diff --git "a/checkpoint-2594880/trainer_state.json" "b/checkpoint-2594880/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2594880/trainer_state.json" @@ -0,0 +1,30705 @@ +{ + "best_metric": 3.8440628051757812, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-case/transformer/0/checkpoints/checkpoint-839520", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2594880, + "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": 10.9819, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8109, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.191, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9683, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.803, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.6962, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5926, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.52, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4384, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3919, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3319, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.2903, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2461, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2002, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1624, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1206, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.0928, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0621, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.98490857024181e-05, + "loss": 5.035, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984069975490758e-05, + "loss": 5.0055, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983231380739706e-05, + "loss": 4.9923, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9647, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9352, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9223, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9113, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.8755, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 4.8571, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.846, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8307, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8077, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 4.7903, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7884, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7724, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7664, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7516, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7332, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7271, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.6934, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7001, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6722, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6729, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6598, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6628, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6413, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6367, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.63, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6121, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.623, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5882, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.5808, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.5924, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.5887, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.565, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5567, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954732262246923e-05, + "loss": 4.5574, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953893667495871e-05, + "loss": 4.5389, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 4.5611, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5212, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5329, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5215, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5065, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5152, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.4986, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4946, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4843, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.4986, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.4717, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4756, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4531, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4628, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 4.4738, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4646, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.447, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4592, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4597, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.434, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.4407, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.4226, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4148, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.4117, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4124, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4179, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4238, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930422841748654e-05, + "loss": 4.4144, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.3893, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.3948, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.3976, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927070100624819e-05, + "loss": 4.3892, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926231505873767e-05, + "loss": 4.3798, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925394549003088e-05, + "loss": 4.3773, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924555954252036e-05, + "loss": 4.3723, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923717359500984e-05, + "loss": 4.3802, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.9228804026303046e-05, + "loss": 4.3674, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922041807879253e-05, + "loss": 4.3732, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921203213128201e-05, + "loss": 4.3643, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920364618377149e-05, + "loss": 4.3622, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919526023626097e-05, + "loss": 4.3465, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918687428875045e-05, + "loss": 4.3496, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917848834123993e-05, + "loss": 4.3468, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.3516, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.3518, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3292, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.336, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3284, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912818903498054e-05, + "loss": 4.3328, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911980308747002e-05, + "loss": 4.3189, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911143351876323e-05, + "loss": 4.3165, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.3241, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3138, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.3106, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.303, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3008, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.9061134212503846e-05, + "loss": 4.3136, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052748264993326e-05, + "loss": 4.3015, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.90443623174828e-05, + "loss": 4.3016, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903597636997228e-05, + "loss": 4.3044, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027606801265495e-05, + "loss": 4.3093, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019220853754975e-05, + "loss": 4.2939, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010834906244455e-05, + "loss": 4.2821, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002448958733935e-05, + "loss": 4.289, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994063011223415e-05, + "loss": 4.2938, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985693442516624e-05, + "loss": 4.2806, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977307495006104e-05, + "loss": 4.2796, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968921547495584e-05, + "loss": 4.277, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2791, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.2731, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.2757, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2673, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.2693, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2617, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891023629372567e-05, + "loss": 4.2794, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.2627, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2554, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2516, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.2607, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.2549, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.2604, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515674187595e-05, + "loss": 4.247, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2529, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2473, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2471, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.2375, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88096376812069e-05, + "loss": 4.2478, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880125173369638e-05, + "loss": 4.2354, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.8792882164989586e-05, + "loss": 4.2258, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2472, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.2313, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876772432245803e-05, + "loss": 4.2294, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875933837494751e-05, + "loss": 4.2391, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.2202, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.1929707527160645, + "eval_runtime": 303.6122, + "eval_samples_per_second": 1256.837, + "eval_steps_per_second": 39.277, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.21, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.2134, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.2211, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2135, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.2212, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.2058, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869228355247081e-05, + "loss": 4.209, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.1986, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675528036253507e-05, + "loss": 4.2129, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667142088742986e-05, + "loss": 4.1954, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865875614123246e-05, + "loss": 4.1943, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865037019372194e-05, + "loss": 4.1977, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642000625015155e-05, + "loss": 4.1939, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633614677504635e-05, + "loss": 4.1855, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862522872999411e-05, + "loss": 4.1868, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861684278248359e-05, + "loss": 4.1708, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860845683497307e-05, + "loss": 4.1818, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860007088746255e-05, + "loss": 4.1743, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859168493995203e-05, + "loss": 4.1688, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858329899244151e-05, + "loss": 4.1941, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574929423734724e-05, + "loss": 4.1726, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566543476224204e-05, + "loss": 4.1747, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558157528713684e-05, + "loss": 4.1715, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549771581203164e-05, + "loss": 4.1866, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854140201249637e-05, + "loss": 4.1592, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853301606498585e-05, + "loss": 4.1627, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852463011747533e-05, + "loss": 4.167, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851624416996481e-05, + "loss": 4.1656, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850785822245429e-05, + "loss": 4.1547, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.84994886537475e-05, + "loss": 4.154, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849110270623698e-05, + "loss": 4.1615, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848271675872646e-05, + "loss": 4.1619, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847433081121595e-05, + "loss": 4.1629, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846594486370543e-05, + "loss": 4.1552, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845757529499864e-05, + "loss": 4.1487, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844918934748812e-05, + "loss": 4.1564, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.84408033999776e-05, + "loss": 4.1319, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843241745246708e-05, + "loss": 4.1513, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842404788376029e-05, + "loss": 4.1307, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841566193624977e-05, + "loss": 4.1399, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840727598873925e-05, + "loss": 4.1361, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839889004122873e-05, + "loss": 4.1457, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.8390520472521936e-05, + "loss": 4.1379, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382134525011416e-05, + "loss": 4.1314, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.83737485775009e-05, + "loss": 4.1365, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836536262999038e-05, + "loss": 4.1282, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835699306128359e-05, + "loss": 4.1406, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834860711377307e-05, + "loss": 4.1134, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834022116626255e-05, + "loss": 4.1139, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833183521875203e-05, + "loss": 4.131, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832346565004524e-05, + "loss": 4.1334, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831507970253472e-05, + "loss": 4.1175, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.83066937550242e-05, + "loss": 4.1132, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829830780751368e-05, + "loss": 4.121, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828993823880689e-05, + "loss": 4.1037, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828155229129637e-05, + "loss": 4.1295, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273166343785856e-05, + "loss": 4.1088, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264780396275336e-05, + "loss": 4.1174, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256410827568545e-05, + "loss": 4.1124, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248024880058025e-05, + "loss": 4.0996, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239638932547505e-05, + "loss": 4.1148, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.8231252985036985e-05, + "loss": 4.1013, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222867037526465e-05, + "loss": 4.0995, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214481090015945e-05, + "loss": 4.0965, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.8206111521309154e-05, + "loss": 4.1139, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.8197725573798634e-05, + "loss": 4.0967, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189339626288114e-05, + "loss": 4.0963, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180953678777594e-05, + "loss": 4.087, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817258411007081e-05, + "loss": 4.0938, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816419816256029e-05, + "loss": 4.1099, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815581221504977e-05, + "loss": 4.1053, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814742626753924e-05, + "loss": 4.0935, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813905669883246e-05, + "loss": 4.1029, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813067075132194e-05, + "loss": 4.1067, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812228480381141e-05, + "loss": 4.0916, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811389885630089e-05, + "loss": 4.0973, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810552928759411e-05, + "loss": 4.0873, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809714334008359e-05, + "loss": 4.0784, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808875739257306e-05, + "loss": 4.0801, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808037144506255e-05, + "loss": 4.0843, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807200187635576e-05, + "loss": 4.0874, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.8063615928845243e-05, + "loss": 4.1034, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.8055229981334717e-05, + "loss": 4.0908, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.8046844033824197e-05, + "loss": 4.0694, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803847446511741e-05, + "loss": 4.0781, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.8030088517606886e-05, + "loss": 4.0839, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.8021702570096366e-05, + "loss": 4.0813, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.8013316622585846e-05, + "loss": 4.0713, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800494705387906e-05, + "loss": 4.0733, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996561106368535e-05, + "loss": 4.0716, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988175158858015e-05, + "loss": 4.0769, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979789211347494e-05, + "loss": 4.0684, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797141964264071e-05, + "loss": 4.0775, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796303369513019e-05, + "loss": 4.0719, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795464774761967e-05, + "loss": 4.0736, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794626180010915e-05, + "loss": 4.056, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793789223140236e-05, + "loss": 4.0674, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792950628389184e-05, + "loss": 4.0622, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792112033638132e-05, + "loss": 4.0683, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.79127343888708e-05, + "loss": 4.0675, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790436482016401e-05, + "loss": 4.0582, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789597887265349e-05, + "loss": 4.06, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788759292514297e-05, + "loss": 4.0584, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787920697763245e-05, + "loss": 4.0615, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870837408925664e-05, + "loss": 4.0484, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786246784021888e-05, + "loss": 4.0508, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785408189270836e-05, + "loss": 4.06, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784569594519783e-05, + "loss": 4.0503, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783730999768731e-05, + "loss": 4.0502, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782892405017679e-05, + "loss": 4.044, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782053810266627e-05, + "loss": 4.0421, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781215215515575e-05, + "loss": 4.0629, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780376620764523e-05, + "loss": 4.045, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779539663893844e-05, + "loss": 4.0533, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778701069142792e-05, + "loss": 4.0513, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.77786247439174e-05, + "loss": 4.0634, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777025517521062e-05, + "loss": 4.0496, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.77618692277001e-05, + "loss": 4.0355, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775348328018958e-05, + "loss": 4.044, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774509733267906e-05, + "loss": 4.0511, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773671138516854e-05, + "loss": 4.036, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.7728341816461747e-05, + "loss": 4.0403, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719955868951227e-05, + "loss": 4.0369, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.7711569921440707e-05, + "loss": 4.0474, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.7703183973930186e-05, + "loss": 4.0344, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.7694798026419666e-05, + "loss": 4.0439, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.7686412078909146e-05, + "loss": 4.036, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.7678026131398626e-05, + "loss": 4.0382, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766965656269184e-05, + "loss": 4.0298, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766127061518132e-05, + "loss": 4.0513, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.76528846676708e-05, + "loss": 4.0418, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764449872016028e-05, + "loss": 4.0265, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763612915145349e-05, + "loss": 4.0289, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762774320394297e-05, + "loss": 4.0373, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761935725643245e-05, + "loss": 4.0364, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761097130892193e-05, + "loss": 4.0444, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760260174021514e-05, + "loss": 4.0279, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759421579270462e-05, + "loss": 4.0357, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.75858298451941e-05, + "loss": 4.0293, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757744389768358e-05, + "loss": 4.0357, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569074328976796e-05, + "loss": 4.0265, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560688381466276e-05, + "loss": 4.0314, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552302433955756e-05, + "loss": 4.0237, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543916486445236e-05, + "loss": 4.018, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535546917738445e-05, + "loss": 4.0388, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527160970227925e-05, + "loss": 4.0253, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518775022717405e-05, + "loss": 4.022, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510389075206885e-05, + "loss": 4.0264, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7502003127696365e-05, + "loss": 4.0177, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.026247978210449, + "eval_runtime": 304.5864, + "eval_samples_per_second": 1252.817, + "eval_steps_per_second": 39.151, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493617180185845e-05, + "loss": 4.0071, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748523123267532e-05, + "loss": 4.0095, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.74768452851648e-05, + "loss": 4.0252, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746845933765428e-05, + "loss": 4.0124, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460073390143764e-05, + "loss": 4.0264, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451687442633244e-05, + "loss": 4.0096, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443301495122724e-05, + "loss": 4.012, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434915547612204e-05, + "loss": 4.0067, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426529600101684e-05, + "loss": 4.0207, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7418143652591164e-05, + "loss": 4.0062, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.7409757705080644e-05, + "loss": 4.0046, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740138813637385e-05, + "loss": 4.0032, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739303494647079e-05, + "loss": 4.0055, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738464899896027e-05, + "loss": 3.9975, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737626305144975e-05, + "loss": 4.0014, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736787710393923e-05, + "loss": 3.9905, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735949115642871e-05, + "loss": 3.9945, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.73511052089182e-05, + "loss": 3.9904, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734271926140768e-05, + "loss": 3.9857, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733433331389716e-05, + "loss": 4.0199, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732594736638664e-05, + "loss": 3.9938, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731756141887612e-05, + "loss": 3.9901, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.73091754713656e-05, + "loss": 3.997, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730080590265881e-05, + "loss": 4.0043, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292436333952016e-05, + "loss": 3.9825, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7284050386441496e-05, + "loss": 3.991, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275664438930976e-05, + "loss": 3.9905, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267278491420456e-05, + "loss": 3.9943, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258892543909936e-05, + "loss": 3.9799, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250506596399416e-05, + "loss": 3.9855, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7242120648888896e-05, + "loss": 3.9876, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723373470137838e-05, + "loss": 3.9938, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722536513267159e-05, + "loss": 3.9991, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721697918516107e-05, + "loss": 3.9877, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720859323765055e-05, + "loss": 3.9806, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720020729014003e-05, + "loss": 3.9915, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719183772143324e-05, + "loss": 3.9727, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718346815272645e-05, + "loss": 3.9854, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717508220521593e-05, + "loss": 3.9675, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716669625770541e-05, + "loss": 3.9742, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715831031019489e-05, + "loss": 3.978, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714992436268437e-05, + "loss": 3.9854, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714153841517385e-05, + "loss": 3.9804, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713315246766333e-05, + "loss": 3.9731, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712476652015281e-05, + "loss": 3.9779, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116396951446025e-05, + "loss": 3.9731, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7108011003935505e-05, + "loss": 3.9817, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709962505642498e-05, + "loss": 3.9597, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091255487718194e-05, + "loss": 3.9587, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082869540207674e-05, + "loss": 3.9771, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074483592697154e-05, + "loss": 3.9757, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706609764518663e-05, + "loss": 3.9645, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705771169767611e-05, + "loss": 3.9632, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704932575016559e-05, + "loss": 3.9681, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.70409561814588e-05, + "loss": 3.9525, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703257023394828e-05, + "loss": 3.9745, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702418428643776e-05, + "loss": 3.9614, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701579833892724e-05, + "loss": 3.9693, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700741239141672e-05, + "loss": 3.9634, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.69990264439062e-05, + "loss": 3.9589, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699064049639568e-05, + "loss": 3.9596, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698225454888516e-05, + "loss": 3.9595, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697388498017837e-05, + "loss": 3.9533, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696549903266785e-05, + "loss": 3.9506, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695711308515733e-05, + "loss": 3.9668, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694872713764681e-05, + "loss": 3.9545, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694035756894003e-05, + "loss": 3.9553, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693197162142951e-05, + "loss": 3.9445, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692358567391899e-05, + "loss": 3.9511, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691519972640847e-05, + "loss": 3.9683, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906846536505406e-05, + "loss": 3.9639, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898460588994886e-05, + "loss": 3.9555, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890074641484366e-05, + "loss": 3.9634, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881688693973846e-05, + "loss": 3.9675, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873302746463326e-05, + "loss": 3.9498, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864916798952806e-05, + "loss": 3.9577, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856547230246015e-05, + "loss": 3.9514, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848161282735495e-05, + "loss": 3.9438, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683977533522498e-05, + "loss": 3.9509, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683138938771446e-05, + "loss": 3.944, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682300344020394e-05, + "loss": 3.9527, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681461749269342e-05, + "loss": 3.9631, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.68062315451829e-05, + "loss": 3.9597, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679786197647611e-05, + "loss": 3.9321, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678947602896559e-05, + "loss": 3.9492, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678109008145507e-05, + "loss": 3.9501, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677270413394455e-05, + "loss": 3.9493, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676433456523776e-05, + "loss": 3.9429, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675594861772724e-05, + "loss": 3.9371, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674756267021672e-05, + "loss": 3.9463, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.67391767227062e-05, + "loss": 3.9422, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730807153999415e-05, + "loss": 3.9384, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722421206488895e-05, + "loss": 3.949, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6714035258978375e-05, + "loss": 3.9409, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705649311467855e-05, + "loss": 3.9483, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697263363957335e-05, + "loss": 3.9321, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688893795250544e-05, + "loss": 3.9365, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680507847740024e-05, + "loss": 3.9374, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6672121900229504e-05, + "loss": 3.9457, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663735952718984e-05, + "loss": 3.9416, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665536638401219e-05, + "loss": 3.933, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664698043650167e-05, + "loss": 3.9362, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663859448899115e-05, + "loss": 3.9332, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663020854148063e-05, + "loss": 3.9374, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662182259397011e-05, + "loss": 3.9222, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661345302526333e-05, + "loss": 3.9255, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660506707775281e-05, + "loss": 3.9428, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659668113024229e-05, + "loss": 3.9317, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658829518273176e-05, + "loss": 3.9253, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657992561402498e-05, + "loss": 3.9232, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657153966651446e-05, + "loss": 3.9233, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656315371900393e-05, + "loss": 3.9391, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655476777149341e-05, + "loss": 3.9298, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654638182398289e-05, + "loss": 3.9282, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6538012255276106e-05, + "loss": 3.9304, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529626307765586e-05, + "loss": 3.9459, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521240360255066e-05, + "loss": 3.9325, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512854412744546e-05, + "loss": 3.9187, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650448484403776e-05, + "loss": 3.9286, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6496098896527235e-05, + "loss": 3.9302, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487712949016715e-05, + "loss": 3.9214, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479327001506195e-05, + "loss": 3.9239, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470941053995675e-05, + "loss": 3.9207, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462571485288884e-05, + "loss": 3.9315, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454185537778364e-05, + "loss": 3.9177, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445799590267844e-05, + "loss": 3.932, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437413642757324e-05, + "loss": 3.9149, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429027695246804e-05, + "loss": 3.9267, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642065812654002e-05, + "loss": 3.9149, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.64122721790295e-05, + "loss": 3.9377, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640388623151898e-05, + "loss": 3.9297, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639550028400846e-05, + "loss": 3.9194, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638713071530167e-05, + "loss": 3.9122, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637874476779115e-05, + "loss": 3.9253, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637035882028063e-05, + "loss": 3.9225, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636197287277011e-05, + "loss": 3.9323, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635358692525959e-05, + "loss": 3.915, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.63452173565528e-05, + "loss": 3.9273, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633683140904228e-05, + "loss": 3.92, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632844546153176e-05, + "loss": 3.9309, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320059514021244e-05, + "loss": 3.9137, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311673566510724e-05, + "loss": 3.9227, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303303997803934e-05, + "loss": 3.9161, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294918050293413e-05, + "loss": 3.9093, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286532102782893e-05, + "loss": 3.9275, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6278146155272373e-05, + "loss": 3.9229, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626976020776185e-05, + "loss": 3.91, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626137426025133e-05, + "loss": 3.9211, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625298831274081e-05, + "loss": 3.9112, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.953259229660034, + "eval_runtime": 312.5733, + "eval_samples_per_second": 1220.805, + "eval_steps_per_second": 38.151, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624461874403402e-05, + "loss": 3.9069, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.62362327965235e-05, + "loss": 3.9035, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622784684901298e-05, + "loss": 3.9145, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621946090150246e-05, + "loss": 3.9111, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621109133279568e-05, + "loss": 3.9243, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620270538528516e-05, + "loss": 3.9013, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619431943777464e-05, + "loss": 3.9091, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618593349026412e-05, + "loss": 3.9022, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617754754275359e-05, + "loss": 3.921, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616916159524307e-05, + "loss": 3.9018, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616079202653629e-05, + "loss": 3.8978, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615240607902577e-05, + "loss": 3.9052, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6144036510318976e-05, + "loss": 3.901, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135650562808456e-05, + "loss": 3.8982, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127264615297936e-05, + "loss": 3.8991, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.6118878667787416e-05, + "loss": 3.8923, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110492720276896e-05, + "loss": 3.8901, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.6102106772766376e-05, + "loss": 3.8921, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.6093720825255856e-05, + "loss": 3.8879, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085334877745336e-05, + "loss": 3.919, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076965309038545e-05, + "loss": 3.8928, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068579361528025e-05, + "loss": 3.8933, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6060193414017505e-05, + "loss": 3.8986, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051807466506985e-05, + "loss": 3.9037, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043437897800194e-05, + "loss": 3.8894, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.6035051950289674e-05, + "loss": 3.8957, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.6026666002779154e-05, + "loss": 3.8906, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018280055268634e-05, + "loss": 3.8953, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600991048656185e-05, + "loss": 3.885, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600152453905133e-05, + "loss": 3.8884, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599313859154081e-05, + "loss": 3.8939, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598475264403029e-05, + "loss": 3.8965, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597636669651977e-05, + "loss": 3.9021, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596799712781298e-05, + "loss": 3.8945, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595961118030246e-05, + "loss": 3.8846, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595122523279194e-05, + "loss": 3.8946, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594283928528142e-05, + "loss": 3.8812, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593446971657463e-05, + "loss": 3.8886, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592608376906411e-05, + "loss": 3.8744, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591769782155359e-05, + "loss": 3.8805, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590931187404307e-05, + "loss": 3.8808, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590094230533628e-05, + "loss": 3.8946, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589255635782576e-05, + "loss": 3.8889, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588417041031524e-05, + "loss": 3.8808, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587578446280472e-05, + "loss": 3.8842, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.58673985152942e-05, + "loss": 3.8822, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585902894658741e-05, + "loss": 3.8892, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585064299907689e-05, + "loss": 3.8715, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584225705156637e-05, + "loss": 3.8672, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583387110405585e-05, + "loss": 3.8874, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582550153534906e-05, + "loss": 3.8856, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581711558783854e-05, + "loss": 3.8694, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580872964032802e-05, + "loss": 3.8769, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580034369281751e-05, + "loss": 3.8801, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579197412411072e-05, + "loss": 3.8646, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.57835881766002e-05, + "loss": 3.8824, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577520222908968e-05, + "loss": 3.87, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576681628157916e-05, + "loss": 3.8845, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758446712872366e-05, + "loss": 3.8699, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5750060765361846e-05, + "loss": 3.879, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741674817851326e-05, + "loss": 3.8674, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733288870340806e-05, + "loss": 3.8727, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724902922830286e-05, + "loss": 3.8613, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716516975319765e-05, + "loss": 3.8649, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5708147406612975e-05, + "loss": 3.8832, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569976145910246e-05, + "loss": 3.8643, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569137551159194e-05, + "loss": 3.8701, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568298956408142e-05, + "loss": 3.8572, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567461999537463e-05, + "loss": 3.8676, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566623404786411e-05, + "loss": 3.8817, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565784810035359e-05, + "loss": 3.8769, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564946215284307e-05, + "loss": 3.8738, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564109258413628e-05, + "loss": 3.8793, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563270663662576e-05, + "loss": 3.8779, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562432068911524e-05, + "loss": 3.8676, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561593474160472e-05, + "loss": 3.8702, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560756517289793e-05, + "loss": 3.8705, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.5599179225387415e-05, + "loss": 3.862, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590793277876895e-05, + "loss": 3.8631, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.5582407330366375e-05, + "loss": 3.8619, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.5574037761659584e-05, + "loss": 3.867, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.5565651814149064e-05, + "loss": 3.8786, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557265866638544e-05, + "loss": 3.8748, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.5548879919128024e-05, + "loss": 3.8482, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.55404939716175e-05, + "loss": 3.8694, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553212440291071e-05, + "loss": 3.8662, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552373845540019e-05, + "loss": 3.8653, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.5515352507889666e-05, + "loss": 3.8609, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550696656037915e-05, + "loss": 3.8521, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549859699167237e-05, + "loss": 3.8665, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549021104416185e-05, + "loss": 3.8597, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548182509665132e-05, + "loss": 3.8594, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.54734391491408e-05, + "loss": 3.8659, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546506958043402e-05, + "loss": 3.8612, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.54566836329235e-05, + "loss": 