 3.5637, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350354732131217e-05, + "loss": 3.5753, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349516137380165e-05, + "loss": 3.5759, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348679180509486e-05, + "loss": 3.5737, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.3478405857584337e-05, + "loss": 3.577, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3470019910073817e-05, + "loss": 3.5596, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.3461633962563296e-05, + "loss": 3.5702, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345326439385651e-05, + "loss": 3.5726, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344487844634599e-05, + "loss": 3.5538, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343649249883547e-05, + "loss": 3.5666, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342810655132495e-05, + "loss": 3.5606, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341972060381443e-05, + "loss": 3.5582, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341135103510764e-05, + "loss": 3.5649, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340296508759712e-05, + "loss": 3.5801, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.33945791400866e-05, + "loss": 3.5618, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338619319257608e-05, + "loss": 3.568, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337782362386929e-05, + "loss": 3.5689, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336943767635877e-05, + "loss": 3.5606, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336105172884825e-05, + "loss": 3.5697, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335266578133773e-05, + "loss": 3.5515, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.3344296212630946e-05, + "loss": 3.5638, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.3335910265120426e-05, + "loss": 3.5647, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.3327524317609906e-05, + "loss": 3.5735, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.3319138370099386e-05, + "loss": 3.5661, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.3310768801392595e-05, + "loss": 3.5565, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.3302382853882075e-05, + "loss": 3.556, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.3293996906371555e-05, + "loss": 3.5585, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.3285610958861035e-05, + "loss": 3.5742, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.3277241390154244e-05, + "loss": 3.5484, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.3268855442643724e-05, + "loss": 3.5709, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.3260469495133204e-05, + "loss": 3.5605, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.3252083547622684e-05, + "loss": 3.545, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.3243697600112164e-05, + "loss": 3.5706, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323532803140538e-05, + "loss": 3.5562, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322694208389486e-05, + "loss": 3.5455, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321855613638433e-05, + "loss": 3.5528, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.321017018887381e-05, + "loss": 3.5645, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320180062016703e-05, + "loss": 3.5579, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319341467265651e-05, + "loss": 3.5545, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318502872514598e-05, + "loss": 3.5527, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317664277763546e-05, + "loss": 3.5509, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316827320892868e-05, + "loss": 3.5607, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315988726141816e-05, + "loss": 3.5651, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315150131390764e-05, + "loss": 3.5641, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314311536639712e-05, + "loss": 3.5665, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313474579769033e-05, + "loss": 3.5656, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.3126359850179806e-05, + "loss": 3.5555, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.3117973902669286e-05, + "loss": 3.5653, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3109587955158766e-05, + "loss": 3.5604, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310121838645198e-05, + "loss": 3.5565, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.3092832438941455e-05, + "loss": 3.5561, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.3084446491430935e-05, + "loss": 3.5582, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.3076060543920415e-05, + "loss": 3.5685, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3067690975213624e-05, + "loss": 3.5704, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305930502770311e-05, + "loss": 3.5598, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.305091908019259e-05, + "loss": 3.5416, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304253313268207e-05, + "loss": 3.5614, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303416356397528e-05, + "loss": 3.5654, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302577761646476e-05, + "loss": 3.5635, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301739166895424e-05, + "loss": 3.5595, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300900572144372e-05, + "loss": 3.571, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300063615273693e-05, + "loss": 3.5581, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299225020522641e-05, + "loss": 3.5615, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298386425771589e-05, + "loss": 3.5566, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297547831020537e-05, + "loss": 3.5669, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296710874149858e-05, + "loss": 3.5677, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.2958722793988065e-05, + "loss": 3.5667, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.2950336846477545e-05, + "loss": 3.5522, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.2941950898967025e-05, + "loss": 3.5489, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.2933581330260234e-05, + "loss": 3.554, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.2925195382749714e-05, + "loss": 3.5704, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.2916809435239194e-05, + "loss": 3.562, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.2908423487728674e-05, + "loss": 3.5571, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.290005391902188e-05, + "loss": 3.5555, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289166797151136e-05, + "loss": 3.5524, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288328202400084e-05, + "loss": 3.56, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287489607649032e-05, + "loss": 3.5575, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286652650778353e-05, + "loss": 3.5515, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285814056027302e-05, + "loss": 3.5637, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.28497546127625e-05, + "loss": 3.5616, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284136866525198e-05, + "loss": 3.5528, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283298271774146e-05, + "loss": 3.5563, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282461314903467e-05, + "loss": 3.5525, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281622720152415e-05, + "loss": 3.5667, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280784125401363e-05, + "loss": 3.5584, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279945530650311e-05, + "loss": 3.5617, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.2791085737796316e-05, + "loss": 3.5584, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.2782699790285796e-05, + "loss": 3.5642, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.2774330221579005e-05, + "loss": 3.5625, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.2765944274068485e-05, + "loss": 3.5547, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275755832655797e-05, + "loss": 3.5614, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274917237904745e-05, + "loss": 3.5555, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.274078643153693e-05, + "loss": 3.549, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273240048402641e-05, + "loss": 3.5545, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272401453651589e-05, + "loss": 3.5567, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271562858900537e-05, + "loss": 3.559, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270725902029858e-05, + "loss": 3.5537, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269887307278806e-05, + "loss": 3.5529, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.269048712527754e-05, + "loss": 3.5502, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268210117776702e-05, + "loss": 3.5534, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267373160906023e-05, + "loss": 3.5664, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266534566154971e-05, + "loss": 3.5567, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265695971403919e-05, + "loss": 3.5636, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264857376652867e-05, + "loss": 3.5459, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.2640204197821886e-05, + "loss": 3.5629, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.2631818250311366e-05, + "loss": 3.5625, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.2623432302800846e-05, + "loss": 3.5641, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.2615046355290326e-05, + "loss": 3.5588, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.2606676786583535e-05, + "loss": 3.5575, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.2598290839073015e-05, + "loss": 3.5689, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.2589904891562495e-05, + "loss": 3.5653, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2581518944051975e-05, + "loss": 3.551, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.2573149375345184e-05, + "loss": 3.558, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.2564763427834664e-05, + "loss": 3.5552, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.2556377480324144e-05, + "loss": 3.5563, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.2547991532813624e-05, + "loss": 3.5455, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253962196410684e-05, + "loss": 3.5598, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253123601659632e-05, + "loss": 3.549, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.25228500690858e-05, + "loss": 3.5623, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251446412157528e-05, + "loss": 3.5513, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.8426969051361084, + "eval_runtime": 303.8327, + "eval_samples_per_second": 1255.925, + "eval_steps_per_second": 39.249, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250609455286849e-05, + "loss": 3.5697, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249770860535797e-05, + "loss": 3.5438, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248932265784745e-05, + "loss": 3.5475, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248093671033693e-05, + "loss": 3.5637, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247256714163014e-05, + "loss": 3.5595, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246418119411962e-05, + "loss": 3.5524, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.24557952466091e-05, + "loss": 3.5494, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244740929909858e-05, + "loss": 3.5445, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243903973039179e-05, + "loss": 3.551, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243065378288127e-05, + "loss": 3.5584, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242226783537075e-05, + "loss": 3.557, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241388188786023e-05, + "loss": 3.555, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240551231915344e-05, + "loss": 3.5608, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239712637164292e-05, + "loss": 3.5361, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.23887404241324e-05, + "loss": 3.547, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238035447662188e-05, + "loss": 3.5399, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237198490791509e-05, + "loss": 3.555, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236359896040457e-05, + "loss": 3.5477, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235521301289405e-05, + "loss": 3.546, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234682706538353e-05, + "loss": 3.5508, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233845749667675e-05, + "loss": 3.5703, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.233007154916623e-05, + "loss": 3.5542, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232168560165571e-05, + "loss": 3.5561, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231329965414518e-05, + "loss": 3.5575, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2304930085438396e-05, + "loss": 3.5668, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2296544137927876e-05, + "loss": 3.5411, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2288158190417356e-05, + "loss": 3.5492, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227977224290683e-05, + "loss": 3.559, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2271402674200045e-05, + "loss": 3.5383, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.2263016726689525e-05, + "loss": 3.5491, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.2254630779179005e-05, + "loss": 3.5578, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.2246244831668485e-05, + "loss": 3.5595, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.22378752629617e-05, + "loss": 3.556, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222948931545118e-05, + "loss": 3.5607, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.2221103367940654e-05, + "loss": 3.5448, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.2212717420430134e-05, + "loss": 3.5575, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220434785172335e-05, + "loss": 3.5528, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219596190421283e-05, + "loss": 3.5402, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.21875759567023e-05, + "loss": 3.5529, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217919000919178e-05, + "loss": 3.5421, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2170820440485e-05, + "loss": 3.5435, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216243449297447e-05, + "loss": 3.5473, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215404854546396e-05, + "loss": 3.5627, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214566259795344e-05, + "loss": 3.5439, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.2137293029246654e-05, + "loss": 3.5565, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212890708173613e-05, + "loss": 3.5512, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212052113422561e-05, + "loss": 3.549, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211213518671509e-05, + "loss": 3.5537, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.21037656180083e-05, + "loss": 3.5362, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2095379670497776e-05, + "loss": 3.5477, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.2086993722987256e-05, + "loss": 3.5466, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.2078607775476736e-05, + "loss": 3.555, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.2070238206769945e-05, + "loss": 3.5518, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2061852259259425e-05, + "loss": 3.538, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205346631174891e-05, + "loss": 3.5373, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204508036423839e-05, + "loss": 3.5428, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.20367107955316e-05, + "loss": 3.5614, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202832484802108e-05, + "loss": 3.5321, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201993890051056e-05, + "loss": 3.5536, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201155295300004e-05, + "loss": 3.5453, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200318338429325e-05, + "loss": 3.529, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199479743678273e-05, + "loss": 3.5504, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198641148927221e-05, + "loss": 3.5432, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197802554176169e-05, + "loss": 3.5315, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.19696559730549e-05, + "loss": 3.5329, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196127002554438e-05, + "loss": 3.5546, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.1952884078033866e-05, + "loss": 3.541, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.1944498130523346e-05, + "loss": 3.5365, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.1936128561816555e-05, + "loss": 3.534, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1927742614306035e-05, + "loss": 3.538, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.1919356666795515e-05, + "loss": 3.5459, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.1910970719284995e-05, + "loss": 3.5497, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.1902601150578204e-05, + "loss": 3.5455, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.1894215203067684e-05, + "loss": 3.5519, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.1885829255557164e-05, + "loss": 3.5493, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.1877443308046643e-05, + "loss": 3.546, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186907373933985e-05, + "loss": 3.5456, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186068779182933e-05, + "loss": 3.5412, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185230184431882e-05, + "loss": 3.5405, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.18439158968083e-05, + "loss": 3.5457, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183554632810151e-05, + "loss": 3.5446, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182716038059099e-05, + "loss": 3.5487, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181877443308047e-05, + "loss": 3.5579, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.181038848556995e-05, + "loss": 3.5427, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180201891686316e-05, + "loss": 3.5272, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179363296935264e-05, + "loss": 3.5444, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178524702184212e-05, + "loss": 3.5517, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.17768610743316e-05, + "loss": 3.553, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1768491505624806e-05, + "loss": 3.5405, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1760105558114286e-05, + "loss": 3.556, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175171961060377e-05, + "loss": 3.5453, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174333366309325e-05, + "loss": 3.5409, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173496409438646e-05, + "loss": 3.5411, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172657814687594e-05, + "loss": 3.5524, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171819219936542e-05, + "loss": 3.5493, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.17098062518549e-05, + "loss": 3.5507, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170143668314811e-05, + "loss": 3.5368, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169305073563759e-05, + "loss": 3.5348, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168466478812707e-05, + "loss": 3.5378, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167627884061655e-05, + "loss": 3.5519, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166790927190976e-05, + "loss": 3.5463, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165952332439924e-05, + "loss": 3.5414, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165113737688872e-05, + "loss": 3.538, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1642751429378207e-05, + "loss": 3.537, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1634381860671416e-05, + "loss": 3.5476, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1625995913160896e-05, + "loss": 3.5379, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.1617609965650376e-05, + "loss": 3.5369, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1609224018139856e-05, + "loss": 3.5474, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.1600854449433065e-05, + "loss": 3.5467, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1592468501922545e-05, + "loss": 3.5387, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.1584082554412025e-05, + "loss": 3.5411, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.1575696606901504e-05, + "loss": 3.535, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.1567327038194714e-05, + "loss": 3.5484, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.1558941090684194e-05, + "loss": 3.5449, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.1550555143173673e-05, + "loss": 3.542, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154216919566316e-05, + "loss": 3.5491, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153379962695637e-05, + "loss": 3.5471, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152543005824958e-05, + "loss": 3.5442, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151704411073906e-05, + "loss": 3.5394, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150865816322854e-05, + "loss": 3.5473, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150027221571802e-05, + "loss": 3.5378, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.14918862682075e-05, + "loss": 3.5344, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148350032069698e-05, + "loss": 3.5421, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147511437318646e-05, + "loss": 3.5396, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146672842567594e-05, + "loss": 3.5449, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145835885696915e-05, + "loss": 3.5331, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144997290945863e-05, + "loss": 3.5436, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.1441586961948114e-05, + "loss": 3.5346, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.1433201014437594e-05, + "loss": 3.5375, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.14248314457308e-05, + "loss": 3.5459, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141644549822028e-05, + "loss": 3.5469, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140805955070976e-05, + "loss": 3.5435, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139967360319924e-05, + "loss": 3.5307, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139130403449245e-05, + "loss": 3.5472, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138291808698193e-05, + "loss": 3.5473, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137453213947141e-05, + "loss": 3.5456, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136614619196089e-05, + "loss": 3.5469, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.13577766232541e-05, + "loss": 3.543, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134939067574358e-05, + "loss": 3.5532, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134100472823307e-05, + "loss": 3.5488, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133261878072255e-05, + "loss": 3.5368, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1324249212015757e-05, + "loss": 3.5419, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1315863264505237e-05, + "loss": 3.539, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1307477316994717e-05, + "loss": 3.5384, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1299091369484196e-05, + "loss": 3.5352, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290721800777406e-05, + "loss": 3.5432, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1282335853266886e-05, + "loss": 3.5335, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1273949905756365e-05, + "loss": 3.5476, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1265563958245845e-05, + "loss": 3.5365, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.844266891479492, + "eval_runtime": 313.2498, + "eval_samples_per_second": 1218.169, + "eval_steps_per_second": 38.069, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.1257194389539055e-05, + "loss": 3.5425, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1248808442028534e-05, + "loss": 3.534, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124042249451802e-05, + "loss": 3.5306, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.12320365470075e-05, + "loss": 3.5471, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122366697830071e-05, + "loss": 3.5462, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121528103079019e-05, + "loss": 3.5397, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120689508327967e-05, + "loss": 3.5338, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119850913576915e-05, + "loss": 3.5291, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.119013956706236e-05, + "loss": 3.541, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118175361955184e-05, + "loss": 3.5413, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117336767204132e-05, + "loss": 3.5407, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.11649817245308e-05, + "loss": 3.5389, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115661215582401e-05, + "loss": 3.5493, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114822620831349e-05, + "loss": 3.5214, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.1139840260802975e-05, + "loss": 3.532, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113145431329245e-05, + "loss": 3.5251, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.1123084744585664e-05, + "loss": 3.5372, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1114698797075144e-05, + "loss": 3.5331, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1106312849564624e-05, + "loss": 3.5315, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.10979269020541e-05, + "loss": 3.5319, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108955733334731e-05, + "loss": 3.5573, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108117138583679e-05, + "loss": 3.5394, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.1072785438326266e-05, + "loss": 3.5364, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.1064399490815746e-05, + "loss": 3.5447, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105602992210896e-05, + "loss": 3.5475, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104764397459844e-05, + "loss": 3.5297, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103925802708792e-05, + "loss": 3.5311, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.10308720795774e-05, + "loss": 3.5459, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102250251087062e-05, + "loss": 3.5246, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.10141165633601e-05, + "loss": 3.5343, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100573061584957e-05, + "loss": 3.5392, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099734466833905e-05, + "loss": 3.547, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.0988975099632267e-05, + "loss": 3.5398, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.098058915212174e-05, + "loss": 3.5425, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097220320461122e-05, + "loss": 3.5304, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.09638172571007e-05, + "loss": 3.5452, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.0955447688393916e-05, + "loss": 3.5387, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0947061740883395e-05, + "loss": 3.522, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.0938675793372875e-05, + "loss": 3.5378, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0930289845862355e-05, + "loss": 3.5252, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092192027715557e-05, + "loss": 3.5328, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.0913534329645044e-05, + "loss": 3.5296, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.0905148382134524e-05, + "loss": 3.5458, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.0896762434624004e-05, + "loss": 3.533, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.0888392865917213e-05, + "loss": 3.535, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.0880006918406693e-05, + "loss": 3.5423, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087162097089617e-05, + "loss": 3.5284, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086323502338565e-05, + "loss": 3.5435, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085486545467887e-05, + "loss": 3.523, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084647950716835e-05, + "loss": 3.5279, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083809355965783e-05, + "loss": 3.5351, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082970761214731e-05, + "loss": 3.5369, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082133804344052e-05, + "loss": 3.5407, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081295209593e-05, + "loss": 3.5217, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080456614841948e-05, + "loss": 3.5283, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079618020090896e-05, + "loss": 3.5236, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078781063220217e-05, + "loss": 3.5479, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077942468469165e-05, + "loss": 3.5161, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077103873718113e-05, + "loss": 3.539, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076265278967061e-05, + "loss": 3.5308, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075428322096382e-05, + "loss": 3.5141, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.07458972734533e-05, + "loss": 3.5347, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073751132594278e-05, + "loss": 3.5288, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072912537843226e-05, + "loss": 3.5144, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072075580972547e-05, + "loss": 3.5208, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071236986221495e-05, + "loss": 3.54, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070398391470443e-05, + "loss": 3.5274, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069559796719391e-05, + "loss": 3.5229, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068722839848712e-05, + "loss": 3.5205, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.06788424509766e-05, + "loss": 3.5222, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067045650346608e-05, + "loss": 3.5291, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066207055595556e-05, + "loss": 3.533, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.0653700987248777e-05, + "loss": 3.5302, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0645315039738256e-05, + "loss": 3.5383, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.0636929092227736e-05, + "loss": 3.5372, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0628543144717216e-05, + "loss": 3.529, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0620173576010425e-05, + "loss": 3.5288, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0611787628499905e-05, + "loss": 3.5267, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.0603401680989385e-05, + "loss": 3.5273, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.0595032112282594e-05, + "loss": 3.5307, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0586646164772074e-05, + "loss": 3.5274, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0578260217261554e-05, + "loss": 3.5372, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.0569874269751034e-05, + "loss": 3.5362, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.0561488322240514e-05, + "loss": 3.5293, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055311875353373e-05, + "loss": 3.516, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054473280602321e-05, + "loss": 3.5262, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053634685851269e-05, + "loss": 3.5407, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052796091100217e-05, + "loss": 3.533, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051959134229538e-05, + "loss": 3.5277, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.051120539478486e-05, + "loss": 3.5427, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.050281944727434e-05, + "loss": 3.5279, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494449878567548e-05, + "loss": 3.5271, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0486063931057028e-05, + "loss": 3.5262, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.047767798354651e-05, + "loss": 3.5368, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.046929203603599e-05, + "loss": 3.5328, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.04609224673292e-05, + "loss": 3.5415, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.045253651981868e-05, + "loss": 3.5174, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.044415057230816e-05, + "loss": 3.5261, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.043576462479764e-05, + "loss": 3.5223, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427395056090853e-05, + "loss": 3.5351, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0419009108580333e-05, + "loss": 3.5373, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410623161069813e-05, + "loss": 3.5219, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0402237213559293e-05, + "loss": 3.5259, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393867644852502e-05, + "loss": 