3.8701, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544829768541297e-05, + "loss": 3.8539, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543991173790245e-05, + "loss": 3.8529, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431542169195667e-05, + "loss": 3.8558, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542315622168514e-05, + "loss": 3.8692, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541477027417462e-05, + "loss": 3.8589, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406384326664106e-05, + "loss": 3.8536, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5397998379153586e-05, + "loss": 3.8529, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389628810446796e-05, + "loss": 3.8564, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5381242862936275e-05, + "loss": 3.8647, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372856915425755e-05, + "loss": 3.8479, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364470967915235e-05, + "loss": 3.8461, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5356101399208444e-05, + "loss": 3.8624, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347715451697924e-05, + "loss": 3.8514, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339329504187404e-05, + "loss": 3.8475, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330943556676884e-05, + "loss": 3.8429, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322573987970093e-05, + "loss": 3.8481, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314188040459573e-05, + "loss": 3.8629, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530580209294906e-05, + "loss": 3.8462, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529741614543854e-05, + "loss": 3.851, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528904657673175e-05, + "loss": 3.8565, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528066062922123e-05, + "loss": 3.8667, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527227468171071e-05, + "loss": 3.8612, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526388873420019e-05, + "loss": 3.841, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.52555191654934e-05, + "loss": 3.853, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524713321798288e-05, + "loss": 3.8499, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523874727047236e-05, + "loss": 3.8482, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523037770176557e-05, + "loss": 3.8496, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522199175425505e-05, + "loss": 3.8417, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521360580674453e-05, + "loss": 3.8555, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520521985923401e-05, + "loss": 3.844, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.5196833911723494e-05, + "loss": 3.8532, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188447964212974e-05, + "loss": 3.8427, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.5180062016702454e-05, + "loss": 3.8509, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171676069191934e-05, + "loss": 3.8389, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516330650048514e-05, + "loss": 3.8669, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515492055297462e-05, + "loss": 3.8475, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.51465346054641e-05, + "loss": 3.8495, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513814865795358e-05, + "loss": 3.8381, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512977908924679e-05, + "loss": 3.8544, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512139314173627e-05, + "loss": 3.8478, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511300719422575e-05, + "loss": 3.855, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510462124671523e-05, + "loss": 3.8435, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509625167800845e-05, + "loss": 3.8521, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508786573049793e-05, + "loss": 3.8471, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507947978298741e-05, + "loss": 3.8602, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507109383547689e-05, + "loss": 3.8374, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.5062724266770096e-05, + "loss": 3.8512, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054338319259576e-05, + "loss": 3.8433, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.5045952371749056e-05, + "loss": 3.8406, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.5037566424238536e-05, + "loss": 3.8502, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.5029180476728016e-05, + "loss": 3.8499, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.5020810908021225e-05, + "loss": 3.8395, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012424960510705e-05, + "loss": 3.8435, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.5004039013000185e-05, + "loss": 3.8429, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.911320447921753, + "eval_runtime": 357.6326, + "eval_samples_per_second": 1066.992, + "eval_steps_per_second": 33.344, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995653065489665e-05, + "loss": 3.8338, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987267117979145e-05, + "loss": 3.8298, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497888117046863e-05, + "loss": 3.8431, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970495222958105e-05, + "loss": 3.8421, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4962109275447585e-05, + "loss": 3.8532, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953723327937065e-05, + "loss": 3.8351, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945337380426545e-05, + "loss": 3.8361, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936951432916025e-05, + "loss": 3.8326, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928581864209234e-05, + "loss": 3.8485, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920195916698714e-05, + "loss": 3.8376, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911809969188194e-05, + "loss": 3.8276, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903424021677674e-05, + "loss": 3.8321, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489507083177462e-05, + "loss": 3.8307, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.48866848842641e-05, + "loss": 3.8277, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487829893675358e-05, + "loss": 3.8356, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486991298924306e-05, + "loss": 3.819, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486152704173254e-05, + "loss": 3.825, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485314109422202e-05, + "loss": 3.8227, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.48447551467115e-05, + "loss": 3.8199, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483636919920098e-05, + "loss": 3.8465, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482799963049419e-05, + "loss": 3.8298, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481961368298367e-05, + "loss": 3.8258, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481122773547315e-05, + "loss": 3.829, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480284178796263e-05, + "loss": 3.8382, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.4794472219255837e-05, + "loss": 3.821, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478608627174532e-05, + "loss": 3.8293, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.47777003242348e-05, + "loss": 3.8231, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476931437672428e-05, + "loss": 3.823, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476094480801749e-05, + "loss": 3.8182, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475255886050697e-05, + "loss": 3.8249, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474417291299645e-05, + "loss": 3.8268, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473578696548593e-05, + "loss": 3.8307, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472741739677914e-05, + "loss": 3.8346, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471903144926862e-05, + "loss": 3.829, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.47106455017581e-05, + "loss": 3.8172, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470225955424758e-05, + "loss": 3.8267, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469388998554079e-05, + "loss": 3.8197, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468550403803028e-05, + "loss": 3.8199, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467711809051976e-05, + "loss": 3.8098, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466873214300924e-05, + "loss": 3.8174, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4660362574302446e-05, + "loss": 3.8189, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651976626791926e-05, + "loss": 3.8278, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.4643590679281406e-05, + "loss": 3.8227, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4635204731770886e-05, + "loss": 3.8184, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626835163064095e-05, + "loss": 3.819, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618449215553575e-05, + "loss": 3.8182, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4610063268043055e-05, + "loss": 3.8235, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601677320532535e-05, + "loss": 3.8079, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593307751825744e-05, + "loss": 3.8003, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584921804315224e-05, + "loss": 3.8222, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457653585680471e-05, + "loss": 3.8211, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456814990929419e-05, + "loss": 3.8045, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.45597803405874e-05, + "loss": 3.8132, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455139439307688e-05, + "loss": 3.8186, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454300844556636e-05, + "loss": 3.8002, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453462249805584e-05, + "loss": 3.8191, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452625292934905e-05, + "loss": 3.8098, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451786698183853e-05, + "loss": 3.8181, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450948103432801e-05, + "loss": 3.8081, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450109508681749e-05, + "loss": 3.8149, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.44927255181107e-05, + "loss": 3.8064, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448433957060018e-05, + "loss": 3.8138, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475953623089664e-05, + "loss": 3.7988, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.4467567675579144e-05, + "loss": 3.8078, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445919810687235e-05, + "loss": 3.8174, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445081215936183e-05, + "loss": 3.8067, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444242621185131e-05, + "loss": 3.8051, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443404026434079e-05, + "loss": 3.7973, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425670695634e-05, + "loss": 3.8032, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441728474812348e-05, + "loss": 3.8141, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440889880061296e-05, + "loss": 3.8182, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440051285310244e-05, + "loss": 3.8123, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439214328439565e-05, + "loss": 3.8189, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438375733688513e-05, + "loss": 3.8192, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437537138937462e-05, + "loss": 3.8045, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.43669854418641e-05, + "loss": 3.8074, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435861587315731e-05, + "loss": 3.8125, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435022992564679e-05, + "loss": 3.7998, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434184397813627e-05, + "loss": 3.801, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433345803062575e-05, + "loss": 3.8058, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4325088461918956e-05, + "loss": 3.8044, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316702514408436e-05, + "loss": 3.8202, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308316566897916e-05, + "loss": 3.8157, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299930619387396e-05, + "loss": 3.7903, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291561050680605e-05, + "loss": 3.8059, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283175103170085e-05, + "loss": 3.8083, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427478915565957e-05, + "loss": 3.8079, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426640320814905e-05, + "loss": 3.8034, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425803363944226e-05, + "loss": 3.7914, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424964769193174e-05, + "loss": 3.8046, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424126174442122e-05, + "loss": 3.8014, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.42328757969107e-05, + "loss": 3.8014, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422450622820391e-05, + "loss": 3.8019, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421612028069339e-05, + "loss": 3.8064, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420773433318287e-05, + "loss": 3.8069, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419934838567235e-05, + "loss": 3.8044, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419097881696556e-05, + "loss": 3.7898, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418259286945504e-05, + "loss": 3.802, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174206921944525e-05, + "loss": 3.8058, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165820974434005e-05, + "loss": 3.8066, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157451405727214e-05, + "loss": 3.7938, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4149065458216694e-05, + "loss": 3.7979, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140679510706174e-05, + "loss": 3.7983, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132293563195654e-05, + "loss": 3.8054, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412392399448886e-05, + "loss": 3.7925, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411553804697834e-05, + "loss": 3.7911, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410715209946782e-05, + "loss": 3.8002, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098766151957296e-05, + "loss": 3.7964, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409039658325051e-05, + "loss": 3.7893, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408201063573999e-05, + "loss": 3.7893, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407362468822948e-05, + "loss": 3.7896, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406523874071895e-05, + "loss": 3.8049, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405686917201217e-05, + "loss": 3.7934, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404848322450165e-05, + "loss": 3.7913, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404009727699113e-05, + "loss": 3.7995, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.40317113294806e-05, + "loss": 3.8112, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402334176077382e-05, + "loss": 3.8013, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.40149558132633e-05, + "loss": 3.7856, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400656986575277e-05, + "loss": 3.793, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399818391824225e-05, + "loss": 3.7928, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.3989814349535466e-05, + "loss": 3.7897, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398144478082868e-05, + "loss": 3.7946, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397305883331816e-05, + "loss": 3.7857, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396467288580764e-05, + "loss": 3.7975, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395628693829712e-05, + "loss": 3.7935, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.39479009907866e-05, + "loss": 3.7977, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939515043276075e-05, + "loss": 3.785, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3931129095765555e-05, + "loss": 3.7929, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922743148255035e-05, + "loss": 3.7912, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914373579548244e-05, + "loss": 3.8042, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905987632037724e-05, + "loss": 3.7912, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897601684527204e-05, + "loss": 3.7968, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889215737016684e-05, + "loss": 3.7838, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.38808461683099e-05, + "loss": 3.8005, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387246022079938e-05, + "loss": 3.7957, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386407427328886e-05, + "loss": 3.7979, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385568832577834e-05, + "loss": 3.7861, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384731875707155e-05, + "loss": 3.802, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383893280956103e-05, + "loss": 3.7893, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383054686205051e-05, + "loss": 3.8066, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382216091453999e-05, + "loss": 3.7844, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.38137913458332e-05, + "loss": 3.797, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380540539832268e-05, + "loss": 3.7889, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379701945081216e-05, + "loss": 3.786, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378863350330164e-05, + "loss": 3.7989, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378026393459485e-05, + "loss": 3.7951, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377187798708433e-05, + "loss": 3.7873, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376349203957381e-05, + "loss": 3.7868, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375510609206329e-05, + "loss": 3.7931, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8865561485290527, + "eval_runtime": 305.1088, + "eval_samples_per_second": 1250.672, + "eval_steps_per_second": 39.084, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.37467365233565e-05, + "loss": 3.7839, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373835057584598e-05, + "loss": 3.778, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372996462833546e-05, + "loss": 3.7897, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372157868082494e-05, + "loss": 3.7874, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371320911211815e-05, + "loss": 3.7968, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370482316460763e-05, + "loss": 3.7823, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369643721709711e-05, + "loss": 3.7815, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368805126958659e-05, + "loss": 3.7811, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367968170087981e-05, + "loss": 3.7967, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367129575336929e-05, + "loss": 3.7819, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366290980585877e-05, + "loss": 3.7772, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365452385834825e-05, + "loss": 3.7791, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364617066844519e-05, + "loss": 3.7811, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.3637784720934665e-05, + "loss": 3.7763, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.3629398773424145e-05, + "loss": 3.7837, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.3621012825913625e-05, + "loss": 3.7683, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.3612626878403105e-05, + "loss": 3.7705, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.3604240930892585e-05, + "loss": 3.7742, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.3595854983382065e-05, + "loss": 3.7669, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.3587469035871545e-05, + "loss": 3.793, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357909946716476e-05, + "loss": 3.7816, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357071351965424e-05, + "loss": 3.7762, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356232757214372e-05, + "loss": 3.7732, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.35539416246332e-05, + "loss": 3.7843, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354557205592641e-05, + "loss": 3.7708, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353718610841589e-05, + "loss": 3.7802, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352880016090537e-05, + "loss": 3.7694, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352041421339485e-05, + "loss": 3.7753, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351204464468806e-05, + "loss": 3.7704, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350365869717754e-05, + "loss": 3.7726, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349527274966702e-05, + "loss": 3.7765, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.34868868021565e-05, + "loss": 3.7793, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3478517233449714e-05, + "loss": 3.7818, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3470131285939194e-05, + "loss": 3.7809, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461745338428674e-05, + "loss": 3.7657, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.3453359390918154e-05, + "loss": 3.7789, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344498982221136e-05, + "loss": 3.7722, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343660387470084e-05, + "loss": 3.7636, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342821792719032e-05, + "loss": 3.7659, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.34198319796798e-05, + "loss": 3.765, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341146241097301e-05, + "loss": 3.7685, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340307646346249e-05, + "loss": 3.7796, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339469051595197e-05, + "loss": 3.77, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338630456844145e-05, + "loss": 3.7682, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337793499973467e-05, + "loss": 3.7744, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336954905222415e-05, + "loss": 3.7687, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336116310471363e-05, + "loss": 3.7708, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335277715720311e-05, + "loss": 3.7596, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334440758849632e-05, + "loss": 3.7506, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.33360216409858e-05, + "loss": 3.7747, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332763569347528e-05, + "loss": 3.7685, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331924974596476e-05, + "loss": 3.7605, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.3310880177257966e-05, + "loss": 3.763, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.3302494229747446e-05, + "loss": 3.767, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3294108282236926e-05, + "loss": 3.7519, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328573871353014e-05, + "loss": 3.7684, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327735276601962e-05, + "loss": 3.7662, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.32689668185091e-05, + "loss": 3.7684, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326058087099858e-05, + "loss": 3.7625, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325219492348806e-05, + "loss": 3.7639, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324382535478127e-05, + "loss": 3.7554, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323543940727075e-05, + "loss": 3.7678, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322705345976023e-05, + "loss": 3.7537, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321866751224971e-05, + "loss": 3.7577, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321029794354292e-05, + "loss": 3.7702, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.32019119960324e-05, + "loss": 3.7598, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319352604852188e-05, + "loss": 3.7557, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318514010101136e-05, + "loss": 3.7539, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.3176770532304575e-05, + "loss": 3.755, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3168384584794055e-05, + "loss": 3.7652, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.3159998637283535e-05, + "loss": 3.7713, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151612689773015e-05, + "loss": 3.7632, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.3143243121066224e-05, + "loss": 3.7717, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.3134857173555704e-05, + "loss": 3.7692, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.3126471226045184e-05, + "loss": 3.7654, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.3118085278534664e-05, + "loss": 3.7582, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310971570982787e-05, + "loss": 3.7602, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310132976231735e-05, + "loss": 3.7592, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309294381480683e-05, + "loss": 3.7514, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308455786729631e-05, + "loss": 3.7649, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307618829858953e-05, + "loss": 3.7543, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306780235107901e-05, + "loss": 3.7709, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305941640356849e-05, + "loss": 3.7722, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305103045605797e-05, + "loss": 3.7432, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304266088735118e-05, + "loss": 3.7626, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303427493984066e-05, + "loss": 3.7549, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302588899233014e-05, + "loss": 3.7624, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301751942362335e-05, + "loss": 3.7573, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300913347611283e-05, + "loss": 3.748, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300074752860231e-05, + "loss": 3.7597, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299236158109179e-05, + "loss": 3.7546, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983992012385e-05, + "loss": 3.7593, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297560606487448e-05, + "loss": 3.7529, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296722011736396e-05, + "loss": 3.7621, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295883416985344e-05, + "loss": 3.761, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295046460114665e-05, + "loss": 3.7587, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294207865363613e-05, + "loss": 3.7428, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293369270612561e-05, + "loss": 3.757, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292530675861509e-05, + "loss": 3.7564, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.29169371899083e-05, + "loss": 3.7623, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290855124239778e-05, + "loss": 3.7486, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.290016529488726e-05, + "loss": 3.754, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289177934737674e-05, + "loss": 3.7485, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.2883409778669956e-05, + "loss": 3.7619, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.2875023831159436e-05, + "loss": 3.7448, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.2866637883648916e-05, + "loss": 3.7483, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858251936138396e-05, + "loss": 3.7529, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.2849882367431605e-05, + "loss": 3.7513, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.2841496419921085e-05, + "loss": 3.7431, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2833110472410565e-05, + "loss": 3.7483, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282472452490004e-05, + "loss": 3.7454, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.2816354956193254e-05, + "loss": 3.7546, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807969008682734e-05, + "loss": 3.7561, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799583061172214e-05, + "loss": 3.7438, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2791197113661694e-05, + "loss": 3.7574, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.27828275449549e-05, + "loss": 3.7672, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277444159744439e-05, + "loss": 3.7587, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276605564993387e-05, + "loss": 3.7395, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275766970242334e-05, + "loss": 3.7514, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274930013371656e-05, + "loss": 3.7478, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274091418620604e-05, + "loss": 3.7441, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273252823869551e-05, + "loss": 3.7497, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272414229118499e-05, + "loss": 3.7398, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271577272247821e-05, + "loss": 3.7535, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270738677496769e-05, + "loss": 3.7476, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269900082745716e-05, + "loss": 3.7559, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269061487994665e-05, + "loss": 3.7438, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268224531123986e-05, + "loss": 3.7448, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.2673859363729344e-05, + "loss": 3.7522, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266547341621882e-05, + "loss": 3.7585, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.26570874687083e-05, + "loss": 3.7483, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264871790000151e-05, + "loss": 3.7528, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.2640331952490986e-05, + "loss": 3.741, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631946004980466e-05, + "loss": 3.7573, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623560057469946e-05, + "loss": 3.7498, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261519048876316e-05, + "loss": 3.7574, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606804541252635e-05, + "loss": 3.7454, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2598418593742115e-05, + "loss": 3.7564, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2590032646231595e-05, + "loss": 3.7451, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258166307752481e-05, + "loss": 3.7663, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257327713001429e-05, + "loss": 3.7398, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256489118250377e-05, + "loss": 3.7563, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255650523499325e-05, + "loss": 3.7431, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254813566628646e-05, + "loss": 3.744, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253974971877594e-05, + "loss": 3.751, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253136377126542e-05, + "loss": 3.7499, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.25229778237549e-05, + "loss": 3.7515, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251460825504811e-05, + "loss": 3.7394, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250622230753759e-05, + "loss": 3.7526, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.8701553344726562, + "eval_runtime": 306.7651, + "eval_samples_per_second": 1243.919, + "eval_steps_per_second": 38.873, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249783636002707e-05, + "loss": 3.7459, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248945041251655e-05, + "loss": 3.7344, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2481064465006035e-05, + "loss": 3.744, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472678517495515e-05, + "loss": 3.7485, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464292569984995e-05, + "loss": 3.7525, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455906622474475e-05, + "loss": 3.7435, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447520674963955e-05, + "loss": 3.7336, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.2439134727453435e-05, + "loss": 3.741, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430765158746644e-05, + "loss": 3.7508, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422379211236124e-05, + "loss": 3.7413, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413993263725604e-05, + "loss": 3.7363, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.2405607316215084e-05, + "loss": 3.7348, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239725412631202e-05, + "loss": 3.7426, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.23888681788015e-05, + "loss": 3.732, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238048223129099e-05, + "loss": 3.7418, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237209628378047e-05, + "loss": 3.7263, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236371033626995e-05, + "loss": 3.7277, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235532438875943e-05, + "loss": 3.73, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234693844124891e-05, + "loss": 3.7271, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233855249373839e-05, + "loss": 3.7506, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.23301829250316e-05, + "loss": 3.7438, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232179697752108e-05, + "loss": 3.7355, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231341103001056e-05, + "loss": 3.7315, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230502508250004e-05, + "loss": 3.7409, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296655513793247e-05, + "loss": 3.7298, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2288269566282726e-05, + "loss": 3.7403, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279883618772206e-05, + "loss": 3.7286, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2271497671261686e-05, + "loss": 3.7349, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.22631281025549e-05, + "loss": 3.7313, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225474215504438e-05, + "loss": 3.7294, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224635620753386e-05, + "loss": 3.7354, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223797026002334e-05, + "loss": 3.7423, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222960069131655e-05, + "loss": 3.7364, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222121474380603e-05, + "loss": 3.7389, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221282879629551e-05, + "loss": 3.7252, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220444284878499e-05, + "loss": 3.7433, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.21960732800782e-05, + "loss": 3.7312, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218768733256768e-05, + "loss": 3.723, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217930138505716e-05, + "loss": 3.7261, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170931816350376e-05, + "loss": 3.7258, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2162545868839856e-05, + "loss": 3.7287, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2154159921329336e-05, + "loss": 3.7347, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145773973818816e-05, + "loss": 3.7299, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137404405112025e-05, + "loss": 3.7308, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2129018457601505e-05, + "loss": 3.7348, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2120632510090985e-05, + "loss": 3.7307, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112246562580465e-05, + "loss": 3.7307, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103876993873674e-05, + "loss": 3.718, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.2095491046363154e-05, + "loss": 3.7089, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.2087105098852634e-05, + "loss": 3.7348, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2078719151342114e-05, + "loss": 3.7339, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207034958263533e-05, + "loss": 3.7189, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206196363512481e-05, + "loss": 3.7287, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205357768761429e-05, + "loss": 3.7239, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204519174010377e-05, + "loss": 3.714, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203682217139698e-05, + "loss": 3.7245, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202843622388646e-05, + "loss": 3.7287, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.202005027637594e-05, + "loss": 3.7288, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201166432886542e-05, + "loss": 3.7222, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200329476015863e-05, + "loss": 3.7278, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199490881264811e-05, + "loss": 3.7168, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198652286513759e-05, + "loss": 3.7301, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197813691762707e-05, + "loss": 3.7156, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196976734892028e-05, + "loss": 3.7183, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196138140140976e-05, + "loss": 3.7306, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195299545389924e-05, + "loss": 3.722, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.1944609506388716e-05, + "loss": 3.7189, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193623993768193e-05, + "loss": 3.7157, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192785399017141e-05, + "loss": 3.7145, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191946804266089e-05, + "loss": 3.721, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1911082095150365e-05, + "loss": 3.7343, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190271252644358e-05, + "loss": 3.7226, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189432657893306e-05, + "loss": 3.7354, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188594063142254e-05, + "loss": 3.7297, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187755468391202e-05, + "loss": 3.731, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186918511520524e-05, + "loss": 3.7208, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186079916769472e-05, + "loss": 3.7222, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185241322018419e-05, + "loss": 3.7211, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184402727267367e-05, + "loss": 3.7113, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835657703966886e-05, + "loss": 3.7262, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1827271756456366e-05, + "loss": 3.7192, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181888580894584e-05, + "loss": 3.7323, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181049986143532e-05, + "loss": 3.7307, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1802130292728535e-05, + "loss": 3.7053, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179374434521801e-05, + "loss": 3.7279, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178535839770749e-05, + "loss": 3.7168, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776972450196975e-05, + "loss": 3.7238, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176860288149019e-05, + "loss": 3.7184, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760216933979664e-05, + "loss": 3.7121, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751830986469144e-05, + "loss": 3.7217, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743445038958624e-05, + "loss": 3.7162, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173507547025183e-05, + "loss": 3.7199, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172668952274131e-05, + "loss": 3.718, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171830357523079e-05, + "loss": 3.7246, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170991762772027e-05, + "loss": 3.7289, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170154805901348e-05, + "loss": 3.7145, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169316211150296e-05, + "loss": 3.7103, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168477616399244e-05, + "loss": 3.7183, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167639021648193e-05, + "loss": 3.7184, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166802064777514e-05, + "loss": 3.7281, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165963470026462e-05, + "loss": 3.7125, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.16512487527541e-05, + "loss": 3.7162, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642879184047307e-05, + "loss": 3.7132, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1634493236536786e-05, + "loss": 3.7254, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1626107289026266e-05, + "loss": 3.7068, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617721341515746e-05, + "loss": 3.713, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609351772808955e-05, + "loss": 3.7129, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.1600965825298435e-05, + "loss": 3.7158, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1592579877787915e-05, + "loss": 3.7058, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.1584193930277395e-05, + "loss": 3.7127, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157582436157061e-05, + "loss": 3.7057, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156743841406009e-05, + "loss": 3.7203, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155905246654957e-05, + "loss": 3.7187, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155066651903905e-05, + "loss": 3.7104, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154229695033226e-05, + "loss": 3.7169, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153391100282174e-05, + "loss": 3.7317, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152552505531122e-05, + "loss": 3.7269, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.15171391078007e-05, + "loss": 3.7049, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.1508785917897645e-05, + "loss": 3.7121, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1500399970387125e-05, + "loss": 3.7129, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.1492014022876605e-05, + "loss": 3.7031, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1483628075366085e-05, + "loss": 3.7161, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1475242127855565e-05, + "loss": 3.6987, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466856180345045e-05, + "loss": 3.7205, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458470232834525e-05, + "loss": 3.7068, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1450084285324005e-05, + "loss": 3.7211, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441714716617214e-05, + "loss": 3.7098, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1433328769106694e-05, + "loss": 3.7098, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424942821596174e-05, + "loss": 3.7132, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1416556874085654e-05, + "loss": 3.7226, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140818730537886e-05, + "loss": 3.7104, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139980135786834e-05, + "loss": 3.718, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139141541035782e-05, + "loss": 3.7036, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.13830294628473e-05, + "loss": 3.7227, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137465989414052e-05, + "loss": 3.7126, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136627394663e-05, + "loss": 3.7163, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135788799911948e-05, + "loss": 3.7119, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134950205160896e-05, + "loss": 3.7193, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134113248290217e-05, + "loss": 3.7115, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133274653539165e-05, + "loss": 3.7281, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132436058788113e-05, + "loss": 3.7058, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131597464037061e-05, + "loss": 3.7196, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307605071663816e-05, + "loss": 3.7117, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1299219124153296e-05, + "loss": 3.7125, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.1290833176642776e-05, + "loss": 3.71, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.1282447229132256e-05, + "loss": 3.7137, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127407766042547e-05, + "loss": 3.7162, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126569171291495e-05, + "loss": 3.7047, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125730576540443e-05, + "loss": 3.7213, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.8593947887420654, + "eval_runtime": 308.7788, + "eval_samples_per_second": 1235.807, + "eval_steps_per_second": 38.62, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124891981789391e-05, + "loss": 3.7047, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.124055024918712e-05, + "loss": 