3.5228, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0385481697341982e-05, + "loss": 3.5335, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0377095749831465e-05, + "loss": 3.5182, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368709802320945e-05, + "loss": 3.5255, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360340233614154e-05, + "loss": 3.5313, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0351954286103634e-05, + "loss": 3.5281, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0343568338593114e-05, + "loss": 3.5275, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0335182391082594e-05, + "loss": 3.5307, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326812822375807e-05, + "loss": 3.5181, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318426874865286e-05, + "loss": 3.535, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0310040927354766e-05, + "loss": 3.5301, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301654979844246e-05, + "loss": 3.5272, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293285411137455e-05, + "loss": 3.5359, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284899463626935e-05, + "loss": 3.5322, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276529894920148e-05, + "loss": 3.53, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0268143947409628e-05, + "loss": 3.5224, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259757999899108e-05, + "loss": 3.532, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251372052388588e-05, + "loss": 3.5237, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0242986104878068e-05, + "loss": 3.52, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234600157367548e-05, + "loss": 3.5231, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0226214209857028e-05, + "loss": 3.5272, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217828262346508e-05, + "loss": 3.5289, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.020945869363972e-05, + "loss": 3.5198, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.02010727461292e-05, + "loss": 3.5291, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.019268679861868e-05, + "loss": 3.52, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018430085110816e-05, + "loss": 3.5268, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017593128240137e-05, + "loss": 3.5265, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167545334890852e-05, + "loss": 3.5315, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0159159387380332e-05, + "loss": 3.5296, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150773439869812e-05, + "loss": 3.5209, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.014240387116302e-05, + "loss": 3.5274, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.01340179236525e-05, + "loss": 3.5332, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.012563197614198e-05, + "loss": 3.5335, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.011724602863146e-05, + "loss": 3.5336, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108876459924674e-05, + "loss": 3.5271, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100490512414154e-05, + "loss": 3.5393, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0092104564903634e-05, + "loss": 3.5304, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083718617393114e-05, + "loss": 3.5252, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075349048686323e-05, + "loss": 3.5281, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066963101175806e-05, + "loss": 3.5209, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058577153665286e-05, + "loss": 3.5263, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0050191206154766e-05, + "loss": 3.5177, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041821637447975e-05, + "loss": 3.5318, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033435689937455e-05, + "loss": 3.5176, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0025049742426935e-05, + "loss": 3.5328, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016663794916415e-05, + "loss": 3.5243, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0008294226209627e-05, + "loss": 3.526, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.8452298641204834, + "eval_runtime": 312.8459, + "eval_samples_per_second": 1219.741, + "eval_steps_per_second": 38.118, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999908278699107e-05, + "loss": 3.5178, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991522331188587e-05, + "loss": 3.5179, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9983136383678067e-05, + "loss": 3.5313, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974766814971276e-05, + "loss": 3.5325, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.996638086746076e-05, + "loss": 3.5259, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.995799491995024e-05, + "loss": 3.5183, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949608972439713e-05, + "loss": 3.5148, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.994123940373293e-05, + "loss": 3.5188, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.993285345622241e-05, + "loss": 3.5312, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992446750871189e-05, + "loss": 3.5237, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9916081561201365e-05, + "loss": 3.5277, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990771199249458e-05, + "loss": 3.5331, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.989932604498406e-05, + "loss": 3.5123, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.989094009747354e-05, + "loss": 3.514, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882554149963014e-05, + "loss": 3.5102, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987418458125623e-05, + "loss": 3.5225, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865798633745713e-05, + "loss": 3.522, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9857412686235187e-05, + "loss": 3.5205, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9849026738724667e-05, + "loss": 3.5158, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840657170017882e-05, + "loss": 3.5419, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832271222507362e-05, + "loss": 3.5244, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.982388527499684e-05, + "loss": 3.5267, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.981549932748632e-05, + "loss": 3.5275, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9807129758779535e-05, + "loss": 3.5359, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798743811269008e-05, + "loss": 3.5153, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790357863758488e-05, + "loss": 3.5211, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9781971916247968e-05, + "loss": 3.5272, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773602347541184e-05, + "loss": 3.5113, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976521640003066e-05, + "loss": 3.5203, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.975683045252014e-05, + "loss": 3.5223, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.974844450500962e-05, + "loss": 3.535, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9740074936302836e-05, + "loss": 3.5223, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731688988792313e-05, + "loss": 3.5278, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723303041281793e-05, + "loss": 3.5238, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714917093771273e-05, + "loss": 3.5266, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.970654752506448e-05, + "loss": 3.5237, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.969816157755396e-05, + "loss": 3.5115, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.968977563004344e-05, + "loss": 3.5214, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.968138968253292e-05, + "loss": 3.5098, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9673020113826134e-05, + "loss": 3.5221, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664634166315614e-05, + "loss": 3.517, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9656248218805094e-05, + "loss": 3.5333, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647862271294574e-05, + "loss": 3.5195, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639492702587783e-05, + "loss": 3.5211, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9631106755077266e-05, + "loss": 3.5263, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622720807566746e-05, + "loss": 3.5162, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9614334860056226e-05, + "loss": 3.5302, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605965291349435e-05, + "loss": 3.506, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597579343838915e-05, + "loss": 3.5161, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9589193396328395e-05, + "loss": 3.5236, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580807448817875e-05, + "loss": 3.5244, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572437880111088e-05, + "loss": 3.5229, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9564051932600568e-05, + "loss": 3.5055, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555665985090048e-05, + "loss": 3.5184, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9547280037579528e-05, + "loss": 3.5046, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538910468872737e-05, + "loss": 3.5352, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.953052452136222e-05, + "loss": 3.5056, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.95221385738517e-05, + "loss": 3.5246, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.951375262634118e-05, + "loss": 3.5139, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.950538305763439e-05, + "loss": 3.5013, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.949699711012387e-05, + "loss": 3.5233, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.948861116261335e-05, + "loss": 3.5171, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.948022521510283e-05, + "loss": 3.4987, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.947185564639604e-05, + "loss": 3.5049, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.946346969888552e-05, + "loss": 3.5257, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9455083751375e-05, + "loss": 3.5142, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944669780386448e-05, + "loss": 3.5081, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943832823515769e-05, + "loss": 3.5081, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9429942287647174e-05, + "loss": 3.5072, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421556340136654e-05, + "loss": 3.5143, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9413170392626134e-05, + "loss": 3.5224, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404800823919343e-05, + "loss": 3.5169, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396414876408823e-05, + "loss": 3.5247, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9388028928898303e-05, + "loss": 3.5187, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379659360191515e-05, + "loss": 3.5196, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9371273412680995e-05, + "loss": 3.5092, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9362903843974204e-05, + "loss": 3.5158, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9354517896463684e-05, + "loss": 3.5172, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9346131948953164e-05, + "loss": 3.5088, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337746001442644e-05, + "loss": 3.5141, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329360053932124e-05, + "loss": 3.5228, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320974106421607e-05, + "loss": 3.5226, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312588158911087e-05, + "loss": 3.5134, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9304218590204296e-05, + "loss": 3.5024, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295832642693776e-05, + "loss": 3.5145, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287446695183256e-05, + "loss": 3.5278, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9279060747672736e-05, + "loss": 3.5221, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.927069117896595e-05, + "loss": 3.5124, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.926230523145543e-05, + "loss": 3.5288, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.925391928394491e-05, + "loss": 3.5149, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.924553333643439e-05, + "loss": 3.5112, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9237163767727598e-05, + "loss": 3.5149, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228777820217078e-05, + "loss": 3.5206, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.922039187270656e-05, + "loss": 3.5167, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.921200592519604e-05, + "loss": 3.5279, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.920363635648925e-05, + "loss": 3.5057, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.919525040897873e-05, + "loss": 3.5079, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.918686446146821e-05, + "loss": 3.5099, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.917847851395769e-05, + "loss": 3.5246, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9170108945250902e-05, + "loss": 3.5209, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161722997740382e-05, + "loss": 3.5118, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9153337050229862e-05, + "loss": 3.5114, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9144951102719342e-05, + "loss": 3.5096, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.913658153401255e-05, + "loss": 3.5219, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.912819558650203e-05, + "loss": 3.4999, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119809638991515e-05, + "loss": 3.5119, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111423691480995e-05, + "loss": 3.5209, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9103054122774204e-05, + "loss": 3.5125, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094668175263684e-05, + "loss": 3.5143, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086282227753164e-05, + "loss": 3.5168, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9077896280242644e-05, + "loss": 3.5056, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069526711535856e-05, + "loss": 3.5165, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9061140764025336e-05, + "loss": 3.5163, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052754816514816e-05, + "loss": 3.5158, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044368869004296e-05, + "loss": 3.5189, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035999300297505e-05, + "loss": 3.5176, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027629731590717e-05, + "loss": 3.5169, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9019243784080197e-05, + "loss": 3.5125, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010857836569677e-05, + "loss": 3.5158, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002471889059157e-05, + "loss": 3.5127, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8994085941548637e-05, + "loss": 3.5033, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985699994038117e-05, + "loss": 3.5104, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977314046527597e-05, + "loss": 3.5125, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968928099017077e-05, + "loss": 3.5198, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.896055853031029e-05, + "loss": 3.5055, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.895217258279977e-05, + "loss": 3.5143, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.894378663528925e-05, + "loss": 3.5061, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.893540068777873e-05, + "loss": 3.5114, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892703111907194e-05, + "loss": 3.5066, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918645171561422e-05, + "loss": 3.5234, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8910259224050902e-05, + "loss": 3.5147, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901873276540382e-05, + "loss": 3.5097, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.889350370783359e-05, + "loss": 3.5113, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.888511776032307e-05, + "loss": 3.5161, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887673181281255e-05, + "loss": 3.5188, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.886834586530203e-05, + "loss": 3.5206, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859976296595243e-05, + "loss": 3.5157, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851590349084723e-05, + "loss": 3.5251, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8843204401574203e-05, + "loss": 3.5152, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834818454063683e-05, + "loss": 3.5142, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826448885356892e-05, + "loss": 3.5101, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8818062937846376e-05, + "loss": 3.5125, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809676990335856e-05, + "loss": 3.5112, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801291042825336e-05, + "loss": 3.5011, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792921474118545e-05, + "loss": 3.516, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784535526608025e-05, + "loss": 3.5088, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8776149579097505e-05, + "loss": 3.5188, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.876776363158698e-05, + "loss": 3.5086, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759394062880197e-05, + "loss": 3.5139, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.847039222717285, + "eval_runtime": 307.3926, + "eval_samples_per_second": 1241.38, + "eval_steps_per_second": 38.794, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8751008115369677e-05, + "loss": 3.5044, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742622167859157e-05, + "loss": 3.5061, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.873423622034863e-05, + "loss": 3.5179, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725866651641846e-05, + "loss": 3.5162, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871748070413133e-05, + "loss": 3.5157, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.870909475662081e-05, + "loss": 3.5049, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700708809110282e-05, + "loss": 3.4997, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8692339240403498e-05, + "loss": 3.5068, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8683953292892978e-05, + "loss": 3.5162, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8675567345382455e-05, + "loss": 3.5121, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8667181397871935e-05, + "loss": 3.5124, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.865881182916515e-05, + "loss": 3.518, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.865042588165463e-05, + "loss": 3.4985, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8642039934144104e-05, + "loss": 3.5044, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8633653986633584e-05, + "loss": 3.505, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.86252844179268e-05, + "loss": 3.499, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.861689847041628e-05, + "loss": 3.5085, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8608512522905756e-05, + "loss": 3.5063, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8600126575395236e-05, + "loss": 3.5018, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591757006688452e-05, + "loss": 3.5326, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858337105917793e-05, + "loss": 3.5104, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.857498511166741e-05, + "loss": 3.5113, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.856659916415689e-05, + "loss": 3.5135, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8558229595450104e-05, + "loss": 3.5202, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549843647939577e-05, + "loss": 3.5025, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541457700429057e-05, + "loss": 3.5064, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8533071752918537e-05, + "loss": 3.5132, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524702184211753e-05, + "loss": 3.5048, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.851631623670123e-05, + "loss": 3.5036, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.850793028919071e-05, + "loss": 3.5043, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.849954434168019e-05, + "loss": 3.5254, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.84911747729734e-05, + "loss": 3.5105, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482788825462882e-05, + "loss": 3.5117, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8474402877952362e-05, + "loss": 3.5084, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8466016930441842e-05, + "loss": 3.5123, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.845764736173505e-05, + "loss": 3.5103, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.844926141422453e-05, + "loss": 3.4985, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.844087546671401e-05, + "loss": 3.5042, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843248951920349e-05, + "loss": 3.4956, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8424119950496704e-05, + "loss": 3.511, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8415734002986184e-05, + "loss": 3.5014, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8407348055475663e-05, + "loss": 3.5167, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398962107965143e-05, + "loss": 3.5075, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390592539258353e-05, + "loss": 3.5068, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8382206591747832e-05, + "loss": 3.5139, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8373820644237316e-05, + "loss": 3.504, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8365434696726796e-05, + "loss": 3.5115, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8357065128020005e-05, + "loss": 3.4991, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348679180509485e-05, + "loss": 3.5025, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8340293232998965e-05, + "loss": 3.5067, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331923664292177e-05, + "loss": 3.509, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323537716781657e-05, + "loss": 3.513, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8315151769271137e-05, + "loss": 3.4884, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306765821760617e-05, + "loss": 3.5086, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8298396253053826e-05, + "loss": 3.489, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8290010305543306e-05, + "loss": 3.5211, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281624358032786e-05, + "loss": 3.4924, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.827323841052227e-05, + "loss": 3.5086, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.826486884181548e-05, + "loss": 3.5055, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.825648289430496e-05, + "loss": 3.4906, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.824809694679444e-05, + "loss": 3.5036, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.823971099928392e-05, + "loss": 3.5044, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.823134143057713e-05, + "loss": 3.486, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.822295548306661e-05, + "loss": 3.4944, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.821456953555609e-05, + "loss": 3.5087, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.820618358804557e-05, + "loss": 3.5037, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.819781401933878e-05, + "loss": 3.4964, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.818942807182826e-05, + "loss": 3.4963, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.818104212431774e-05, + "loss": 3.4914, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172656176807223e-05, + "loss": 3.503, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8164286608100432e-05, + "loss": 3.5048, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155900660589912e-05, + "loss": 3.5032, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147514713079392e-05, + "loss": 3.5126, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8139128765568872e-05, + "loss": 3.5063, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130759196862085e-05, + "loss": 3.507, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122373249351565e-05, + "loss": 3.4952, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113987301841045e-05, + "loss": 3.5066, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105601354330524e-05, + "loss": 3.5009, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8097231785623734e-05, + "loss": 3.497, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8088845838113214e-05, + "loss": 3.5009, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080459890602693e-05, + "loss": 3.506, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8072073943092177e-05, + "loss": 3.5119, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063704374385386e-05, + "loss": 3.5028, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8055318426874866e-05, + "loss": 3.4877, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8046932479364346e-05, + "loss": 3.494, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8038546531853826e-05, + "loss": 3.5152, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8030176963147038e-05, + "loss": 3.5081, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8021791015636518e-05, + "loss": 3.5031, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8013405068125998e-05, + "loss": 3.5097, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8005019120615478e-05, + "loss": 3.508, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996649551908687e-05, + "loss": 3.4936, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7988263604398167e-05, + "loss": 3.499, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979877656887647e-05, + "loss": 3.5094, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.797149170937713e-05, + "loss": 3.5058, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.796312214067034e-05, + "loss": 3.5147, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.795473619315982e-05, + "loss": 3.4931, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.79463502456493e-05, + "loss": 3.4956, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.793796429813878e-05, + "loss": 3.4991, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929594729431992e-05, + "loss": 3.5092, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7921208781921472e-05, + "loss": 3.5083, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912822834410952e-05, + "loss": 3.4994, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7904436886900432e-05, + "loss": 3.497, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.789606731819364e-05, + "loss": 3.4963, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.788768137068312e-05, + "loss": 3.5133, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.78792954231726e-05, + "loss": 3.4879, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870909475662084e-05, + "loss": 3.4944, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862539906955293e-05, + "loss": 3.5108, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7854153959444773e-05, + "loss": 3.502, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7845768011934253e-05, + "loss": 3.496, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7837382064423733e-05, + "loss": 3.5022, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7829012495716946e-05, + "loss": 3.4951, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820626548206426e-05, + "loss": 3.505, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7812240600695906e-05, + "loss": 3.5, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7803854653185385e-05, + "loss": 3.5021, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795485084478595e-05, + "loss": 3.5063, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7787099136968075e-05, + "loss": 3.5097, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778729568261287e-05, + "loss": 3.5006, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7770343620750767e-05, + "loss": 3.4996, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761957673240247e-05, + "loss": 3.5042, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753571725729727e-05, + "loss": 3.4988, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7745185778219207e-05, + "loss": 3.4906, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736799830708687e-05, + "loss": 3.4958, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728413883198167e-05, + "loss": 3.4969, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7720027935687647e-05, + "loss": 3.5056, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.771165836698086e-05, + "loss": 3.4923, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.770327241947034e-05, + "loss": 3.5023, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.769488647195982e-05, + "loss": 3.4857, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.76865005244493e-05, + "loss": 3.4997, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7678130955742508e-05, + "loss": 3.4972, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7669745008231988e-05, + "loss": 3.5102, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.766135906072147e-05, + "loss": 3.5045, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.765297311321095e-05, + "loss": 3.4993, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.764460354450416e-05, + "loss": 3.4906, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.763621759699364e-05, + "loss": 3.5005, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.762783164948312e-05, + "loss": 3.5093, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.76194457019726e-05, + "loss": 3.5087, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7611076133265813e-05, + "loss": 3.5062, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602690185755293e-05, + "loss": 3.5081, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7594304238244773e-05, + "loss": 3.4977, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7585918290734246e-05, + "loss": 3.5029, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577548722027462e-05, + "loss": 3.4972, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7569162774516942e-05, + "loss": 3.5006, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560776827006425e-05, + "loss": 3.5012, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7552390879495898e-05, + "loss": 3.486, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7544021310789114e-05, + "loss": 3.5027, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535635363278594e-05, + "loss": 3.4968, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7527249415768074e-05, + "loss": 3.5025, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.751886346825755e-05, + "loss": 3.4964, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510493899550767e-05, + "loss": 3.5014, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.8481199741363525, + "eval_runtime": 305.7156, + "eval_samples_per_second": 1248.19, + "eval_steps_per_second": 39.007, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7502107952040246e-05, + "loss": 3.4885, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.749372200452972e-05, + "loss": 3.4955, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.74853360570192e-05, + "loss": 3.5021, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.747695010950868e-05, + "loss": 3.5027, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468580540801895e-05, + "loss": 3.5072, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7460194593291372e-05, + "loss": 3.4865, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451808645780852e-05, + "loss": 3.4907, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443439077074068e-05, + "loss": 3.4918, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7435053129563548e-05, + "loss": 3.5018, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426667182053024e-05, + "loss": 3.5005, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7418281234542504e-05, + "loss": 3.4992, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409895287031984e-05, + "loss": 3.5015, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401525718325193e-05, + "loss": 3.4885, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7393139770814673e-05, + "loss": 3.4879, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384753823304153e-05, + "loss": 3.4946, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7376367875793633e-05, + "loss": 3.4873, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7367998307086846e-05, + "loss": 3.4923, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359612359576326e-05, + "loss": 3.4937, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7351226412065806e-05, + "loss": 3.4876, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342840464555286e-05, + "loss": 3.5206, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7334470895848495e-05, + "loss": 3.4958, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7326084948337978e-05, + "loss": 3.5023, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317699000827458e-05, + "loss": 3.5022, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7309313053316938e-05, + "loss": 3.5054, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300943484610147e-05, + "loss": 3.4889, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292557537099627e-05, + "loss": 3.4944, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7284171589589107e-05, + "loss": 3.4986, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275785642078587e-05, + "loss": 3.4937, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.72674160733718e-05, + "loss": 3.4867, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725903012586128e-05, + "loss": 3.493, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.725064417835076e-05, + "loss": 3.5098, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.724225823084024e-05, + "loss": 3.4989, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.723388866213345e-05, + "loss": 3.4983, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.722550271462293e-05, + "loss": 3.4987, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.721711676711241e-05, + "loss": 3.4979, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.720873081960189e-05, + "loss": 3.4976, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.72003612508951e-05, + "loss": 3.4842, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.719197530338458e-05, + "loss": 3.4976, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.718358935587406e-05, + "loss": 3.4829, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.717520340836354e-05, + "loss": 3.4955, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166833839656753e-05, + "loss": 3.4883, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158447892146233e-05, + "loss": 3.5052, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7150061944635713e-05, + "loss": 3.4942, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141675997125193e-05, + "loss": 3.4937, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7133306428418402e-05, + "loss": 3.4998, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124920480907885e-05, + "loss": 3.4939, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116534533397365e-05, + "loss": 3.4973, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7108164964690574e-05, + "loss": 3.4862, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099779017180054e-05, + "loss": 3.4886, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7091393069669534e-05, + "loss": 3.4947, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7083007122159014e-05, + "loss": 3.4966, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074621174648494e-05, + "loss": 3.4952, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7066251605941707e-05, + "loss": 3.4793, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057865658431187e-05, + "loss": 3.4943, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049479710920667e-05, + "loss": 3.4759, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7041093763410147e-05, + "loss": 3.506, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032724194703356e-05, + "loss": 3.4775, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.702433824719284e-05, + "loss": 3.4985, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.701595229968232e-05, + "loss": 3.4892, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007582730975528e-05, + "loss": 3.4862, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6999196783465008e-05, + "loss": 3.4869, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990810835954488e-05, + "loss": 3.4922, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982424888443968e-05, + "loss": 3.4736, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.697405531973718e-05, + "loss": 3.4832, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.696566937222666e-05, + "loss": 3.4912, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.695728342471614e-05, + "loss": 3.4944, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694889747720562e-05, + "loss": 3.4795, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.694052790849883e-05, + "loss": 3.4832, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.693214196098831e-05, + "loss": 3.4833, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923756013477793e-05, + "loss": 3.4858, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6915370065967273e-05, + "loss": 3.4908, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6907000497260482e-05, + "loss": 3.4902, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898614549749962e-05, + "loss": 3.5009, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.689022860223944e-05, + "loss": 3.4985, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.688184265472892e-05, + "loss": 3.4961, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873473086022134e-05, + "loss": 3.4807, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6865087138511614e-05, + "loss": 3.492, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856701191001094e-05, + "loss": 3.4927, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6848315243490574e-05, + "loss": 3.482, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6839945674783783e-05, + "loss": 3.4931, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6831559727273263e-05, + "loss": 3.4913, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6823173779762746e-05, + "loss": 3.5002, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814787832252226e-05, + "loss": 3.4897, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6806418263545435e-05, + "loss": 3.4761, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6798032316034915e-05, + "loss": 3.4847, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789646368524395e-05, + "loss": 3.5, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6781260421013875e-05, + "loss": 3.4949, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772890852307088e-05, + "loss": 3.4905, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764504904796568e-05, + "loss": 3.4971, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6756118957286048e-05, + "loss": 3.4962, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747733009775528e-05, + "loss": 3.4763, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739363441068737e-05, + "loss": 3.4927, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730977493558217e-05, + "loss": 3.4923, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722591546047697e-05, + "loss": 3.4898, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.671420559853718e-05, + "loss": 3.5033, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.670583602983039e-05, + "loss": 3.4849, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.669745008231987e-05, + "loss": 3.4774, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.668906413480935e-05, + "loss": 3.487, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.668067818729883e-05, + "loss": 3.4968, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.667230861859204e-05, + "loss": 3.4942, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.666392267108152e-05, + "loss": 3.4901, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6655536723571e-05, + "loss": 3.4803, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664715077606048e-05, + "loss": 3.4811, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.663878120735369e-05, + "loss": 3.5012, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.663039525984317e-05, + "loss": 3.4742, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.662200931233265e-05, + "loss": 3.4866, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613623364822134e-05, + "loss": 3.4953, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6605253796115343e-05, + "loss": 3.4875, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596867848604823e-05, + "loss": 3.4838, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6588481901094303e-05, + "loss": 3.4923, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6580095953583783e-05, + "loss": 3.4863, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571726384876995e-05, + "loss": 3.49, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6563340437366475e-05, + "loss": 3.4856, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554954489855955e-05, + "loss": 3.4877, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546568542345435e-05, + "loss": 3.4921, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6538198973638644e-05, + "loss": 3.4961, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529829404931857e-05, + "loss": 3.494, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521443457421336e-05, + "loss": 3.482, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6513057509910816e-05, + "loss": 3.4885, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504671562400296e-05, + "loss": 3.4853, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6496285614889776e-05, + "loss": 3.478, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487899667379256e-05, + "loss": 3.4891, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479513719868736e-05, + "loss": 3.4808, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6471127772358216e-05, + "loss": 3.4931, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.646275820365143e-05, + "loss": 3.4803, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.645437225614091e-05, + "loss": 3.4908, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.644598630863039e-05, + "loss": 3.4747, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.643760036111987e-05, + "loss": 3.4871, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6429230792413078e-05, + "loss": 3.4802, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6420844844902558e-05, + "loss": 3.4982, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.641245889739204e-05, + "loss": 3.4941, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6404072949881514e-05, + "loss": 3.4875, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.639570338117473e-05, + "loss": 3.478, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.638731743366421e-05, + "loss": 3.4907, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.637893148615369e-05, + "loss": 3.4965, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370545538643167e-05, + "loss": 3.496, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6362175969936382e-05, + "loss": 3.4911, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353790022425862e-05, + "loss": 3.4975, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6345404074915342e-05, + "loss": 3.4872, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6337018127404815e-05, + "loss": 3.4904, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.632864855869803e-05, + "loss": 3.4866, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.632026261118751e-05, + "loss": 3.4852, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311876663676988e-05, + "loss": 3.4908, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303490716166468e-05, + "loss": 3.4772, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6295121147459684e-05, + "loss": 3.4878, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286735199949164e-05, + "loss": 3.4885, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627834925243864e-05, + "loss": 3.4874, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.626996330492812e-05, + "loss": 3.4843, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6261593736221336e-05, + "loss": 3.484, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.849435567855835, + "eval_runtime": 303.3969, + "eval_samples_per_second": 1257.729, + "eval_steps_per_second": 39.305, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6253207788710816e-05, + "loss": 3.4758, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.624482184120029e-05, + "loss": 3.4803, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.623643589368977e-05, + "loss": 3.4941, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.622804994617925e-05, + "loss": 3.4865, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.621968037747246e-05, + "loss": 3.4965, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.621129442996194e-05, + "loss": 3.4736, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.620290848245142e-05, + "loss": 3.4798, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.61945225349409e-05, + "loss": 3.4751, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.618615296623411e-05, + "loss": 3.4923, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6177767018723594e-05, + "loss": 3.4887, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6169381071213074e-05, + "loss": 3.4844, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6160995123702554e-05, + "loss": 3.4876, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152625554995763e-05, + "loss": 3.4734, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6144239607485243e-05, + "loss": 3.4769, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6135853659974723e-05, + "loss": 3.4805, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6127467712464203e-05, + "loss": 3.4798, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6119098143757415e-05, + "loss": 3.4787, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.6110712196246895e-05, + "loss": 3.4835, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6102326248736375e-05, + "loss": 3.4731, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.6093940301225855e-05, + "loss": 3.5081, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6085570732519064e-05, + "loss": 3.4825, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6077184785008548e-05, + "loss": 3.4879, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6068798837498028e-05, + "loss": 3.4894, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.6060412889987507e-05, + "loss": 3.4896, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6052043321280717e-05, + "loss": 3.477, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6043657373770197e-05, + "loss": 3.4862, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6035271426259676e-05, + "loss": 3.4824, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.602690185755289e-05, + "loss": 3.4822, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.601851591004237e-05, + "loss": 3.4716, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.601012996253185e-05, + "loss": 3.4833, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.600174401502133e-05, + "loss": 3.4967, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5993374446314538e-05, + "loss": 3.4865, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5984988498804018e-05, + "loss": 3.4884, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.59766025512935e-05, + "loss": 3.487, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.596821660378298e-05, + "loss": 3.4808, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.595984703507619e-05, + "loss": 3.49, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.595146108756567e-05, + "loss": 3.4698, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.594307514005515e-05, + "loss": 3.4866, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.593468919254463e-05, + "loss": 3.4673, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5926319623837843e-05, + "loss": 3.4845, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5917933676327323e-05, + "loss": 3.4762, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5909547728816803e-05, + "loss": 3.492, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5901161781306282e-05, + "loss": 3.4834, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.589279221259949e-05, + "loss": 3.4778, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.588440626508897e-05, + "loss": 3.4883, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5876020317578455e-05, + "loss": 3.4824, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5867634370067935e-05, + "loss": 3.485, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5859264801361144e-05, + "loss": 3.4787, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5850878853850624e-05, + "loss": 3.4703, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5842492906340104e-05, + "loss": 3.483, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5834106958829584e-05, + "loss": 3.4831, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.5825737390122796e-05, + "loss": 3.4825, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.5817351442612276e-05, + "loss": 3.4716, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5808965495101756e-05, + "loss": 3.4852, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.5800579547591236e-05, + "loss": 3.4623, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5792209978884445e-05, + "loss": 3.494, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5783824031373925e-05, + "loss": 3.4677, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5775438083863405e-05, + "loss": 3.4816, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.576705213635289e-05, + "loss": 3.4759, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5758682567646098e-05, + "loss": 3.4745, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.5750296620135578e-05, + "loss": 3.4713, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5741910672625058e-05, + "loss": 3.4849, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5733524725114537e-05, + "loss": 3.4607, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.572515515640775e-05, + "loss": 3.4684, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.571676920889723e-05, + "loss": 3.4825, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.570838326138671e-05, + "loss": 3.4816, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.569999731387619e-05, + "loss": 3.4699, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.56916277451694e-05, + "loss": 3.4733, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.568324179765888e-05, + "loss": 3.466, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.567485585014836e-05, + "loss": 3.4727, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.5666469902637842e-05, + "loss": 3.4803, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.565810033393105e-05, + "loss": 3.4766, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.564971438642053e-05, + "loss": 3.4902, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.564132843891001e-05, + "loss": 3.4817, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.563294249139949e-05, + "loss": 3.4859, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5624572922692704e-05, + "loss": 3.4697, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.5616186975182184e-05, + "loss": 3.4774, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5607801027671664e-05, + "loss": 3.4804, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.5599415080161143e-05, + "loss": 3.4678, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5591045511454353e-05, + "loss": 3.4828, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5582659563943833e-05, + "loss": 3.4777, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5574273616433313e-05, + "loss": 3.4851, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5565887668922796e-05, + "loss": 3.4777, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5557518100216005e-05, + "loss": 3.4662, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5549132152705485e-05, + "loss": 3.476, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5540746205194965e-05, + "loss": 3.4838, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5532360257684445e-05, + "loss": 3.4866, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.5523990688977657e-05, + "loss": 3.4803, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5515604741467137e-05, + "loss": 3.4808, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5507218793956617e-05, + "loss": 3.4868, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5498832846446097e-05, + "loss": 3.4662, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5490463277739306e-05, + "loss": 3.4826, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5482077330228786e-05, + "loss": 3.4748, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5473691382718266e-05, + "loss": 3.4779, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.546530543520775e-05, + "loss": 3.4886, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.545693586650096e-05, + "loss": 3.4762, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.544854991899044e-05, + "loss": 3.4639, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.544016397147992e-05, + "loss": 3.4768, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.54317780239694e-05, + "loss": 3.482, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.542340845526261e-05, + "loss": 3.4846, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.541502250775209e-05, + "loss": 3.4761, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.540663656024157e-05, + "loss": 3.4699, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.539825061273105e-05, + "loss": 3.4719, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.538988104402426e-05, + "loss": 3.4866, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.538149509651374e-05, + "loss": 3.4654, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.537310914900322e-05, + "loss": 3.4727, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.5364723201492703e-05, + "loss": 3.4815, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.5356353632785912e-05, + "loss": 3.4789, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5347967685275392e-05, + "loss": 3.4673, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.5339581737764872e-05, + "loss": 3.4826, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.5331195790254352e-05, + "loss": 3.4755, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5322826221547565e-05, + "loss": 3.4744, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5314440274037045e-05, + "loss": 3.4763, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5306054326526525e-05, + "loss": 3.4752, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5297668379016004e-05, + "loss": 3.4877, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5289298810309214e-05, + "loss": 3.4789, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5280929241602426e-05, + "loss": 3.4822, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5272543294091906e-05, + "loss": 3.4708, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5264157346581386e-05, + "loss": 3.4773, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.5255771399070866e-05, + "loss": 3.4764, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5247385451560346e-05, + "loss": 3.4665, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5238999504049826e-05, + "loss": 3.4754, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5230613556539306e-05, + "loss": 3.4718, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5222227609028782e-05, + "loss": 3.4782, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5213858040321998e-05, + "loss": 3.4681, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5205472092811478e-05, + "loss": 3.4803, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5197086145300958e-05, + "loss": 3.4579, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.518870019779043e-05, + "loss": 3.4771, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.5180330629083647e-05, + "loss": 3.473, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.5171944681573127e-05, + "loss": 3.482, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.516355873406261e-05, + "loss": 3.4797, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.5155172786552084e-05, + "loss": 3.4804, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.51468032178453e-05, + "loss": 3.4629, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.513841727033478e-05, + "loss": 3.4777, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.5130031322824256e-05, + "loss": 3.4825, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.5121645375313736e-05, + "loss": 3.4856, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.5113275806606952e-05, + "loss": 3.4798, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.5104889859096432e-05, + "loss": 3.4801, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5096503911585905e-05, + "loss": 3.4774, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5088117964075385e-05, + "loss": 3.4845, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.50797483953686e-05, + "loss": 3.47, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.507136244785808e-05, + "loss": 3.4734, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5062976500347557e-05, + "loss": 3.4774, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5054590552837037e-05, + "loss": 3.4666, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5046220984130253e-05, + "loss": 3.4733, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5037835036619726e-05, + "loss": 3.4795, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.502944908910921e-05, + "loss": 3.4732, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.502106314159869e-05, + "loss": 3.4693, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5012693572891906e-05, + "loss": 3.4797, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.8495023250579834, + "eval_runtime": 303.8363, + "eval_samples_per_second": 1255.91, + "eval_steps_per_second": 39.248, + "step": 1526400 + }, + { + "epoch": 1.0, + "learning_rate": 2.500430762538138e-05, + "loss": 3.4656, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.4995921677870862e-05, + "loss": 3.4682, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.4987535730360342e-05, + "loss": 3.4789, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.497916616165355e-05, + "loss": 3.4755, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.4970780214143035e-05, + "loss": 3.4869, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.4962394266632514e-05, + "loss": 3.4623, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.4954008319121994e-05, + "loss": 3.4681, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.4945638750415204e-05, + "loss": 3.4618, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.4937252802904683e-05, + "loss": 3.4801, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.4928866855394163e-05, + "loss": 3.4787, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.4920480907883643e-05, + "loss": 3.4673, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.4912111339176856e-05, + "loss": 3.4829, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.4903725391666336e-05, + "loss": 3.4585, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.4895339444155816e-05, + "loss": 3.4664, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.4886953496645292e-05, + "loss": 3.4708, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.4878583927938505e-05, + "loss": 3.4659, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.4870197980427988e-05, + "loss": 3.4692, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.4861812032917468e-05, + "loss": 3.4689, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.4853426085406945e-05, + "loss": 3.4639, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.4845056516700157e-05, + "loss": 3.4959, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.4836670569189637e-05, + "loss": 3.4734, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.4828284621679117e-05, + "loss": 3.4729, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.4819898674168597e-05, + "loss": 3.4806, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.481152910546181e-05, + "loss": 3.4784, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.480314315795129e-05, + "loss": 3.4657, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.4794757210440766e-05, + "loss": 3.475, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.4786371262930246e-05, + "loss": 3.4701, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.477800169422346e-05, + "loss": 3.4694, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.4769615746712942e-05, + "loss": 3.46, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.476122979920242e-05, + "loss": 3.4714, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.475286023049563e-05, + "loss": 3.487, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.474447428298511e-05, + "loss": 3.4727, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.473608833547459e-05, + "loss": 3.4752, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.4727702387964067e-05, + "loss": 3.475, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.4719332819257283e-05, + "loss": 3.4692, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.4710946871746763e-05, + "loss": 3.4775, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.470256092423624e-05, + "loss": 3.4588, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.469417497672572e-05, + "loss": 3.4718, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.4685805408018932e-05, + "loss": 3.46, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.4677419460508412e-05, + "loss": 3.467, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.4669033512997892e-05, + "loss": 3.4661, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.4660647565487372e-05, + "loss": 3.4802, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.4652277996780585e-05, + "loss": 3.4715, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.4643892049270065e-05, + "loss": 3.4699, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.463550610175954e-05, + "loss": 3.4754, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.462712015424902e-05, + "loss": 3.4698, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.4618750585542237e-05, + "loss": 3.4717, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.4610364638031713e-05, + "loss": 3.4694, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.4601978690521193e-05, + "loss": 3.4564, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.4593592743010673e-05, + "loss": 3.4729, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.4585223174303886e-05, + "loss": 3.466, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.4576837226793366e-05, + "loss": 3.4755, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.4568451279282846e-05, + "loss": 3.4621, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.4560065331772326e-05, + "loss": 3.4703, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.4551695763065535e-05, + "loss": 3.4492, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.4543326194358747e-05, + "loss": 3.4796, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.4534940246848227e-05, + "loss": 3.4561, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.452655429933771e-05, + "loss": 3.4654, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.4518168351827187e-05, + "loss": 3.4691, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.4509782404316667e-05, + "loss": 3.4602, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.4501396456806147e-05, + "loss": 3.465, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.4493010509295627e-05, + "loss": 3.4683, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.4484624561785107e-05, + "loss": 3.4565, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.447625499307832e-05, + "loss": 3.4531, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.44678690455678e-05, + "loss": 3.4687, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.445948309805728e-05, + "loss": 3.4704, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.445109715054676e-05, + "loss": 3.4577, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.444272758183997e-05, + "loss": 3.4647, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.443434163432945e-05, + "loss": 3.4537, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.442595568681893e-05, + "loss": 3.4595, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.4417569739308412e-05, + "loss": 3.4683, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.440920017060162e-05, + "loss": 3.463, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.44008142230911e-05, + "loss": 3.4768, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.439242827558058e-05, + "loss": 3.4701, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.438404232807006e-05, + "loss": 3.4793, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.4375672759363273e-05, + "loss": 3.4555, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4367286811852753e-05, + "loss": 3.4658, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.4358900864342233e-05, + "loss": 3.4705, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.4350514916831713e-05, + "loss": 3.4526, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.4342145348124922e-05, + "loss": 3.4739, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.4333759400614402e-05, + "loss": 3.4682, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.4325389831907615e-05, + "loss": 3.4727, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.4317003884397095e-05, + "loss": 3.4675, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.4308617936886574e-05, + "loss": 3.4548, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.4300231989376054e-05, + "loss": 3.4649, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.4291846041865534e-05, + "loss": 3.4677, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.4283460094355014e-05, + "loss": 3.4706, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.427507414684449e-05, + "loss": 3.4674, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.4266688199333974e-05, + "loss": 3.4702, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.4258318630627187e-05, + "loss": 3.4723, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.4249932683116663e-05, + "loss": 3.4592, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.4241546735606143e-05, + "loss": 3.4697, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.4233160788095623e-05, + "loss": 3.4617, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.4224791219388836e-05, + "loss": 3.47, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.4216405271878316e-05, + "loss": 3.4787, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.4208019324367796e-05, + "loss": 3.4617, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.4199633376857276e-05, + "loss": 