3.7008, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.12321643016766e-05, + "loss": 3.7091, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122377835416608e-05, + "loss": 3.7105, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121540878545929e-05, + "loss": 3.7173, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120702283794877e-05, + "loss": 3.7105, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119863689043825e-05, + "loss": 3.7034, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119025094292773e-05, + "loss": 3.7034, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.1181881374220946e-05, + "loss": 3.7161, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.1173495426710426e-05, + "loss": 3.7094, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.1165109479199906e-05, + "loss": 3.7013, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1156723531689386e-05, + "loss": 3.6989, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1148370341786324e-05, + "loss": 3.7062, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139984394275804e-05, + "loss": 3.6988, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.1131598446765284e-05, + "loss": 3.7065, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.1123212499254764e-05, + "loss": 3.6901, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.1114826551744244e-05, + "loss": 3.6957, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.1106440604233724e-05, + "loss": 3.6971, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.1098054656723204e-05, + "loss": 3.6935, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.1089668709212684e-05, + "loss": 3.7127, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.1081282761702164e-05, + "loss": 3.709, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107289681419165e-05, + "loss": 3.702, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106451086668113e-05, + "loss": 3.6968, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105612491917061e-05, + "loss": 3.7064, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104775535046382e-05, + "loss": 3.6974, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.10393694029533e-05, + "loss": 3.7063, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103098345544278e-05, + "loss": 3.693, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102259750793226e-05, + "loss": 3.705, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101422793922547e-05, + "loss": 3.7017, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100584199171495e-05, + "loss": 3.6929, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099745604420443e-05, + "loss": 3.6986, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098907009669391e-05, + "loss": 3.7076, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.098070052798712e-05, + "loss": 3.7018, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.09723145804766e-05, + "loss": 3.7118, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963928632966084e-05, + "loss": 3.6911, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0955542685455564e-05, + "loss": 3.7034, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094717311674877e-05, + "loss": 3.7005, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093878716923825e-05, + "loss": 3.6912, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.093040122172773e-05, + "loss": 3.6926, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092203165302094e-05, + "loss": 3.6914, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091364570551042e-05, + "loss": 3.6933, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.09052597579999e-05, + "loss": 3.7035, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089687381048938e-05, + "loss": 3.6971, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088850424178259e-05, + "loss": 3.698, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.088011829427207e-05, + "loss": 3.7028, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087173234676155e-05, + "loss": 3.6963, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086334639925104e-05, + "loss": 3.6944, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085497683054425e-05, + "loss": 3.6907, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084659088303373e-05, + "loss": 3.6699, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083820493552321e-05, + "loss": 3.7068, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082981898801269e-05, + "loss": 3.6935, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.0821449419305896e-05, + "loss": 3.6937, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.0813063471795376e-05, + "loss": 3.6918, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.0804677524284856e-05, + "loss": 3.6917, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079629157677433e-05, + "loss": 3.6805, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.0787922008067545e-05, + "loss": 3.6901, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.0779536060557025e-05, + "loss": 3.6968, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0771150113046505e-05, + "loss": 3.694, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0762764165535985e-05, + "loss": 3.6963, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.07543945968292e-05, + "loss": 3.6878, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074600864931868e-05, + "loss": 3.6844, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073762270180816e-05, + "loss": 3.7008, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.0729236754297634e-05, + "loss": 3.6791, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072086718559085e-05, + "loss": 3.6863, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071248123808033e-05, + "loss": 3.6962, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.07040952905698e-05, + "loss": 3.6909, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069570934305928e-05, + "loss": 3.6828, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.06873397743525e-05, + "loss": 3.6864, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067895382684198e-05, + "loss": 3.6787, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067056787933146e-05, + "loss": 3.6883, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066218193182094e-05, + "loss": 3.7014, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0653812363114154e-05, + "loss": 3.6906, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.0645426415603634e-05, + "loss": 3.7023, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063704046809311e-05, + "loss": 3.6959, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062865452058259e-05, + "loss": 3.704, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.06202849518758e-05, + "loss": 3.6862, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611899004365276e-05, + "loss": 3.694, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0603513056854756e-05, + "loss": 3.6905, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0595127109344236e-05, + "loss": 3.676, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.058675754063745e-05, + "loss": 3.6946, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.057837159312693e-05, + "loss": 3.6872, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056998564561641e-05, + "loss": 3.6985, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056159969810589e-05, + "loss": 3.7012, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055323012939911e-05, + "loss": 3.6765, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054484418188858e-05, + "loss": 3.6915, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053645823437806e-05, + "loss": 3.6854, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052808866567128e-05, + "loss": 3.6944, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051970271816075e-05, + "loss": 3.6849, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051131677065023e-05, + "loss": 3.6814, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050293082313971e-05, + "loss": 3.6864, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049454487562919e-05, + "loss": 3.6855, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048615892811867e-05, + "loss": 3.6884, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047777298060815e-05, + "loss": 3.6869, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.0469387033097637e-05, + "loss": 3.6965, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.0461017464390846e-05, + "loss": 3.6948, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.0452631516880326e-05, + "loss": 3.6831, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.0444245569369806e-05, + "loss": 3.6775, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.0435859621859285e-05, + "loss": 3.6859, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.0427490053152495e-05, + "loss": 3.6917, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.0419104105641975e-05, + "loss": 3.6921, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.0410718158131454e-05, + "loss": 3.6854, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.0402332210620934e-05, + "loss": 3.6831, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.0393962641914144e-05, + "loss": 3.6792, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.0385576694403623e-05, + "loss": 3.6967, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.0377190746893103e-05, + "loss": 3.672, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036880479938259e-05, + "loss": 3.6827, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.03604352306758e-05, + "loss": 3.6781, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035204928316528e-05, + "loss": 3.6865, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034366333565476e-05, + "loss": 3.6752, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033527738814424e-05, + "loss": 3.687, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032690781943745e-05, + "loss": 3.6736, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031852187192693e-05, + "loss": 3.6875, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.031013592441641e-05, + "loss": 3.6874, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030176635570962e-05, + "loss": 3.6782, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.02933804081991e-05, + "loss": 3.686, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028499446068858e-05, + "loss": 3.7022, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027660851317806e-05, + "loss": 3.6854, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026823894447127e-05, + "loss": 3.6841, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025986937576448e-05, + "loss": 3.6746, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025148342825396e-05, + "loss": 3.6816, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024309748074344e-05, + "loss": 3.6792, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023471153323292e-05, + "loss": 3.6823, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.02263255857224e-05, + "loss": 3.6673, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021793963821188e-05, + "loss": 3.6886, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020955369070136e-05, + "loss": 3.6781, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020116774319084e-05, + "loss": 3.6873, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019279817448405e-05, + "loss": 3.6786, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018441222697353e-05, + "loss": 3.6824, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017602627946301e-05, + "loss": 3.6797, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016764033195249e-05, + "loss": 3.6942, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0159270763245707e-05, + "loss": 3.6805, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0150884815735187e-05, + "loss": 3.6885, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.0142498868224667e-05, + "loss": 3.6707, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.0134112920714146e-05, + "loss": 3.6925, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.0125743352007356e-05, + "loss": 3.6827, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.0117357404496836e-05, + "loss": 3.6863, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.0108971456986315e-05, + "loss": 3.6813, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.0100585509475795e-05, + "loss": 3.6885, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.0092215940769005e-05, + "loss": 3.6774, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.0083829993258484e-05, + "loss": 3.6963, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.0075444045747964e-05, + "loss": 3.6758, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.0067058098237444e-05, + "loss": 3.6889, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005868852953066e-05, + "loss": 3.6825, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005030258202014e-05, + "loss": 3.6809, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004191663450962e-05, + "loss": 3.6773, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.00335306869991e-05, + "loss": 3.6862, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002516111829231e-05, + "loss": 3.6867, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001677517078179e-05, + "loss": 3.6757, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000838922327127e-05, + "loss": 3.6897, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.853278398513794, + "eval_runtime": 313.1401, + "eval_samples_per_second": 1218.595, + "eval_steps_per_second": 38.082, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 4.000000327576075e-05, + "loss": 3.6777, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999161732825023e-05, + "loss": 3.6712, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998323138073971e-05, + "loss": 3.6763, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997484543322918e-05, + "loss": 3.6819, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996645948571867e-05, + "loss": 3.687, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995807353820815e-05, + "loss": 3.6781, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994968759069763e-05, + "loss": 3.6789, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994130164318711e-05, + "loss": 3.6741, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993293207448032e-05, + "loss": 3.683, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.99245461269698e-05, + "loss": 3.6831, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991616017945928e-05, + "loss": 3.6701, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990777423194876e-05, + "loss": 3.6677, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.98994210420457e-05, + "loss": 3.6821, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989103509453518e-05, + "loss": 3.668, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882649147024656e-05, + "loss": 3.6715, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874263199514136e-05, + "loss": 3.6644, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986587725200362e-05, + "loss": 3.6651, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.98574913044931e-05, + "loss": 3.6717, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984910535698258e-05, + "loss": 3.6638, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984071940947206e-05, + "loss": 3.6824, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983234984076527e-05, + "loss": 3.68, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982396389325475e-05, + "loss": 3.6762, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981557794574423e-05, + "loss": 3.6681, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980719199823371e-05, + "loss": 3.6736, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979882242952692e-05, + "loss": 3.6706, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.97904364820164e-05, + "loss": 3.674, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978205053450588e-05, + "loss": 3.6668, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977366458699536e-05, + "loss": 3.676, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9765295018288576e-05, + "loss": 3.6665, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9756909070778056e-05, + "loss": 3.667, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748523123267536e-05, + "loss": 3.6652, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9740137175757016e-05, + "loss": 3.681, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.9731767607050225e-05, + "loss": 3.677, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.9723398038343434e-05, + "loss": 3.6806, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.9715012090832914e-05, + "loss": 3.6615, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9706626143322394e-05, + "loss": 3.6683, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.9698240195811874e-05, + "loss": 3.6781, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.9689854248301354e-05, + "loss": 3.6617, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.9681468300790834e-05, + "loss": 3.6615, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.9673082353280314e-05, + "loss": 3.662, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.9664696405769794e-05, + "loss": 3.6652, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965632683706301e-05, + "loss": 3.6679, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964794088955249e-05, + "loss": 3.676, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963955494204197e-05, + "loss": 3.6715, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963116899453145e-05, + "loss": 3.6674, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962279942582466e-05, + "loss": 3.671, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961441347831414e-05, + "loss": 3.6623, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960602753080362e-05, + "loss": 3.6635, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.95976415832931e-05, + "loss": 3.6399, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958927201458631e-05, + "loss": 3.6789, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958088606707579e-05, + "loss": 3.6638, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957250011956527e-05, + "loss": 3.671, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956411417205475e-05, + "loss": 3.6612, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9555744603347964e-05, + "loss": 3.6618, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9547358655837444e-05, + "loss": 3.6533, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953898908713065e-05, + "loss": 3.6611, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953060313962013e-05, + "loss": 3.671, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952221719210961e-05, + "loss": 3.6638, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951383124459909e-05, + "loss": 3.6723, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.95054616758923e-05, + "loss": 3.661, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949707572838178e-05, + "loss": 3.6528, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948868978087126e-05, + "loss": 3.6742, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.948030383336074e-05, + "loss": 3.6499, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947191788585022e-05, + "loss": 3.6544, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.94635319383397e-05, + "loss": 3.6692, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945514599082918e-05, + "loss": 3.6671, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944676004331866e-05, + "loss": 3.6503, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943839047461188e-05, + "loss": 3.6641, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.943000452710136e-05, + "loss": 3.6479, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942161857959084e-05, + "loss": 3.6635, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941323263208032e-05, + "loss": 3.6681, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9404863063373526e-05, + "loss": 3.6682, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9396477115863006e-05, + "loss": 3.6669, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9388091168352486e-05, + "loss": 3.6686, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937970522084196e-05, + "loss": 3.6781, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937131927333144e-05, + "loss": 3.6564, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.9362949704624655e-05, + "loss": 3.6675, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.9354563757114135e-05, + "loss": 3.662, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9346177809603615e-05, + "loss": 3.6437, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9337791862093095e-05, + "loss": 3.668, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329405914582575e-05, + "loss": 3.6618, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9321019967072055e-05, + "loss": 3.6664, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9312634019561535e-05, + "loss": 3.6774, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9304248072051015e-05, + "loss": 3.6508, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295878503344224e-05, + "loss": 3.6567, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9287492555833704e-05, + "loss": 3.6587, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927912298712691e-05, + "loss": 3.6674, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927073703961639e-05, + "loss": 3.6544, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926235109210587e-05, + "loss": 3.6563, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925396514459535e-05, + "loss": 3.659, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924557919708484e-05, + "loss": 3.6607, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923719324957432e-05, + "loss": 3.6573, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.92288073020638e-05, + "loss": 3.6609, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922042135455328e-05, + "loss": 3.6685, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921205178584649e-05, + "loss": 3.6616, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920366583833597e-05, + "loss": 3.6635, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919527989082545e-05, + "loss": 3.6477, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918691032211866e-05, + "loss": 3.6587, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917852437460814e-05, + "loss": 3.6612, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.917013842709762e-05, + "loss": 3.6686, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.91617524795871e-05, + "loss": 3.6574, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915336653207658e-05, + "loss": 3.654, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914498058456606e-05, + "loss": 3.6585, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913659463705554e-05, + "loss": 3.6634, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.9128208689545024e-05, + "loss": 3.6476, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911983912083823e-05, + "loss": 3.6557, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911145317332771e-05, + "loss": 3.6462, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910306722581719e-05, + "loss": 3.6652, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909468127830667e-05, + "loss": 3.6478, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908631170959988e-05, + "loss": 3.656, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907792576208936e-05, + "loss": 3.6479, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906953981457884e-05, + "loss": 3.6584, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906117024587205e-05, + "loss": 3.6629, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905278429836153e-05, + "loss": 3.6515, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904439835085101e-05, + "loss": 3.6569, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903601240334049e-05, + "loss": 3.6706, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902762645582998e-05, + "loss": 3.6637, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901924050831945e-05, + "loss": 3.6523, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010870939612667e-05, + "loss": 3.6471, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.9002484992102147e-05, + "loss": 3.6528, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899409904459162e-05, + "loss": 3.658, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.89857130970811e-05, + "loss": 3.6493, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897732714957058e-05, + "loss": 3.644, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896894120206006e-05, + "loss": 3.6606, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896055525454954e-05, + "loss": 3.6535, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895218568584275e-05, + "loss": 3.6615, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894379973833223e-05, + "loss": 3.6492, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8935413790821715e-05, + "loss": 3.6555, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8927027843311195e-05, + "loss": 3.6503, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.8918641895800675e-05, + "loss": 3.6649, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.8910255948290155e-05, + "loss": 3.6575, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.8901886379583364e-05, + "loss": 3.6589, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.8893500432072844e-05, + "loss": 3.6455, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.8885114484562324e-05, + "loss": 3.6689, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.8876728537051804e-05, + "loss": 3.6563, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886835896834501e-05, + "loss": 3.6617, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885997302083449e-05, + "loss": 3.6539, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885158707332397e-05, + "loss": 3.6565, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884320112581345e-05, + "loss": 3.6543, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883481517830293e-05, + "loss": 3.6703, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882642923079241e-05, + "loss": 3.6498, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881804328328189e-05, + "loss": 3.6642, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880965733577138e-05, + "loss": 3.6564, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880128776706459e-05, + "loss": 3.6524, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879290181955407e-05, + "loss": 3.6529, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878451587204355e-05, + "loss": 3.6606, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877612992453303e-05, + "loss": 3.6574, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876776035582624e-05, + "loss": 3.6547, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875937440831572e-05, + "loss": 3.6622, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.848841428756714, + "eval_runtime": 303.5435, + "eval_samples_per_second": 1257.121, + "eval_steps_per_second": 39.286, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.87509884608052e-05, + "loss": 3.6455, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874260251329468e-05, + "loss": 3.6426, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873423294458789e-05, + "loss": 3.6505, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872584699707737e-05, + "loss": 3.6587, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871746104956685e-05, + "loss": 3.6619, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.8709075102056333e-05, + "loss": 3.65, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870070553334954e-05, + "loss": 3.6534, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869231958583902e-05, + "loss": 3.6499, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.86839336383285e-05, + "loss": 3.6548, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867554769081798e-05, + "loss": 3.6623, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866717812211119e-05, + "loss": 3.643, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865879217460067e-05, + "loss": 3.6415, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865043898469761e-05, + "loss": 3.6603, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864205303718709e-05, + "loss": 3.6401, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863366708967657e-05, + "loss": 3.6458, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8625281142166056e-05, + "loss": 3.6382, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616895194655536e-05, + "loss": 3.6384, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8608509247145016e-05, + "loss": 3.6416, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8600123299634496e-05, + "loss": 3.6379, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8591737352123976e-05, + "loss": 3.6514, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.8583351404613456e-05, + "loss": 3.6544, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857496545710293e-05, + "loss": 3.652, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856657950959241e-05, + "loss": 3.6435, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855819356208189e-05, + "loss": 3.646, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8549823993375105e-05, + "loss": 3.6494, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854143804586458e-05, + "loss": 3.6463, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853305209835406e-05, + "loss": 3.6408, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852466615084354e-05, + "loss": 3.6547, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851631296094049e-05, + "loss": 3.6392, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850792701342997e-05, + "loss": 3.6408, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849954106591945e-05, + "loss": 3.6389, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849115511840893e-05, + "loss": 3.6523, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.84827691708984e-05, + "loss": 3.6526, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847438322338788e-05, + "loss": 3.6598, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846599727587736e-05, + "loss": 3.634, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845761132836684e-05, + "loss": 3.6465, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844924175966005e-05, + "loss": 3.6541, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.844085581214953e-05, + "loss": 3.6307, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843246986463901e-05, + "loss": 3.638, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842410029593223e-05, + "loss": 3.6386, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841571434842171e-05, + "loss": 3.6402, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840732840091119e-05, + "loss": 3.6424, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839894245340067e-05, + "loss": 3.6459, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839057288469388e-05, + "loss": 3.6466, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838218693718336e-05, + "loss": 3.6428, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8373800989672837e-05, + "loss": 3.6452, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8365415042162317e-05, + "loss": 3.6387, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8357029094651796e-05, + "loss": 3.6407, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8348643147141276e-05, + "loss": 3.6122, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8340257199630756e-05, + "loss": 3.6538, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331871252120236e-05, + "loss": 3.6361, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8323501683413445e-05, + "loss": 3.6463, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831511573590293e-05, + "loss": 3.6369, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830672978839241e-05, + "loss": 3.64, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829836021968562e-05, + "loss": 3.629, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.82899742721751e-05, + "loss": 3.6341, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828158832466458e-05, + "loss": 3.6505, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827320237715406e-05, + "loss": 3.6332, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826483280844727e-05, + "loss": 3.647, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825644686093675e-05, + "loss": 3.6415, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824806091342623e-05, + "loss": 3.6242, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823967496591571e-05, + "loss": 3.6517, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823128901840519e-05, + "loss": 3.6267, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822290307089467e-05, + "loss": 3.6321, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821451712338415e-05, + "loss": 3.6462, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8206147554677366e-05, + "loss": 3.6382, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8197761607166846e-05, + "loss": 3.6271, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8189375659656326e-05, + "loss": 3.6388, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180989712145806e-05, + "loss": 3.6213, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8172603764635286e-05, + "loss": 3.6423, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8164234195928495e-05, + "loss": 3.6433, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8155848248417975e-05, + "loss": 3.6391, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8147462300907455e-05, + "loss": 3.6439, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8139076353396935e-05, + "loss": 3.6451, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.8130690405886415e-05, + "loss": 3.6549, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.8122320837179624e-05, + "loss": 3.6318, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.8113934889669104e-05, + "loss": 3.6399, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.8105548942158584e-05, + "loss": 3.6424, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.8097162994648064e-05, + "loss": 3.6159, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.8088777047137543e-05, + "loss": 3.642, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.8080391099627023e-05, + "loss": 3.6414, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807202153092024e-05, + "loss": 3.6409, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806363558340971e-05, + "loss": 3.6518, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805524963589919e-05, + "loss": 3.6268, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804686368838867e-05, + "loss": 3.6329, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803847774087815e-05, + "loss": 3.6348, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.803010817217136e-05, + "loss": 3.6401, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802172222466084e-05, + "loss": 3.6363, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801333627715032e-05, + "loss": 3.6322, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.80049503296398e-05, + "loss": 3.6293, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799656438212929e-05, + "loss": 3.6377, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798817843461877e-05, + "loss": 3.6321, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797979248710825e-05, + "loss": 3.6351, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797140653959773e-05, + "loss": 3.6454, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796303697089094e-05, + "loss": 3.6386, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795465102338042e-05, + "loss": 3.6412, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.79462650758699e-05, + "loss": 3.6244, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793787912835938e-05, + "loss": 3.6348, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7929509559652586e-05, + "loss": 3.634, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7921123612142066e-05, + "loss": 3.6422, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7912754043435275e-05, + "loss": 3.6323, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7904368095924755e-05, + "loss": 3.6325, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789598214841424e-05, + "loss": 3.6342, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788759620090372e-05, + "loss": 3.6363, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.78792102533932e-05, + "loss": 3.6238, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787084068468641e-05, + "loss": 3.6343, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786245473717589e-05, + "loss": 3.6206, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785406878966537e-05, + "loss": 3.6399, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784568284215485e-05, + "loss": 3.6288, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783729689464433e-05, + "loss": 3.6292, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782891094713381e-05, + "loss": 3.6214, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782052499962329e-05, + "loss": 3.6386, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.78121554309165e-05, + "loss": 3.6353, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780376948340598e-05, + "loss": 3.6273, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779538353589546e-05, + "loss": 3.6358, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778699758838494e-05, + "loss": 3.644, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7778611640874426e-05, + "loss": 3.6418, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.77702256933639e-05, + "loss": 3.6302, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.7761856124657115e-05, + "loss": 3.6241, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.7753470177146595e-05, + "loss": 3.6317, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.7745084229636075e-05, + "loss": 3.6345, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773669828212555e-05, + "loss": 3.6236, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772831233461503e-05, + "loss": 3.6228, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771992638710451e-05, + "loss": 3.6385, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771155681839772e-05, + "loss": 3.6342, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.77031708708872e-05, + "loss": 3.6333, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769478492337668e-05, + "loss": 3.6281, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.7686398975866164e-05, + "loss": 3.6322, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.7678013028355644e-05, + "loss": 3.6291, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.7669627080845124e-05, + "loss": 3.643, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.7661241133334604e-05, + "loss": 3.6293, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765287156462781e-05, + "loss": 3.6384, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764448561711729e-05, + "loss": 3.6199, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763609966960677e-05, + "loss": 3.6465, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762771372209625e-05, + "loss": 3.6256, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761932777458573e-05, + "loss": 3.641, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.761095820587894e-05, + "loss": 3.6299, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760257225836842e-05, + "loss": 3.6362, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.75941863108579e-05, + "loss": 3.627, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758580036334738e-05, + "loss": 3.6486, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757741441583686e-05, + "loss": 3.6255, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756902846832634e-05, + "loss": 3.6393, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756064252081583e-05, + "loss": 3.6336, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755227295210904e-05, + "loss": 3.6279, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754388700459852e-05, + "loss": 3.6318, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7535501057088e-05, + "loss": 3.6324, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752711510957748e-05, + "loss": 3.6354, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.7518761919674416e-05, + "loss": 3.6314, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.7510375972163895e-05, + "loss": 3.6372, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.8459105491638184, + "eval_runtime": 303.9269, + "eval_samples_per_second": 1255.535, + "eval_steps_per_second": 39.236, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.7501990024653375e-05, + "loss": 3.6288, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.7493604077142855e-05, + "loss": 3.6196, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7485218129632335e-05, + "loss": 3.6254, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7476832182121815e-05, + "loss": 3.6346, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.7468446234611295e-05, + "loss": 3.6399, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.746007666590451e-05, + "loss": 3.6294, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745169071839399e-05, + "loss": 3.6285, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744330477088347e-05, + "loss": 3.6263, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743491882337295e-05, + "loss": 3.6286, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742653287586243e-05, + "loss": 3.6356, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7418146928351904e-05, + "loss": 3.621, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7409760980841384e-05, + "loss": 3.6226, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740140779093833e-05, + "loss": 3.6372, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739302184342781e-05, + "loss": 3.6166, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738463589591729e-05, + "loss": 3.6246, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737624994840677e-05, + "loss": 3.611, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736786400089625e-05, + "loss": 3.6192, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7359478053385736e-05, + "loss": 3.6196, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735109210587521e-05, + "loss": 3.6123, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734270615836469e-05, + "loss": 3.6301, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733432021085417e-05, + "loss": 3.6288, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732595064214738e-05, + "loss": 3.6281, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731756469463686e-05, + "loss": 3.6214, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730917874712634e-05, + "loss": 3.6255, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730079279961582e-05, + "loss": 3.6294, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.72924068521053e-05, + "loss": 3.6204, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728402090459478e-05, + "loss": 3.6133, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727565133588799e-05, + "loss": 3.6326, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.7267265388377473e-05, + "loss": 3.6199, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.7258879440866953e-05, + "loss": 3.6186, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725049349335643e-05, + "loss": 3.6178, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724210754584591e-05, + "loss": 3.6286, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723373797713912e-05, + "loss": 3.6238, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.72253520296286e-05, + "loss": 3.6393, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721696608211808e-05, + "loss": 3.6146, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720858013460756e-05, + "loss": 3.6186, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.720021056590077e-05, + "loss": 3.6345, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719182461839025e-05, + "loss": 3.6077, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718343867087973e-05, + "loss": 3.6171, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717505272336921e-05, + "loss": 3.6191, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716666677585869e-05, + "loss": 3.6124, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715829720715191e-05, + "loss": 3.6213, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714991125964139e-05, + "loss": 3.6243, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714152531213087e-05, + "loss": 3.6273, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713313936462035e-05, + "loss": 3.6169, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712475341710983e-05, + "loss": 3.6276, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711636746959931e-05, + "loss": 3.6117, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710798152208879e-05, + "loss": 3.6225, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709959557457827e-05, + "loss": 3.5896, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.7091226005871476e-05, + "loss": 3.6276, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.7082840058360956e-05, + "loss": 3.6163, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.7074454110850436e-05, + "loss": 3.6244, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7066068163339916e-05, + "loss": 3.6153, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7057698594633125e-05, + "loss": 3.6166, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704932902592634e-05, + "loss": 3.6045, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704094307841582e-05, + "loss": 3.6106, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.70325571309053e-05, + "loss": 3.6291, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702417118339478e-05, + "loss": 3.6071, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701580161468799e-05, + "loss": 3.6239, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700741566717747e-05, + "loss": 3.6226, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699902971966695e-05, + "loss": 3.6, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699064377215643e-05, + "loss": 3.626, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698225782464591e-05, + "loss": 3.6084, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697388825593912e-05, + "loss": 3.6085, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.69655023084286e-05, + "loss": 3.6219, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695711636091808e-05, + "loss": 3.616, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694873041340756e-05, + "loss": 3.6061, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.6940344465897045e-05, + "loss": 3.6171, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693195851838652e-05, + "loss": 3.6038, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923572570876e-05, + "loss": 3.6168, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691518662336548e-05, + "loss": 3.6199, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690683343346242e-05, + "loss": 3.6195, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.68984474859519e-05, + "loss": 3.6232, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.689006153844138e-05, + "loss": 3.6212, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688167559093086e-05, + "loss": 3.6309, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687330602222407e-05, + "loss": 3.6097, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686492007471355e-05, + "loss": 3.6216, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685653412720303e-05, + "loss": 3.6171, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684814817969251e-05, + "loss": 3.599, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683976223218199e-05, + "loss": 3.6182, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683139266347521e-05, + "loss": 3.6207, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682300671596469e-05, + "loss": 3.6148, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681462076845416e-05, + "loss": 3.633, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680623482094364e-05, + "loss": 3.602, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679784887343312e-05, + "loss": 3.6093, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.67894629259226e-05, + "loss": 3.6149, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678109335721581e-05, + "loss": 3.6176, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677270740970529e-05, + "loss": 3.6167, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676432146219477e-05, + "loss": 3.6121, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675593551468425e-05, + "loss": 3.6036, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6747565945977466e-05, + "loss": 3.6166, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6739179998466946e-05, + "loss": 3.6144, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6730794050956426e-05, + "loss": 3.6118, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6722408103445906e-05, + "loss": 3.6222, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6714022155935386e-05, + "loss": 3.6204, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.6705652587228595e-05, + "loss": 3.6138, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.6697266639718075e-05, + "loss": 3.6049, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.6688880692207555e-05, + "loss": 3.6129, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.6680494744697035e-05, + "loss": 3.6098, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.6672108797186515e-05, + "loss": 3.6233, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.6663739228479724e-05, + "loss": 3.612, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.6655353280969204e-05, + "loss": 3.6095, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664696733345869e-05, + "loss": 3.6123, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663858138594817e-05, + "loss": 3.6109, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.663021181724138e-05, + "loss": 3.6091, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662182586973086e-05, + "loss": 3.6119, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661343992222034e-05, + "loss": 3.5993, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660505397470982e-05, + "loss": 3.621, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.65966680271993e-05, + "loss": 3.6079, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658828207968878e-05, + "loss": 3.6038, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657989613217826e-05, + "loss": 3.5991, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657152656347147e-05, + "loss": 3.615, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656314061596095e-05, + "loss": 3.6169, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655475466845043e-05, + "loss": 3.6039, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654636872093991e-05, + "loss": 3.6145, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653798277342939e-05, + "loss": 3.6274, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.6529596825918875e-05, + "loss": 3.618, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652121087840835e-05, + "loss": 3.6098, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.6512841309701564e-05, + "loss": 3.6056, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.6504455362191044e-05, + "loss": 3.6088, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.6496069414680524e-05, + "loss": 3.614, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648768346717e-05, + "loss": 3.6001, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647929751965948e-05, + "loss": 3.6006, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647092795095269e-05, + "loss": 3.6151, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646254200344217e-05, + "loss": 3.611, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6454156055931646e-05, + "loss": 3.6113, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6445770108421126e-05, + "loss": 3.6122, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643738416091061e-05, + "loss": 3.6083, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642899821340009e-05, + "loss": 3.6082, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642061226588957e-05, + "loss": 3.6196, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641222631837905e-05, + "loss": 3.6071, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640385674967226e-05, + "loss": 3.6182, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639547080216174e-05, + "loss": 3.6012, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638708485465122e-05, + "loss": 3.6187, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.63786989071407e-05, + "loss": 3.6115, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637031295963018e-05, + "loss": 3.6178, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636194339092339e-05, + "loss": 3.6095, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635355744341287e-05, + "loss": 3.6113, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634517149590235e-05, + "loss": 3.6111, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633678554839183e-05, + "loss": 3.6235, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632839960088131e-05, + "loss": 3.6092, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6320030032174526e-05, + "loss": 3.6134, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6311644084664006e-05, + "loss": 3.6154, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.6303258137153486e-05, + "loss": 3.6066, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6294872189642966e-05, + "loss": 3.6088, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.6286502620936175e-05, + "loss": 3.6159, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6278116673425655e-05, + "loss": 3.6135, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6269730725915135e-05, + "loss": 3.612, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6261344778404615e-05, + "loss": 3.6129, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8440628051757812, + "eval_runtime": 303.6351, + "eval_samples_per_second": 1256.742, + "eval_steps_per_second": 39.274, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6252958830894095e-05, + "loss": 3.6009, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6244572883383575e-05, + "loss": 3.6022, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6236186935873055e-05, + "loss": 3.6061, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622780098836253e-05, + "loss": 3.6139, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.6219431419655744e-05, + "loss": 3.6171, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621104547214523e-05, + "loss": 3.6074, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620265952463471e-05, + "loss": 3.6091, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.6194273577124184e-05, + "loss": 3.6054, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6185887629613664e-05, + "loss": 3.6071, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617751806090688e-05, + "loss": 3.6116, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616913211339636e-05, + "loss": 3.6056, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616074616588583e-05, + "loss": 3.599, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615237659717905e-05, + "loss": 3.6127, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614399064966853e-05, + "loss": 3.5971, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6135604702158e-05, + "loss": 3.6036, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612721875464748e-05, + "loss": 3.5898, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611883280713697e-05, + "loss": 3.6007, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611044685962645e-05, + "loss": 3.5992, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610206091211593e-05, + "loss": 3.5908, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609367496460541e-05, + "loss": 3.6089, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608528901709489e-05, + "loss": 3.6068, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.60769194483881e-05, + "loss": 3.6037, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606853350087758e-05, + "loss": 3.6032, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.606014755336706e-05, + "loss": 3.6034, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605176160585654e-05, + "loss": 3.6096, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604337565834602e-05, + "loss": 3.6031, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.60349897108355e-05, + "loss": 3.5894, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602660376332498e-05, + "loss": 3.6131, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.6018234194618186e-05, + "loss": 3.5957, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6009848247107666e-05, + "loss": 3.5957, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600146229959715e-05, + "loss": 3.6018, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599307635208663e-05, + "loss": 3.6057, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598470678337984e-05, + "loss": 3.6024, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597632083586932e-05, + "loss": 3.6189, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.59679348883588e-05, + "loss": 3.5952, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595954894084828e-05, + "loss": 3.5986, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595117937214149e-05, + "loss": 3.6141, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594279342463097e-05, + "loss": 3.5858, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593440747712045e-05, + "loss": 3.5983, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592602152960993e-05, + "loss": 3.5976, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591765196090314e-05, + "loss": 3.5923, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590926601339262e-05, + "loss": 3.6012, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5900880065882106e-05, + "loss": 3.6028, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892494118371586e-05, + "loss": 3.605, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5884108170861066e-05, + "loss": 3.5995, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5875722223350546e-05, + "loss": 3.604, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586733627584002e-05, + "loss": 3.5901, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.58589503283295e-05, + "loss": 3.6066, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5850597138426445e-05, + "loss": 3.5699, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5842211190915924e-05, + "loss": 3.6031, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.5833825243405404e-05, + "loss": 3.598, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.5825439295894884e-05, + "loss": 3.6055, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5817053348384364e-05, + "loss": 3.5922, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5808667400873844e-05, + "loss": 3.5986, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580029783216706e-05, + "loss": 3.5859, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579191188465654e-05, + "loss": 3.5892, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578352593714602e-05, + "loss": 3.6119, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577513998963549e-05, + "loss": 3.584, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576677042092871e-05, + "loss": 3.6024, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575838447341819e-05, + "loss": 3.6042, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574999852590767e-05, + "loss": 3.5777, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574161257839714e-05, + "loss": 3.6088, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573322663088662e-05, + "loss": 3.5872, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572485706217984e-05, + "loss": 3.587, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571647111466931e-05, + "loss": 3.5994, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.57080851671588e-05, + "loss": 3.5996, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569969921964828e-05, + "loss": 3.5857, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569131327213776e-05, + "loss": 3.5962, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568292732462724e-05, + "loss": 3.5815, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567454137711672e-05, + "loss": 3.6003, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566617180840993e-05, + "loss": 3.601, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565778586089941e-05, + "loss": 3.5999, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564939991338889e-05, + "loss": 3.5994, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564101396587837e-05, + "loss": 3.5991, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563262801836785e-05, + "loss": 3.6111, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.5624258449661056e-05, + "loss": 3.589, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5615872502150536e-05, + "loss": 3.6035, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5607486554640016e-05, + "loss": 3.5911, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5599100607129496e-05, + "loss": 3.5839, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5590714659618976e-05, + "loss": 3.5948, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558234509091219e-05, + "loss": 3.5999, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557395914340167e-05, + "loss": 3.5971, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556557319589115e-05, + "loss": 3.614, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555718724838063e-05, + "loss": 3.581, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554880130087011e-05, + "loss": 3.5911, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554041535335959e-05, + "loss": 3.595, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.55320457846528e-05, + "loss": 3.5973, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552365983714228e-05, + "loss": 3.5928, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551527388963176e-05, + "loss": 3.5875, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550688794212124e-05, + "loss": 3.5897, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549850199461072e-05, + "loss": 3.5953, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549013242590393e-05, + "loss": 3.5958, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.5481746478393416e-05, + "loss": 3.5913, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473360530882896e-05, + "loss": 3.6018, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5464974583372376e-05, + "loss": 3.6002, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5456605014665585e-05, + "loss": 3.595, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5448219067155065e-05, + "loss": 3.585, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5439833119644545e-05, + "loss": 3.5939, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5431447172134025e-05, + "loss": 3.5933, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.54230612246235e-05, + "loss": 3.6007, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.5414691655916714e-05, + "loss": 3.5934, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.5406305708406194e-05, + "loss": 3.5874, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.5397919760895674e-05, + "loss": 3.5933, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.5389533813385154e-05, + "loss": 3.5937, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538116424467837e-05, + "loss": 3.5906, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537277829716785e-05, + "loss": 3.59, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536439234965733e-05, + "loss": 3.5804, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.53560064021468e-05, + "loss": 3.5987, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534763683344002e-05, + "loss": 3.5934, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.53392508859295e-05, + "loss": 3.5811, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533086493841897e-05, + "loss": 3.5798, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532247899090845e-05, + "loss": 3.5939, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531409304339793e-05, + "loss": 3.5958, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530572347469115e-05, + "loss": 3.5842, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529733752718062e-05, + "loss": 3.5964, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528895157967011e-05, + "loss": 3.6076, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528056563215959e-05, + "loss": 3.5952, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527217968464907e-05, + "loss": 3.5911, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.5263810115942276e-05, + "loss": 3.5877, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.5255424168431756e-05, + "loss": 3.5909, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.5247038220921236e-05, + "loss": 3.5963, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.5238652273410716e-05, + "loss": 3.5809, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.5230266325900196e-05, + "loss": 3.579, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.5221880378389676e-05, + "loss": 3.5928, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.5213510809682885e-05, + "loss": 3.5881, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.5205124862172365e-05, + "loss": 3.5944, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5196738914661845e-05, + "loss": 3.5929, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.5188352967151325e-05, + "loss": 3.586, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517998339844454e-05, + "loss": 3.5879, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517159745093402e-05, + "loss": 3.6001, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.51632115034235e-05, + "loss": 3.5912, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515482555591298e-05, + "loss": 3.6, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514643960840246e-05, + "loss": 3.5837, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513805366089194e-05, + "loss": 3.5953, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512968409218515e-05, + "loss": 3.595, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512129814467463e-05, + "loss": 3.5958, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511291219716411e-05, + "loss": 3.5947, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510452624965359e-05, + "loss": 3.5896, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.50961566809468e-05, + "loss": 3.5911, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508777073343628e-05, + "loss": 3.6035, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507938478592576e-05, + "loss": 3.5893, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507099883841524e-05, + "loss": 3.5941, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.5062629269708455e-05, + "loss": 3.5977, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.5054243322197935e-05, + "loss": 3.5871, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.5045857374687415e-05, + "loss": 3.5875, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.5037471427176895e-05, + "loss": 3.6006, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5029101858470104e-05, + "loss": 3.5888, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.5020715910959584e-05, + "loss": 3.5904, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.5012329963449064e-05, + "loss": 3.5925, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.8449668884277344, + "eval_runtime": 304.424, + "eval_samples_per_second": 1253.485, + "eval_steps_per_second": 39.172, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5003944015938544e-05, + "loss": 3.5972, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.4995558068428023e-05, + "loss": 3.581, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.4987172120917503e-05, + "loss": 3.5869, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497878617340698e-05, + "loss": 3.5973, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.497041660470019e-05, + "loss": 3.5911, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496203065718968e-05, + "loss": 3.5927, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495364470967916e-05, + "loss": 3.5948, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494525876216863e-05, + "loss": 3.5855, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493687281465811e-05, + "loss": 3.584, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492850324595133e-05, + "loss": 3.591, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.492011729844081e-05, + "loss": 3.5916, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491173135093028e-05, + "loss": 3.577, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.49033617822235e-05, + "loss": 3.5965, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489497583471298e-05, + "loss": 3.5792, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488658988720246e-05, + "loss": 3.5831, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487820393969193e-05, + "loss": 3.5746, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486981799218142e-05, + "loss": 3.5817, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.48614320446709e-05, + "loss": 3.5805, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485304609716038e-05, + "loss": 3.5737, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484466014964986e-05, + "loss": 3.5847, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483627420213934e-05, + "loss": 3.5927, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.4827904633432546e-05, + "loss": 3.5873, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.4819518685922026e-05, + "loss": 3.5797, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.4811132738411506e-05, + "loss": 3.5868, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.4802746790900986e-05, + "loss": 3.5933, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4794377222194195e-05, + "loss": 3.5809, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4785991274683675e-05, + "loss": 3.574, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4777605327173155e-05, + "loss": 3.5924, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4769219379662635e-05, + "loss": 3.5791, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.476084981095585e-05, + "loss": 3.5762, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475246386344533e-05, + "loss": 3.5825, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474407791593481e-05, + "loss": 3.5847, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473569196842429e-05, + "loss": 3.5878, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.47273223997175e-05, + "loss": 3.5993, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471893645220698e-05, + "loss": 3.5722, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471055050469646e-05, + "loss": 3.5866, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470216455718594e-05, + "loss": 3.5923, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469379498847915e-05, + "loss": 3.5641, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468540904096863e-05, + "loss": 3.5807, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467702309345811e-05, + "loss": 3.5812, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466863714594759e-05, + "loss": 3.569, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.4660267577240804e-05, + "loss": 3.5884, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.4651881629730284e-05, + "loss": 3.5805, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.4643495682219764e-05, + "loss": 3.5885, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.4635109734709244e-05, + "loss": 3.5789, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4626723787198724e-05, + "loss": 3.5857, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4618337839688204e-05, + "loss": 3.5707, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460996827098141e-05, + "loss": 3.5871, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460158232347089e-05, + "loss": 3.5555, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459319637596037e-05, + "loss": 3.5836, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458481042844985e-05, + "loss": 3.5778, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457644085974306e-05, + "loss": 3.5885, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456805491223254e-05, + "loss": 3.5723, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455966896472202e-05, + "loss": 3.5755, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455128301721151e-05, + "loss": 3.572, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454289706970099e-05, + "loss": 3.5716, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.45345275009942e-05, + "loss": 3.5927, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452614155348368e-05, + "loss": 3.5635, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451775560597316e-05, + "loss": 3.587, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450936965846264e-05, + "loss": 3.5858, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450100008975585e-05, + "loss": 3.5599, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449261414224533e-05, + "loss": 3.5888, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448422819473481e-05, + "loss": 3.568, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447584224722429e-05, + "loss": 3.5696, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.4467456299713767e-05, + "loss": 3.582, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4459086731006976e-05, + "loss": 3.5814, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4450700783496456e-05, + "loss": 3.569, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444231483598594e-05, + "loss": 3.579, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.4433928888475416e-05, + "loss": 3.5619, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.4425542940964896e-05, + "loss": 3.5776, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441717337225811e-05, + "loss": 3.5862, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440878742474759e-05, + "loss": 3.5789, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4400401477237065e-05, + "loss": 3.5831, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4392015529726544e-05, + "loss": 3.5797, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438364596101976e-05, + "loss": 3.5932, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.4375260013509234e-05, + "loss": 3.5738, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.4366874065998713e-05, + "loss": 3.5849, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.4358488118488193e-05, + "loss": 3.5736, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435011854978141e-05, + "loss": 3.562, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434173260227089e-05, + "loss": 3.5784, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433334665476037e-05, + "loss": 3.5801, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432496070724985e-05, + "loss": 3.58, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431657475973933e-05, + "loss": 3.5927, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430820519103254e-05, + "loss": 3.5673, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429981924352202e-05, + "loss": 3.569, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.42914332960115e-05, + "loss": 3.5724, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428304734850098e-05, + "loss": 3.5857, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427466140099046e-05, + "loss": 3.5729, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426629183228367e-05, + "loss": 3.5701, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425790588477315e-05, + "loss": 3.5711, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.4249519937262634e-05, + "loss": 3.5768, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.4241133989752114e-05, + "loss": 3.5755, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423276442104532e-05, + "loss": 3.5733, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.42243784735348e-05, + "loss": 3.5844, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421599252602428e-05, + "loss": 3.5827, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420760657851376e-05, + "loss": 3.5778, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419922063100324e-05, + "loss": 3.5655, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419085106229645e-05, + "loss": 3.5739, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418246511478593e-05, + "loss": 3.5737, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417407916727541e-05, + "loss": 3.5851, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416569321976489e-05, + "loss": 3.571, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.41573236510581e-05, + "loss": 3.5706, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414893770354759e-05, + "loss": 3.5747, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414055175603707e-05, + "loss": 3.573, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413216580852655e-05, + "loss": 3.5769, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4123796239819757e-05, + "loss": 3.5728, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.4115410292309236e-05, + "loss": 3.5603, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4107024344798716e-05, + "loss": 3.5813, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.4098638397288196e-05, + "loss": 3.5737, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4090252449777676e-05, + "loss": 3.567, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.4081882881070885e-05, + "loss": 3.5592, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.4073496933560365e-05, + "loss": 3.5746, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.4065110986049845e-05, + "loss": 3.5809, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4056725038539325e-05, + "loss": 3.5644, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4048339091028805e-05, + "loss": 3.5779, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403996952232202e-05, + "loss": 3.5847, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.40315835748115e-05, + "loss": 3.5833, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402319762730098e-05, + "loss": 3.573, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401481167979046e-05, + "loss": 3.5685, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400644211108367e-05, + "loss": 3.5696, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399805616357315e-05, + "loss": 3.5801, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398967021606263e-05, + "loss": 3.5626, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398128426855211e-05, + "loss": 3.5672, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397291469984532e-05, + "loss": 3.5687, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.39645287523348e-05, + "loss": 3.5773, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395614280482428e-05, + "loss": 3.5756, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394775685731376e-05, + "loss": 3.5759, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3939387288606975e-05, + "loss": 3.5652, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3931001341096455e-05, + "loss": 3.5705, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3922615393585935e-05, + "loss": 3.5849, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3914229446075415e-05, + "loss": 3.5704, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3905859877368624e-05, + "loss": 3.5849, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897473929858104e-05, + "loss": 3.5606, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3889087982347584e-05, + "loss": 3.58, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3880702034837064e-05, + "loss": 3.576, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387233246613027e-05, + "loss": 3.5772, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386394651861975e-05, + "loss": 3.5777, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385556057110923e-05, + "loss": 3.5692, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384717462359871e-05, + "loss": 3.5803, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383878867608819e-05, + "loss": 3.5849, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383041910738141e-05, + "loss": 3.5742, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382203315987089e-05, + "loss": 3.574, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381364721236037e-05, + "loss": 3.5783, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380526126484985e-05, + "loss": 3.5675, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379689169614306e-05, + "loss": 3.57, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378850574863254e-05, + "loss": 3.5841, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.378011980112202e-05, + "loss": 3.5735, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377173385361149e-05, + "loss": 3.5742, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3763364284904706e-05, + "loss": 3.5722, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.845510244369507, + "eval_runtime": 302.424, + "eval_samples_per_second": 1261.775, + "eval_steps_per_second": 39.431, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.3754978337394186e-05, + "loss": 3.5671, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.3746592389883666e-05, + "loss": 3.562, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.3738206442373146e-05, + "loss": 3.5688, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372983687366636e-05, + "loss": 3.5794, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372145092615584e-05, + "loss": 3.5743, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.3713064978645315e-05, + "loss": 3.5756, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.3704679031134795e-05, + "loss": 3.5702, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.3696293083624275e-05, + "loss": 3.571, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368792351491749e-05, + "loss": 3.5675, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.3679537567406964e-05, + "loss": 3.5787, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.3671151619896444e-05, + "loss": 3.5668, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.3662765672385924e-05, + "loss": 3.5628, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365441248248287e-05, + "loss": 3.5797, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.3646026534972356e-05, + "loss": 3.5588, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3637640587461836e-05, + "loss": 3.5637, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.3629254639951316e-05, + "loss": 3.5558, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362086869244079e-05, + "loss": 3.5645, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361248274493027e-05, + "loss": 3.5605, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360409679741975e-05, + "loss": 3.5585, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359571084990923e-05, + "loss": 3.5626, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358732490239871e-05, + "loss": 3.5782, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357895533369192e-05, + "loss": 3.5667, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.35705693861814e-05, + "loss": 3.5637, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356218343867088e-05, + "loss": 3.5722, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355379749116036e-05, + "loss": 3.5785, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.3545427922453574e-05, + "loss": 3.5602, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.3537041974943054e-05, + "loss": 3.5575, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.3528656027432534e-05, + "loss": 3.5758, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.3520270079922013e-05, + "loss": 3.5589, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.3511884132411493e-05, + "loss": 3.5601, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.35035145637047e-05, + "loss": 3.5636, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349512861619418e-05, + "loss": 3.5629, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348674266868366e-05, + "loss": 3.5738, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347835672117314e-05, + "loss": 3.5773, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.346998715246635e-05, + "loss": 3.5603, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346160120495583e-05, + "loss": 3.5662, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345321525744531e-05, + "loss": 3.5749, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344482930993479e-05, + "loss": 3.5476, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343645974122801e-05, + "loss": 3.5687, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342807379371749e-05, + "loss": 3.5589, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341968784620697e-05, + "loss": 3.5525, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341130189869645e-05, + "loss": 3.5677, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.3402932329989656e-05, + "loss": 3.57, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.3394546382479136e-05, + "loss": 3.5677, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.3386160434968616e-05, + "loss": 3.5622, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.3377774487458096e-05, + "loss": 3.5648, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.3369404918751305e-05, + "loss": 3.5588, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.3361018971240785e-05, + "loss": 3.5665, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.3352633023730265e-05, + "loss": 3.5413, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.3344247076219745e-05, + "loss": 3.5642, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333587750751296e-05, + "loss": 3.5631, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332749156000244e-05, + "loss": 3.5706, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331910561249192e-05, + "loss": 3.5576, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.33107196649814e-05, + "loss": 3.5595, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330233371747088e-05, + "loss": 3.5519, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329396414876409e-05, + "loss": 3.5556, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328557820125357e-05, + "loss": 3.575, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327719225374305e-05, + "loss": 3.5434, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326880630623253e-05, + "loss": 3.5718, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.326043673752574e-05, + "loss": 3.5676, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325205079001522e-05, + "loss": 3.5471, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.32436648425047e-05, + "loss": 3.5703, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323527889499418e-05, + "loss": 3.5488, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3226909326287395e-05, + "loss": 3.5532, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.3218523378776874e-05, + "loss": 3.5629, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.3210137431266354e-05, + "loss": 3.5668, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.3201751483755834e-05, + "loss": 3.5479, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.3193365536245314e-05, + "loss": 3.569, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.3184995967538523e-05, + "loss": 3.5449, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.3176610020028e-05, + "loss": 3.5575, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316822407251748e-05, + "loss": 3.5698, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315983812500696e-05, + "loss": 3.5606, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315146855630017e-05, + "loss": 3.5646, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314308260878965e-05, + "loss": 3.5648, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313469666127913e-05, + "loss": 3.5771, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312631071376862e-05, + "loss": 3.5572, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311794114506183e-05, + "loss": 3.5702, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310955519755131e-05, + "loss": 3.5527, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310116925004079e-05, + "loss": 3.5484, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309278330253027e-05, + "loss": 3.562, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308441373382348e-05, + "loss": 3.5608, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307602778631296e-05, + "loss": 3.5644, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306764183880244e-05, + "loss": 3.5761, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305925589129192e-05, + "loss": 3.5573, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.305086994378139e-05, + "loss": 3.5502, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3042500375074606e-05, + "loss": 3.5545, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.3034114427564086e-05, + "loss": 3.5687, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302572848005357e-05, + "loss": 3.5563, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.3017342532543046e-05, + "loss": 3.5536, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300897296383626e-05, + "loss": 3.5566, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300058701632574e-05, + "loss": 3.555, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299220106881522e-05, + "loss": 3.5625, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.2983815121304695e-05, + "loss": 3.5558, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297544555259791e-05, + "loss": 3.5658, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296705960508739e-05, + "loss": 3.5693, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.2958673657576864e-05, + "loss": 3.5573, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.2950287710066344e-05, + "loss": 3.5523, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294191814135956e-05, + "loss": 3.5575, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293353219384904e-05, + "loss": 3.559, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292514624633852e-05, + "loss": 3.5676, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.2916760298828e-05, + "loss": 3.5557, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.2908390730121215e-05, + "loss": 3.5531, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.2900004782610695e-05, + "loss": 3.5593, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289161883510017e-05, + "loss": 3.5568, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288323288758965e-05, + "loss": 3.5557, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.2874863318882864e-05, + "loss": 3.5555, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286647737137234e-05, + "loss": 3.5463, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285809142386182e-05, + "loss": 3.5637, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.28497054763513e-05, + "loss": 3.5572, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284131952884078e-05, + "loss": 3.5469, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283294996013399e-05, + "loss": 3.5433, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282456401262347e-05, + "loss": 3.5557, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281617806511295e-05, + "loss": 3.566, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280779211760243e-05, + "loss": 3.5504, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279942254889564e-05, + "loss": 3.5588, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279103660138512e-05, + "loss": 