3.4563, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.4191263808150488e-05, + "loss": 3.4622, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.4182877860639965e-05, + "loss": 3.4665, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.4174491913129445e-05, + "loss": 3.4773, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.4166105965618928e-05, + "loss": 3.461, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.4157736396912137e-05, + "loss": 3.4604, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.4149350449401617e-05, + "loss": 3.4576, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.4140964501891097e-05, + "loss": 3.4741, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.4132578554380577e-05, + "loss": 3.4525, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.412420898567379e-05, + "loss": 3.4627, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.411582303816327e-05, + "loss": 3.4691, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.410743709065275e-05, + "loss": 3.4653, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.409905114314223e-05, + "loss": 3.457, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.409068157443544e-05, + "loss": 3.472, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.4082295626924918e-05, + "loss": 3.4631, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.4073909679414398e-05, + "loss": 3.46, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.406552373190388e-05, + "loss": 3.4667, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.405715416319709e-05, + "loss": 3.4633, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.404876821568657e-05, + "loss": 3.4738, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.404038226817605e-05, + "loss": 3.4699, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.403201269946926e-05, + "loss": 3.4682, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.4023626751958743e-05, + "loss": 3.4576, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4015240804448223e-05, + "loss": 3.4663, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.4006854856937703e-05, + "loss": 3.4635, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.3998468909427183e-05, + "loss": 3.4524, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.3990082961916663e-05, + "loss": 3.4673, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.3981697014406143e-05, + "loss": 3.4572, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.397331106689562e-05, + "loss": 3.4682, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.3964941498188835e-05, + "loss": 3.4611, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.3956555550678315e-05, + "loss": 3.4671, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.3948169603167792e-05, + "loss": 3.4481, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.3939783655657272e-05, + "loss": 3.4624, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.3931414086950484e-05, + "loss": 3.4636, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.3923028139439964e-05, + "loss": 3.4666, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.3914642191929444e-05, + "loss": 3.4681, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.3906256244418924e-05, + "loss": 3.471, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.3897886675712137e-05, + "loss": 3.4516, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.3889500728201613e-05, + "loss": 3.4681, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.3881114780691093e-05, + "loss": 3.4725, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.3872728833180573e-05, + "loss": 3.4711, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.386435926447379e-05, + "loss": 3.4695, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.3855973316963265e-05, + "loss": 3.4712, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.3847587369452745e-05, + "loss": 3.4639, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.3839201421942225e-05, + "loss": 3.4713, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.3830831853235438e-05, + "loss": 3.4557, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.3822445905724914e-05, + "loss": 3.4638, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.3814059958214398e-05, + "loss": 3.4589, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.3805674010703878e-05, + "loss": 3.4598, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.3797304441997087e-05, + "loss": 3.4634, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.3788918494486567e-05, + "loss": 3.4626, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.3780532546976047e-05, + "loss": 3.4656, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.3772146599465527e-05, + "loss": 3.452, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.376377703075874e-05, + "loss": 3.4685, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 3.851916551589966, + "eval_runtime": 304.146, + "eval_samples_per_second": 1254.631, + "eval_steps_per_second": 39.208, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.375539108324822e-05, + "loss": 3.454, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.37470051357377e-05, + "loss": 3.455, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.373861918822718e-05, + "loss": 3.4642, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.373023324071666e-05, + "loss": 3.4694, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3721863672009868e-05, + "loss": 3.4695, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.371347772449935e-05, + "loss": 3.4573, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.370509177698883e-05, + "loss": 3.4525, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.369670582947831e-05, + "loss": 3.4541, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.368833626077152e-05, + "loss": 3.4649, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3679950313261e-05, + "loss": 3.47, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.367156436575048e-05, + "loss": 3.4559, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.366317841823996e-05, + "loss": 3.4693, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3654808849533173e-05, + "loss": 3.4512, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3646422902022653e-05, + "loss": 3.4541, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3638036954512133e-05, + "loss": 3.4594, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3629651007001613e-05, + "loss": 3.452, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3621281438294822e-05, + "loss": 3.4566, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3612895490784305e-05, + "loss": 3.4595, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3604509543273785e-05, + "loss": 3.4503, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3596123595763265e-05, + "loss": 3.4815, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3587754027056474e-05, + "loss": 3.4648, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3579368079545954e-05, + "loss": 3.4637, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3570982132035434e-05, + "loss": 3.467, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3562596184524914e-05, + "loss": 3.4714, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3554226615818126e-05, + "loss": 3.4526, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3545840668307606e-05, + "loss": 3.464, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3537454720797086e-05, + "loss": 3.4614, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3529068773286566e-05, + "loss": 3.4555, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3520699204579775e-05, + "loss": 3.4463, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.351231325706926e-05, + "loss": 3.4641, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.350392730955874e-05, + "loss": 3.4757, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3495541362048215e-05, + "loss": 3.4608, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3487171793341428e-05, + "loss": 3.4661, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3478785845830908e-05, + "loss": 3.4601, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3470399898320388e-05, + "loss": 3.4567, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3462013950809868e-05, + "loss": 3.4638, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.345364438210308e-05, + "loss": 3.4531, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.344525843459256e-05, + "loss": 3.4551, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.343687248708204e-05, + "loss": 3.4523, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.342850291837525e-05, + "loss": 3.4565, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.342011697086473e-05, + "loss": 3.4559, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3411731023354212e-05, + "loss": 3.4661, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.340334507584369e-05, + "loss": 3.4593, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.33949755071369e-05, + "loss": 3.4582, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.338658955962638e-05, + "loss": 3.4647, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.337820361211586e-05, + "loss": 3.4593, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3369817664605338e-05, + "loss": 3.4605, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3361448095898554e-05, + "loss": 3.457, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.3353062148388034e-05, + "loss": 3.4445, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3344676200877514e-05, + "loss": 3.4635, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.333629025336699e-05, + "loss": 3.456, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3327920684660203e-05, + "loss": 3.4633, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3319534737149683e-05, + "loss": 3.4535, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3311148789639163e-05, + "loss": 3.457, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3302762842128643e-05, + "loss": 3.4403, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3294393273421855e-05, + "loss": 3.4655, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.3286007325911335e-05, + "loss": 3.446, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.3277621378400812e-05, + "loss": 3.4563, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.326923543089029e-05, + "loss": 3.4572, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3260849483379775e-05, + "loss": 3.4465, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3252463535869255e-05, + "loss": 3.4512, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3244077588358735e-05, + "loss": 3.4644, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3235691640848215e-05, + "loss": 3.4421, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.3227322072141424e-05, + "loss": 3.4399, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.3218936124630904e-05, + "loss": 3.4562, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.3210550177120384e-05, + "loss": 3.4594, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3202164229609867e-05, + "loss": 3.4433, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3193794660903076e-05, + "loss": 3.4551, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3185408713392556e-05, + "loss": 3.4413, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.3177022765882036e-05, + "loss": 3.4466, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.3168636818371516e-05, + "loss": 3.4587, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.316026724966473e-05, + "loss": 3.4539, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.315188130215421e-05, + "loss": 3.462, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.314349535464369e-05, + "loss": 3.4597, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3135109407133165e-05, + "loss": 3.4675, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3126739838426378e-05, + "loss": 3.4433, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3118353890915858e-05, + "loss": 3.4582, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3109967943405338e-05, + "loss": 3.4599, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3101581995894818e-05, + "loss": 3.4372, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.309321242718803e-05, + "loss": 3.4618, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.308482647967751e-05, + "loss": 3.4563, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.307644053216699e-05, + "loss": 3.4567, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3068054584656466e-05, + "loss": 3.4579, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059685015949682e-05, + "loss": 3.4446, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3051299068439162e-05, + "loss": 3.4478, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.304291312092864e-05, + "loss": 3.4568, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.303452717341812e-05, + "loss": 3.4641, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.302615760471133e-05, + "loss": 3.4516, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.301777165720081e-05, + "loss": 3.4621, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.300938570969029e-05, + "loss": 3.4643, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.300099976217977e-05, + "loss": 3.4462, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2992630193472984e-05, + "loss": 3.4589, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2984244245962464e-05, + "loss": 3.4471, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.297585829845194e-05, + "loss": 3.4602, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.296747235094142e-05, + "loss": 3.4709, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2959102782234636e-05, + "loss": 3.4449, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2950716834724113e-05, + "loss": 3.4485, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2942330887213593e-05, + "loss": 3.4491, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2933961318506805e-05, + "loss": 3.4561, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.2925575370996285e-05, + "loss": 3.4684, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.291718942348576e-05, + "loss": 3.4495, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2908803475975245e-05, + "loss": 3.4517, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2900417528464725e-05, + "loss": 3.4419, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2892031580954205e-05, + "loss": 3.4641, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2883645633443685e-05, + "loss": 3.4394, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.2875259685933165e-05, + "loss": 3.4536, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.2866890117226374e-05, + "loss": 3.4525, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.2858504169715854e-05, + "loss": 3.4586, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.2850118222205337e-05, + "loss": 3.4468, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2841732274694817e-05, + "loss": 3.4571, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2833362705988026e-05, + "loss": 3.4553, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2824976758477506e-05, + "loss": 3.4486, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2816590810966986e-05, + "loss": 3.4555, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.2808204863456466e-05, + "loss": 3.4532, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.279983529474968e-05, + "loss": 3.4616, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.279144934723916e-05, + "loss": 3.4611, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2783079778532368e-05, + "loss": 3.4553, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2774693831021848e-05, + "loss": 3.4478, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2766307883511327e-05, + "loss": 3.4522, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2757921936000807e-05, + "loss": 3.4567, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.274953598849029e-05, + "loss": 3.442, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.2741150040979767e-05, + "loss": 3.4528, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2732764093469247e-05, + "loss": 3.445, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2724378145958727e-05, + "loss": 3.4586, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.271600857725194e-05, + "loss": 3.4479, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707622629741416e-05, + "loss": 3.4536, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.26992366822309e-05, + "loss": 3.4444, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.269085073472038e-05, + "loss": 3.4472, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2682481166013592e-05, + "loss": 3.4549, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.267409521850307e-05, + "loss": 3.4572, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.266570927099255e-05, + "loss": 3.4503, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.265732332348203e-05, + "loss": 3.4594, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.264895375477524e-05, + "loss": 3.4456, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.264056780726472e-05, + "loss": 3.4555, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.26321818597542e-05, + "loss": 3.4625, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.262379591224368e-05, + "loss": 3.4585, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.261542634353689e-05, + "loss": 3.4561, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.260704039602637e-05, + "loss": 3.4633, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598654448515853e-05, + "loss": 3.4514, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2590268501005333e-05, + "loss": 3.4639, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2581898932298542e-05, + "loss": 3.4447, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2573512984788022e-05, + "loss": 3.4531, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2565127037277502e-05, + "loss": 3.4494, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2556741089766982e-05, + "loss": 3.4471, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2548371521060195e-05, + "loss": 3.4524, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2539985573549675e-05, + "loss": 3.449, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2531599626039155e-05, + "loss": 3.4613, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2523213678528635e-05, + "loss": 3.435, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2514844109821844e-05, + "loss": 3.4629, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.8525896072387695, + "eval_runtime": 305.8662, + "eval_samples_per_second": 1247.575, + "eval_steps_per_second": 38.988, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2506458162311324e-05, + "loss": 3.4443, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2498072214800807e-05, + "loss": 3.4453, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2489686267290287e-05, + "loss": 3.4559, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2481316698583496e-05, + "loss": 3.4567, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2472930751072976e-05, + "loss": 3.4588, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2464544803562456e-05, + "loss": 3.4441, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.2456158856051936e-05, + "loss": 3.437, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.244778928734515e-05, + "loss": 3.4464, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.243940333983463e-05, + "loss": 3.4539, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2431017392324108e-05, + "loss": 3.4582, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2422631444813588e-05, + "loss": 3.4498, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2414261876106797e-05, + "loss": 3.4534, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2405875928596277e-05, + "loss": 3.4432, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.239748998108576e-05, + "loss": 3.4422, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.238910403357524e-05, + "loss": 3.4484, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.238073446486845e-05, + "loss": 3.4399, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.237234851735793e-05, + "loss": 3.4452, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.236396256984741e-05, + "loss": 3.45, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.235557662233689e-05, + "loss": 3.4379, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.2347207053630102e-05, + "loss": 3.4685, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.2338821106119582e-05, + "loss": 3.4561, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2330435158609062e-05, + "loss": 3.4483, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.232206558990227e-05, + "loss": 3.4575, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.231367964239175e-05, + "loss": 3.4608, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.230529369488123e-05, + "loss": 3.4411, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2296907747370714e-05, + "loss": 3.4546, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2288538178663923e-05, + "loss": 3.4481, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2280152231153403e-05, + "loss": 3.4455, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.2271766283642883e-05, + "loss": 3.4371, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.2263380336132363e-05, + "loss": 3.4514, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2255010767425576e-05, + "loss": 3.4606, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2246624819915056e-05, + "loss": 3.4512, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2238238872404536e-05, + "loss": 3.4586, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2229852924894016e-05, + "loss": 3.4531, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.2221483356187225e-05, + "loss": 3.4427, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.2213097408676705e-05, + "loss": 3.4515, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.2204711461166185e-05, + "loss": 3.4471, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2196325513655665e-05, + "loss": 3.443, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2187955944948877e-05, + "loss": 3.4401, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2179569997438357e-05, + "loss": 3.4444, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2171184049927837e-05, + "loss": 3.4457, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.2162798102417314e-05, + "loss": 3.4552, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.215442853371053e-05, + "loss": 3.4484, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.214604258620001e-05, + "loss": 3.4463, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.213765663868949e-05, + "loss": 3.4547, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.2129270691178966e-05, + "loss": 3.447, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.212090112247218e-05, + "loss": 3.4502, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.211251517496166e-05, + "loss": 3.4479, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.2104129227451138e-05, + "loss": 3.4299, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.2095743279940618e-05, + "loss": 3.456, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.208737371123383e-05, + "loss": 3.4429, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.207898776372331e-05, + "loss": 3.4553, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2070601816212787e-05, + "loss": 3.445, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2062215868702267e-05, + "loss": 3.4422, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.2053846299995483e-05, + "loss": 3.433, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.2045476731288692e-05, + "loss": 3.45, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.2037090783778172e-05, + "loss": 3.4361, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2028704836267652e-05, + "loss": 3.4427, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.2020318888757132e-05, + "loss": 3.4517, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.201193294124661e-05, + "loss": 3.4326, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2003546993736092e-05, + "loss": 3.4375, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.1995161046225572e-05, + "loss": 3.4581, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.1986775098715052e-05, + "loss": 3.4255, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.197840553000826e-05, + "loss": 3.4314, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.197001958249774e-05, + "loss": 3.4433, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.196163363498722e-05, + "loss": 3.4472, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.19532476874767e-05, + "loss": 3.4341, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1944878118769913e-05, + "loss": 3.4442, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.1936492171259393e-05, + "loss": 3.4308, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1928106223748873e-05, + "loss": 3.4342, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1919720276238353e-05, + "loss": 3.4471, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1911350707531562e-05, + "loss": 3.4422, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1902964760021046e-05, + "loss": 3.4501, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1894578812510526e-05, + "loss": 3.45, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1886192865000006e-05, + "loss": 3.4551, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1877823296293215e-05, + "loss": 3.4359, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1869437348782695e-05, + "loss": 3.4458, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1861051401272175e-05, + "loss": 3.4464, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1852665453761655e-05, + "loss": 3.429, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1844295885054867e-05, + "loss": 3.4504, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1835909937544347e-05, + "loss": 3.4468, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1827540368837556e-05, + "loss": 3.4502, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1819154421327036e-05, + "loss": 3.4452, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1810768473816516e-05, + "loss": 3.437, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.1802382526306e-05, + "loss": 3.4362, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.179399657879548e-05, + "loss": 3.4464, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.178561063128496e-05, + "loss": 3.449, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.177722468377444e-05, + "loss": 3.4435, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1768838736263916e-05, + "loss": 3.4507, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1760469167557128e-05, + "loss": 3.4491, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.1752083220046608e-05, + "loss": 3.4388, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.1743697272536088e-05, + "loss": 3.4453, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.1735311325025568e-05, + "loss": 3.4346, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.172694175631878e-05, + "loss": 3.454, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.171855580880826e-05, + "loss": 3.4566, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1710169861297737e-05, + "loss": 3.4369, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1701783913787217e-05, + "loss": 3.4368, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1693414345080433e-05, + "loss": 3.4341, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.1685044776373642e-05, + "loss": 3.4477, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.1676658828863122e-05, + "loss": 3.4569, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.1668272881352602e-05, + "loss": 3.4407, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1659886933842082e-05, + "loss": 3.4424, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1651500986331562e-05, + "loss": 3.4335, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1643115038821042e-05, + "loss": 3.449, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.1634729091310522e-05, + "loss": 3.4327, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.1626343143800002e-05, + "loss": 3.4425, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.161797357509321e-05, + "loss": 3.4354, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.160958762758269e-05, + "loss": 3.4506, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.1601218058875907e-05, + "loss": 3.4373, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1592832111365387e-05, + "loss": 3.4452, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1584446163854863e-05, + "loss": 3.445, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1576060216344343e-05, + "loss": 3.4361, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.1567674268833823e-05, + "loss": 3.4461, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.1559288321323303e-05, + "loss": 3.4429, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.1550902373812783e-05, + "loss": 3.4485, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1542516426302263e-05, + "loss": 3.4528, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1534163236399208e-05, + "loss": 3.4385, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.1525777288888685e-05, + "loss": 3.443, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.1517391341378164e-05, + "loss": 3.4377, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1509005393867644e-05, + "loss": 3.4452, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.1500619446357124e-05, + "loss": 3.4378, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.1492233498846608e-05, + "loss": 3.44, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1483847551336088e-05, + "loss": 3.43, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1475461603825568e-05, + "loss": 3.4468, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1467092035118777e-05, + "loss": 3.4367, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.1458706087608257e-05, + "loss": 3.445, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.1450320140097737e-05, + "loss": 3.4299, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1441934192587217e-05, + "loss": 3.4405, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.143356462388043e-05, + "loss": 3.4388, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.142517867636991e-05, + "loss": 3.4503, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.141679272885939e-05, + "loss": 3.4392, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.1408406781348866e-05, + "loss": 3.4484, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1400037212642078e-05, + "loss": 3.4332, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.139165126513156e-05, + "loss": 3.4461, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.138326531762104e-05, + "loss": 3.4492, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.1374879370110518e-05, + "loss": 3.4478, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.136650980140373e-05, + "loss": 3.4443, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.135812385389321e-05, + "loss": 3.4519, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1349737906382687e-05, + "loss": 3.4403, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.134135195887217e-05, + "loss": 3.4532, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1332982390165383e-05, + "loss": 3.4327, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1324596442654863e-05, + "loss": 3.4436, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.131621049514434e-05, + "loss": 3.4382, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.130782454763382e-05, + "loss": 3.4404, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1299454978927032e-05, + "loss": 3.4348, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.129106903141651e-05, + "loss": 3.4347, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.128268308390599e-05, + "loss": 3.4479, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.127429713639547e-05, + "loss": 3.4277, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.1265927567688684e-05, + "loss": 3.4548, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.854764223098755, + "eval_runtime": 304.6541, + "eval_samples_per_second": 1252.538, + "eval_steps_per_second": 39.143, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.125754162017816e-05, + "loss": 3.4335, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.124915567266764e-05, + "loss": 3.4328, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1240769725157124e-05, + "loss": 3.4418, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232383777646604e-05, + "loss": 3.4451, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1224014208939813e-05, + "loss": 3.444, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215628261429293e-05, + "loss": 3.4373, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1207242313918773e-05, + "loss": 3.4304, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1198856366408253e-05, + "loss": 3.4345, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1190486797701465e-05, + "loss": 3.4423, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1182100850190945e-05, + "loss": 3.4463, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173714902680425e-05, + "loss": 3.4385, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1165328955169905e-05, + "loss": 3.4392, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1156959386463114e-05, + "loss": 3.4373, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.1148573438952594e-05, + "loss": 3.429, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1140187491442078e-05, + "loss": 3.4362, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1131801543931558e-05, + "loss": 3.4271, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1123431975224767e-05, + "loss": 3.4358, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1115046027714247e-05, + "loss": 3.4379, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1106660080203727e-05, + "loss": 3.4289, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1098274132693207e-05, + "loss": 3.4533, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.108990456398642e-05, + "loss": 3.4489, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.10815186164759e-05, + "loss": 3.4386, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.107313266896538e-05, + "loss": 3.445, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.106474672145486e-05, + "loss": 3.4473, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1056377152748068e-05, + "loss": 3.4305, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1047991205237548e-05, + "loss": 3.444, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.103960525772703e-05, + "loss": 3.4385, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.103121931021651e-05, + "loss": 3.4343, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.102284974150972e-05, + "loss": 3.4247, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.10144637939992e-05, + "loss": 3.441, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.100607784648868e-05, + "loss": 3.451, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.099769189897816e-05, + "loss": 3.4434, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0989322330271373e-05, + "loss": 3.4452, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0980936382760853e-05, + "loss": 3.4367, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972550435250333e-05, + "loss": 3.4348, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.096418086654354e-05, + "loss": 3.4414, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.095579491903302e-05, + "loss": 3.4365, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.09474089715225e-05, + "loss": 3.4269, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0939023024011985e-05, + "loss": 3.4283, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0930653455305194e-05, + "loss": 3.4346, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0922267507794674e-05, + "loss": 3.4337, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0913881560284154e-05, + "loss": 3.4443, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0905495612773634e-05, + "loss": 3.4404, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0897126044066846e-05, + "loss": 3.433, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0888740096556326e-05, + "loss": 3.4426, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0880354149045806e-05, + "loss": 3.4385, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0871968201535286e-05, + "loss": 3.4388, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0863598632828495e-05, + "loss": 3.4353, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0855212685317975e-05, + "loss": 3.4137, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0846826737807455e-05, + "loss": 3.4479, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.083844079029694e-05, + "loss": 3.4316, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0830071221590148e-05, + "loss": 3.4448, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0821685274079628e-05, + "loss": 3.434, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0813299326569108e-05, + "loss": 3.4321, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0804913379058584e-05, + "loss": 3.4223, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.079656018915553e-05, + "loss": 3.4373, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.078817424164501e-05, + "loss": 3.4289, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.077978829413449e-05, + "loss": 3.4318, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.077140234662397e-05, + "loss": 3.4435, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.076301639911345e-05, + "loss": 3.4244, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.075463045160293e-05, + "loss": 3.4254, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.074624450409241e-05, + "loss": 3.4445, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.073785855658189e-05, + "loss": 3.4206, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.07294889878751e-05, + "loss": 3.4161, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.072110304036458e-05, + "loss": 3.4329, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0712717092854058e-05, + "loss": 3.4357, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0704331145343538e-05, + "loss": 3.425, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0695961576636754e-05, + "loss": 3.4338, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687575629126234e-05, + "loss": 3.4167, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.067918968161571e-05, + "loss": 3.4266, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.067080373410519e-05, + "loss": 3.438, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0662434165398403e-05, + "loss": 3.4306, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.065404821788788e-05, + "loss": 3.4417, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0645662270377363e-05, + "loss": 3.4374, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0637276322866843e-05, + "loss": 3.4425, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0628906754160055e-05, + "loss": 3.4221, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.062052080664953e-05, + "loss": 3.4357, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.061213485913901e-05, + "loss": 3.4348, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.060374891162849e-05, + "loss": 3.421, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0595379342921704e-05, + "loss": 3.4372, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0586993395411184e-05, + "loss": 3.4371, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0578607447900664e-05, + "loss": 3.4388, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0570237879193876e-05, + "loss": 3.4426, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0561851931683353e-05, + "loss": 3.4226, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0553465984172833e-05, + "loss": 3.4249, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0545080036662316e-05, + "loss": 3.4352, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.053671046795553e-05, + "loss": 3.4392, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0528324520445005e-05, + "loss": 3.4347, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0519938572934485e-05, + "loss": 3.4357, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0511552625423965e-05, + "loss": 3.4399, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0503166677913445e-05, + "loss": 3.4315, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.0494780730402925e-05, + "loss": 3.4314, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.048639478289241e-05, + "loss": 3.4253, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.047800883538189e-05, + "loss": 3.441, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0469639266675098e-05, + "loss": 3.4427, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0461253319164577e-05, + "loss": 3.43, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0452867371654057e-05, + "loss": 3.4241, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0444481424143534e-05, + "loss": 3.4267, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.043612823424048e-05, + "loss": 3.4327, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.042774228672996e-05, + "loss": 3.4483, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.041935633921944e-05, + "loss": 3.4279, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.041097039170892e-05, + "loss": 3.4319, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.04025844441984e-05, + "loss": 3.4254, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.039419849668788e-05, + "loss": 3.4329, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0385812549177362e-05, + "loss": 3.4248, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.037742660166684e-05, + "loss": 3.4341, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.036905703296005e-05, + "loss": 3.4216, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.036067108544953e-05, + "loss": 3.4389, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.035230151674274e-05, + "loss": 3.4282, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0343915569232224e-05, + "loss": 3.4318, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.0335529621721704e-05, + "loss": 3.4336, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.0327143674211184e-05, + "loss": 3.4311, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.031875772670066e-05, + "loss": 3.4306, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.031037177919014e-05, + "loss": 3.4327, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.030198583167962e-05, + "loss": 3.4352, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.02935998841691e-05, + "loss": 3.4443, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0285246694266045e-05, + "loss": 3.4277, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0276860746755525e-05, + "loss": 3.4349, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.0268474799245005e-05, + "loss": 3.4276, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.026008885173448e-05, + "loss": 3.4332, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.025170290422396e-05, + "loss": 3.4292, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.024331695671344e-05, + "loss": 3.4293, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0234931009202925e-05, + "loss": 3.4199, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0226545061692405e-05, + "loss": 3.4313, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0218175492985614e-05, + "loss": 3.4298, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0209789545475094e-05, + "loss": 3.4336, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0201403597964574e-05, + "loss": 3.4178, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0193017650454054e-05, + "loss": 3.4302, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0184648081747266e-05, + "loss": 3.4294, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0176262134236746e-05, + "loss": 3.4381, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0167876186726226e-05, + "loss": 3.4301, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0159490239215706e-05, + "loss": 3.4364, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0151120670508915e-05, + "loss": 3.4226, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0142734722998395e-05, + "loss": 3.4371, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.013434877548788e-05, + "loss": 3.4366, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.012596282797736e-05, + "loss": 3.4368, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0117593259270567e-05, + "loss": 3.4346, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0109207311760047e-05, + "loss": 3.4378, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0100821364249527e-05, + "loss": 3.4301, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0092435416739007e-05, + "loss": 3.4407, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.008406584803222e-05, + "loss": 3.4233, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.00756799005217e-05, + "loss": 3.4346, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.006729395301118e-05, + "loss": 3.426, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.005890800550066e-05, + "loss": 3.435, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.005053843679387e-05, + "loss": 3.4229, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.004215248928335e-05, + "loss": 3.4239, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0033766541772832e-05, + "loss": 3.434, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0025380594262312e-05, + "loss": 3.4221, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.001701102555552e-05, + "loss": 3.4438, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.8550865650177, + "eval_runtime": 304.3716, + "eval_samples_per_second": 1253.701, + "eval_steps_per_second": 39.179, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.0008625078045e-05, + "loss": 3.4206, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 2.000023913053448e-05, + "loss": 3.4238, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.9991853183023958e-05, + "loss": 3.427, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9983483614317173e-05, + "loss": 3.4359, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.9975097666806653e-05, + "loss": 3.4355, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.9966711719296133e-05, + "loss": 3.4226, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.995832577178561e-05, + "loss": 3.426, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.9949956203078822e-05, + "loss": 3.4232, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.9941570255568302e-05, + "loss": 3.4286, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.9933184308057786e-05, + "loss": 3.4387, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.9924798360547262e-05, + "loss": 3.4254, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.9916428791840475e-05, + "loss": 3.4271, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.9908042844329955e-05, + "loss": 3.4256, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.989965689681943e-05, + "loss": 3.4185, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.989127094930891e-05, + "loss": 3.4291, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.9882901380602127e-05, + "loss": 3.4166, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.9874515433091607e-05, + "loss": 3.4244, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.9866129485581084e-05, + "loss": 3.4289, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.9857743538070564e-05, + "loss": 3.4152, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.9849373969363776e-05, + "loss": 3.4403, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.9840988021853256e-05, + "loss": 3.4404, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.9832602074342736e-05, + "loss": 3.4289, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9824216126832216e-05, + "loss": 3.4293, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.981584655812543e-05, + "loss": 3.4372, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9807460610614905e-05, + "loss": 3.4257, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9799074663104385e-05, + "loss": 3.4273, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.9790688715593865e-05, + "loss": 3.4273, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.978231914688708e-05, + "loss": 3.4266, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.9773933199376557e-05, + "loss": 3.4212, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9765547251866037e-05, + "loss": 3.4262, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.975717768315925e-05, + "loss": 3.4339, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.974879173564873e-05, + "loss": 3.4355, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.974040578813821e-05, + "loss": 3.4375, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.973201984062769e-05, + "loss": 3.4279, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9723650271920902e-05, + "loss": 3.4194, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.971526432441038e-05, + "loss": 3.4327, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.970687837689986e-05, + "loss": 3.4281, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.969849242938934e-05, + "loss": 3.4181, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.969012286068255e-05, + "loss": 3.4186, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.968173691317203e-05, + "loss": 3.4205, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.967335096566151e-05, + "loss": 3.4239, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.966496501815099e-05, + "loss": 3.4298, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9656595449444203e-05, + "loss": 3.431, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.964820950193368e-05, + "loss": 3.4255, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9639823554423163e-05, + "loss": 3.4278, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9631437606912643e-05, + "loss": 3.43, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9623068038205852e-05, + "loss": 3.4258, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9614682090695332e-05, + "loss": 3.4289, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.9606296143184812e-05, + "loss": 3.4031, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.9597910195674292e-05, + "loss": 3.4361, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.9589540626967505e-05, + "loss": 3.4189, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.9581154679456985e-05, + "loss": 3.4358, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.9572768731946465e-05, + "loss": 3.4213, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.9564382784435945e-05, + "loss": 3.4197, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.9556013215729154e-05, + "loss": 3.4119, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.9547643647022366e-05, + "loss": 3.4238, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.953925769951185e-05, + "loss": 3.4208, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.9530871752001326e-05, + "loss": 3.4206, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.9522485804490806e-05, + "loss": 3.4313, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.9514099856980286e-05, + "loss": 3.4162, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.9505713909469766e-05, + "loss": 3.4117, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.9497327961959246e-05, + "loss": 3.4351, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.9488942014448726e-05, + "loss": 3.4119, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.948057244574194e-05, + "loss": 3.4065, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.947218649823142e-05, + "loss": 3.4236, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.9463800550720898e-05, + "loss": 3.4254, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.9455414603210378e-05, + "loss": 3.4161, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.9447045034503587e-05, + "loss": 3.422, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.943865908699307e-05, + "loss": 3.4077, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.943027313948255e-05, + "loss": 3.4162, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.942188719197203e-05, + "loss": 3.4275, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.941351762326524e-05, + "loss": 3.4177, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.940513167575472e-05, + "loss": 3.4312, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.93967457282442e-05, + "loss": 3.423, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.938835978073368e-05, + "loss": 3.4346, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.9379990212026892e-05, + "loss": 3.4119, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.9371604264516372e-05, + "loss": 3.4281, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.9363218317005852e-05, + "loss": 3.4195, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.935483236949533e-05, + "loss": 3.4131, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.934646280078854e-05, + "loss": 3.4265, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.933807685327802e-05, + "loss": 3.4282, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.9329690905767504e-05, + "loss": 3.4247, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.9321321337060713e-05, + "loss": 3.4323, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.9312935389550193e-05, + "loss": 3.408, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.9304549442039673e-05, + "loss": 3.413, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.9296163494529153e-05, + "loss": 3.428, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9287793925822366e-05, + "loss": 3.4288, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.9279407978311846e-05, + "loss": 3.4236, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.9271022030801326e-05, + "loss": 3.4285, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9262636083290802e-05, + "loss": 3.4245, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.9254250135780282e-05, + "loss": 3.4246, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.9245864188269762e-05, + "loss": 3.4208, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.9237478240759242e-05, + "loss": 3.4147, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.9229092293248725e-05, + "loss": 3.4341, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.9220722724541935e-05, + "loss": 3.4283, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.9212336777031414e-05, + "loss": 3.4218, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.9203950829520894e-05, + "loss": 3.4159, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.9195564882010374e-05, + "loss": 3.4124, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.9187195313303587e-05, + "loss": 3.4219, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.9178809365793067e-05, + "loss": 3.4352, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9170423418282547e-05, + "loss": 3.4204, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.9162037470772027e-05, + "loss": 3.4226, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9153667902065236e-05, + "loss": 3.4156, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9145281954554716e-05, + "loss": 3.4185, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.9136896007044196e-05, + "loss": 3.4193, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.912851005953368e-05, + "loss": 3.4183, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9120140490826888e-05, + "loss": 3.4096, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9111754543316368e-05, + "loss": 3.4294, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9103384974609577e-05, + "loss": 3.4195, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9094999027099057e-05, + "loss": 3.4196, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.908661307958854e-05, + "loss": 3.4165, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.907822713207802e-05, + "loss": 3.4246, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.90698411845675e-05, + "loss": 3.4219, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.906145523705698e-05, + "loss": 3.421, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9053069289546457e-05, + "loss": 3.4265, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9044683342035937e-05, + "loss": 3.4301, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.903631377332915e-05, + "loss": 3.4177, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.9027944204622362e-05, + "loss": 3.4277, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.9019558257111842e-05, + "loss": 3.4137, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.9011172309601322e-05, + "loss": 3.4236, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.9002786362090802e-05, + "loss": 3.419, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8994400414580282e-05, + "loss": 3.4155, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.898601446706976e-05, + "loss": 3.4131, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.897762851955924e-05, + "loss": 3.422, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.8969258950852454e-05, + "loss": 3.4204, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.896087300334193e-05, + "loss": 3.4221, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.895248705583141e-05, + "loss": 3.4092, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.894410110832089e-05, + "loss": 3.4171, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.8935731539614103e-05, + "loss": 3.4188, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.8927345592103583e-05, + "loss": 3.4256, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.8918959644593063e-05, + "loss": 3.4238, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.8910573697082543e-05, + "loss": 3.4227, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.8902204128375755e-05, + "loss": 3.4124, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.8893818180865232e-05, + "loss": 3.4291, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.8885432233354712e-05, + "loss": 3.4263, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.8877046285844195e-05, + "loss": 3.4277, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.8868676717137404e-05, + "loss": 3.4247, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.8860290769626884e-05, + "loss": 3.4245, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.8851904822116364e-05, + "loss": 3.4228, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.8843518874605844e-05, + "loss": 3.4286, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8835149305899057e-05, + "loss": 3.4123, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.8826763358388537e-05, + "loss": 3.4229, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.8818377410878017e-05, + "loss": 3.4172, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.8809991463367497e-05, + "loss": 3.4218, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.8801621894660706e-05, + "loss": 3.4104, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.8793235947150186e-05, + "loss": 3.4154, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.8784849999639666e-05, + "loss": 3.4212, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.877646405212915e-05, + "loss": 3.4169, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8768094483422358e-05, + "loss": 3.4307, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.856520891189575, + "eval_runtime": 307.0444, + "eval_samples_per_second": 1242.788, + "eval_steps_per_second": 38.838, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8759708535911838e-05, + "loss": 3.4072, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8751322588401318e-05, + "loss": 3.4119, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8742936640890798e-05, + "loss": 3.4169, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734550693380278e-05, + "loss": 3.4296, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.872618112467349e-05, + "loss": 3.4258, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.871779517716297e-05, + "loss": 3.4112, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.870940922965245e-05, + "loss": 3.4183, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.870102328214193e-05, + "loss": 3.412, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.869265371343514e-05, + "loss": 3.4153, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.868426776592462e-05, + "loss": 3.4308, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8675881818414103e-05, + "loss": 3.4143, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667495870903583e-05, + "loss": 3.4147, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8659126302196792e-05, + "loss": 3.4257, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.865074035468627e-05, + "loss": 3.4009, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.864235440717575e-05, + "loss": 3.4157, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.863396845966523e-05, + "loss": 3.406, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8625598890958444e-05, + "loss": 3.4176, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8617212943447924e-05, + "loss": 3.4167, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8608826995937404e-05, + "loss": 3.4042, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.860044104842688e-05, + "loss": 3.4272, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8592071479720093e-05, + "loss": 3.4288, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.8583685532209573e-05, + "loss": 3.4206, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8575299584699053e-05, + "loss": 3.4221, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8566913637188533e-05, + "loss": 3.4218, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8558544068481745e-05, + "loss": 3.4185, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8550158120971225e-05, + "loss": 3.4149, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8541772173460705e-05, + "loss": 3.4211, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8533386225950182e-05, + "loss": 3.4206, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8525016657243398e-05, + "loss": 3.4077, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8516630709732878e-05, + "loss": 3.4162, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8508244762222354e-05, + "loss": 3.4231, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.8499858814711834e-05, + "loss": 3.4289, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8491489246005047e-05, + "loss": 3.4248, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8483103298494527e-05, + "loss": 3.42, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8474717350984007e-05, + "loss": 3.412, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8466331403473487e-05, + "loss": 3.4154, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.84579618347667e-05, + "loss": 3.4219, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.844957588725618e-05, + "loss": 3.4104, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8441189939745656e-05, + "loss": 3.409, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8432820371038868e-05, + "loss": 3.4098, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.842443442352835e-05, + "loss": 3.4148, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8416048476017828e-05, + "loss": 3.4156, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8407662528507308e-05, + "loss": 3.4239, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.839929295980052e-05, + "loss": 3.4173, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.839090701229e-05, + "loss": 3.4188, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.838252106477948e-05, + "loss": 3.4181, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.837413511726896e-05, + "loss": 3.4151, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8365765548562173e-05, + "loss": 3.4236, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8357379601051653e-05, + "loss": 3.3918, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.834899365354113e-05, + "loss": 3.4213, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.834060770603061e-05, + "loss": 3.4098, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8332238137323822e-05, + "loss": 3.4258, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.83238521898133e-05, + "loss": 3.4119, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.831546624230278e-05, + "loss": 3.4098, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.830708029479226e-05, + "loss": 3.4003, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8298727104889203e-05, + "loss": 3.4143, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.8290341157378683e-05, + "loss": 3.4159, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8281955209868167e-05, + "loss": 3.4069, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.8273569262357646e-05, + "loss": 3.4212, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8265183314847126e-05, + "loss": 3.4097, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8256797367336603e-05, + "loss": 3.3951, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.8248411419826083e-05, + "loss": 3.4247, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.8240025472315563e-05, + "loss": 3.4043, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8231655903608775e-05, + "loss": 3.3979, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8223269956098255e-05, + "loss": 3.4146, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8214884008587735e-05, + "loss": 3.4129, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8206498061077215e-05, + "loss": 3.4019, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8198128492370424e-05, + "loss": 3.4175, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8189742544859904e-05, + "loss": 3.3992, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8181356597349388e-05, + "loss": 3.4024, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8172970649838868e-05, + "loss": 3.4165, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8164601081132077e-05, + "loss": 3.4085, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8156215133621557e-05, + "loss": 3.4236, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8147829186111037e-05, + "loss": 3.4115, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8139443238600517e-05, + "loss": 3.4222, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.813107366989373e-05, + "loss": 3.4042, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.812268772238321e-05, + "loss": 3.4196, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.811430177487269e-05, + "loss": 3.4059, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.810591582736217e-05, + "loss": 3.4049, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097546258655378e-05, + "loss": 3.4152, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8089160311144858e-05, + "loss": 3.4174, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.808077436363434e-05, + "loss": 3.4155, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.807240479492755e-05, + "loss": 3.4232, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.806401884741703e-05, + "loss": 3.3987, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.805563289990651e-05, + "loss": 3.4024, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.804724695239599e-05, + "loss": 3.4184, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.803886100488547e-05, + "loss": 3.4196, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.803047505737495e-05, + "loss": 3.4117, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.802208910986443e-05, + "loss": 