3.5632, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.27826506538746e-05, + "loss": 3.5693, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277426470636408e-05, + "loss": 3.5581, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276589513765729e-05, + "loss": 3.5509, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275750919014677e-05, + "loss": 3.5546, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274912324263625e-05, + "loss": 3.5643, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.274073729512573e-05, + "loss": 3.5444, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273236772641895e-05, + "loss": 3.5505, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272398177890843e-05, + "loss": 3.5524, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271559583139791e-05, + "loss": 3.5578, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270720988388739e-05, + "loss": 3.5566, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.2698840315180596e-05, + "loss": 3.5643, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.2690454367670076e-05, + "loss": 3.5476, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.2682068420159556e-05, + "loss": 3.5535, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2673682472649036e-05, + "loss": 3.5684, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.2665296525138516e-05, + "loss": 3.5556, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.2656926956431725e-05, + "loss": 3.5657, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.2648541008921205e-05, + "loss": 3.5454, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.2640155061410685e-05, + "loss": 3.5619, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.2631769113900165e-05, + "loss": 3.5621, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262339954519338e-05, + "loss": 3.5598, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261501359768286e-05, + "loss": 3.5561, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260662765017234e-05, + "loss": 3.5546, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259824170266182e-05, + "loss": 3.5679, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.25898557551513e-05, + "loss": 3.5608, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258146980764078e-05, + "loss": 3.5634, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257310023893399e-05, + "loss": 3.5545, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256471429142347e-05, + "loss": 3.5655, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255632834391295e-05, + "loss": 3.5535, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254794239640243e-05, + "loss": 3.5495, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253957282769564e-05, + "loss": 3.5708, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253118688018512e-05, + "loss": 3.5521, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.2522800932674605e-05, + "loss": 3.5633, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.2514414985164085e-05, + "loss": 3.5523, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.8454413414001465, + "eval_runtime": 303.1393, + "eval_samples_per_second": 1258.798, + "eval_steps_per_second": 39.338, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.2506045416457294e-05, + "loss": 3.5526, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.2497659468946774e-05, + "loss": 3.5497, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2489273521436254e-05, + "loss": 3.5541, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2480887573925734e-05, + "loss": 3.5603, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.2472501626415214e-05, + "loss": 3.5587, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246413205770842e-05, + "loss": 3.5584, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.24557461101979e-05, + "loss": 3.5527, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244736016268738e-05, + "loss": 3.5529, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243897421517686e-05, + "loss": 3.5514, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243060464647007e-05, + "loss": 3.5632, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242221869895956e-05, + "loss": 3.5518, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241383275144904e-05, + "loss": 3.5517, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240546318274225e-05, + "loss": 3.5629, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239707723523173e-05, + "loss": 3.5425, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238869128772121e-05, + "loss": 3.5457, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238030534021069e-05, + "loss": 3.5425, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237191939270017e-05, + "loss": 3.5523, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236353344518965e-05, + "loss": 3.5401, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235514749767912e-05, + "loss": 3.5426, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.23467615501686e-05, + "loss": 3.5498, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233839198146182e-05, + "loss": 3.5584, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2330006033951297e-05, + "loss": 3.5537, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321620086440777e-05, + "loss": 3.5431, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2313234138930256e-05, + "loss": 3.5571, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230486457022347e-05, + "loss": 3.5627, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2296478622712946e-05, + "loss": 3.5449, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2288092675202425e-05, + "loss": 3.5393, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.2279706727691905e-05, + "loss": 3.5586, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2271320780181385e-05, + "loss": 3.5387, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.2262951211474595e-05, + "loss": 3.5462, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.2254565263964074e-05, + "loss": 3.5467, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.2246179316453554e-05, + "loss": 3.5491, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.2237793368943034e-05, + "loss": 3.5558, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222942380023625e-05, + "loss": 3.5617, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222103785272573e-05, + "loss": 3.549, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221265190521521e-05, + "loss": 3.5466, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220426595770469e-05, + "loss": 3.5593, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.21958963889979e-05, + "loss": 3.5334, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218751044148738e-05, + "loss": 3.5532, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217912449397686e-05, + "loss": 3.5404, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.217073854646634e-05, + "loss": 3.5407, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216235259895582e-05, + "loss": 3.5483, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215398303024903e-05, + "loss": 3.5565, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214559708273851e-05, + "loss": 3.5466, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213721113522799e-05, + "loss": 3.547, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212882518771747e-05, + "loss": 3.5507, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2120455619010684e-05, + "loss": 3.542, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2112069671500164e-05, + "loss": 3.5514, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2103683723989644e-05, + "loss": 3.5268, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2095297776479124e-05, + "loss": 3.5482, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208692820777233e-05, + "loss": 3.5463, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207854226026181e-05, + "loss": 3.5545, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207015631275129e-05, + "loss": 3.5406, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206177036524077e-05, + "loss": 3.5395, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205340079653398e-05, + "loss": 3.5378, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204501484902346e-05, + "loss": 3.5371, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203662890151294e-05, + "loss": 3.5617, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202824295400242e-05, + "loss": 3.5324, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201987338529564e-05, + "loss": 3.5533, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201148743778512e-05, + "loss": 3.5503, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.20031014902746e-05, + "loss": 3.5343, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199471554276408e-05, + "loss": 3.5528, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.1986345974057287e-05, + "loss": 3.535, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.1977960026546766e-05, + "loss": 3.5363, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.1969574079036246e-05, + "loss": 3.5466, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.1961188131525726e-05, + "loss": 3.5525, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.1952818562818935e-05, + "loss": 3.5328, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.1944432615308415e-05, + "loss": 3.5522, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.1936046667797895e-05, + "loss": 3.5273, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1927660720287375e-05, + "loss": 3.5427, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191929115158059e-05, + "loss": 3.5549, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191090520407007e-05, + "loss": 3.547, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190251925655955e-05, + "loss": 3.5464, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189413330904903e-05, + "loss": 3.5494, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188576374034224e-05, + "loss": 3.5591, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187737779283172e-05, + "loss": 3.5443, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.18689918453212e-05, + "loss": 3.5555, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186060589781068e-05, + "loss": 3.5377, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185223632910389e-05, + "loss": 3.5297, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184385038159337e-05, + "loss": 3.5456, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183546443408285e-05, + "loss": 3.5438, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182707848657233e-05, + "loss": 3.5446, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181869253906181e-05, + "loss": 3.5633, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.1810322970355025e-05, + "loss": 3.5437, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1801937022844505e-05, + "loss": 3.5297, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1793551075333985e-05, + "loss": 3.5421, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.1785165127823465e-05, + "loss": 3.5493, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1776795559116674e-05, + "loss": 3.5411, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1768409611606154e-05, + "loss": 3.5386, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1760023664095634e-05, + "loss": 3.5438, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.1751637716585114e-05, + "loss": 3.5386, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174326814787832e-05, + "loss": 3.5497, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.17348822003678e-05, + "loss": 3.5382, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172649625285728e-05, + "loss": 3.5513, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171811030534676e-05, + "loss": 3.5539, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170972435783624e-05, + "loss": 3.5418, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170135478912946e-05, + "loss": 3.5323, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169296884161894e-05, + "loss": 3.5428, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168458289410842e-05, + "loss": 3.5407, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.16761969465979e-05, + "loss": 3.5519, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166782737789111e-05, + "loss": 3.5414, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165944143038059e-05, + "loss": 3.538, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165105548287007e-05, + "loss": 3.541, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164266953535955e-05, + "loss": 3.5428, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1634299966652756e-05, + "loss": 3.5425, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1625914019142236e-05, + "loss": 3.5392, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.1617528071631716e-05, + "loss": 3.5307, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1609142124121196e-05, + "loss": 3.5446, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160077255541441e-05, + "loss": 3.5415, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159238660790389e-05, + "loss": 3.5322, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158400066039337e-05, + "loss": 3.5308, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157561471288285e-05, + "loss": 3.5355, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156724514417606e-05, + "loss": 3.5535, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155885919666554e-05, + "loss": 3.538, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155047324915502e-05, + "loss": 3.5417, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.1542087301644494e-05, + "loss": 3.5435, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153371773293771e-05, + "loss": 3.5609, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152533178542719e-05, + "loss": 3.5419, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151694583791667e-05, + "loss": 3.5339, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150855989040615e-05, + "loss": 3.5419, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150017394289563e-05, + "loss": 3.5416, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.1491804374188846e-05, + "loss": 3.5286, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1483418426678326e-05, + "loss": 3.5347, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.14750324791678e-05, + "loss": 3.5361, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1466662910461015e-05, + "loss": 3.543, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1458276962950495e-05, + "loss": 3.5365, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144989101543997e-05, + "loss": 3.5464, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144150506792945e-05, + "loss": 3.5357, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143311912041893e-05, + "loss": 3.5393, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.1424749551712144e-05, + "loss": 3.5516, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.1416363604201624e-05, + "loss": 3.5416, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.1407977656691104e-05, + "loss": 3.5472, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.1399591709180584e-05, + "loss": 3.5332, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.13912221404738e-05, + "loss": 3.5459, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138283619296327e-05, + "loss": 3.5485, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137445024545275e-05, + "loss": 3.5433, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136606429794223e-05, + "loss": 3.542, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135769472923544e-05, + "loss": 3.5353, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134930878172492e-05, + "loss": 3.5525, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.13409228342144e-05, + "loss": 3.5452, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133253688670388e-05, + "loss": 3.5459, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.13241673179971e-05, + "loss": 3.5414, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131578137048658e-05, + "loss": 3.5466, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130739542297606e-05, + "loss": 3.5365, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129900947546554e-05, + "loss": 3.5328, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290639906758746e-05, + "loss": 3.5564, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1282253959248226e-05, + "loss": 3.5392, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1273868011737706e-05, + "loss": 3.5462, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1265482064227186e-05, + "loss": 3.5404, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8462979793548584, + "eval_runtime": 307.7755, + "eval_samples_per_second": 1239.835, + "eval_steps_per_second": 38.746, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.1257112495520395e-05, + "loss": 3.5349, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1248726548009875e-05, + "loss": 3.5329, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.1240340600499355e-05, + "loss": 3.5344, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1231954652988835e-05, + "loss": 3.5463, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122358508428205e-05, + "loss": 3.5423, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121519913677153e-05, + "loss": 3.5461, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120681318926101e-05, + "loss": 3.5374, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119842724175049e-05, + "loss": 3.5354, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.11900576730437e-05, + "loss": 3.5385, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118167172553318e-05, + "loss": 3.5481, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117328577802266e-05, + "loss": 3.5293, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116489983051214e-05, + "loss": 3.5362, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.1156546640609085e-05, + "loss": 3.5434, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.1148160693098565e-05, + "loss": 3.5338, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113977474558804e-05, + "loss": 3.5308, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113138879807752e-05, + "loss": 3.531, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.1123002850567e-05, + "loss": 3.5282, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1114616903056485e-05, + "loss": 3.5285, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1106230955545965e-05, + "loss": 3.5289, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.1097845008035445e-05, + "loss": 3.5315, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.1089475439328654e-05, + "loss": 3.5443, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.1081089491818134e-05, + "loss": 3.5339, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.1072703544307614e-05, + "loss": 3.532, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.1064317596797093e-05, + "loss": 3.5411, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.10559480280903e-05, + "loss": 3.5502, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104756208057978e-05, + "loss": 3.5262, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103917613306926e-05, + "loss": 3.5292, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103079018555874e-05, + "loss": 3.5405, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102242061685195e-05, + "loss": 3.5268, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101403466934144e-05, + "loss": 3.5292, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100564872183092e-05, + "loss": 3.5304, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.09972627743204e-05, + "loss": 3.5355, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098889320561361e-05, + "loss": 3.5398, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.098050725810309e-05, + "loss": 3.5421, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097212131059257e-05, + "loss": 3.5353, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096373536308205e-05, + "loss": 3.532, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.0955365794375256e-05, + "loss": 3.5414, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0946979846864736e-05, + "loss": 3.521, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.0938593899354216e-05, + "loss": 3.5408, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0930207951843696e-05, + "loss": 3.5245, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0921838383136905e-05, + "loss": 3.5268, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091345243562639e-05, + "loss": 3.5312, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090506648811587e-05, + "loss": 3.5408, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089668054060535e-05, + "loss": 3.5338, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088831097189856e-05, + "loss": 3.5329, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087992502438804e-05, + "loss": 3.5321, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087153907687752e-05, + "loss": 3.529, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.0863153129367e-05, + "loss": 3.5395, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085478356066021e-05, + "loss": 3.508, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084639761314969e-05, + "loss": 3.5268, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083801166563917e-05, + "loss": 3.5372, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082962571812865e-05, + "loss": 3.5363, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082125614942186e-05, + "loss": 3.5227, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.0812870201911346e-05, + "loss": 3.5267, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0804484254400826e-05, + "loss": 3.5226, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0796098306890306e-05, + "loss": 3.5224, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0787728738183515e-05, + "loss": 3.5494, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.0779342790672995e-05, + "loss": 3.5166, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.0770956843162475e-05, + "loss": 3.5384, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.0762570895651954e-05, + "loss": 3.5313, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.0754201326945164e-05, + "loss": 3.5225, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.0745815379434644e-05, + "loss": 3.5348, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.0737429431924124e-05, + "loss": 3.5197, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.0729043484413603e-05, + "loss": 3.5252, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072067391570681e-05, + "loss": 3.5262, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.07122879681963e-05, + "loss": 3.5433, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070390202068578e-05, + "loss": 3.5157, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069551607317526e-05, + "loss": 3.5347, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068714650446847e-05, + "loss": 3.5149, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067876055695795e-05, + "loss": 3.5258, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067037460944743e-05, + "loss": 3.5395, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066198866193691e-05, + "loss": 3.5372, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065361909323012e-05, + "loss": 3.5309, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.06452331457196e-05, + "loss": 3.5337, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063684719820908e-05, + "loss": 3.5445, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062846125069856e-05, + "loss": 3.5252, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0620091681991766e-05, + "loss": 3.5396, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061170573448125e-05, + "loss": 3.5258, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060331978697073e-05, + "loss": 3.5203, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059493383946021e-05, + "loss": 3.5266, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058656427075342e-05, + "loss": 3.529, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.05781783232429e-05, + "loss": 3.5331, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056979237573238e-05, + "loss": 3.5425, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056140642822186e-05, + "loss": 3.5345, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055303685951507e-05, + "loss": 3.5155, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054465091200455e-05, + "loss": 3.5228, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053626496449403e-05, + "loss": 3.5353, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052787901698351e-05, + "loss": 3.5276, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051950944827672e-05, + "loss": 3.523, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0511123500766203e-05, + "loss": 3.5297, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502737553255683e-05, + "loss": 3.522, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494351605745163e-05, + "loss": 3.5324, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0485982037038376e-05, + "loss": 3.5255, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477596089527856e-05, + "loss": 3.5334, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469210142017336e-05, + "loss": 3.5348, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460824194506815e-05, + "loss": 3.5311, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452454625800025e-05, + "loss": 3.5187, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0444068678289505e-05, + "loss": 3.5297, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435682730778985e-05, + "loss": 3.5283, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427296783268468e-05, + "loss": 3.5347, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0418927214561677e-05, + "loss": 3.5252, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410541267051157e-05, + "loss": 3.5211, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0402155319540637e-05, + "loss": 3.5261, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393769372030117e-05, + "loss": 3.5295, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038539980332333e-05, + "loss": 3.5304, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037701385581281e-05, + "loss": 3.524, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036862790830229e-05, + "loss": 3.5159, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360241960791762e-05, + "loss": 3.5334, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0351872392084978e-05, + "loss": 3.5273, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0343486444574458e-05, + "loss": 3.5134, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0335100497063938e-05, + "loss": 3.5175, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326714549553415e-05, + "loss": 3.5176, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.031834498084663e-05, + "loss": 3.5364, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.030995903333611e-05, + "loss": 3.524, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.030157308582559e-05, + "loss": 3.5268, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293187138315067e-05, + "loss": 3.5308, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284817569608283e-05, + "loss": 3.5448, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276431622097763e-05, + "loss": 3.5262, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0268045674587236e-05, + "loss": 3.5165, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259659727076716e-05, + "loss": 3.531, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251290158369932e-05, + "loss": 3.5243, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0242904210859412e-05, + "loss": 3.5187, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.023451826334889e-05, + "loss": 3.5187, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.022613231583837e-05, + "loss": 3.5235, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.021774636832785e-05, + "loss": 3.5276, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0209376799621064e-05, + "loss": 3.5226, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0200990852110537e-05, + "loss": 3.5333, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.019260490460002e-05, + "loss": 3.5214, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.01842189570895e-05, + "loss": 3.5262, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017584938838271e-05, + "loss": 3.5286, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016746344087219e-05, + "loss": 3.5346, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015907749336167e-05, + "loss": 3.5328, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.015069154585115e-05, + "loss": 3.5173, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142321977144362e-05, + "loss": 3.5269, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0133936029633842e-05, + "loss": 3.5344, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125550082123322e-05, + "loss": 3.5263, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117164134612802e-05, + "loss": 3.5303, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.010879456590601e-05, + "loss": 3.5213, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.010040861839549e-05, + "loss": 3.5389, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0092022670884974e-05, + "loss": 3.5293, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083636723374454e-05, + "loss": 3.5316, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075267154667663e-05, + "loss": 3.5257, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066881207157143e-05, + "loss": 3.5355, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058495259646623e-05, + "loss": 3.5211, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0050109312136103e-05, + "loss": 3.5161, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041739743429316e-05, + "loss": 3.5407, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033353795918796e-05, + "loss": 3.5245, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0024967848408276e-05, + "loss": 3.5294, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016581900897756e-05, + "loss": 3.5268, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0008212332190965e-05, + "loss": 3.5187, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.8466694355010986, + "eval_runtime": 312.6169, + "eval_samples_per_second": 1220.635, + "eval_steps_per_second": 38.146, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999826384680445e-05, + "loss": 3.5188, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991440437169928e-05, + "loss": 3.5215, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9983054489659408e-05, + "loss": 3.5311, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974684920952617e-05, + "loss": 3.5271, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966298973442097e-05, + "loss": 3.5323, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9957913025931577e-05, + "loss": 3.5221, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949527078421057e-05, + "loss": 3.5226, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.994115750971427e-05, + "loss": 3.52, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.993277156220375e-05, + "loss": 3.538, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992438561469323e-05, + "loss": 3.5176, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991599966718271e-05, + "loss": 3.5218, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9907646477279654e-05, + "loss": 3.5291, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.989926052976913e-05, + "loss": 3.5221, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.989087458225861e-05, + "loss": 3.5125, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.988248863474809e-05, + "loss": 3.5143, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987410268723757e-05, + "loss": 3.5128, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.986571673972705e-05, + "loss": 3.5159, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.985733079221653e-05, + "loss": 3.5157, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.984894484470601e-05, + "loss": 3.5138, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840575275999223e-05, + "loss": 3.5349, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832189328488703e-05, + "loss": 3.5205, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823803380978183e-05, + "loss": 3.5163, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815417433467663e-05, + "loss": 3.5269, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9807047864760872e-05, + "loss": 3.5368, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798661917250352e-05, + "loss": 3.5119, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790275969739832e-05, + "loss": 3.518, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9781890022229315e-05, + "loss": 3.5206, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773520453522524e-05, + "loss": 3.5206, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9765134506012004e-05, + "loss": 3.5129, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756748558501484e-05, + "loss": 3.5131, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748362610990964e-05, + "loss": 3.5238, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9739993042284177e-05, + "loss": 3.5266, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731607094773657e-05, + "loss": 3.527, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723221147263137e-05, + "loss": 3.5222, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714835199752617e-05, + "loss": 3.5187, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706465631045826e-05, + "loss": 3.5237, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9698079683535306e-05, + "loss": 3.5052, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689693736024786e-05, + "loss": 3.5255, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.968130778851427e-05, + "loss": 3.512, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9672938219807478e-05, + "loss": 3.5149, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664552272296958e-05, + "loss": 3.5149, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9656166324786438e-05, + "loss": 3.5291, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647780377275918e-05, + "loss": 3.5178, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963941080856913e-05, + "loss": 3.5164, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.963102486105861e-05, + "loss": 3.5218, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.962263891354809e-05, + "loss": 3.5108, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961425296603757e-05, + "loss": 3.525, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.960588339733078e-05, + "loss": 3.4949, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.959749744982026e-05, + "loss": 3.5111, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.958911150230974e-05, + "loss": 3.5215, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580725554799223e-05, + "loss": 3.5232, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572355986092432e-05, + "loss": 3.5131, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9563970038581912e-05, + "loss": 3.5111, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555584091071392e-05, + "loss": 3.514, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.954719814356087e-05, + "loss": 3.5016, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538828574854084e-05, + "loss": 3.5311, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530442627343564e-05, + "loss": 3.5081, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9522056679833044e-05, + "loss": 3.5216, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513670732322524e-05, + "loss": 3.5173, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505301163615733e-05, + "loss": 3.5045, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9496915216105213e-05, + "loss": 3.5191, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488529268594693e-05, + "loss": 3.5104, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9480143321084176e-05, + "loss": 3.5115, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471773752377385e-05, + "loss": 3.5068, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463387804866865e-05, + "loss": 3.5286, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9455001857356345e-05, + "loss": 3.5058, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446615909845825e-05, + "loss": 3.5156, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9438246341139038e-05, + "loss": 3.5004, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9429860393628518e-05, + "loss": 3.513, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421474446117998e-05, + "loss": 3.5226, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9413088498607478e-05, + "loss": 3.5219, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404718929900687e-05, + "loss": 3.5158, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396332982390167e-05, + "loss": 3.5231, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9387947034879647e-05, + "loss": 3.5291, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937956108736913e-05, + "loss": 3.5128, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.937119151866234e-05, + "loss": 3.5227, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936280557115182e-05, + "loss": 3.513, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.93544196236413e-05, + "loss": 3.5047, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934603367613078e-05, + "loss": 3.5132, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.933766410742399e-05, + "loss": 3.5123, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.932927815991347e-05, + "loss": 3.5216, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.932089221240295e-05, + "loss": 3.5315, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.931250626489243e-05, + "loss": 3.5211, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930413669618564e-05, + "loss": 3.4991, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.929575074867512e-05, + "loss": 3.5122, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.92873648011646e-05, + "loss": 3.5176, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9278978853654084e-05, + "loss": 3.5153, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270609284947293e-05, + "loss": 3.5106, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262223337436773e-05, + "loss": 3.5138, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253837389926253e-05, + "loss": 3.5083, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245451442415733e-05, + "loss": 3.5171, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9237081873708945e-05, + "loss": 3.5135, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228695926198425e-05, + "loss": 3.5228, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220309978687905e-05, + "loss": 3.518, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9211924031177385e-05, + "loss": 3.5212, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203554462470594e-05, + "loss": 3.4998, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9195168514960074e-05, + "loss": 3.5136, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186782567449554e-05, + "loss": 3.5165, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.917839661993903e-05, + "loss": 3.5194, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9170027051232246e-05, + "loss": 3.5166, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161641103721726e-05, + "loss": 3.5071, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9153255156211206e-05, + "loss": 3.5112, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9144869208700683e-05, + "loss": 3.513, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.91364996399939e-05, + "loss": 3.5178, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.912811369248338e-05, + "loss": 3.5074, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.911972774497286e-05, + "loss": 3.5044, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111341797462332e-05, + "loss": 3.5208, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102972228755548e-05, + "loss": 3.5118, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094586281245028e-05, + "loss": 3.502, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086200333734504e-05, + "loss": 3.503, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9077814386223984e-05, + "loss": 3.5022, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.90694448175172e-05, + "loss": 3.5217, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.906105887000668e-05, + "loss": 3.5105, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052672922496153e-05, + "loss": 3.5134, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044286974985637e-05, + "loss": 3.5189, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035917406278853e-05, + "loss": 3.5311, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027531458768332e-05, + "loss": 3.5073, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9019145511257806e-05, + "loss": 3.5066, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010759563747286e-05, + "loss": 3.5133, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.90023899950405e-05, + "loss": 3.5144, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8994004047529978e-05, + "loss": 3.5033, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985618100019458e-05, + "loss": 3.5059, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977232152508938e-05, + "loss": 3.5066, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968846204998418e-05, + "loss": 3.5134, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960476636291627e-05, + "loss": 3.5094, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8952090688781107e-05, + "loss": 3.5169, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.894370474127059e-05, + "loss": 3.5084, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.893531879376007e-05, + "loss": 3.5115, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892694922505328e-05, + "loss": 3.51, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.891856327754276e-05, + "loss": 3.5237, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.891017733003224e-05, + "loss": 3.5178, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.890179138252172e-05, + "loss": 3.5078, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893421813814932e-05, + "loss": 3.5059, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.888503586630441e-05, + "loss": 3.5211, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887664991879389e-05, + "loss": 3.5142, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.886826397128337e-05, + "loss": 3.5169, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.885989440257658e-05, + "loss": 3.5077, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.885150845506606e-05, + "loss": 3.5238, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884312250755554e-05, + "loss": 3.5136, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834736560045024e-05, + "loss": 3.5172, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826366991338233e-05, + "loss": 3.514, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8817981043827713e-05, + "loss": 3.5213, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809595096317193e-05, + "loss": 3.5128, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801209148806673e-05, + "loss": 3.4996, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792839580099885e-05, + "loss": 3.5269, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784453632589365e-05, + "loss": 3.5165, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8776067685078845e-05, + "loss": 3.5145, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767681737568325e-05, + "loss": 3.5126, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759312168861534e-05, + "loss": 3.5027, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.8479747772216797, + "eval_runtime": 304.9332, + "eval_samples_per_second": 1251.392, + "eval_steps_per_second": 39.107, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8750926221351014e-05, + "loss": 3.5056, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742540273840494e-05, + "loss": 3.5086, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8734154326329978e-05, + "loss": 3.5197, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725784757623187e-05, + "loss": 3.5083, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8717398810112667e-05, + "loss": 3.5204, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8709012862602147e-05, + "loss": 3.5078, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700626915091627e-05, + "loss": 3.5093, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.869225734638484e-05, + "loss": 3.5068, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.868387139887432e-05, + "loss": 3.5219, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.86754854513638e-05, + "loss": 3.508, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866709950385328e-05, + "loss": 3.5049, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8658729935146488e-05, + "loss": 3.5095, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.86503603664397e-05, + "loss": 3.5115, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.864197441892918e-05, + "loss": 3.5001, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.863358847141866e-05, + "loss": 3.5077, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.862520252390814e-05, + "loss": 3.4923, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.861681657639762e-05, + "loss": 3.504, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.86084306288871e-05, + "loss": 3.502, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.860004468137658e-05, + "loss": 3.4963, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591675112669793e-05, + "loss": 3.5252, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8583289165159273e-05, + "loss": 