3.4194, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.801370316235391e-05, + "loss": 3.4126, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8005333593647123e-05, + "loss": 3.4158, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7996947646136603e-05, + "loss": 3.4131, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.798856169862608e-05, + "loss": 3.4034, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.798019212991929e-05, + "loss": 3.4199, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7971806182408775e-05, + "loss": 3.4202, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.796342023489825e-05, + "loss": 3.4117, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.795503428738773e-05, + "loss": 3.4099, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.7946664718680944e-05, + "loss": 3.3973, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.7938295149974153e-05, + "loss": 3.4115, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.7929909202463636e-05, + "loss": 3.4244, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7921523254953116e-05, + "loss": 3.4091, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7913137307442596e-05, + "loss": 3.413, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7904751359932076e-05, + "loss": 3.4035, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7896365412421553e-05, + "loss": 3.4074, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7887979464911033e-05, + "loss": 3.4126, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7879593517400513e-05, + "loss": 3.4056, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7871223948693725e-05, + "loss": 3.4029, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7862838001183205e-05, + "loss": 3.4197, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7854468432476418e-05, + "loss": 3.4154, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7846082484965898e-05, + "loss": 3.402, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7837696537455374e-05, + "loss": 3.4101, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.7829310589944858e-05, + "loss": 3.4099, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.7820924642434337e-05, + "loss": 3.4168, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.7812538694923817e-05, + "loss": 3.4067, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7804152747413297e-05, + "loss": 3.4195, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7795766799902777e-05, + "loss": 3.4199, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7787397231195986e-05, + "loss": 3.4053, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.77790276624892e-05, + "loss": 3.4154, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.777064171497868e-05, + "loss": 3.4064, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.776225576746816e-05, + "loss": 3.4111, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.775386981995764e-05, + "loss": 3.4123, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.774548387244712e-05, + "loss": 3.4049, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.77370979249366e-05, + "loss": 3.402, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.772871197742608e-05, + "loss": 3.413, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.772034240871929e-05, + "loss": 3.4128, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.771195646120877e-05, + "loss": 3.4106, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.770357051369825e-05, + "loss": 3.3982, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.769518456618773e-05, + "loss": 3.4045, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.768681499748094e-05, + "loss": 3.4057, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.767842904997042e-05, + "loss": 3.4179, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.76700431024599e-05, + "loss": 3.4131, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.766165715494938e-05, + "loss": 3.4148, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7653287586242592e-05, + "loss": 3.3999, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7644901638732072e-05, + "loss": 3.4214, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7636515691221552e-05, + "loss": 3.4127, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.762812974371103e-05, + "loss": 3.4178, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7619760175004245e-05, + "loss": 3.4095, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7611374227493725e-05, + "loss": 3.4141, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7602988279983205e-05, + "loss": 3.4109, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.759460233247268e-05, + "loss": 3.4232, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7586232763765894e-05, + "loss": 3.3971, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.7577846816255374e-05, + "loss": 3.4158, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7569460868744854e-05, + "loss": 3.4068, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7561074921234334e-05, + "loss": 3.4107, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7552705352527546e-05, + "loss": 3.4028, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7544319405017026e-05, + "loss": 3.406, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7535933457506503e-05, + "loss": 3.41, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7527547509995983e-05, + "loss": 3.4091, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.75191779412892e-05, + "loss": 3.4156, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.8581125736236572, + "eval_runtime": 310.7561, + "eval_samples_per_second": 1227.944, + "eval_steps_per_second": 38.374, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.751079199377868e-05, + "loss": 3.4008, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.7502406046268155e-05, + "loss": 3.4016, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7494020098757635e-05, + "loss": 3.4032, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7485650530050847e-05, + "loss": 3.4173, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7477264582540327e-05, + "loss": 3.4194, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.7468878635029807e-05, + "loss": 3.3988, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.7460492687519287e-05, + "loss": 3.4062, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.74521231188125e-05, + "loss": 3.4022, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7443737171301976e-05, + "loss": 3.4089, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7435351223791456e-05, + "loss": 3.4178, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7426965276280936e-05, + "loss": 3.4026, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.741859570757415e-05, + "loss": 3.407, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.741020976006363e-05, + "loss": 3.4143, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.740182381255311e-05, + "loss": 3.3944, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.739343786504259e-05, + "loss": 3.4045, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7385068296335798e-05, + "loss": 3.3937, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.737668234882528e-05, + "loss": 3.4089, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.736829640131476e-05, + "loss": 3.4072, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.735991045380424e-05, + "loss": 3.3961, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.735154088509745e-05, + "loss": 3.4155, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.734315493758693e-05, + "loss": 3.4186, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.733476899007641e-05, + "loss": 3.4133, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.732638304256589e-05, + "loss": 3.4121, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.7318013473859102e-05, + "loss": 3.4105, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.7309627526348582e-05, + "loss": 3.4112, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.7301241578838062e-05, + "loss": 3.4051, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.7292855631327542e-05, + "loss": 3.4067, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.728448606262075e-05, + "loss": 3.4128, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.7276100115110235e-05, + "loss": 3.3961, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.7267714167599715e-05, + "loss": 3.4053, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7259344598892924e-05, + "loss": 3.414, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7250958651382404e-05, + "loss": 3.4098, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7242572703871884e-05, + "loss": 3.42, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.7234186756361364e-05, + "loss": 3.406, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.7225817187654576e-05, + "loss": 3.4016, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.7217431240144056e-05, + "loss": 3.4058, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.7209045292633536e-05, + "loss": 3.412, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.7200659345123016e-05, + "loss": 3.3975, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.7192289776416225e-05, + "loss": 3.4012, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7183920207709438e-05, + "loss": 3.4011, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.717553426019892e-05, + "loss": 3.4004, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.7167148312688397e-05, + "loss": 3.4061, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.7158762365177877e-05, + "loss": 3.411, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.7150376417667357e-05, + "loss": 3.4073, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7141990470156837e-05, + "loss": 3.4037, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7133604522646317e-05, + "loss": 3.409, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7125218575135797e-05, + "loss": 3.4017, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.711684900642901e-05, + "loss": 3.4115, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.710846305891849e-05, + "loss": 3.3841, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.710007711140797e-05, + "loss": 3.4102, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.709169116389745e-05, + "loss": 3.4005, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.708332159519066e-05, + "loss": 3.4169, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.707493564768014e-05, + "loss": 3.4024, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.7066549700169622e-05, + "loss": 3.4002, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.705818013146283e-05, + "loss": 3.3937, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.704979418395231e-05, + "loss": 3.3998, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.704142461524552e-05, + "loss": 3.4113, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.7033038667735e-05, + "loss": 3.3907, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.7024652720224483e-05, + "loss": 3.414, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7016266772713963e-05, + "loss": 3.401, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.7007880825203443e-05, + "loss": 3.3831, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6999494877692923e-05, + "loss": 3.4157, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.69911089301824e-05, + "loss": 3.395, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.6982739361475612e-05, + "loss": 3.3855, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.6974353413965092e-05, + "loss": 3.4045, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.6965967466454576e-05, + "loss": 3.4022, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6957581518944052e-05, + "loss": 3.3889, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.6949211950237265e-05, + "loss": 3.4092, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.6940826002726745e-05, + "loss": 3.3881, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.693244005521622e-05, + "loss": 3.3916, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.6924054107705705e-05, + "loss": 3.4064, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.6915684538998917e-05, + "loss": 3.4022, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.6907298591488397e-05, + "loss": 3.4093, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.6898912643977874e-05, + "loss": 3.4037, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6890526696467354e-05, + "loss": 3.4111, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.6882157127760566e-05, + "loss": 3.395, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.6873771180250046e-05, + "loss": 3.4123, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.6865385232739526e-05, + "loss": 3.3938, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.6856999285229006e-05, + "loss": 3.3951, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.684862971652222e-05, + "loss": 3.4045, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6840243769011695e-05, + "loss": 3.4009, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6831857821501175e-05, + "loss": 3.4075, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.682348825279439e-05, + "loss": 3.413, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.681510230528387e-05, + "loss": 3.3932, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.6806716357773347e-05, + "loss": 3.3916, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.6798330410262827e-05, + "loss": 3.4038, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.678996084155604e-05, + "loss": 3.4129, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.678157489404552e-05, + "loss": 3.3962, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.6773188946535e-05, + "loss": 3.4095, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.676480299902448e-05, + "loss": 3.4055, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.675641705151396e-05, + "loss": 3.4047, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.674803110400344e-05, + "loss": 3.4001, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.673964515649292e-05, + "loss": 3.3938, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.67312592089824e-05, + "loss": 3.4095, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.672288964027561e-05, + "loss": 3.4083, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6714503692765092e-05, + "loss": 3.4056, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.6706117745254572e-05, + "loss": 3.3944, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.6697731797744052e-05, + "loss": 3.389, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.668937860784099e-05, + "loss": 3.4013, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.6680992660330473e-05, + "loss": 3.4142, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.6672606712819953e-05, + "loss": 3.3993, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.6664220765309433e-05, + "loss": 3.4031, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.6655834817798913e-05, + "loss": 3.3972, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.6647448870288393e-05, + "loss": 3.3956, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.6639062922777873e-05, + "loss": 3.4046, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.663067697526735e-05, + "loss": 3.392, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.6622307406560562e-05, + "loss": 3.3947, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.6613921459050046e-05, + "loss": 3.4055, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6605535511539526e-05, + "loss": 3.4063, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.6597165942832735e-05, + "loss": 3.3976, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.6588779995322215e-05, + "loss": 3.3969, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6580394047811695e-05, + "loss": 3.3959, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.6572008100301174e-05, + "loss": 3.4083, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.6563622152790654e-05, + "loss": 3.3958, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.6555236205280134e-05, + "loss": 3.4106, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.6546850257769614e-05, + "loss": 3.4086, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.6538480689062823e-05, + "loss": 3.3984, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.6530111120356036e-05, + "loss": 3.4019, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.6521725172845516e-05, + "loss": 3.3989, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.6513339225335e-05, + "loss": 3.3989, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.6504953277824476e-05, + "loss": 3.4067, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6496567330313956e-05, + "loss": 3.392, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6488181382803436e-05, + "loss": 3.3919, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6479795435292916e-05, + "loss": 3.4016, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6471409487782396e-05, + "loss": 3.4008, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.6463039919075608e-05, + "loss": 3.3992, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6454653971565088e-05, + "loss": 3.3922, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.6446268024054568e-05, + "loss": 3.3978, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.6437898455347777e-05, + "loss": 3.3925, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.6429512507837257e-05, + "loss": 3.4119, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.6421126560326737e-05, + "loss": 3.4001, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.6412740612816217e-05, + "loss": 3.4042, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.640437104410943e-05, + "loss": 3.3893, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.639598509659891e-05, + "loss": 3.4099, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.638759914908839e-05, + "loss": 3.4005, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.637921320157787e-05, + "loss": 3.4109, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6370843632871082e-05, + "loss": 3.4072, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6362457685360562e-05, + "loss": 3.401, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6354071737850042e-05, + "loss": 3.4012, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.634568579033952e-05, + "loss": 3.4143, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.633731622163273e-05, + "loss": 3.3891, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.632893027412221e-05, + "loss": 3.405, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.632054432661169e-05, + "loss": 3.3949, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.631215837910117e-05, + "loss": 3.4013, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.6303788810394383e-05, + "loss": 3.3937, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.6295402862883863e-05, + "loss": 3.3947, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.6287016915373343e-05, + "loss": 3.3948, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.6278630967862823e-05, + "loss": 3.4046, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.6270261399156032e-05, + "loss": 3.4028, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.8593807220458984, + "eval_runtime": 310.1219, + "eval_samples_per_second": 1230.455, + "eval_steps_per_second": 38.453, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.6261875451645515e-05, + "loss": 3.3916, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.6253489504134995e-05, + "loss": 3.3895, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6245103556624475e-05, + "loss": 3.3934, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6236717609113952e-05, + "loss": 3.4083, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6228348040407164e-05, + "loss": 3.4099, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6219962092896644e-05, + "loss": 3.3899, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.6211576145386124e-05, + "loss": 3.3954, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.6203190197875604e-05, + "loss": 3.3907, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6194820629168817e-05, + "loss": 3.3985, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.6186434681658297e-05, + "loss": 3.4009, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.6178048734147773e-05, + "loss": 3.3996, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.6169662786637253e-05, + "loss": 3.3971, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.616129321793047e-05, + "loss": 3.406, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.615290727041995e-05, + "loss": 3.3826, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.6144521322909426e-05, + "loss": 3.3931, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6136135375398906e-05, + "loss": 3.3821, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.6127765806692118e-05, + "loss": 3.401, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6119379859181598e-05, + "loss": 3.4007, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6110993911671078e-05, + "loss": 3.3796, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6102607964160558e-05, + "loss": 3.4027, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.609423839545377e-05, + "loss": 3.4101, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.6085852447943247e-05, + "loss": 3.3995, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6077466500432727e-05, + "loss": 3.4036, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6069080552922207e-05, + "loss": 3.4024, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6060710984215423e-05, + "loss": 3.3999, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.60523250367049e-05, + "loss": 3.3936, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.604393908919438e-05, + "loss": 3.3946, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.603555314168386e-05, + "loss": 3.401, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.602718357297707e-05, + "loss": 3.3874, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.601879762546655e-05, + "loss": 3.3964, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.601041167795603e-05, + "loss": 3.4053, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.600202573044551e-05, + "loss": 3.4048, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.599365616173872e-05, + "loss": 3.3997, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.59852702142282e-05, + "loss": 3.4065, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.597688426671768e-05, + "loss": 3.3868, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.596849831920716e-05, + "loss": 3.3987, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5960128750500373e-05, + "loss": 3.4033, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.5951742802989853e-05, + "loss": 3.3831, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.5943356855479333e-05, + "loss": 3.393, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5934987286772542e-05, + "loss": 3.3914, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.5926601339262022e-05, + "loss": 3.3897, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.5918215391751505e-05, + "loss": 3.3944, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.5909829444240985e-05, + "loss": 3.4039, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.5901443496730465e-05, + "loss": 3.396, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5893057549219945e-05, + "loss": 3.3972, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5884671601709425e-05, + "loss": 3.3994, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.5876285654198902e-05, + "loss": 3.3917, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5867916085492114e-05, + "loss": 3.402, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.5859530137981594e-05, + "loss": 3.3774, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5851144190471078e-05, + "loss": 3.3994, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5842758242960554e-05, + "loss": 3.3868, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5834388674253767e-05, + "loss": 3.4069, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5826002726743247e-05, + "loss": 3.3927, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5817616779232723e-05, + "loss": 3.3865, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.5809230831722206e-05, + "loss": 3.3835, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.580086126301542e-05, + "loss": 3.3919, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5792491694308628e-05, + "loss": 3.4001, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5784105746798108e-05, + "loss": 3.3818, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.5775719799287588e-05, + "loss": 3.4047, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5767333851777068e-05, + "loss": 3.392, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5758947904266548e-05, + "loss": 3.3714, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.5750561956756028e-05, + "loss": 3.403, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.5742176009245508e-05, + "loss": 3.3849, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.573380644053872e-05, + "loss": 3.3774, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5725420493028197e-05, + "loss": 3.3898, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5717034545517677e-05, + "loss": 3.3934, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.570864859800716e-05, + "loss": 3.3831, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5700279029300373e-05, + "loss": 3.3996, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.569189308178985e-05, + "loss": 3.3739, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.568350713427933e-05, + "loss": 3.3828, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.567512118676881e-05, + "loss": 3.3962, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.566675161806202e-05, + "loss": 3.3947, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.56583656705515e-05, + "loss": 3.3943, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.564997972304098e-05, + "loss": 3.3952, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.564159377553046e-05, + "loss": 3.3981, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.563322420682367e-05, + "loss": 3.3885, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.562483825931315e-05, + "loss": 3.4011, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.561645231180263e-05, + "loss": 3.3862, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.5608066364292114e-05, + "loss": 3.3826, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5599696795585323e-05, + "loss": 3.3918, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5591310848074803e-05, + "loss": 3.3949, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5582924900564283e-05, + "loss": 3.3976, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5574555331857495e-05, + "loss": 3.4024, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5566169384346975e-05, + "loss": 3.3844, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.5557783436836455e-05, + "loss": 3.3801, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5549397489325935e-05, + "loss": 3.3942, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5541027920619144e-05, + "loss": 3.4031, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5532641973108624e-05, + "loss": 3.3855, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5524256025598104e-05, + "loss": 3.398, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5515870078087584e-05, + "loss": 3.3974, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.5507484130577064e-05, + "loss": 3.3932, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.5499098183066547e-05, + "loss": 3.3907, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.5490712235556027e-05, + "loss": 3.3837, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.5482326288045504e-05, + "loss": 3.4006, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.5473956719338716e-05, + "loss": 3.3983, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5465570771828196e-05, + "loss": 3.3923, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.5457184824317676e-05, + "loss": 3.3868, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.5448798876807156e-05, + "loss": 3.3791, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.5440445686904098e-05, + "loss": 3.3905, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5432059739393578e-05, + "loss": 3.4033, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.5423673791883058e-05, + "loss": 3.3904, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5415287844372538e-05, + "loss": 3.3914, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5406901896862018e-05, + "loss": 3.3871, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.53985159493515e-05, + "loss": 3.3879, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5390130001840978e-05, + "loss": 3.3928, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5381744054330458e-05, + "loss": 3.3885, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.537337448562367e-05, + "loss": 3.3826, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5364988538113147e-05, + "loss": 3.3959, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.535660259060263e-05, + "loss": 3.3941, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.5348233021895842e-05, + "loss": 3.3862, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.5339847074385322e-05, + "loss": 3.3902, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.53314611268748e-05, + "loss": 3.3849, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.532307517936428e-05, + "loss": 3.3982, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.531468923185376e-05, + "loss": 3.3847, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.530630328434324e-05, + "loss": 3.3987, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5297917336832722e-05, + "loss": 3.3994, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.528954776812593e-05, + "loss": 3.3888, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5281178199419144e-05, + "loss": 3.3938, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.527279225190862e-05, + "loss": 3.3893, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.52644063043981e-05, + "loss": 3.3884, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5256020356887582e-05, + "loss": 3.3951, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5247634409377062e-05, + "loss": 3.3842, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5239248461866542e-05, + "loss": 3.3836, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5230862514356024e-05, + "loss": 3.3905, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5222476566845503e-05, + "loss": 3.3895, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5214106998138714e-05, + "loss": 3.3893, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5205721050628194e-05, + "loss": 3.3808, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5197335103117674e-05, + "loss": 3.3836, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5188965534410885e-05, + "loss": 3.386, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5180579586900365e-05, + "loss": 3.4006, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5172193639389845e-05, + "loss": 3.3872, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5163807691879325e-05, + "loss": 3.399, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5155438123172536e-05, + "loss": 3.3811, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5147052175662016e-05, + "loss": 3.396, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5138666228151496e-05, + "loss": 3.3926, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5130280280640977e-05, + "loss": 3.3978, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5121910711934186e-05, + "loss": 3.3954, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5113541143227397e-05, + "loss": 3.3896, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5105155195716877e-05, + "loss": 3.3937, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5096769248206357e-05, + "loss": 3.3977, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5088383300695839e-05, + "loss": 3.3837, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5079997353185319e-05, + "loss": 3.3936, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5071611405674799e-05, + "loss": 3.3893, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5063225458164277e-05, + "loss": 3.3899, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5054839510653757e-05, + "loss": 3.38, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.504646994194697e-05, + "loss": 3.3904, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.503808399443645e-05, + "loss": 3.3844, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5029698046925927e-05, + "loss": 3.3869, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5021312099415407e-05, + "loss": 3.3947, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.8606388568878174, + "eval_runtime": 303.6197, + "eval_samples_per_second": 1256.806, + "eval_steps_per_second": 39.276, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.5012942530708622e-05, + "loss": 3.3908, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5004556583198102e-05, + "loss": 3.3778, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4996170635687578e-05, + "loss": 3.3865, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.498778468817706e-05, + "loss": 3.395, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4979415119470272e-05, + "loss": 3.3949, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4971029171959749e-05, + "loss": 3.3831, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.496264322444923e-05, + "loss": 3.3898, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.495425727693871e-05, + "loss": 3.3818, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4945887708231923e-05, + "loss": 3.3859, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4937501760721401e-05, + "loss": 3.3895, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4929115813210881e-05, + "loss": 3.3936, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4920729865700361e-05, + "loss": 3.3841, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4912360296993574e-05, + "loss": 3.3976, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4903974349483052e-05, + "loss": 3.3701, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4895588401972532e-05, + "loss": 3.3851, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4887218833265746e-05, + "loss": 3.3738, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4878832885755223e-05, + "loss": 3.3899, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4870446938244702e-05, + "loss": 3.3912, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4862060990734184e-05, + "loss": 3.3764, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4853691422027397e-05, + "loss": 3.3908, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4845305474516873e-05, + "loss": 3.4016, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4836919527006355e-05, + "loss": 3.388, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4828533579495835e-05, + "loss": 3.3941, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4820164010789046e-05, + "loss": 3.3929, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4811778063278526e-05, + "loss": 3.392, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4803392115768006e-05, + "loss": 3.3843, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4795006168257485e-05, + "loss": 3.3822, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4786636599550696e-05, + "loss": 3.395, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4778250652040176e-05, + "loss": 3.3771, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4769864704529656e-05, + "loss": 3.3852, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4761478757019138e-05, + "loss": 3.3989, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4753109188312347e-05, + "loss": 3.3912, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4744723240801827e-05, + "loss": 3.3893, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4736337293291309e-05, + "loss": 3.3969, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4727951345780788e-05, + "loss": 3.3808, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4719581777074e-05, + "loss": 3.3879, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.471119582956348e-05, + "loss": 3.388, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.470280988205296e-05, + "loss": 3.377, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4694423934542439e-05, + "loss": 3.3839, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.468605436583565e-05, + "loss": 3.3829, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.467766841832513e-05, + "loss": 3.379, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.466928247081461e-05, + "loss": 3.3843, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4660896523304091e-05, + "loss": 3.3966, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4652510575793571e-05, + "loss": 3.3869, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4644124628283051e-05, + "loss": 3.3868, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.463573868077253e-05, + "loss": 3.3911, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.462735273326201e-05, + "loss": 3.3784, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4618983164555222e-05, + "loss": 3.3923, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.46105972170447e-05, + "loss": 3.3726, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.460221126953418e-05, + "loss": 3.3874, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.459382532202366e-05, + "loss": 3.3776, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4585455753316873e-05, + "loss": 3.3971, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4577069805806351e-05, + "loss": 3.3834, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4568683858295831e-05, + "loss": 3.3753, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4560297910785311e-05, + "loss": 3.3744, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4551928342078525e-05, + "loss": 3.3793, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4543558773371734e-05, + "loss": 3.3934, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4535172825861216e-05, + "loss": 3.3689, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4526786878350696e-05, + "loss": 3.3965, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4518400930840172e-05, + "loss": 3.3818, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4510014983329654e-05, + "loss": 3.364, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4501629035819134e-05, + "loss": 3.3938, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4493243088308614e-05, + "loss": 3.3737, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4484873519601825e-05, + "loss": 3.3694, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4476487572091305e-05, + "loss": 3.377, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4468101624580785e-05, + "loss": 3.3875, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4459715677070265e-05, + "loss": 3.379, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4451346108363475e-05, + "loss": 3.3826, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4442960160852955e-05, + "loss": 3.3685, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4434574213342435e-05, + "loss": 3.3711, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4426188265831917e-05, + "loss": 3.3856, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4417818697125126e-05, + "loss": 3.3891, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4409432749614608e-05, + "loss": 3.3845, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4401046802104088e-05, + "loss": 3.3836, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4392660854593568e-05, + "loss": 3.3896, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4384291285886778e-05, + "loss": 3.3767, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4375905338376258e-05, + "loss": 3.3868, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4367519390865738e-05, + "loss": 3.3798, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4359133443355218e-05, + "loss": 3.3736, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4350763874648429e-05, + "loss": 3.3858, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4342377927137909e-05, + "loss": 3.3776, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4333991979627389e-05, + "loss": 3.3898, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.43256224109206e-05, + "loss": 3.3945, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.431723646341008e-05, + "loss": 3.3804, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4308850515899561e-05, + "loss": 3.3647, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4300464568389041e-05, + "loss": 3.3861, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.429209499968225e-05, + "loss": 3.3909, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4283709052171732e-05, + "loss": 3.3798, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4275323104661212e-05, + "loss": 3.3867, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4266937157150692e-05, + "loss": 3.3917, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4258551209640172e-05, + "loss": 3.3792, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4250165262129654e-05, + "loss": 3.3826, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.424177931461913e-05, + "loss": 3.3747, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.423339336710861e-05, + "loss": 3.3897, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4225023798401824e-05, + "loss": 3.3888, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4216654229695033e-05, + "loss": 3.3841, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4208268282184515e-05, + "loss": 3.3761, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4199882334673995e-05, + "loss": 3.369, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4191496387163475e-05, + "loss": 3.3789, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4183110439652953e-05, + "loss": 3.3938, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4174724492142433e-05, + "loss": 3.3811, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4166338544631913e-05, + "loss": 3.3779, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4157952597121393e-05, + "loss": 3.3814, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4149583028414604e-05, + "loss": 3.3788, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4141197080904084e-05, + "loss": 3.3813, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4132811133393564e-05, + "loss": 3.3799, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4124425185883044e-05, + "loss": 3.3725, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4116055617176255e-05, + "loss": 3.3837, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4107669669665734e-05, + "loss": 3.3854, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4099300100958949e-05, + "loss": 3.379, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4090914153448425e-05, + "loss": 3.3759, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4082528205937905e-05, + "loss": 3.3772, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4074142258427387e-05, + "loss": 3.3848, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4065756310916867e-05, + "loss": 3.3783, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4057370363406347e-05, + "loss": 3.3832, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4048984415895827e-05, + "loss": 3.3851, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4040614847189037e-05, + "loss": 3.3842, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4032245278482248e-05, + "loss": 3.3852, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4023859330971728e-05, + "loss": 3.3778, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4015473383461208e-05, + "loss": 3.3797, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4007087435950688e-05, + "loss": 3.3823, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.399870148844017e-05, + "loss": 3.3723, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.399031554092965e-05, + "loss": 3.3795, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.398192959341913e-05, + "loss": 3.375, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3973543645908608e-05, + "loss": 3.3811, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.396517407720182e-05, + "loss": 3.3809, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.39567881296913e-05, + "loss": 3.3727, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3948402182180779e-05, + "loss": 3.3728, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3940016234670259e-05, + "loss": 3.3775, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3931646665963471e-05, + "loss": 3.3912, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3923260718452951e-05, + "loss": 3.3791, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.391487477094243e-05, + "loss": 3.3873, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3906505202235642e-05, + "loss": 3.3709, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3898119254725123e-05, + "loss": 3.3836, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3889733307214603e-05, + "loss": 3.385, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.388134735970408e-05, + "loss": 3.3856, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3872977790997294e-05, + "loss": 3.3867, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3864608222290503e-05, + "loss": 3.3793, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3856222274779985e-05, + "loss": 3.3887, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3847836327269465e-05, + "loss": 3.3896, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3839450379758945e-05, + "loss": 3.3702, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3831064432248425e-05, + "loss": 3.3832, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3822678484737903e-05, + "loss": 3.3766, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3814292537227383e-05, + "loss": 3.3803, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3805906589716863e-05, + "loss": 3.3726, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3797537021010077e-05, + "loss": 3.3801, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3789151073499554e-05, + "loss": 3.3741, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3780765125989034e-05, + "loss": 3.379, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3772379178478514e-05, + "loss": 3.3823, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.8616771697998047, + "eval_runtime": 303.7846, + "eval_samples_per_second": 1256.124, + "eval_steps_per_second": 39.255, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3764009609771724e-05, + "loss": 3.3892, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3755623662261204e-05, + "loss": 3.3664, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3747237714750686e-05, + "loss": 3.376, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3738851767240166e-05, + "loss": 3.3863, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3730482198533377e-05, + "loss": 3.3824, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3722096251022857e-05, + "loss": 3.3767, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3713710303512337e-05, + "loss": 3.3788, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3705324356001817e-05, + "loss": 3.3705, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3696954787295027e-05, + "loss": 3.3755, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3688568839784507e-05, + "loss": 3.3833, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3680182892273987e-05, + "loss": 3.3804, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3671796944763467e-05, + "loss": 3.3777, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3663427376056678e-05, + "loss": 3.388, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3655041428546158e-05, + "loss": 3.358, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.364665548103564e-05, + "loss": 3.3739, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.363826953352512e-05, + "loss": 3.3625, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3629899964818329e-05, + "loss": 3.3836, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.362151401730781e-05, + "loss": 3.3778, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.361312806979729e-05, + "loss": 3.3683, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.360474212228677e-05, + "loss": 3.3767, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3596372553579981e-05, + "loss": 3.3947, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3587986606069461e-05, + "loss": 3.3781, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3579600658558941e-05, + "loss": 3.3817, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3571214711048421e-05, + "loss": 3.3866, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3562845142341632e-05, + "loss": 3.3828, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3554459194831112e-05, + "loss": 3.3721, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3546073247320593e-05, + "loss": 3.3725, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3537687299810073e-05, + "loss": 3.3835, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3529317731103282e-05, + "loss": 3.3664, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3520931783592764e-05, + "loss": 3.3743, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3512545836082244e-05, + "loss": 3.3888, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3504159888571724e-05, + "loss": 3.3821, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3495790319864935e-05, + "loss": 3.3819, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3487404372354415e-05, + "loss": 3.3842, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3479018424843895e-05, + "loss": 3.3697, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3470632477333375e-05, + "loss": 3.3804, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3462262908626585e-05, + "loss": 3.3804, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3453876961116065e-05, + "loss": 3.3643, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3445491013605547e-05, + "loss": 3.3773, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3437121444898756e-05, + "loss": 3.3707, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3428735497388236e-05, + "loss": 3.3681, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3420349549877718e-05, + "loss": 3.3738, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3411963602367198e-05, + "loss": 3.3941, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3403577654856674e-05, + "loss": 3.3712, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3395191707346156e-05, + "loss": 3.3789, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3386805759835636e-05, + "loss": 3.3796, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3378419812325116e-05, + "loss": 3.3706, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3370050243618327e-05, + "loss": 3.3797, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3361664296107807e-05, + "loss": 3.3642, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3353278348597286e-05, + "loss": 3.3756, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3344892401086766e-05, + "loss": 3.3706, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3336522832379977e-05, + "loss": 3.385, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3328136884869457e-05, + "loss": 3.376, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3319750937358937e-05, + "loss": 3.3675, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3311364989848419e-05, + "loss": 3.3662, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3302995421141628e-05, + "loss": 3.3686, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3294625852434842e-05, + "loss": 3.3855, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3286239904924322e-05, + "loss": 3.3604, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.32778539574138e-05, + "loss": 3.3829, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.326946800990328e-05, + "loss": 3.371, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.326108206239276e-05, + "loss": 3.3576, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.325269611488224e-05, + "loss": 3.3812, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.324431016737172e-05, + "loss": 3.3667, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3235924219861202e-05, + "loss": 3.3607, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3227554651154411e-05, + "loss": 3.3656, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.321916870364389e-05, + "loss": 3.3771, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3210782756133372e-05, + "loss": 3.3719, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3202396808622852e-05, + "loss": 3.367, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3194027239916063e-05, + "loss": 3.3659, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3185641292405543e-05, + "loss": 3.3626, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3177255344895023e-05, + "loss": 3.3717, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3168885776188234e-05, + "loss": 3.3761, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3160499828677714e-05, + "loss": 3.374, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3152113881167194e-05, + "loss": 3.3785, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3143727933656674e-05, + "loss": 3.3772, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3135358364949885e-05, + "loss": 3.3658, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3126972417439365e-05, + "loss": 3.3772, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3118586469928844e-05, + "loss": 3.372, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3110200522418326e-05, + "loss": 3.3673, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3101830953711535e-05, + "loss": 3.3703, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3093445006201017e-05, + "loss": 3.3697, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3085059058690497e-05, + "loss": 3.381, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3076673111179977e-05, + "loss": 3.3822, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3068303542473188e-05, + "loss": 3.3727, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3059917594962668e-05, + "loss": 3.3545, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3051531647452147e-05, + "loss": 3.3765, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3043162078745358e-05, + "loss": 3.3809, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3034776131234838e-05, + "loss": 3.3735, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3026390183724318e-05, + "loss": 3.3716, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3018004236213798e-05, + "loss": 3.3834, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3009618288703276e-05, + "loss": 3.3701, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3001232341192756e-05, + "loss": 3.3725, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2992846393682236e-05, + "loss": 3.3672, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2984460446171718e-05, + "loss": 3.3789, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2976090877464927e-05, + "loss": 3.3795, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2967704929954409e-05, + "loss": 3.3785, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2959318982443889e-05, + "loss": 3.3657, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2950933034933369e-05, + "loss": 3.364, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2942579845030312e-05, + "loss": 3.3673, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2934193897519792e-05, + "loss": 3.3817, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2925807950009272e-05, + "loss": 3.3743, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.291742200249875e-05, + "loss": 3.37, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.290903605498823e-05, + "loss": 3.3681, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.290065010747771e-05, + "loss": 3.3664, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.289226415996719e-05, + "loss": 3.3732, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2883878212456672e-05, + "loss": 3.3672, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.287550864374988e-05, + "loss": 3.3644, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.286712269623936e-05, + "loss": 3.3755, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2858736748728842e-05, + "loss": 3.3757, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2850367180022051e-05, + "loss": 3.3672, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2841981232511533e-05, + "loss": 3.3703, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2833595285001013e-05, + "loss": 3.3672, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2825209337490493e-05, + "loss": 3.3767, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2816823389979973e-05, + "loss": 3.3696, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2808437442469453e-05, + "loss": 3.3752, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2800051494958931e-05, + "loss": 3.3724, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2791665547448411e-05, + "loss": 3.376, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2783312357545354e-05, + "loss": 3.3761, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2774926410034834e-05, + "loss": 3.3658, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2766540462524314e-05, + "loss": 3.375, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2758154515013796e-05, + "loss": 3.3692, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2749768567503276e-05, + "loss": 3.3627, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2741382619992753e-05, + "loss": 3.3686, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2732996672482234e-05, + "loss": 3.3676, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2724610724971714e-05, + "loss": 3.372, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2716257535068657e-05, + "loss": 3.3664, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2707871587558137e-05, + "loss": 3.3668, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2699485640047617e-05, + "loss": 3.3638, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2691099692537097e-05, + "loss": 3.368, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2682713745026579e-05, + "loss": 3.3814, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2674327797516056e-05, + "loss": 3.3708, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2665941850005535e-05, + "loss": 3.378, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2657555902495017e-05, + "loss": 3.3596, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2649186333788226e-05, + "loss": 3.3767, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2640800386277706e-05, + "loss": 3.3763, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2632414438767188e-05, + "loss": 3.3777, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2624028491256668e-05, + "loss": 3.3714, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2615658922549879e-05, + "loss": 3.3696, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2607272975039359e-05, + "loss": 3.3826, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2598887027528838e-05, + "loss": 3.378, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2590501080018318e-05, + "loss": 3.3636, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2582115132507798e-05, + "loss": 3.3716, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.257372918499728e-05, + "loss": 3.3706, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.256534323748676e-05, + "loss": 3.3713, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2556957289976237e-05, + "loss": 3.3612, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.254858772126945e-05, + "loss": 3.372, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.254020177375893e-05, + "loss": 3.3622, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2531815826248407e-05, + "loss": 3.3754, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2523429878737889e-05, + "loss": 3.3677, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.862948417663574, + "eval_runtime": 303.9623, + "eval_samples_per_second": 1255.389, + "eval_steps_per_second": 39.232, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2515060310031101e-05, + "loss": 3.3748, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2506674362520581e-05, + "loss": 3.3586, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2498288415010061e-05, + "loss": 3.3671, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2489902467499541e-05, + "loss": 3.3748, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2481532898792752e-05, + "loss": 3.376, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2473146951282232e-05, + "loss": 3.3677, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2464761003771712e-05, + "loss": 3.362, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.245637505626119e-05, + "loss": 3.3599, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.2448005487554403e-05, + "loss": 3.3668, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.2439619540043883e-05, + "loss": 3.3733, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2431233592533363e-05, + "loss": 3.3722, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.2422864023826573e-05, + "loss": 3.3693, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.2414478076316053e-05, + "loss": 3.3774, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2406092128805533e-05, + "loss": 3.3521, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2397706181295015e-05, + "loss": 3.3632, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2389336612588224e-05, + "loss": 3.3543, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.2380950665077706e-05, + "loss": 3.3724, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2372564717567186e-05, + "loss": 3.3631, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2364178770056664e-05, + "loss": 3.3634, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2355809201349876e-05, + "loss": 3.3665, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2347423253839356e-05, + "loss": 3.3843, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2339037306328836e-05, + "loss": 3.3706, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2330651358818315e-05, + "loss": 3.3702, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.2322281790111527e-05, + "loss": 3.3746, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2313895842601007e-05, + "loss": 3.3814, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2305509895090487e-05, + "loss": 3.3584, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2297123947579967e-05, + "loss": 3.3643, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2288754378873178e-05, + "loss": 3.3757, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2280368431362658e-05, + "loss": 3.355, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2271982483852138e-05, + "loss": 3.3658, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.2263596536341618e-05, + "loss": 3.3766, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.225522696763483e-05, + "loss": 3.374, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.224684102012431e-05, + "loss": 3.3713, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.2238455072613788e-05, + "loss": 3.3746, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.2230069125103268e-05, + "loss": 3.3615, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.222169955639648e-05, + "loss": 3.3752, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2213313608885959e-05, + "loss": 3.3663, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.220492766137544e-05, + "loss": 3.356, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.219654171386492e-05, + "loss": 3.3699, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2188188523961864e-05, + "loss": 3.3593, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2179802576451342e-05, + "loss": 3.3616, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2171416628940822e-05, + "loss": 3.3631, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2163030681430302e-05, + "loss": 3.3823, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2154644733919784e-05, + "loss": 3.3582, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2146258786409262e-05, + "loss": 3.3717, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2137872838898742e-05, + "loss": 3.3675, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2129486891388222e-05, + "loss": 3.3639, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2121117322681433e-05, + "loss": 3.3687, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2112731375170913e-05, + "loss": 3.3538, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2104345427660393e-05, + "loss": 3.3672, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.2095959480149874e-05, + "loss": 3.3614, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.2087589911443083e-05, + "loss": 3.3731, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2079203963932565e-05, + "loss": 3.369, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2070818016422045e-05, + "loss": 3.3543, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.2062432068911523e-05, + "loss": 3.3539, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.2054062500204736e-05, + "loss": 3.3569, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2045692931497947e-05, + "loss": 3.3769, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2037306983987426e-05, + "loss": 3.3518, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2028921036476906e-05, + "loss": 3.371, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2020535088966386e-05, + "loss": 3.3633, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2012149141455866e-05, + "loss": 3.3485, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.2003763193945346e-05, + "loss": 3.3691, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1995377246434826e-05, + "loss": 3.3613, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1986991298924306e-05, + "loss": 3.3504, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1978621730217519e-05, + "loss": 3.3531, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1970235782706997e-05, + "loss": 3.3719, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1961849835196477e-05, + "loss": 3.359, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1953463887685957e-05, + "loss": 3.3535, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.194509431897917e-05, + "loss": 3.3525, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.1936708371468648e-05, + "loss": 3.3545, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1928322423958128e-05, + "loss": 3.3626, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.191995285525134e-05, + "loss": 3.3677, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.191156690774082e-05, + "loss": 3.3635, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.19031809602303e-05, + "loss": 3.3702, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.189479501271978e-05, + "loss": 3.3672, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.188642544401299e-05, + "loss": 3.3628, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.187803949650247e-05, + "loss": 3.3636, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.186965354899195e-05, + "loss": 3.3586, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.186126760148143e-05, + "loss": 3.3588, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1852898032774643e-05, + "loss": 3.364, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1844512085264121e-05, + "loss": 3.3635, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1836126137753601e-05, + "loss": 