3.5001, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8574903217648753e-05, + "loss": 3.5093, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566517270138233e-05, + "loss": 3.5072, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8558131322627713e-05, + "loss": 3.5223, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.854976175392092e-05, + "loss": 3.4974, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.85413758064104e-05, + "loss": 3.5048, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8532989858899885e-05, + "loss": 3.5063, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524603911389365e-05, + "loss": 3.5074, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8516234342682574e-05, + "loss": 3.5003, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8507848395172054e-05, + "loss": 3.5015, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8499462447661534e-05, + "loss": 3.5107, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8491076500151014e-05, + "loss": 3.5108, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482706931444226e-05, + "loss": 3.5128, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8474320983933706e-05, + "loss": 3.5087, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8465935036423186e-05, + "loss": 3.5003, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457549088912666e-05, + "loss": 3.5142, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8449179520205875e-05, + "loss": 3.4912, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8440793572695355e-05, + "loss": 3.513, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843240762518484e-05, + "loss": 3.4983, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.842402167767432e-05, + "loss": 3.5021, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8415652108967528e-05, + "loss": 3.4993, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8407266161457008e-05, + "loss": 3.5146, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398880213946488e-05, + "loss": 3.5071, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390494266435968e-05, + "loss": 3.5004, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.838212469772918e-05, + "loss": 3.5101, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.837373875021866e-05, + "loss": 3.5017, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.836535280270814e-05, + "loss": 3.5095, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835696685519762e-05, + "loss": 3.4861, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.834859728649083e-05, + "loss": 3.4931, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.834021133898031e-05, + "loss": 3.5067, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331825391469792e-05, + "loss": 3.5099, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323439443959272e-05, + "loss": 3.4979, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.831506987525248e-05, + "loss": 3.4919, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.830668392774196e-05, + "loss": 3.5033, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.829829798023144e-05, + "loss": 3.4857, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8289928411524654e-05, + "loss": 3.5149, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281542464014134e-05, + "loss": 3.501, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8273156516503614e-05, + "loss": 3.5064, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264770568993094e-05, + "loss": 3.5049, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8256401000286303e-05, + "loss": 3.4925, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8248015052775783e-05, + "loss": 3.5075, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239629105265263e-05, + "loss": 3.4962, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8231243157754746e-05, + "loss": 3.497, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8222873589047955e-05, + "loss": 3.4932, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214487641537435e-05, + "loss": 3.5135, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8206101694026915e-05, + "loss": 3.4962, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197715746516395e-05, + "loss": 3.4991, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8189346177809607e-05, + "loss": 3.49, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8180960230299087e-05, + "loss": 3.4993, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172574282788567e-05, + "loss": 3.5078, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8164188335278047e-05, + "loss": 3.5075, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155818766571256e-05, + "loss": 3.5023, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147432819060736e-05, + "loss": 3.5085, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8139046871550216e-05, + "loss": 3.5132, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130660924039696e-05, + "loss": 3.5013, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.812229135533291e-05, + "loss": 3.5079, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.811390540782239e-05, + "loss": 3.5027, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.810551946031187e-05, + "loss": 3.4917, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.809713351280135e-05, + "loss": 3.4988, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.808876394409456e-05, + "loss": 3.5018, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.808037799658404e-05, + "loss": 3.504, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.807199204907352e-05, + "loss": 3.5192, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063606101563e-05, + "loss": 3.5072, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.805523653285621e-05, + "loss": 3.4871, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.804685058534569e-05, + "loss": 3.4967, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803846463783517e-05, + "loss": 3.504, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.803007869032465e-05, + "loss": 3.5034, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8021709121617862e-05, + "loss": 3.496, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8013323174107342e-05, + "loss": 3.4991, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8004937226596822e-05, + "loss": 3.4984, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996551279086302e-05, + "loss": 3.5023, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.798818171037951e-05, + "loss": 3.4982, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979795762868995e-05, + "loss": 3.5101, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7971409815358475e-05, + "loss": 3.5052, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7963023867847948e-05, + "loss": 3.5066, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954637920337428e-05, + "loss": 3.4892, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7946268351630644e-05, + "loss": 3.5036, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7937882404120124e-05, + "loss": 3.5019, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.79294964566096e-05, + "loss": 3.5047, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7921126887902816e-05, + "loss": 3.5003, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912740940392296e-05, + "loss": 3.4985, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.790435499288177e-05, + "loss": 3.4964, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.789596904537125e-05, + "loss": 3.5017, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887599476664465e-05, + "loss": 3.5016, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.787921352915395e-05, + "loss": 3.4922, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.787082758164342e-05, + "loss": 3.4925, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.78624416341329e-05, + "loss": 3.5067, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7854072065426117e-05, + "loss": 3.4959, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7845686117915597e-05, + "loss": 3.4901, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7837300170405074e-05, + "loss": 3.4911, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7828914222894554e-05, + "loss": 3.4896, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.782054465418777e-05, + "loss": 3.511, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7812158706677243e-05, + "loss": 3.4954, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7803772759166723e-05, + "loss": 3.504, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795386811656203e-05, + "loss": 3.5012, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.778701724294942e-05, + "loss": 3.5181, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778631295438895e-05, + "loss": 3.498, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7770245347928375e-05, + "loss": 3.4921, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761859400417855e-05, + "loss": 3.5001, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.775348983171107e-05, + "loss": 3.4987, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7745103884200548e-05, + "loss": 3.4881, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736717936690028e-05, + "loss": 3.4951, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728331989179507e-05, + "loss": 3.4902, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7719962420472717e-05, + "loss": 3.5044, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7711576472962197e-05, + "loss": 3.4916, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7703190525451676e-05, + "loss": 3.5066, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694804577941156e-05, + "loss": 3.4973, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.768643500923437e-05, + "loss": 3.4987, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.767804906172385e-05, + "loss": 3.495, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.766966311421333e-05, + "loss": 3.513, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.766127716670281e-05, + "loss": 3.5073, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7652907597996018e-05, + "loss": 3.4934, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.76445216504855e-05, + "loss": 3.4962, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.763613570297498e-05, + "loss": 3.5061, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.762774975546446e-05, + "loss": 3.5048, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.761938018675767e-05, + "loss": 3.5052, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.761099423924715e-05, + "loss": 3.4957, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.760260829173663e-05, + "loss": 3.5115, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.759422234422611e-05, + "loss": 3.4968, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7585852775519323e-05, + "loss": 3.5057, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577466828008803e-05, + "loss": 3.5009, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7569080880498283e-05, + "loss": 3.5057, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560694932987762e-05, + "loss": 3.4994, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.755232536428097e-05, + "loss": 3.4877, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7543939416770455e-05, + "loss": 3.5113, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535553469259935e-05, + "loss": 3.5041, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7527167521749415e-05, + "loss": 3.5009, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518797953042624e-05, + "loss": 3.4976, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510412005532104e-05, + "loss": 3.4924, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.849392890930176, + "eval_runtime": 305.1152, + "eval_samples_per_second": 1250.646, + "eval_steps_per_second": 39.084, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7502026058021584e-05, + "loss": 3.4924, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493640110511064e-05, + "loss": 3.494, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485254163000547e-05, + "loss": 3.5073, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476868215490027e-05, + "loss": 3.4948, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468498646783236e-05, + "loss": 3.5113, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7460112699272716e-05, + "loss": 3.4946, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451726751762196e-05, + "loss": 3.4964, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443340804251676e-05, + "loss": 3.4951, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.743497123554489e-05, + "loss": 3.5107, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.742658528803437e-05, + "loss": 3.496, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.741819934052385e-05, + "loss": 3.4912, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.740981339301333e-05, + "loss": 3.4934, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.740146020311027e-05, + "loss": 3.4994, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.739307425559975e-05, + "loss": 3.4865, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.738468830808923e-05, + "loss": 3.4936, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.737630236057871e-05, + "loss": 3.4847, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.736791641306819e-05, + "loss": 3.4872, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.735953046555767e-05, + "loss": 3.4887, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.735114451804715e-05, + "loss": 3.4821, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.734275857053663e-05, + "loss": 3.5182, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7334389001829842e-05, + "loss": 3.4913, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7326003054319322e-05, + "loss": 3.4916, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317617106808802e-05, + "loss": 3.4982, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7309231159298282e-05, + "loss": 3.5054, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.730086159059149e-05, + "loss": 3.4855, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.729247564308097e-05, + "loss": 3.4929, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7284089695570454e-05, + "loss": 3.4922, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275703748059934e-05, + "loss": 3.4964, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7267334179353144e-05, + "loss": 3.4831, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7258948231842623e-05, + "loss": 3.4895, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250562284332103e-05, + "loss": 3.4939, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7242176336821583e-05, + "loss": 3.4977, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233806768114796e-05, + "loss": 3.5037, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225420820604276e-05, + "loss": 3.4986, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7217034873093756e-05, + "loss": 3.4855, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208648925583236e-05, + "loss": 3.5003, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7200279356876445e-05, + "loss": 3.4835, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191893409365925e-05, + "loss": 3.4988, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183507461855405e-05, + "loss": 3.484, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7175121514344888e-05, + "loss": 3.4864, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166751945638097e-05, + "loss": 3.4899, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158365998127577e-05, + "loss": 3.5001, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7149980050617057e-05, + "loss": 3.4948, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141594103106537e-05, + "loss": 3.4867, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.713322453439975e-05, + "loss": 3.4946, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.712483858688923e-05, + "loss": 3.49, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.711645263937871e-05, + "loss": 3.4957, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.710808307067192e-05, + "loss": 3.4759, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.70996971231614e-05, + "loss": 3.4784, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.709131117565088e-05, + "loss": 3.4948, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.708292522814036e-05, + "loss": 3.4937, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.707455565943357e-05, + "loss": 3.4858, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.706616971192305e-05, + "loss": 3.4842, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.705778376441253e-05, + "loss": 3.489, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.704939781690201e-05, + "loss": 3.475, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.704102824819522e-05, + "loss": 3.4991, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032642300684703e-05, + "loss": 3.4878, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024256353174183e-05, + "loss": 3.4947, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015870405663663e-05, + "loss": 3.4892, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007500836956872e-05, + "loss": 3.4861, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6999114889446352e-05, + "loss": 3.4872, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990728941935832e-05, + "loss": 3.4855, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982342994425312e-05, + "loss": 3.4828, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973973425718525e-05, + "loss": 3.4787, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6965587478208005e-05, + "loss": 3.4986, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6957201530697484e-05, + "loss": 3.4852, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6948815583186964e-05, + "loss": 3.4851, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940446014480174e-05, + "loss": 3.479, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6932060066969657e-05, + "loss": 3.4855, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923674119459137e-05, + "loss": 3.4968, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6915288171948617e-05, + "loss": 3.4936, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6906918603241826e-05, + "loss": 3.4899, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898532655731306e-05, + "loss": 3.4957, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6890146708220786e-05, + "loss": 3.4977, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881760760710266e-05, + "loss": 3.4845, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873391192003478e-05, + "loss": 3.4952, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6865005244492958e-05, + "loss": 3.4901, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856619296982438e-05, + "loss": 3.4813, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6848233349471918e-05, + "loss": 3.4916, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6839863780765127e-05, + "loss": 3.4849, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.683147783325461e-05, + "loss": 3.4902, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.682309188574409e-05, + "loss": 3.5017, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.681470593823357e-05, + "loss": 3.4976, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6806319990723044e-05, + "loss": 3.4728, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.679795042201626e-05, + "loss": 3.4908, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.678956447450574e-05, + "loss": 3.4889, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6781178526995216e-05, + "loss": 3.4899, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772792579484696e-05, + "loss": 3.4852, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764423010777912e-05, + "loss": 3.4816, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6756037063267392e-05, + "loss": 3.4908, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747651115756865e-05, + "loss": 3.4854, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.673926516824635e-05, + "loss": 3.4851, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730895599539564e-05, + "loss": 3.4959, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722509652029044e-05, + "loss": 3.4913, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6714123704518517e-05, + "loss": 3.4955, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705737757007997e-05, + "loss": 3.4791, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697368188301213e-05, + "loss": 3.4884, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.668898224079069e-05, + "loss": 3.4881, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.668059629328017e-05, + "loss": 3.4929, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6672226724573386e-05, + "loss": 3.4881, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6663840777062866e-05, + "loss": 3.4842, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.665545482955234e-05, + "loss": 3.484, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664706888204182e-05, + "loss": 3.4873, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638699313335035e-05, + "loss": 3.4922, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6630313365824518e-05, + "loss": 3.4767, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.662192741831399e-05, + "loss": 3.4764, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.661354147080347e-05, + "loss": 3.4961, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6605171902096687e-05, + "loss": 3.4867, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596785954586163e-05, + "loss": 3.4764, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6588400007075643e-05, + "loss": 3.48, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6580014059565123e-05, + "loss": 3.4772, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.657164449085834e-05, + "loss": 3.4947, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6563258543347812e-05, + "loss": 3.4853, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554872595837292e-05, + "loss": 3.4858, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546486648326772e-05, + "loss": 3.4876, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6538117079619985e-05, + "loss": 3.505, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529731132109465e-05, + "loss": 3.4888, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521345184598945e-05, + "loss": 3.4792, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512959237088425e-05, + "loss": 3.4901, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504589668381634e-05, + "loss": 3.4839, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6496203720871117e-05, + "loss": 3.4819, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487817773360597e-05, + "loss": 3.481, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479431825850077e-05, + "loss": 3.4795, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6471062257143286e-05, + "loss": 3.4925, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462676309632766e-05, + "loss": 3.4781, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454290362122246e-05, + "loss": 3.4952, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445904414611726e-05, + "loss": 3.479, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.643753484590494e-05, + "loss": 3.4888, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.642914889839442e-05, + "loss": 3.4812, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.64207629508839e-05, + "loss": 3.5003, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.641237700337338e-05, + "loss": 3.4947, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6404007434666587e-05, + "loss": 3.4852, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.639562148715607e-05, + "loss": 3.4779, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.638723553964555e-05, + "loss": 3.4936, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.637884959213503e-05, + "loss": 3.4869, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.637048002342824e-05, + "loss": 3.4932, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.636209407591772e-05, + "loss": 3.4803, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.63537081284072e-05, + "loss": 3.4985, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.634532218089668e-05, + "loss": 3.4854, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6336952612189892e-05, + "loss": 3.4978, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328566664679372e-05, + "loss": 3.4849, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320180717168852e-05, + "loss": 3.4932, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311794769658332e-05, + "loss": 3.4871, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.630342520095154e-05, + "loss": 3.4781, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6295039253441024e-05, + "loss": 3.497, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286653305930504e-05, + "loss": 3.4947, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6278267358419984e-05, + "loss": 3.4829, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6269897789713193e-05, + "loss": 3.4879, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6261511842202673e-05, + "loss": 3.477, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.8511803150177, + "eval_runtime": 314.4733, + "eval_samples_per_second": 1213.429, + "eval_steps_per_second": 37.921, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6253125894692153e-05, + "loss": 3.4818, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244739947181633e-05, + "loss": 3.4809, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6236370378474846e-05, + "loss": 3.4906, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6227984430964326e-05, + "loss": 3.488, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6219598483453806e-05, + "loss": 3.5009, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.6211212535943286e-05, + "loss": 3.4797, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6202842967236495e-05, + "loss": 3.4854, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6194457019725978e-05, + "loss": 3.4814, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6186071072215458e-05, + "loss": 3.4987, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6177685124704938e-05, + "loss": 3.4809, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6169315555998147e-05, + "loss": 3.4757, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160929608487627e-05, + "loss": 3.4867, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.615256003978084e-05, + "loss": 3.4831, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.614417409227032e-05, + "loss": 3.4776, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.61357881447598e-05, + "loss": 3.4797, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.612740219724928e-05, + "loss": 3.4743, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.611901624973876e-05, + "loss": 3.4729, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.611063030222824e-05, + "loss": 3.4749, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.610224435471772e-05, + "loss": 3.4734, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.60938584072072e-05, + "loss": 3.5012, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085488838500412e-05, + "loss": 3.4764, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.607710289098989e-05, + "loss": 3.4776, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.606871694347937e-05, + "loss": 3.4865, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.606034737477258e-05, + "loss": 3.491, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.605196142726206e-05, + "loss": 3.4759, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.604357547975154e-05, + "loss": 3.4848, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.603518953224102e-05, + "loss": 3.4789, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026819963534233e-05, + "loss": 3.482, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018434016023713e-05, + "loss": 3.4722, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6010048068513193e-05, + "loss": 3.4766, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.6001662121002673e-05, + "loss": 3.4827, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5993292552295882e-05, + "loss": 3.4843, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5984906604785365e-05, + "loss": 3.4901, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976520657274845e-05, + "loss": 3.4863, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5968134709764325e-05, + "loss": 3.4752, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5959765141057534e-05, + "loss": 3.4868, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5951379193547014e-05, + "loss": 3.4717, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5942993246036494e-05, + "loss": 3.4814, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5934607298525974e-05, + "loss": 3.4699, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5926237729819187e-05, + "loss": 3.4733, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5917851782308667e-05, + "loss": 3.4751, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5909465834798147e-05, + "loss": 3.4911, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5901079887287627e-05, + "loss": 3.4836, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5892710318580836e-05, + "loss": 3.4746, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.588432437107032e-05, + "loss": 3.4804, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.58759384235598e-05, + "loss": 3.4766, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.586755247604928e-05, + "loss": 3.4837, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5859182907342488e-05, + "loss": 3.4668, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5850796959831968e-05, + "loss": 3.4627, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842411012321448e-05, + "loss": 3.4848, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5834025064810928e-05, + "loss": 3.4848, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.582565549610414e-05, + "loss": 3.4706, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.581726954859362e-05, + "loss": 3.4739, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.58088836010831e-05, + "loss": 3.4786, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.580049765357258e-05, + "loss": 3.4649, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.579212808486579e-05, + "loss": 3.4823, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783742137355273e-05, + "loss": 3.4733, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5775356189844753e-05, + "loss": 3.4842, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5766970242334233e-05, + "loss": 3.473, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5758600673627442e-05, + "loss": 3.4795, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.575021472611692e-05, + "loss": 3.47, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.57418287786064e-05, + "loss": 3.4737, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.573344283109588e-05, + "loss": 3.4667, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5725073262389094e-05, + "loss": 3.4718, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716687314878574e-05, + "loss": 3.4891, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5708301367368054e-05, + "loss": 3.4699, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5699915419857534e-05, + "loss": 3.4752, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5691545851150743e-05, + "loss": 3.4634, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5683159903640226e-05, + "loss": 3.4758, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5674773956129706e-05, + "loss": 3.4847, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666388008619186e-05, + "loss": 3.4806, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5658018439912395e-05, + "loss": 3.4789, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5649632492401875e-05, + "loss": 3.4849, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5641246544891355e-05, + "loss": 3.4833, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5632860597380835e-05, + "loss": 3.4773, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624491028674048e-05, + "loss": 3.4805, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5616105081163528e-05, + "loss": 3.478, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5607719133653008e-05, + "loss": 3.4705, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.559933318614248e-05, + "loss": 3.4743, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5590963617435697e-05, + "loss": 3.474, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.558257766992518e-05, + "loss": 3.4774, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.557419172241466e-05, + "loss": 3.487, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5565805774904133e-05, + "loss": 3.4836, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.555743620619735e-05, + "loss": 3.4584, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.554905025868683e-05, + "loss": 3.4794, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.554066431117631e-05, + "loss": 3.4769, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5532278363665786e-05, + "loss": 3.4784, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5523908794959e-05, + "loss": 3.475, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.551552284744848e-05, + "loss": 3.4709, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5507136899937955e-05, + "loss": 3.478, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5498750952427435e-05, + "loss": 3.4725, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.549038138372065e-05, + "loss": 3.4735, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5481995436210134e-05, + "loss": 3.4818, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473609488699607e-05, + "loss": 3.4768, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5465223541189087e-05, + "loss": 3.4856, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5456853972482303e-05, + "loss": 3.4697, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5448468024971783e-05, + "loss": 3.4717, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.544008207746126e-05, + "loss": 3.4749, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.543169612995074e-05, + "loss": 3.4837, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5423326561243955e-05, + "loss": 3.4725, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5414940613733428e-05, + "loss": 3.4718, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406554666222908e-05, + "loss": 3.4711, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5398168718712388e-05, + "loss": 3.4742, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5389799150005604e-05, + "loss": 3.4849, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.538141320249508e-05, + "loss": 3.4674, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.537302725498456e-05, + "loss": 3.4631, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.536464130747404e-05, + "loss": 3.4835, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5356271738767256e-05, + "loss": 3.4709, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5347885791256733e-05, + "loss": 3.4639, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5339499843746213e-05, + "loss": 3.4678, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5331113896235693e-05, + "loss": 3.4687, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5322744327528902e-05, + "loss": 3.4816, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5314358380018382e-05, + "loss": 3.4684, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5305972432507862e-05, + "loss": 3.4728, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5297586484997342e-05, + "loss": 3.4776, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5289216916290554e-05, + "loss": 3.4898, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5280830968780034e-05, + "loss": 3.4807, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5272445021269514e-05, + "loss": 3.465, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.5264059073758994e-05, + "loss": 3.4776, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5255689505052203e-05, + "loss": 3.469, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5247303557541687e-05, + "loss": 3.4715, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5238917610031167e-05, + "loss": 3.4703, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5230531662520647e-05, + "loss": 3.4648, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5222162093813856e-05, + "loss": 3.4776, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5213776146303336e-05, + "loss": 3.4686, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5205390198792816e-05, + "loss": 3.4793, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5197004251282296e-05, + "loss": 3.4701, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188634682575508e-05, + "loss": 3.4756, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5180248735064988e-05, + "loss": 3.4697, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5171862787554468e-05, + "loss": 3.4905, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163476840043948e-05, + "loss": 3.4757, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5155107271337157e-05, + "loss": 3.4751, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146721323826637e-05, + "loss": 3.4661, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.513833537631612e-05, + "loss": 3.4819, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.51299494288056e-05, + "loss": 3.4747, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.512157986009881e-05, + "loss": 3.4797, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.511319391258829e-05, + "loss": 3.4702, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.510480796507777e-05, + "loss": 3.4827, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.509642201756725e-05, + "loss": 3.4753, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.508805244886046e-05, + "loss": 3.4879, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.507966650134994e-05, + "loss": 3.471, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.507128055383942e-05, + "loss": 3.4795, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.50628946063289e-05, + "loss": 3.4733, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.505452503762211e-05, + "loss": 3.4684, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.504613909011159e-05, + "loss": 3.4812, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5037753142601074e-05, + "loss": 3.4826, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5029367195090554e-05, + "loss": 3.4738, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5020997626383763e-05, + "loss": 3.473, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5012611678873243e-05, + "loss": 3.4702, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.8523828983306885, + "eval_runtime": 303.6346, + "eval_samples_per_second": 1256.744, + "eval_steps_per_second": 39.274, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.5004225731362723e-05, + "loss": 3.4689, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.4995839783852203e-05, + "loss": 3.4657, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4987453836341683e-05, + "loss": 3.4759, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4979067888831166e-05, + "loss": 3.4778, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970698320124375e-05, + "loss": 3.4868, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962312372613855e-05, + "loss": 3.4715, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4953926425103335e-05, + "loss": 3.4695, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4945540477592815e-05, + "loss": 3.4698, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4937170908886028e-05, + "loss": 3.4831, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928784961375508e-05, + "loss": 3.4732, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920399013864988e-05, + "loss": 3.4632, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4912013066354467e-05, + "loss": 3.4701, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.490365987645141e-05, + "loss": 3.4718, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.489527392894089e-05, + "loss": 3.4655, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.488688798143037e-05, + "loss": 3.4719, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.487850203391985e-05, + "loss": 3.4581, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.487011608640933e-05, + "loss": 3.4632, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.486173013889881e-05, + "loss": 3.461, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.485334419138829e-05, + "loss": 3.4613, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.484495824387777e-05, + "loss": 3.4868, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.483658867517098e-05, + "loss": 3.4679, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482820272766046e-05, + "loss": 3.4665, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.481981678014994e-05, + "loss": 3.4719, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811430832639418e-05, + "loss": 3.4829, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.480306126393263e-05, + "loss": 3.4633, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.479467531642211e-05, + "loss": 3.4735, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.478628936891159e-05, + "loss": 3.4663, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777919800204803e-05, + "loss": 3.4679, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4769533852694283e-05, + "loss": 3.4588, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4761147905183763e-05, + "loss": 3.4672, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752761957673242e-05, + "loss": 3.4713, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.474439238896645e-05, + "loss": 3.4734, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4736006441455935e-05, + "loss": 3.4778, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727620493945415e-05, + "loss": 3.475, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.471923454643489e-05, + "loss": 3.4591, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4710864977728104e-05, + "loss": 3.472, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702479030217584e-05, + "loss": 3.4637, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4694093082707064e-05, + "loss": 3.4675, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685707135196544e-05, + "loss": 3.4593, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677337566489756e-05, + "loss": 3.463, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668951618979236e-05, + "loss": 3.4646, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660565671468716e-05, + "loss": 3.4754, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4652179723958193e-05, + "loss": 3.4728, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4643810155251405e-05, + "loss": 3.464, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.463542420774089e-05, + "loss": 3.4695, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4627038260230365e-05, + "loss": 3.4653, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618652312719845e-05, + "loss": 3.472, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610282744013058e-05, + "loss": 3.4559, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601896796502538e-05, + "loss": 3.4498, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593510848992014e-05, + "loss": 3.4712, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4585124901481497e-05, + "loss": 3.4717, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.457675533277471e-05, + "loss": 3.4586, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568369385264187e-05, + "loss": 3.4626, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559983437753666e-05, + "loss": 3.4684, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551597490243146e-05, + "loss": 3.454, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.454322792153636e-05, + "loss": 3.4724, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.453484197402584e-05, + "loss": 3.4634, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.452645602651532e-05, + "loss": 3.4701, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.45180700790048e-05, + "loss": 3.4634, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.450970051029801e-05, + "loss": 3.4673, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501314562787488e-05, + "loss": 3.4594, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492928615276968e-05, + "loss": 3.4678, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.448454266776645e-05, + "loss": 3.4553, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.447617309905966e-05, + "loss": 3.4624, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.446778715154914e-05, + "loss": 3.4726, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.445940120403862e-05, + "loss": 3.4638, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.44510152565281e-05, + "loss": 3.4612, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442645687821313e-05, + "loss": 3.4523, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434259740310793e-05, + "loss": 3.4629, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4425873792800272e-05, + "loss": 3.4659, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417487845289752e-05, + "loss": 3.471, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440911827658296e-05, + "loss": 3.467, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.440073232907244e-05, + "loss": 3.4743, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439234638156192e-05, + "loss": 3.4719, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4383960434051405e-05, + "loss": 3.4657, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375590865344614e-05, + "loss": 3.4664, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4367221296637826e-05, + "loss": 3.4712, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358835349127306e-05, + "loss": 3.4574, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4350449401616783e-05, + "loss": 3.4607, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4342063454106266e-05, + "loss": 3.4673, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333677506595746e-05, + "loss": 3.4629, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325291559085226e-05, + "loss": 3.4763, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316905611574706e-05, + "loss": 3.4713, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308519664064186e-05, + "loss": 3.4487, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4300150095357395e-05, + "loss": 3.4629, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291764147846875e-05, + "loss": 3.4683, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428337820033636e-05, + "loss": 3.4657, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.427499225282584e-05, + "loss": 3.464, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266622684119048e-05, + "loss": 3.4559, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258236736608527e-05, + "loss": 3.4658, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249850789098007e-05, + "loss": 3.4608, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241464841587487e-05, + "loss": 3.462, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.42330952728807e-05, + "loss": 3.4656, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422470932537018e-05, + "loss": 3.4696, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.421632337785966e-05, + "loss": 3.4687, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.420793743034914e-05, + "loss": 3.4671, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.419956786164235e-05, + "loss": 3.455, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.419118191413183e-05, + "loss": 3.4669, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182795966621312e-05, + "loss": 3.4663, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.417441001911079e-05, + "loss": 3.4679, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4166040450404e-05, + "loss": 3.457, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.415765450289348e-05, + "loss": 3.4622, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.414926855538296e-05, + "loss": 3.4614, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140882607872438e-05, + "loss": 3.4713, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132513039165654e-05, + "loss": 3.4582, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4124127091655133e-05, + "loss": 3.4538, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115741144144613e-05, + "loss": 3.4651, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107371575437823e-05, + "loss": 3.46, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4098985627927303e-05, + "loss": 3.4532, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090599680416782e-05, + "loss": 3.4565, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4082213732906262e-05, + "loss": 3.4548, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073844164199475e-05, + "loss": 3.4694, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065458216688955e-05, + "loss": 3.4601, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4057072269178435e-05, + "loss": 3.458, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404868632166791e-05, + "loss": 3.4667, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4040316752961127e-05, + "loss": 3.481, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031930805450607e-05, + "loss": 3.4685, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023544857940087e-05, + "loss": 3.4552, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4015175289233296e-05, + "loss": 3.4644, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006789341722776e-05, + "loss": 3.4589, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998403394212256e-05, + "loss": 3.458, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3990017446701736e-05, + "loss": 3.4596, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3981631499191216e-05, + "loss": 3.4529, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3973245551680696e-05, + "loss": 3.4661, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964859604170176e-05, + "loss": 3.46, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956473656659656e-05, + "loss": 3.4672, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3948104087952865e-05, + "loss": 3.455, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939718140442345e-05, + "loss": 3.4599, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.393133219293183e-05, + "loss": 3.4647, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3922946245421308e-05, + "loss": 3.4712, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914576676714517e-05, + "loss": 3.4622, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3906190729203997e-05, + "loss": 3.4704, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897804781693477e-05, + "loss": 3.4552, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889418834182957e-05, + "loss": 3.4715, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.388104926547617e-05, + "loss": 3.4672, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387266331796565e-05, + "loss": 3.4681, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386427737045513e-05, + "loss": 3.4561, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.385589142294461e-05, + "loss": 3.4747, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.384752185423782e-05, + "loss": 3.4592, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.38391359067273e-05, + "loss": 3.4796, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830749959216782e-05, + "loss": 3.4592, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822364011706262e-05, + "loss": 3.4687, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381399444299947e-05, + "loss": 3.4623, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380560849548895e-05, + "loss": 3.4571, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.379722254797843e-05, + "loss": 3.4695, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.378883660046791e-05, + "loss": 3.4686, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780467031761123e-05, + "loss": 3.4636, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3772081084250603e-05, + "loss": 3.4567, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763695136740083e-05, + "loss": 3.4613, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.853100538253784, + "eval_runtime": 303.6741, + "eval_samples_per_second": 1256.581, + "eval_steps_per_second": 39.269, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3755309189229563e-05, + "loss": 3.4601, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.374692324171904e-05, + "loss": 3.4566, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.373853729420852e-05, + "loss": 3.4652, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3730151346698e-05, + "loss": 3.465, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3721781777991212e-05, + "loss": 3.4722, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3713395830480692e-05, + "loss": 3.4602, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3705009882970172e-05, + "loss": 3.4597, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.3696623935459652e-05, + "loss": 3.4586, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.368825436675286e-05, + "loss": 3.4708, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3679868419242345e-05, + "loss": 3.4595, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3671482471731825e-05, + "loss": 3.4568, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3663096524221304e-05, + "loss": 3.4567, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3654743334318246e-05, + "loss": 3.4597, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3646357386807726e-05, + "loss": 3.4548, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3637971439297206e-05, + "loss": 3.4625, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3629585491786686e-05, + "loss": 3.4488, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3621199544276166e-05, + "loss": 3.4501, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3612813596765646e-05, + "loss": 3.453, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3604427649255126e-05, + "loss": 3.4507, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3596041701744606e-05, + "loss": 3.4725, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3587672133037815e-05, + "loss": 3.4583, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3579286185527298e-05, + "loss": 3.4556, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3570900238016778e-05, + "loss": 3.4568, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3562514290506258e-05, + "loss": 3.4673, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3554144721799467e-05, + "loss": 3.4533, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3545758774288947e-05, + "loss": 3.464, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3537372826778427e-05, + "loss": 3.4514, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3528986879267907e-05, + "loss": 3.4577, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.352061731056112e-05, + "loss": 3.4496, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.35122313630506e-05, + "loss": 3.4543, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.350384541554008e-05, + "loss": 3.4585, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.349547584683329e-05, + "loss": 3.4621, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.348708989932277e-05, + "loss": 3.4636, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3478703951812252e-05, + "loss": 3.4643, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3470318004301732e-05, + "loss": 3.4485, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.346194843559494e-05, + "loss": 3.4624, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.345356248808442e-05, + "loss": 3.4557, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.34451765405739e-05, + "loss": 3.4489, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.343679059306338e-05, + "loss": 3.4535, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3428421024356593e-05, + "loss": 3.4495, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3420035076846073e-05, + "loss": 3.4515, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3411649129335553e-05, + "loss": 3.4667, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3403263181825033e-05, + "loss": 3.4577, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3394877234314513e-05, + "loss": 3.4506, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3386507665607722e-05, + "loss": 3.4628, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3378121718097206e-05, + "loss": 3.4555, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3369735770586686e-05, + "loss": 3.4547, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3361366201879895e-05, + "loss": 3.4462, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.3352980254369375e-05, + "loss": 3.4363, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3344594306858855e-05, + "loss": 3.4608, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.3336208359348334e-05, + "loss": 3.4569, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3327838790641547e-05, + "loss": 3.4513, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3319452843131027e-05, + "loss": 3.4516, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3311066895620507e-05, + "loss": 3.4529, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3302680948109987e-05, + "loss": 3.441, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3294311379403196e-05, + "loss": 3.4559, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.3285925431892676e-05, + "loss": 3.458, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.327753948438216e-05, + "loss": 3.4558, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3269153536871636e-05, + "loss": 3.4531, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3260783968164848e-05, + "loss": 3.4553, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3252398020654328e-05, + "loss": 3.4454, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3244012073143808e-05, + "loss": 3.4564, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3235626125633285e-05, + "loss": 3.4441, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.32272565569265e-05, + "loss": 3.4477, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321887060941598e-05, + "loss": 3.4619, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.321048466190546e-05, + "loss": 3.4529, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3202098714394937e-05, + "loss": 3.4471, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.319372914568815e-05, + "loss": 3.4443, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.318534319817763e-05, + "loss": 3.4473, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.317695725066711e-05, + "loss": 3.455, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.316857130315659e-05, + "loss": 3.4595, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3160201734449802e-05, + "loss": 3.4521, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3151815786939282e-05, + "loss": 3.4631, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.314342983942876e-05, + "loss": 3.4594, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.313504389191824e-05, + "loss": 3.4595, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3126674323211454e-05, + "loss": 3.4528, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3118304754504663e-05, + "loss": 3.4539, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3109918806994143e-05, + "loss": 3.4537, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3101532859483623e-05, + "loss": 3.4472, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3093146911973103e-05, + "loss": 3.4604, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084760964462583e-05, + "loss": 3.4473, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3076375016952063e-05, + "loss": 3.4613, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3067989069441543e-05, + "loss": 3.462, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059603121931023e-05, + "loss": 3.4376, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3051233553224232e-05, + "loss": 3.4554, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3042847605713712e-05, + "loss": 3.4499, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3034461658203192e-05, + "loss": 3.4556, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3026075710692675e-05, + "loss": 3.4535, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3017706141985885e-05, + "loss": 3.4462, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3009320194475364e-05, + "loss": 3.4558, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.3000934246964844e-05, + "loss": 3.4485, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2992548299454324e-05, + "loss": 3.454, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2984178730747537e-05, + "loss": 3.4502, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2975792783237017e-05, + "loss": 3.461, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2967406835726497e-05, + "loss": 3.4573, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2959020888215977e-05, + "loss": 3.4559, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2950651319509186e-05, + "loss": 3.442, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2942265371998666e-05, + "loss": 3.4586, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2933879424488146e-05, + "loss": 3.4537, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.292549347697763e-05, + "loss": 3.4578, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2917123908270838e-05, + "loss": 3.4452, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2908737960760318e-05, + "loss": 3.4522, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2900352013249798e-05, + "loss": 3.4472, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2891966065739278e-05, + "loss": 3.4593, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.288359649703249e-05, + "loss": 3.4443, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.287521054952197e-05, + "loss": 3.4447, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.286682460201145e-05, + "loss": 3.4528, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285843865450093e-05, + "loss": 3.4511, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.285006908579414e-05, + "loss": 3.4403, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.284168313828362e-05, + "loss": 3.449, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.28332971907731e-05, + "loss": 3.4461, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2824927622066312e-05, + "loss": 3.4534, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2816541674555792e-05, + "loss": 3.4541, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.2808155727045272e-05, + "loss": 3.4435, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.2799769779534752e-05, + "loss": 3.4567, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.279140021082796e-05, + "loss": 3.4699, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2783014263317444e-05, + "loss": 3.4596, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2774628315806924e-05, + "loss": 3.4412, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2766242368296404e-05, + "loss": 3.4537, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2757872799589613e-05, + "loss": 3.4477, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2749486852079093e-05, + "loss": 3.4439, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.2741100904568573e-05, + "loss": 3.4492, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2732714957058053e-05, + "loss": 3.4414, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2724345388351266e-05, + "loss": 3.456, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2715959440840746e-05, + "loss": 3.4483, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707573493330225e-05, + "loss": 3.4587, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2699187545819705e-05, + "loss": 3.4467, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2690817977112915e-05, + "loss": 3.4469, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2682432029602398e-05, + "loss": 3.4578, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.2674046082091878e-05, + "loss": 3.4578, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2665660134581358e-05, + "loss": 3.4517, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2657290565874567e-05, + "loss": 3.4562, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2648904618364047e-05, + "loss": 3.4439, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2640518670853527e-05, + "loss": 3.4607, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.2632132723343007e-05, + "loss": 3.4558, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.262376315463622e-05, + "loss": 3.457, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.26153772071257e-05, + "loss": 3.4445, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.260699125961518e-05, + "loss": 3.4608, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598605312104656e-05, + "loss": 3.4471, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2590235743397868e-05, + "loss": 3.47, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2581849795887348e-05, + "loss": 3.4449, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.257346384837683e-05, + "loss": 3.4598, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2565077900866308e-05, + "loss": 3.4481, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.255670833215952e-05, + "loss": 3.4481, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2548322384649e-05, + "loss": 3.4557, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2539936437138477e-05, + "loss": 3.4545, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.253155048962796e-05, + "loss": 3.4563, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2523180920921173e-05, + "loss": 3.4433, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2514794973410653e-05, + "loss": 3.4552, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.855222463607788, + "eval_runtime": 309.5486, + "eval_samples_per_second": 1232.734, + "eval_steps_per_second": 38.524, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.250640902590013e-05, + "loss": 3.4516, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.249802307838961e-05, + "loss": 3.4436, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.248963713087909e-05, + "loss": 3.4489, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.248125118336857e-05, + "loss": 3.4549, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472881614661782e-05, + "loss": 3.4614, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464495667151262e-05, + "loss": 3.4511, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.2456109719640742e-05, + "loss": 3.4416, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244772377213022e-05, + "loss": 3.4493, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243935420342343e-05, + "loss": 3.4569, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2430968255912914e-05, + "loss": 3.4477, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2422582308402394e-05, + "loss": 3.4456, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2414196360891874e-05, + "loss": 3.4445, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2405843170988816e-05, + "loss": 3.4515, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2397457223478296e-05, + "loss": 3.4415, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2389071275967776e-05, + "loss": 3.4509, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2380685328457255e-05, + "loss": 3.436, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2372299380946735e-05, + "loss": 3.4381, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2363913433436215e-05, + "loss": 3.4393, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355527485925695e-05, + "loss": 3.4405, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2347141538415175e-05, + "loss": 3.4596, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338771969708384e-05, + "loss": 3.4503, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2330386022197868e-05, + "loss": 3.4453, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2322000074687348e-05, + "loss": 3.4446, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313614127176828e-05, + "loss": 3.4543, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2305244558470037e-05, + "loss": 3.4426, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2296858610959517e-05, + "loss": 3.4547, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2288472663448997e-05, + "loss": 3.4385, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2280086715938477e-05, + "loss": 3.4474, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.227171714723169e-05, + "loss": 3.4421, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.226333119972117e-05, + "loss": 3.4423, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.225494525221065e-05, + "loss": 3.4479, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246575683503858e-05, + "loss": 3.4534, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2238189735993338e-05, + "loss": 3.4486, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.222980378848282e-05, + "loss": 3.4549, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.22214178409723e-05, + "loss": 3.4382, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.221304827226551e-05, + "loss": 3.4569, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.220466232475499e-05, + "loss": 3.4433, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.219627637724447e-05, + "loss": 3.4372, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.218789042973395e-05, + "loss": 3.442, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179520861027163e-05, + "loss": 3.4388, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2171134913516643e-05, + "loss": 3.442, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2162748966006123e-05, + "loss": 3.4527, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2154363018495603e-05, + "loss": 3.4442, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2145993449788812e-05, + "loss": 3.4428, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137607502278292e-05, + "loss": 3.4481, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2129221554767772e-05, + "loss": 3.444, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120835607257255e-05, + "loss": 3.4468, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2112466038550464e-05, + "loss": 3.4337, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2104080091039944e-05, + "loss": 3.4241, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2095694143529424e-05, + "loss": 3.4511, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2087308196018904e-05, + "loss": 3.4501, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2078938627312116e-05, + "loss": 3.4392, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2070552679801596e-05, + "loss": 3.4459, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2062166732291076e-05, + "loss": 3.4384, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2053780784780553e-05, + "loss": 3.432, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2045411216073765e-05, + "loss": 3.4427, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2037025268563245e-05, + "loss": 3.4469, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028639321052725e-05, + "loss": 3.444, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2020253373542205e-05, + "loss": 3.44, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011883804835418e-05, + "loss": 3.4451, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003497857324898e-05, + "loss": 3.4353, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1995111909814374e-05, + "loss": 3.4472, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986725962303854e-05, + "loss": 3.4333, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1978340014793338e-05, + "loss": 3.436, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1969954067282818e-05, + "loss": 3.4531, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961568119772298e-05, + "loss": 3.4422, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1953182172261778e-05, + "loss": 3.44, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944812603554987e-05, + "loss": 3.4321, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936426656044467e-05, + "loss": 3.4357, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1928040708533947e-05, + "loss": 3.4384, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.191967113982716e-05, + "loss": 3.4521, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.191128519231664e-05, + "loss": 3.4418, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.190289924480612e-05, + "loss": 3.4521, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.18945132972956e-05, + "loss": 3.4453, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.188612734978508e-05, + "loss": 3.4522, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877741402274555e-05, + "loss": 3.4422, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.186937183356777e-05, + "loss": 3.4417, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.186098588605725e-05, + "loss": 3.4419, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.185259993854673e-05, + "loss": 3.4328, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1844213991036208e-05, + "loss": 3.4481, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1835828043525688e-05, + "loss": 3.4394, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827442096015168e-05, + "loss": 3.4515, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1819056148504648e-05, + "loss": 3.4496, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.181067020099413e-05, + "loss": 3.4264, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.180230063228734e-05, + "loss": 3.4484, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179391468477682e-05, + "loss": 3.4407, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.17855287372663e-05, + "loss": 3.4433, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.177714278975578e-05, + "loss": 3.4404, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768773221048992e-05, + "loss": 3.4365, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1760387273538472e-05, + "loss": 3.4435, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.1752001326027952e-05, + "loss": 3.4374, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.1743615378517432e-05, + "loss": 3.4417, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173524580981064e-05, + "loss": 3.4411, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.172685986230012e-05, + "loss": 3.4501, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.17184739147896e-05, + "loss": 3.4496, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1710087967279085e-05, + "loss": 3.4373, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701718398572294e-05, + "loss": 3.4353, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693332451061774e-05, + "loss": 3.4453, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1684946503551254e-05, + "loss": 3.4398, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1676560556040734e-05, + "loss": 3.4486, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1668190987333946e-05, + "loss": 3.4371, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1659805039823426e-05, + "loss": 3.4399, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651419092312906e-05, + "loss": 3.4375, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1643033144802386e-05, + "loss": 3.4471, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634663576095595e-05, + "loss": 3.4313, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1626277628585075e-05, + "loss": 3.4362, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1617891681074555e-05, + "loss": 3.438, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1609505733564038e-05, + "loss": 3.4399, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1601136164857247e-05, + "loss": 3.4303, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592750217346727e-05, + "loss": 3.4401, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584364269836207e-05, + "loss": 3.4318, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1575978322325684e-05, + "loss": 3.4425, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.15676087536189e-05, + "loss": 3.4404, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.155922280610838e-05, + "loss": 3.4358, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.155083685859786e-05, + "loss": 3.4416, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1542450911087336e-05, + "loss": 3.4565, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.153408134238055e-05, + "loss": 3.4523, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.152569539487003e-05, + "loss": 3.4316, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.151732582616324e-05, + "loss": 3.4401, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.150893987865272e-05, + "loss": 3.4384, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.15005539311422e-05, + "loss": 3.4307, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.149216798363168e-05, + "loss": 3.4412, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1483782036121158e-05, + "loss": 3.4258, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1475396088610638e-05, + "loss": 3.4496, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1467010141100117e-05, + "loss": 3.4335, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.14586241935896e-05, + "loss": 3.4486, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.145025462488281e-05, + "loss": 3.4377, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.144186867737229e-05, + "loss": 3.4383, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.143348272986177e-05, + "loss": 3.4424, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.142509678235125e-05, + "loss": 3.4473, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1416727213644462e-05, + "loss": 3.4378, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1408341266133942e-05, + "loss": 3.4473, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1399955318623422e-05, + "loss": 3.4337, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1391569371112902e-05, + "loss": 3.4518, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.138319980240611e-05, + "loss": 3.4425, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.137481385489559e-05, + "loss": 3.4411, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.136642790738507e-05, + "loss": 3.4377, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1358041959874554e-05, + "loss": 3.4483, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349672391167764e-05, + "loss": 3.4397, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1341286443657244e-05, + "loss": 3.4557, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1332900496146723e-05, + "loss": 3.4337, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1324514548636203e-05, + "loss": 3.4455, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1316144979929416e-05, + "loss": 3.4397, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307759032418896e-05, + "loss": 3.4389, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299373084908376e-05, + "loss": 3.4377, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1290987137397856e-05, + "loss": 3.4444, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282617568691065e-05, + "loss": 3.4459, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1274231621180545e-05, + "loss": 3.4326, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1265845673670025e-05, + "loss": 3.4478, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.856431245803833, + "eval_runtime": 311.0453, + "eval_samples_per_second": 1226.802, + "eval_steps_per_second": 38.338, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.1257459726159508e-05, + "loss": 3.4326, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1249090157452717e-05, + "loss": 3.4343, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1240704209942197e-05, + "loss": 3.4371, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.1232318262431677e-05, + "loss": 3.442, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.1223932314921157e-05, + "loss": 3.4479, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.121556274621437e-05, + "loss": 3.4401, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.120717679870385e-05, + "loss": 3.4357, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.119879085119333e-05, + "loss": 3.4359, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.119040490368281e-05, + "loss": 3.4467, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.118203533497602e-05, + "loss": 3.4383, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.11736493874655e-05, + "loss": 3.4337, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.116526343995498e-05, + "loss": 3.4318, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.115689387124819e-05, + "loss": 3.4407, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.114850792373767e-05, + "loss": 3.4305, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.114012197622715e-05, + "loss": 3.4391, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.113173602871663e-05, + "loss": 3.4242, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.1123350081206107e-05, + "loss": 3.429, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.1114964133695587e-05, + "loss": 3.4302, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.110657818618507e-05, + "loss": 3.4289, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.109819223867455e-05, + "loss": 3.4466, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.108982266996776e-05, + "loss": 3.4408, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.108143672245724e-05, + "loss": 3.4344, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.107305077494672e-05, + "loss": 3.4329, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.10646648274362e-05, + "loss": 3.4415, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1056295258729412e-05, + "loss": 3.4336, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1047909311218892e-05, + "loss": 3.4426, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1039523363708372e-05, + "loss": 3.4254, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.1031137416197852e-05, + "loss": 3.438, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.102276784749106e-05, + "loss": 3.4369, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.101438189998054e-05, + "loss": 3.4283, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1005995952470024e-05, + "loss": 3.4338, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0997610004959504e-05, + "loss": 3.4431, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0989240436252713e-05, + "loss": 3.436, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.0980854488742193e-05, + "loss": 3.4473, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.0972468541231673e-05, + "loss": 3.4273, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0964082593721153e-05, + "loss": 3.4392, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0955713025014366e-05, + "loss": 3.4357, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0947327077503846e-05, + "loss": 3.4274, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0938941129993326e-05, + "loss": 3.4304, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0930555182482806e-05, + "loss": 3.4289, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.0922185613776015e-05, + "loss": 3.4296, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0913799666265495e-05, + "loss": 3.4393, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0905413718754978e-05, + "loss": 3.4344, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.0897044150048187e-05, + "loss": 3.4337, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0888658202537667e-05, + "loss": 3.4414, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0880272255027147e-05, + "loss": 3.4333, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.0871886307516627e-05, + "loss": 3.4327, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.086351673880984e-05, + "loss": 3.4274, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.085513079129932e-05, + "loss": 3.4087, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.08467448437888e-05, + "loss": 3.4437, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.083835889627828e-05, + "loss": 3.4341, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.082998932757149e-05, + "loss": 3.4347, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.082160338006097e-05, + "loss": 3.4316, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.081321743255045e-05, + "loss": 3.4302, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.0804831485039932e-05, + "loss": 3.4215, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.079646191633314e-05, + "loss": 3.4283, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.078807596882262e-05, + "loss": 3.4373, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.07796900213121e-05, + "loss": 3.4334, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.077130407380158e-05, + "loss": 3.4379, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.0762950883898526e-05, + "loss": 3.4264, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.0754564936388002e-05, + "loss": 3.4254, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.0746178988877482e-05, + "loss": 3.4411, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.0737793041366962e-05, + "loss": 3.418, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.0729407093856442e-05, + "loss": 3.4243, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.0721021146345922e-05, + "loss": 3.4387, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.0712635198835402e-05, + "loss": 3.4331, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0704249251324885e-05, + "loss": 3.4249, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0695879682618094e-05, + "loss": 3.4268, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0687493735107574e-05, + "loss": 3.422, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.0679107787597054e-05, + "loss": 3.4298, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.067072184008653e-05, + "loss": 3.4422, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0662352271379747e-05, + "loss": 3.4315, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0653966323869227e-05, + "loss": 3.4411, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0645580376358707e-05, + "loss": 3.4355, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0637194428848183e-05, + "loss": 3.4442, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.0628824860141396e-05, + "loss": 3.4272, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.0620438912630876e-05, + "loss": 3.4362, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.0612052965120356e-05, + "loss": 3.431, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0603667017609836e-05, + "loss": 3.4188, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0595297448903048e-05, + "loss": 3.4376, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0586911501392528e-05, + "loss": 3.429, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0578525553882005e-05, + "loss": 3.4389, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.0570139606371485e-05, + "loss": 3.4404, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.0561770037664697e-05, + "loss": 3.4197, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.055338409015418e-05, + "loss": 3.4332, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.0544998142643657e-05, + "loss": 3.4291, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.053662857393687e-05, + "loss": 3.4339, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.052824262642635e-05, + "loss": 3.4301, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.051985667891583e-05, + "loss": 3.4286, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.051147073140531e-05, + "loss": 3.4289, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.050308478389479e-05, + "loss": 3.4268, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.049469883638427e-05, + "loss": 3.4315, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.048631288887375e-05, + "loss": 3.4285, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.047792694136323e-05, + "loss": 3.4433, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0469557372656438e-05, + "loss": 3.4379, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0461171425145918e-05, + "loss": 3.4257, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.04527854776354e-05, + "loss": 3.4231, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.044439953012488e-05, + "loss": 3.4308, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.043602996141809e-05, + "loss": 3.4346, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.042764401390757e-05, + "loss": 3.4333, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.041925806639705e-05, + "loss": 3.4286, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.041087211888653e-05, + "loss": 3.4302, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.0402502550179743e-05, + "loss": 3.4264, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.0394116602669223e-05, + "loss": 3.4416, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.0385730655158703e-05, + "loss": 3.4173, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.0377344707648183e-05, + "loss": 3.4291, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.0368975138941392e-05, + "loss": 3.4248, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.0360589191430872e-05, + "loss": 3.4291, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0352203243920355e-05, + "loss": 3.4189, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.0343817296409835e-05, + "loss": 3.4325, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0335447727703044e-05, + "loss": 3.4175, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.0327061780192524e-05, + "loss": 3.4313, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.0318675832682004e-05, + "loss": 3.4326, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.0310289885171484e-05, + "loss": 3.4252, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0301920316464697e-05, + "loss": 3.4317, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0293534368954177e-05, + "loss": 3.4466, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.0285148421443657e-05, + "loss": 3.4319, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.0276778852736866e-05, + "loss": 3.4282, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.0268409284030078e-05, + "loss": 3.4229, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.0260023336519558e-05, + "loss": 3.4294, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.0251637389009038e-05, + "loss": 3.4277, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.0243251441498518e-05, + "loss": 3.4295, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.0234865493987998e-05, + "loss": 3.4134, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.0226479546477478e-05, + "loss": 3.4344, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.0218093598966958e-05, + "loss": 3.4255, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.0209707651456434e-05, + "loss": 3.4348, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.020133808274965e-05, + "loss": 3.4252, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.019295213523913e-05, + "loss": 3.4266, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0184566187728607e-05, + "loss": 3.4296, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0176180240218087e-05, + "loss": 3.4412, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.01678106715113e-05, + "loss": 