3.3664, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1827756569046814e-05, + "loss": 3.3737, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1819370621536294e-05, + "loss": 3.3615, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1810984674025772e-05, + "loss": 3.3443, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1802598726515254e-05, + "loss": 3.3619, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1794229157808464e-05, + "loss": 3.3693, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1785843210297943e-05, + "loss": 3.367, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.1777457262787424e-05, + "loss": 3.3578, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.1769071315276904e-05, + "loss": 3.3725, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.1760685367766384e-05, + "loss": 3.3628, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1752299420255864e-05, + "loss": 3.361, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1743913472745344e-05, + "loss": 3.3575, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.1735527525234824e-05, + "loss": 3.3694, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.1727157956528035e-05, + "loss": 3.3662, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1718772009017515e-05, + "loss": 3.3706, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1710386061506995e-05, + "loss": 3.3562, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.1702000113996475e-05, + "loss": 3.3541, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1693630545289686e-05, + "loss": 3.3573, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.1685260976582896e-05, + "loss": 3.3733, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1676875029072378e-05, + "loss": 3.366, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1668489081561856e-05, + "loss": 3.3603, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1660103134051336e-05, + "loss": 3.3582, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.1651717186540816e-05, + "loss": 3.3572, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.1643331239030298e-05, + "loss": 3.3674, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1634945291519776e-05, + "loss": 3.357, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.1626575722812989e-05, + "loss": 3.3556, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1618189775302469e-05, + "loss": 3.3644, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1609803827791947e-05, + "loss": 3.3652, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.160143425908516e-05, + "loss": 3.3602, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.159304831157464e-05, + "loss": 3.3611, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.158466236406412e-05, + "loss": 3.354, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.15762764165536e-05, + "loss": 3.3659, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1567890469043079e-05, + "loss": 3.3609, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1559504521532559e-05, + "loss": 3.3606, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1551118574022037e-05, + "loss": 3.3692, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1542732626511519e-05, + "loss": 3.3669, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.153437943660846e-05, + "loss": 3.3648, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1525993489097942e-05, + "loss": 3.3572, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.151760754158742e-05, + "loss": 3.3651, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.15092215940769e-05, + "loss": 3.3565, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.150083564656638e-05, + "loss": 3.3536, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1492449699055862e-05, + "loss": 3.3603, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.148406375154534e-05, + "loss": 3.3582, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.147567780403482e-05, + "loss": 3.3651, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1467308235328033e-05, + "loss": 3.352, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1458922287817511e-05, + "loss": 3.3625, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1450536340306991e-05, + "loss": 3.3545, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1442150392796473e-05, + "loss": 3.3564, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1433780824089683e-05, + "loss": 3.3651, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1425394876579162e-05, + "loss": 3.3662, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1417008929068643e-05, + "loss": 3.365, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1408622981558123e-05, + "loss": 3.3497, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1400253412851334e-05, + "loss": 3.3674, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1391867465340814e-05, + "loss": 3.3658, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1383481517830294e-05, + "loss": 3.3641, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.1375095570319774e-05, + "loss": 3.3641, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.1366726001612985e-05, + "loss": 3.3631, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.1358340054102465e-05, + "loss": 3.3737, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.1349954106591945e-05, + "loss": 3.3669, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.1341584537885157e-05, + "loss": 3.3556, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.1333198590374635e-05, + "loss": 3.3616, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.1324812642864115e-05, + "loss": 3.3581, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.1316426695353597e-05, + "loss": 3.3588, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.1308057126646808e-05, + "loss": 3.3552, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.1299671179136288e-05, + "loss": 3.3629, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.1291285231625768e-05, + "loss": 3.3516, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.1282899284115248e-05, + "loss": 3.3673, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.1274529715408458e-05, + "loss": 3.3549, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.863475799560547, + "eval_runtime": 305.5952, + "eval_samples_per_second": 1248.681, + "eval_steps_per_second": 39.022, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.1266143767897938e-05, + "loss": 3.3269, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1257757820387418e-05, + "loss": 3.3556, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.1249371872876898e-05, + "loss": 3.35, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.1240985925366378e-05, + "loss": 3.3665, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1232616356659589e-05, + "loss": 3.3665, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1224230409149069e-05, + "loss": 3.3579, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.1215844461638549e-05, + "loss": 3.3536, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1207458514128029e-05, + "loss": 3.3495, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.119908894542124e-05, + "loss": 3.3609, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1190702997910721e-05, + "loss": 3.3624, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.11823170504002e-05, + "loss": 3.362, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.117393110288968e-05, + "loss": 3.3605, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.1165561534182892e-05, + "loss": 3.3683, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1157175586672372e-05, + "loss": 3.3414, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.114878963916185e-05, + "loss": 3.3546, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1140403691651332e-05, + "loss": 3.3468, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1132034122944543e-05, + "loss": 3.3617, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1123648175434023e-05, + "loss": 3.3545, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1115262227923503e-05, + "loss": 3.3545, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1106876280412983e-05, + "loss": 3.3555, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1098506711706193e-05, + "loss": 3.3768, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1090120764195673e-05, + "loss": 3.3616, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1081734816685153e-05, + "loss": 3.3565, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1073348869174633e-05, + "loss": 3.3674, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1064979300467846e-05, + "loss": 3.368, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1056593352957324e-05, + "loss": 3.353, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1048207405446804e-05, + "loss": 3.3533, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1039821457936286e-05, + "loss": 3.3675, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1031451889229495e-05, + "loss": 3.3468, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1023065941718975e-05, + "loss": 3.3556, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1014679994208456e-05, + "loss": 3.3627, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1006294046697935e-05, + "loss": 3.3675, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0997924477991147e-05, + "loss": 3.362, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0989538530480627e-05, + "loss": 3.3609, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0981152582970107e-05, + "loss": 3.3536, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0972766635459585e-05, + "loss": 3.3683, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0964397066752798e-05, + "loss": 3.3568, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.0956011119242278e-05, + "loss": 3.3437, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0947625171731758e-05, + "loss": 3.3583, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0939255603024968e-05, + "loss": 3.3462, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0930869655514448e-05, + "loss": 3.3549, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0922483708003928e-05, + "loss": 3.3509, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.0914097760493408e-05, + "loss": 3.3695, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0905711812982888e-05, + "loss": 3.3551, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0897325865472368e-05, + "loss": 3.3576, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0888939917961848e-05, + "loss": 3.3632, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.0880553970451328e-05, + "loss": 3.3522, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0872184401744539e-05, + "loss": 3.3649, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.086379845423402e-05, + "loss": 3.3449, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0855412506723499e-05, + "loss": 3.3527, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0847026559212979e-05, + "loss": 3.3548, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0838656990506191e-05, + "loss": 3.3605, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0830271042995671e-05, + "loss": 3.3603, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.082188509548515e-05, + "loss": 3.3433, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0813499147974631e-05, + "loss": 3.3505, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.0805129579267842e-05, + "loss": 3.3458, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0796760010561054e-05, + "loss": 3.3699, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0788374063050533e-05, + "loss": 3.3412, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.0779988115540013e-05, + "loss": 3.3626, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0771602168029493e-05, + "loss": 3.3524, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0763216220518973e-05, + "loss": 3.339, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0754830273008452e-05, + "loss": 3.3604, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0746444325497932e-05, + "loss": 3.3531, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0738058377987412e-05, + "loss": 3.3394, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0729688809280623e-05, + "loss": 3.3434, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0721302861770103e-05, + "loss": 3.363, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0712916914259583e-05, + "loss": 3.3501, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0704530966749063e-05, + "loss": 3.3479, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0696161398042274e-05, + "loss": 3.3443, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0687775450531755e-05, + "loss": 3.3437, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0679389503021235e-05, + "loss": 3.3527, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0671003555510714e-05, + "loss": 3.3564, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0662633986803926e-05, + "loss": 3.3508, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0654248039293406e-05, + "loss": 3.3616, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.0645862091782886e-05, + "loss": 3.3592, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.0637476144272366e-05, + "loss": 3.3513, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0629106575565577e-05, + "loss": 3.3555, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0620720628055057e-05, + "loss": 3.3489, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.0612334680544537e-05, + "loss": 3.3506, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0603965111837748e-05, + "loss": 3.3538, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0595579164327228e-05, + "loss": 3.3493, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.058719321681671e-05, + "loss": 3.3593, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0578823648109918e-05, + "loss": 3.3589, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0570437700599398e-05, + "loss": 3.3548, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.056205175308888e-05, + "loss": 3.3388, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.055366580557836e-05, + "loss": 3.3477, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0545279858067838e-05, + "loss": 3.3665, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.053691028936105e-05, + "loss": 3.3558, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.052852434185053e-05, + "loss": 3.3518, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0520138394340009e-05, + "loss": 3.3642, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.051175244682949e-05, + "loss": 3.3498, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.050336649931897e-05, + "loss": 3.3502, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.049498055180845e-05, + "loss": 3.3484, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0486594604297929e-05, + "loss": 3.3598, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0478225035591141e-05, + "loss": 3.3563, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0469839088080621e-05, + "loss": 3.3639, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0461453140570101e-05, + "loss": 3.3403, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0453067193059581e-05, + "loss": 3.3499, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0444697624352792e-05, + "loss": 3.3482, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0436328055646004e-05, + "loss": 3.3596, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0427942108135482e-05, + "loss": 3.3619, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0419556160624962e-05, + "loss": 3.3477, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0411170213114444e-05, + "loss": 3.351, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0402784265603924e-05, + "loss": 3.3495, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0394398318093402e-05, + "loss": 3.3581, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0386012370582882e-05, + "loss": 3.3443, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0377642801876095e-05, + "loss": 3.351, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0369256854365573e-05, + "loss": 3.3542, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0360870906855055e-05, + "loss": 3.3519, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0352501338148265e-05, + "loss": 3.3521, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0344115390637745e-05, + "loss": 3.3533, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.0335729443127225e-05, + "loss": 3.3416, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0327343495616705e-05, + "loss": 3.3568, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.0318957548106185e-05, + "loss": 3.3541, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0310571600595664e-05, + "loss": 3.3507, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0302185653085145e-05, + "loss": 3.3587, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0293799705574625e-05, + "loss": 3.3585, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0285446515671568e-05, + "loss": 3.3547, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0277060568161047e-05, + "loss": 3.3477, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0268674620650527e-05, + "loss": 3.355, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.0260288673140007e-05, + "loss": 3.3476, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.0251902725629487e-05, + "loss": 3.3463, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0243516778118967e-05, + "loss": 3.3473, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0235130830608447e-05, + "loss": 3.3514, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0226744883097928e-05, + "loss": 3.355, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0218375314391137e-05, + "loss": 3.3448, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.021000574568435e-05, + "loss": 3.3517, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.020161979817383e-05, + "loss": 3.3449, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.019323385066331e-05, + "loss": 3.35, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.018484790315279e-05, + "loss": 3.3526, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.017646195564227e-05, + "loss": 3.3567, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.016807600813175e-05, + "loss": 3.3547, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0159690060621228e-05, + "loss": 3.3445, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.015132049191444e-05, + "loss": 3.3522, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.014293454440392e-05, + "loss": 3.3563, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.01345485968934e-05, + "loss": 3.3561, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.012616264938288e-05, + "loss": 3.3564, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0117793080676091e-05, + "loss": 3.3518, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0109407133165571e-05, + "loss": 3.3642, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.010102118565505e-05, + "loss": 3.3524, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.009263523814453e-05, + "loss": 3.3493, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.008424929063401e-05, + "loss": 3.351, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.007586334312349e-05, + "loss": 3.3467, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.006747739561297e-05, + "loss": 3.3501, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.005909144810245e-05, + "loss": 3.3416, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0050721879395663e-05, + "loss": 3.3562, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0042335931885141e-05, + "loss": 3.3423, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0033949984374621e-05, + "loss": 3.3578, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0025564036864101e-05, + "loss": 3.3483, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0017194468157314e-05, + "loss": 3.3524, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.864598274230957, + "eval_runtime": 476.7192, + "eval_samples_per_second": 800.452, + "eval_steps_per_second": 25.015, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0008808520646792e-05, + "loss": 3.3422, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 1.0000422573136272e-05, + "loss": 3.3444, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.992036625625754e-06, + "loss": 3.3559, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.983667056918964e-06, + "loss": 3.3575, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.975281109408444e-06, + "loss": 3.352, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.966895161897924e-06, + "loss": 3.3437, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.958509214387404e-06, + "loss": 3.3428, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.950139645680615e-06, + "loss": 3.3449, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.941753698170095e-06, + "loss": 3.3554, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.933367750659575e-06, + "loss": 3.3491, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.924981803149055e-06, + "loss": 3.3554, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.916612234442266e-06, + "loss": 3.3582, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.908226286931746e-06, + "loss": 3.3368, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.899840339421226e-06, + "loss": 3.3382, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.891454391910706e-06, + "loss": 3.3391, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.883084823203916e-06, + "loss": 3.3489, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.874698875693398e-06, + "loss": 3.3473, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.866312928182878e-06, + "loss": 3.3489, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.857926980672356e-06, + "loss": 3.3428, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.849557411965569e-06, + "loss": 3.367, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.841171464455049e-06, + "loss": 3.3508, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.832785516944529e-06, + "loss": 3.3509, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.82441594823774e-06, + "loss": 3.3539, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.81603000072722e-06, + "loss": 3.3632, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.8076440532167e-06, + "loss": 3.342, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.79925810570618e-06, + "loss": 3.3473, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.79088853699939e-06, + "loss": 3.3527, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.78250258948887e-06, + "loss": 3.34, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.774116641978352e-06, + "loss": 3.3475, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.76573069446783e-06, + "loss": 3.3513, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.75736112576104e-06, + "loss": 3.3615, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.748975178250522e-06, + "loss": 3.3493, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.74058923074e-06, + "loss": 3.3528, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.73220328322948e-06, + "loss": 3.3497, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.723833714522693e-06, + "loss": 3.3536, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.715447767012173e-06, + "loss": 3.3493, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.707061819501651e-06, + "loss": 3.3394, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.698675871991133e-06, + "loss": 3.3479, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.690322682088075e-06, + "loss": 3.3373, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.681936734577556e-06, + "loss": 3.3486, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.673550787067035e-06, + "loss": 3.3408, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.665164839556514e-06, + "loss": 3.3613, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.656778892045994e-06, + "loss": 3.3461, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.648392944535474e-06, + "loss": 3.3467, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.640006997024954e-06, + "loss": 3.3547, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.631621049514434e-06, + "loss": 3.3428, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.623251480807647e-06, + "loss": 3.3572, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.614865533297125e-06, + "loss": 3.3331, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.606479585786605e-06, + "loss": 3.3427, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.598093638276087e-06, + "loss": 3.3483, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.589724069569297e-06, + "loss": 3.3504, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.581338122058776e-06, + "loss": 3.3488, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.572952174548257e-06, + "loss": 3.3321, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.564566227037737e-06, + "loss": 3.3454, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.556196658330948e-06, + "loss": 3.3341, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.547827089624159e-06, + "loss": 3.3614, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.539441142113639e-06, + "loss": 3.3342, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.531055194603119e-06, + "loss": 3.353, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.522669247092599e-06, + "loss": 3.3403, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.514283299582079e-06, + "loss": 3.3303, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.505897352071559e-06, + "loss": 3.3499, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.497511404561039e-06, + "loss": 3.3456, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.489125457050519e-06, + "loss": 3.3276, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.48075588834373e-06, + "loss": 3.3345, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.472386319636942e-06, + "loss": 3.353, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.46400037212642e-06, + "loss": 3.3424, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.455614424615902e-06, + "loss": 3.3368, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.447228477105382e-06, + "loss": 3.3376, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.438842529594862e-06, + "loss": 3.3344, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.43045658208434e-06, + "loss": 3.3414, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.422070634573822e-06, + "loss": 3.3492, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.413684687063302e-06, + "loss": 3.3437, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.40531511835651e-06, + "loss": 3.3524, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.396929170845992e-06, + "loss": 3.3473, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.388543223335472e-06, + "loss": 3.346, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.380157275824952e-06, + "loss": 3.3401, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.371787707118163e-06, + "loss": 3.3437, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.363401759607643e-06, + "loss": 3.3456, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.355015812097123e-06, + "loss": 3.3392, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.346629864586603e-06, + "loss": 3.3428, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.338260295879814e-06, + "loss": 3.3477, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.329890727173026e-06, + "loss": 3.3531, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.321504779662506e-06, + "loss": 3.3436, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.313118832151984e-06, + "loss": 3.3305, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.304732884641464e-06, + "loss": 3.3415, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.296346937130946e-06, + "loss": 3.3566, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.287977368424157e-06, + "loss": 3.3497, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.279591420913637e-06, + "loss": 3.341, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.271205473403117e-06, + "loss": 3.3538, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.262819525892597e-06, + "loss": 3.3431, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.254433578382075e-06, + "loss": 3.3383, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.246047630871557e-06, + "loss": 3.3428, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.237661683361036e-06, + "loss": 3.3484, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.229292114654247e-06, + "loss": 3.3455, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.220906167143727e-06, + "loss": 3.3549, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.212520219633207e-06, + "loss": 3.3342, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.204134272122687e-06, + "loss": 3.3351, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.1957647034159e-06, + "loss": 3.3381, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.187395134709109e-06, + "loss": 3.3516, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.179009187198589e-06, + "loss": 3.3475, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.17062323968807e-06, + "loss": 3.3406, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.162237292177549e-06, + "loss": 3.3395, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.153851344667029e-06, + "loss": 3.3401, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.14546539715651e-06, + "loss": 3.3516, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.13707944964599e-06, + "loss": 3.3313, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.1287098809392e-06, + "loss": 3.3404, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.120323933428681e-06, + "loss": 3.3485, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.11193798591816e-06, + "loss": 3.344, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.103568417211372e-06, + "loss": 3.3408, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.095182469700852e-06, + "loss": 3.3469, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.086796522190332e-06, + "loss": 3.3331, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.078410574679811e-06, + "loss": 3.3458, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.070024627169291e-06, + "loss": 3.343, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.061638679658771e-06, + "loss": 3.3434, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.053252732148251e-06, + "loss": 3.3474, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.04486678463773e-06, + "loss": 3.3486, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.036513594734673e-06, + "loss": 3.3481, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.028127647224153e-06, + "loss": 3.3422, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.019741699713635e-06, + "loss": 3.3435, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.011355752203113e-06, + "loss": 3.338, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 9.002969804692593e-06, + "loss": 3.3341, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.994583857182073e-06, + "loss": 3.3401, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.986197909671553e-06, + "loss": 3.3402, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.977811962161033e-06, + "loss": 3.35, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.969442393454245e-06, + "loss": 3.3343, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.961072824747456e-06, + "loss": 3.3438, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.952686877236934e-06, + "loss": 3.3354, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.944300929726416e-06, + "loss": 3.3418, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.935914982215896e-06, + "loss": 3.3374, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.927529034705376e-06, + "loss": 3.3525, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.919143087194854e-06, + "loss": 3.3423, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.910757139684336e-06, + "loss": 3.3379, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.902387570977546e-06, + "loss": 3.341, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.894001623467026e-06, + "loss": 3.3433, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.885615675956506e-06, + "loss": 3.3483, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.877229728445986e-06, + "loss": 3.3467, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.868860159739197e-06, + "loss": 3.3457, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.860474212228677e-06, + "loss": 3.3532, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.852088264718157e-06, + "loss": 3.3454, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.843702317207637e-06, + "loss": 3.3431, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.835316369697117e-06, + "loss": 3.341, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.826930422186597e-06, + "loss": 3.343, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.818544474676077e-06, + "loss": 3.3399, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.810158527165557e-06, + "loss": 3.3316, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.801788958458768e-06, + "loss": 3.3462, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.793403010948248e-06, + "loss": 3.3381, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.785017063437727e-06, + "loss": 3.3467, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.776631115927207e-06, + "loss": 3.3394, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.768261547220418e-06, + "loss": 3.3413, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.864156484603882, + "eval_runtime": 426.2473, + "eval_samples_per_second": 895.234, + "eval_steps_per_second": 27.977, + "step": 2518560 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.7415424135364936e+18, + "trial_name": null, + "trial_params": null +}