3.428, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.015942472400078e-05, + "loss": 3.4355, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.015103877649026e-05, + "loss": 3.4226, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.014265282897974e-05, + "loss": 3.442, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.013428326027295e-05, + "loss": 3.4346, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.012589731276243e-05, + "loss": 3.4328, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0117511365251908e-05, + "loss": 3.426, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0109125417741388e-05, + "loss": 3.4356, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0100755849034604e-05, + "loss": 3.4263, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.009236990152408e-05, + "loss": 3.4446, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.008398395401356e-05, + "loss": 3.4251, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.007559800650304e-05, + "loss": 3.439, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0067228437796253e-05, + "loss": 3.4315, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.0058842490285733e-05, + "loss": 3.4271, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0050456542775213e-05, + "loss": 3.4252, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0042070595264693e-05, + "loss": 3.4353, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.0033701026557902e-05, + "loss": 3.4348, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.0025315079047382e-05, + "loss": 3.4235, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.0016929131536862e-05, + "loss": 3.4355, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.857499599456787, + "eval_runtime": 310.5924, + "eval_samples_per_second": 1228.591, + "eval_steps_per_second": 38.394, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0008543184026342e-05, + "loss": 3.4253, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 2.0000157236515825e-05, + "loss": 3.4228, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.9991771289005305e-05, + "loss": 3.4254, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.9983385341494785e-05, + "loss": 3.4332, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.9975015772787994e-05, + "loss": 3.4388, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.9966629825277474e-05, + "loss": 3.4278, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.9958243877766954e-05, + "loss": 3.4298, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9949857930256434e-05, + "loss": 3.425, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9941488361549646e-05, + "loss": 3.4331, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9933102414039126e-05, + "loss": 3.4325, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9924716466528606e-05, + "loss": 3.4221, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9916330519018083e-05, + "loss": 3.4185, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9907977329115028e-05, + "loss": 3.4343, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9899591381604508e-05, + "loss": 3.4183, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9891205434093988e-05, + "loss": 3.4223, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9882819486583468e-05, + "loss": 3.4162, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9874433539072948e-05, + "loss": 3.4157, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9866047591562428e-05, + "loss": 3.4223, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.9857661644051908e-05, + "loss": 3.4181, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.9849275696541388e-05, + "loss": 3.4353, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.98409061278346e-05, + "loss": 3.4299, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.983253655912781e-05, + "loss": 3.4278, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.982415061161729e-05, + "loss": 3.4218, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.981576466410677e-05, + "loss": 3.4277, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.980737871659625e-05, + "loss": 3.4262, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.979899276908573e-05, + "loss": 3.4299, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.979060682157521e-05, + "loss": 3.4185, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.978222087406469e-05, + "loss": 3.43, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.977383492655417e-05, + "loss": 3.4189, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.976546535784738e-05, + "loss": 3.4188, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9757079410336858e-05, + "loss": 3.4183, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.974869346282634e-05, + "loss": 3.4358, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.974030751531582e-05, + "loss": 3.4288, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.973193794660903e-05, + "loss": 3.4346, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.972355199909851e-05, + "loss": 3.4166, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.971516605158799e-05, + "loss": 3.4225, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.970678010407747e-05, + "loss": 3.4317, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.9698410535370683e-05, + "loss": 3.4175, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9690024587860163e-05, + "loss": 3.4183, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.9681638640349643e-05, + "loss": 3.4174, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.9673252692839123e-05, + "loss": 3.4206, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.966488312413233e-05, + "loss": 3.4238, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.965649717662181e-05, + "loss": 3.4281, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9648111229111295e-05, + "loss": 3.4254, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9639725281600775e-05, + "loss": 3.4242, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9631355712893984e-05, + "loss": 3.4271, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.9622969765383464e-05, + "loss": 3.4186, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.9614583817872944e-05, + "loss": 3.4169, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.9606197870362424e-05, + "loss": 3.3963, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.9597828301655636e-05, + "loss": 3.4345, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.9589442354145116e-05, + "loss": 3.4209, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9581056406634596e-05, + "loss": 3.4288, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.9572670459124076e-05, + "loss": 3.4189, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9564300890417285e-05, + "loss": 3.4193, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.9555914942906765e-05, + "loss": 3.4087, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.954752899539625e-05, + "loss": 3.4168, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.9539159426689458e-05, + "loss": 3.4277, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9530773479178938e-05, + "loss": 3.4211, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9522387531668418e-05, + "loss": 3.4294, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9514017962961627e-05, + "loss": 3.4193, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.950563201545111e-05, + "loss": 3.4108, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.949724606794059e-05, + "loss": 3.4315, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.948886012043007e-05, + "loss": 3.4061, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.948047417291955e-05, + "loss": 3.41, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.947208822540903e-05, + "loss": 3.4291, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9463702277898506e-05, + "loss": 3.425, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9455316330387986e-05, + "loss": 3.4087, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9446946761681202e-05, + "loss": 3.424, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9438560814170682e-05, + "loss": 3.4062, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.943017486666016e-05, + "loss": 3.4225, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.942178891914964e-05, + "loss": 3.4246, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.941341935044285e-05, + "loss": 3.4251, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.940503340293233e-05, + "loss": 3.4246, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.939664745542181e-05, + "loss": 3.4263, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.938826150791129e-05, + "loss": 3.4365, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9379891939204504e-05, + "loss": 3.4174, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.937150599169398e-05, + "loss": 3.4255, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.936312004418346e-05, + "loss": 3.4225, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.935473409667294e-05, + "loss": 3.4045, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9346364527966153e-05, + "loss": 3.4246, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9337978580455633e-05, + "loss": 3.4206, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.9329592632945113e-05, + "loss": 3.4248, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.9321206685434592e-05, + "loss": 3.4362, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.9312837116727805e-05, + "loss": 3.4101, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.930445116921728e-05, + "loss": 3.4152, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.9296065221706765e-05, + "loss": 3.4196, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9287679274196245e-05, + "loss": 3.4265, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9279293326685725e-05, + "loss": 3.4149, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9270907379175205e-05, + "loss": 3.4209, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.9262521431664685e-05, + "loss": 3.4177, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.9254151862957894e-05, + "loss": 3.4175, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.9245765915447374e-05, + "loss": 3.4163, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9237379967936857e-05, + "loss": 3.4208, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.9228994020426337e-05, + "loss": 3.4297, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.9220624451719546e-05, + "loss": 3.422, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.9212238504209026e-05, + "loss": 3.4242, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.9203852556698506e-05, + "loss": 3.4087, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.9195466609187986e-05, + "loss": 3.4219, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.91870970404812e-05, + "loss": 3.4205, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.917871109297068e-05, + "loss": 3.4265, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.917032514546016e-05, + "loss": 3.417, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9161939197949635e-05, + "loss": 3.4169, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9153569629242847e-05, + "loss": 3.4196, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9145183681732327e-05, + "loss": 3.4231, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.913679773422181e-05, + "loss": 3.4102, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.9128411786711287e-05, + "loss": 3.4172, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.91200422180045e-05, + "loss": 3.4091, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.911165627049398e-05, + "loss": 3.4255, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.910327032298346e-05, + "loss": 3.4102, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.9094884375472936e-05, + "loss": 3.4169, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.9086514806766152e-05, + "loss": 3.4096, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9078128859255632e-05, + "loss": 3.4225, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.906974291174511e-05, + "loss": 3.4236, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.906135696423459e-05, + "loss": 3.414, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.90529873955278e-05, + "loss": 3.4217, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.904460144801728e-05, + "loss": 3.433, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.903621550050676e-05, + "loss": 3.4282, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.902782955299624e-05, + "loss": 3.4163, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.9019476363093183e-05, + "loss": 3.4126, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9011090415582663e-05, + "loss": 3.4162, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.9002704468072143e-05, + "loss": 3.4195, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8994318520561626e-05, + "loss": 3.414, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8985932573051106e-05, + "loss": 3.4067, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8977546625540582e-05, + "loss": 3.4217, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.8969160678030062e-05, + "loss": 3.4162, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.8960774730519542e-05, + "loss": 3.4237, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.8952405161812755e-05, + "loss": 3.414, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8944019214302235e-05, + "loss": 3.4174, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8935633266791715e-05, + "loss": 3.4167, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8927247319281195e-05, + "loss": 3.43, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8918877750574407e-05, + "loss": 3.4203, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.8910491803063884e-05, + "loss": 3.4232, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.8902105855553364e-05, + "loss": 3.4122, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.8893719908042844e-05, + "loss": 3.4338, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.8885350339336056e-05, + "loss": 3.4212, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.8876964391825536e-05, + "loss": 3.4234, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8868578444315016e-05, + "loss": 3.4148, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8860192496804496e-05, + "loss": 3.4194, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8851822928097705e-05, + "loss": 3.4178, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.884343698058719e-05, + "loss": 3.4357, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.883505103307667e-05, + "loss": 3.414, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.882666508556615e-05, + "loss": 3.4277, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8818295516859357e-05, + "loss": 3.4206, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8809909569348837e-05, + "loss": 3.4157, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8801523621838317e-05, + "loss": 3.4172, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8793137674327797e-05, + "loss": 3.4237, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.878476810562101e-05, + "loss": 3.4237, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.877638215811049e-05, + "loss": 3.4194, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.876799621059997e-05, + "loss": 3.4237, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.8584282398223877, + "eval_runtime": 302.9079, + "eval_samples_per_second": 1259.759, + "eval_steps_per_second": 39.368, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.875961026308945e-05, + "loss": 3.4093, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.875124069438266e-05, + "loss": 3.4123, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.8742854746872142e-05, + "loss": 3.4145, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.8734468799361622e-05, + "loss": 3.4256, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.8726082851851102e-05, + "loss": 3.4282, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.871771328314431e-05, + "loss": 3.4159, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.870932733563379e-05, + "loss": 3.4196, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.870094138812327e-05, + "loss": 3.4173, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.869255544061275e-05, + "loss": 3.4182, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.8684185871905963e-05, + "loss": 3.4252, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.8675799924395443e-05, + "loss": 3.411, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.8667413976884923e-05, + "loss": 3.4065, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.8659044408178132e-05, + "loss": 3.4286, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.8650658460667612e-05, + "loss": 3.4079, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.8642272513157096e-05, + "loss": 3.4121, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.8633886565646576e-05, + "loss": 3.4052, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.8625500618136056e-05, + "loss": 3.4092, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.8617114670625532e-05, + "loss": 3.4101, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.8608728723115012e-05, + "loss": 3.407, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.8600342775604492e-05, + "loss": 3.4211, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.8591973206897705e-05, + "loss": 3.4201, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8583587259387185e-05, + "loss": 3.4192, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.8575201311876665e-05, + "loss": 3.4112, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.8566815364366144e-05, + "loss": 3.4159, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8558445795659357e-05, + "loss": 3.418, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.8550059848148834e-05, + "loss": 3.4173, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.8541673900638313e-05, + "loss": 3.4073, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.8533287953127797e-05, + "loss": 3.4241, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.8524918384421006e-05, + "loss": 3.4076, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8516532436910486e-05, + "loss": 3.4102, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.8508146489399966e-05, + "loss": 3.4085, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.8499760541889446e-05, + "loss": 3.4201, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.8491390973182658e-05, + "loss": 3.4191, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.8483005025672138e-05, + "loss": 3.4267, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.8474619078161618e-05, + "loss": 3.4044, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.8466233130651098e-05, + "loss": 3.4143, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8457863561944307e-05, + "loss": 3.4245, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.8449477614433787e-05, + "loss": 3.4012, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8441091666923267e-05, + "loss": 3.4075, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.843270571941275e-05, + "loss": 3.4098, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.842433615070596e-05, + "loss": 3.4113, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.841595020319544e-05, + "loss": 3.4124, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.840756425568492e-05, + "loss": 3.4159, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.839919468697813e-05, + "loss": 3.4157, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.8390808739467612e-05, + "loss": 3.4125, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.8382422791957092e-05, + "loss": 3.4164, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.8374036844446572e-05, + "loss": 3.4095, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.8365650896936052e-05, + "loss": 3.4091, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.8357264949425532e-05, + "loss": 3.382, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.8348879001915012e-05, + "loss": 3.4245, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.8340493054404488e-05, + "loss": 3.4076, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8332123485697704e-05, + "loss": 3.4172, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.8323737538187184e-05, + "loss": 3.409, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.831535159067666e-05, + "loss": 3.4132, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.830696564316614e-05, + "loss": 3.3979, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.8298596074459353e-05, + "loss": 3.4043, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.8290210126948833e-05, + "loss": 3.4219, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8281824179438313e-05, + "loss": 3.4056, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8273438231927793e-05, + "loss": 3.4191, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.8265085042024735e-05, + "loss": 3.4111, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.8256699094514215e-05, + "loss": 3.3979, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.8248313147003695e-05, + "loss": 3.4228, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8239927199493174e-05, + "loss": 3.3957, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.8231541251982658e-05, + "loss": 3.4017, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.8223155304472134e-05, + "loss": 3.4179, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.8214769356961614e-05, + "loss": 3.4093, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.8206383409451094e-05, + "loss": 3.3997, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.8198013840744307e-05, + "loss": 3.4119, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.8189627893233783e-05, + "loss": 3.3962, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.8181241945723267e-05, + "loss": 3.4146, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.817287237701648e-05, + "loss": 3.4176, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.8164486429505956e-05, + "loss": 3.411, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.8156100481995436e-05, + "loss": 3.4161, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.8147714534484916e-05, + "loss": 3.4171, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.8139328586974396e-05, + "loss": 3.4266, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.8130942639463876e-05, + "loss": 3.408, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.8122573070757088e-05, + "loss": 3.4127, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.8114187123246568e-05, + "loss": 3.4166, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.8105801175736048e-05, + "loss": 3.3913, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.8097415228225528e-05, + "loss": 3.4154, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.8089029280715008e-05, + "loss": 3.4152, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.808065971200822e-05, + "loss": 3.414, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.80722737644977e-05, + "loss": 3.4247, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.806388781698718e-05, + "loss": 3.4019, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.805550186947666e-05, + "loss": 3.4045, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.8047115921966137e-05, + "loss": 3.4074, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.803874635325935e-05, + "loss": 3.4134, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.803036040574883e-05, + "loss": 3.4077, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.8021974458238313e-05, + "loss": 3.4097, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.801358851072779e-05, + "loss": 3.4045, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.800520256321727e-05, + "loss": 3.4106, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.799681661570675e-05, + "loss": 3.4077, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.798843066819623e-05, + "loss": 3.4086, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.798004472068571e-05, + "loss": 3.421, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.797167515197892e-05, + "loss": 3.4124, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.79632892044684e-05, + "loss": 3.4146, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.795490325695788e-05, + "loss": 3.4004, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.794651730944736e-05, + "loss": 3.411, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.793814774074057e-05, + "loss": 3.4102, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.792976179323005e-05, + "loss": 3.415, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.792137584571953e-05, + "loss": 3.406, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.7912989898209014e-05, + "loss": 3.4083, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.7904620329502223e-05, + "loss": 3.4097, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.7896234381991703e-05, + "loss": 3.4131, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.7887848434481183e-05, + "loss": 3.3997, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.7879462486970663e-05, + "loss": 3.4102, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.7871092918263875e-05, + "loss": 3.3968, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.7862706970753355e-05, + "loss": 3.4149, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.7854321023242835e-05, + "loss": 3.4021, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.7845935075732315e-05, + "loss": 3.4059, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.7837565507025524e-05, + "loss": 3.3957, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.7829179559515004e-05, + "loss": 3.4159, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.7820793612004484e-05, + "loss": 3.4097, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7812407664493967e-05, + "loss": 3.4033, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7804038095787176e-05, + "loss": 3.4128, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.7795652148276656e-05, + "loss": 3.4206, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.7787266200766136e-05, + "loss": 3.4175, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.7778880253255616e-05, + "loss": 3.4056, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.7770527063352558e-05, + "loss": 3.4027, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.7762141115842038e-05, + "loss": 3.4087, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.7753755168331518e-05, + "loss": 3.41, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.7745369220820998e-05, + "loss": 3.3977, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.7736983273310478e-05, + "loss": 3.4, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.7728597325799958e-05, + "loss": 3.4131, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.7720211378289438e-05, + "loss": 3.4088, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.7711825430778918e-05, + "loss": 3.4111, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.770345586207213e-05, + "loss": 3.4046, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.769506991456161e-05, + "loss": 3.4057, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.768668396705109e-05, + "loss": 3.4067, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.7678298019540567e-05, + "loss": 3.4204, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.7669928450833782e-05, + "loss": 3.4044, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.7661542503323262e-05, + "loss": 3.4158, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.765315655581274e-05, + "loss": 3.3993, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.764477060830222e-05, + "loss": 3.4237, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.763640103959543e-05, + "loss": 3.4063, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.762801509208491e-05, + "loss": 3.418, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.761962914457439e-05, + "loss": 3.4062, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.761124319706387e-05, + "loss": 3.4122, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.7602873628357084e-05, + "loss": 3.4057, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.7594487680846564e-05, + "loss": 3.4266, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.758610173333604e-05, + "loss": 3.4046, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.757771578582552e-05, + "loss": 3.4163, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7569346217118736e-05, + "loss": 3.4125, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7560960269608213e-05, + "loss": 3.4034, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.7552574322097693e-05, + "loss": 3.4083, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.7544188374587173e-05, + "loss": 3.4101, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.7535818805880385e-05, + "loss": 3.4141, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.752743285836986e-05, + "loss": 3.4091, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.7519046910859345e-05, + "loss": 3.4124, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.8610236644744873, + "eval_runtime": 302.8338, + "eval_samples_per_second": 1260.067, + "eval_steps_per_second": 39.378, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.7510660963348825e-05, + "loss": 3.404, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7502275015838305e-05, + "loss": 3.4025, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.7493889068327785e-05, + "loss": 3.4048, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7485503120817265e-05, + "loss": 3.4139, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7477149930914206e-05, + "loss": 3.4188, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7468763983403686e-05, + "loss": 3.4072, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7460378035893166e-05, + "loss": 3.408, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7451992088382646e-05, + "loss": 3.407, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.7443606140872126e-05, + "loss": 3.4084, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.7435220193361606e-05, + "loss": 3.4153, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.7426834245851086e-05, + "loss": 3.4012, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.7418448298340566e-05, + "loss": 3.4024, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.741007872963378e-05, + "loss": 3.4164, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.740169278212326e-05, + "loss": 3.3969, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.739330683461274e-05, + "loss": 3.4033, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.7384920887102215e-05, + "loss": 3.3931, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.7376534939591695e-05, + "loss": 3.4001, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.7368148992081175e-05, + "loss": 3.4004, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.7359763044570655e-05, + "loss": 3.3947, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.735137709706014e-05, + "loss": 3.4129, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.7343007528353347e-05, + "loss": 3.4089, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.733463795964656e-05, + "loss": 3.4085, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.732625201213604e-05, + "loss": 3.4028, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.7317866064625516e-05, + "loss": 3.4038, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.7309480117115e-05, + "loss": 3.4104, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.730109416960448e-05, + "loss": 3.4055, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.729270822209396e-05, + "loss": 3.3948, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.728432227458344e-05, + "loss": 3.4134, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.727593632707292e-05, + "loss": 3.3989, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.726756675836613e-05, + "loss": 3.401, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.725918081085561e-05, + "loss": 3.3992, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.7250794863345092e-05, + "loss": 3.4103, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.7242408915834572e-05, + "loss": 3.4034, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.723403934712778e-05, + "loss": 3.4206, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.722565339961726e-05, + "loss": 3.3981, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.721726745210674e-05, + "loss": 3.4003, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.720888150459622e-05, + "loss": 3.4154, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.7200511935889433e-05, + "loss": 3.3878, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.7192125988378913e-05, + "loss": 3.4008, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.7183740040868393e-05, + "loss": 3.4011, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.717535409335787e-05, + "loss": 3.3948, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.7166984524651082e-05, + "loss": 3.4043, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.7158598577140562e-05, + "loss": 3.4052, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7150229008433775e-05, + "loss": 3.4084, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.7141843060923255e-05, + "loss": 3.399, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.7133457113412735e-05, + "loss": 3.4088, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.7125071165902215e-05, + "loss": 3.3932, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.7116685218391695e-05, + "loss": 3.4054, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.7108299270881175e-05, + "loss": 3.3713, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.7099913323370655e-05, + "loss": 3.4107, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.7091527375860134e-05, + "loss": 3.3994, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.7083157807153344e-05, + "loss": 3.4097, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.7074771859642824e-05, + "loss": 3.3989, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.7066385912132303e-05, + "loss": 3.4017, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7057999964621783e-05, + "loss": 3.387, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.7049630395914996e-05, + "loss": 3.3953, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.7041244448404476e-05, + "loss": 3.4133, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.7032858500893956e-05, + "loss": 3.3921, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.7024472553383436e-05, + "loss": 3.4094, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.7016119363480377e-05, + "loss": 3.4068, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.700773341596986e-05, + "loss": 3.3844, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.699934746845934e-05, + "loss": 3.4097, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.6990961520948817e-05, + "loss": 3.3924, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.6982575573438297e-05, + "loss": 3.391, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.6974189625927777e-05, + "loss": 3.4042, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.6965803678417257e-05, + "loss": 3.3985, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.6957417730906737e-05, + "loss": 3.3917, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.694904816219995e-05, + "loss": 3.4015, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.694066221468943e-05, + "loss": 3.3884, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.693227626717891e-05, + "loss": 3.4013, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.692389031966839e-05, + "loss": 3.406, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.69155207509616e-05, + "loss": 3.4025, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.690713480345108e-05, + "loss": 3.4061, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.6898748855940562e-05, + "loss": 3.4051, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.6890362908430042e-05, + "loss": 3.413, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.688199333972325e-05, + "loss": 3.3969, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6873623771016463e-05, + "loss": 3.4044, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.686523782350594e-05, + "loss": 3.4021, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.6856851875995423e-05, + "loss": 3.3851, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.6848465928484903e-05, + "loss": 3.4025, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.6840079980974383e-05, + "loss": 3.4062, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.6831710412267592e-05, + "loss": 3.3996, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.6823324464757072e-05, + "loss": 3.4152, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.6814938517246552e-05, + "loss": 3.3875, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.6806552569736032e-05, + "loss": 3.3944, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.6798166622225516e-05, + "loss": 3.4002, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789797053518725e-05, + "loss": 3.403, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.6781411106008205e-05, + "loss": 3.402, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.6773025158497685e-05, + "loss": 3.3989, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6764639210987164e-05, + "loss": 3.391, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.6756253263476644e-05, + "loss": 3.4002, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.6747867315966124e-05, + "loss": 3.4005, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.6739481368455604e-05, + "loss": 3.3978, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.6731095420945084e-05, + "loss": 3.409, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.6722725852238293e-05, + "loss": 3.4063, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.6714339904727773e-05, + "loss": 3.3997, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.6705953957217253e-05, + "loss": 3.3931, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.6697568009706733e-05, + "loss": 3.3992, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.6689198440999946e-05, + "loss": 3.3968, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.6680812493489426e-05, + "loss": 3.4054, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.6672426545978906e-05, + "loss": 3.3986, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.6664040598468386e-05, + "loss": 3.3984, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.6655671029761598e-05, + "loss": 3.399, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.6647285082251078e-05, + "loss": 3.3964, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.6638899134740558e-05, + "loss": 3.3946, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.6630513187230038e-05, + "loss": 3.3981, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6622143618523247e-05, + "loss": 3.3852, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.6613757671012727e-05, + "loss": 3.4082, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.6605371723502207e-05, + "loss": 3.3958, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.6596985775991687e-05, + "loss": 3.3894, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.65886162072849e-05, + "loss": 3.3875, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.658023025977438e-05, + "loss": 3.402, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.657184431226386e-05, + "loss": 3.402, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.656345836475334e-05, + "loss": 3.3932, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.655508879604655e-05, + "loss": 3.4029, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.6546702848536032e-05, + "loss": 3.4136, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.6538316901025512e-05, + "loss": 3.4058, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.652993095351499e-05, + "loss": 3.3972, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.6521577763611933e-05, + "loss": 3.3953, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.6513191816101413e-05, + "loss": 3.396, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.6504805868590893e-05, + "loss": 3.4023, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.6496419921080373e-05, + "loss": 3.3887, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.6488033973569853e-05, + "loss": 3.391, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.6479648026059333e-05, + "loss": 3.4024, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.6471278457352542e-05, + "loss": 3.3998, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.6462892509842022e-05, + "loss": 3.3989, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.6454506562331502e-05, + "loss": 3.4, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.6446120614820985e-05, + "loss": 3.3926, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.6437734667310465e-05, + "loss": 3.3963, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.6429348719799945e-05, + "loss": 3.4097, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.6420962772289422e-05, + "loss": 3.3938, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.6412593203582634e-05, + "loss": 3.4076, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.6404207256072114e-05, + "loss": 3.3896, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.6395821308561594e-05, + "loss": 3.4085, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.6387435361051074e-05, + "loss": 3.4031, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.6379049413540554e-05, + "loss": 3.4059, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.6370663466030034e-05, + "loss": 3.3971, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.6362277518519514e-05, + "loss": 3.3977, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.6353891571008994e-05, + "loss": 3.4003, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6345522002302207e-05, + "loss": 3.4121, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.6337136054791687e-05, + "loss": 3.3971, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.6328750107281166e-05, + "loss": 3.4017, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.6320364159770646e-05, + "loss": 3.4052, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.6311994591063856e-05, + "loss": 3.3927, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.6303608643553335e-05, + "loss": 3.3964, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.6295222696042815e-05, + "loss": 3.4027, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.6286836748532295e-05, + "loss": 3.4033, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.6278467179825508e-05, + "loss": 3.4003, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.6270081232314988e-05, + "loss": 3.3986, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.85964298248291, + "eval_runtime": 304.376, + "eval_samples_per_second": 1253.683, + "eval_steps_per_second": 39.179, + "step": 2060640 + }, + { + "epoch": 1.0, + "learning_rate": 1.6261695284804468e-05, + "loss": 3.3871, + "step": 2060800 + }, + { + "epoch": 1.0, + "learning_rate": 1.6253309337293948e-05, + "loss": 3.3943, + "step": 2061312 + }, + { + "epoch": 1.0, + "learning_rate": 1.6244939768587157e-05, + "loss": 3.3948, + "step": 2061824 + }, + { + "epoch": 1.0, + "learning_rate": 1.623655382107664e-05, + "loss": 3.403, + "step": 2062336 + }, + { + "epoch": 1.0, + "learning_rate": 1.622816787356612e-05, + "loss": 3.4071, + "step": 2062848 + }, + { + "epoch": 1.0, + "learning_rate": 1.621979830485933e-05, + "loss": 3.3979, + "step": 2063360 + }, + { + "epoch": 1.0, + "learning_rate": 1.621141235734881e-05, + "loss": 3.3983, + "step": 2063872 + }, + { + "epoch": 1.0, + "learning_rate": 1.620302640983829e-05, + "loss": 3.3972, + "step": 2064384 + }, + { + "epoch": 1.0, + "learning_rate": 1.619464046232777e-05, + "loss": 3.3983, + "step": 2064896 + }, + { + "epoch": 1.0, + "learning_rate": 1.618627089362098e-05, + "loss": 3.3999, + "step": 2065408 + }, + { + "epoch": 1.0, + "learning_rate": 1.617788494611046e-05, + "loss": 3.3971, + "step": 2065920 + }, + { + "epoch": 1.0, + "learning_rate": 1.616949899859994e-05, + "loss": 3.391, + "step": 2066432 + }, + { + "epoch": 1.0, + "learning_rate": 1.616112942989315e-05, + "loss": 3.4062, + "step": 2066944 + }, + { + "epoch": 1.0, + "learning_rate": 1.615274348238263e-05, + "loss": 3.3895, + "step": 2067456 + }, + { + "epoch": 1.0, + "learning_rate": 1.614435753487211e-05, + "loss": 3.3924, + "step": 2067968 + }, + { + "epoch": 1.0, + "learning_rate": 1.6135971587361594e-05, + "loss": 3.3821, + "step": 2068480 + }, + { + "epoch": 1.0, + "learning_rate": 1.6127585639851074e-05, + "loss": 3.3915, + "step": 2068992 + }, + { + "epoch": 1.0, + "learning_rate": 1.611919969234055e-05, + "loss": 3.3909, + "step": 2069504 + }, + { + "epoch": 1.0, + "learning_rate": 1.611081374483003e-05, + "loss": 3.3828, + "step": 2070016 + }, + { + "epoch": 1.0, + "learning_rate": 1.610242779731951e-05, + "loss": 3.4021, + "step": 2070528 + }, + { + "epoch": 1.0, + "learning_rate": 1.6094058228612723e-05, + "loss": 3.398, + "step": 2071040 + }, + { + "epoch": 1.0, + "learning_rate": 1.6085688659905935e-05, + "loss": 3.3949, + "step": 2071552 + }, + { + "epoch": 1.0, + "learning_rate": 1.6077302712395415e-05, + "loss": 3.3935, + "step": 2072064 + }, + { + "epoch": 1.0, + "learning_rate": 1.6068916764884895e-05, + "loss": 3.3943, + "step": 2072576 + }, + { + "epoch": 1.0, + "learning_rate": 1.6060530817374372e-05, + "loss": 3.4039, + "step": 2073088 + }, + { + "epoch": 1.0, + "learning_rate": 1.605214486986385e-05, + "loss": 3.3966, + "step": 2073600 + }, + { + "epoch": 1.0, + "learning_rate": 1.604375892235333e-05, + "loss": 3.3812, + "step": 2074112 + }, + { + "epoch": 1.0, + "learning_rate": 1.6035372974842815e-05, + "loss": 3.4036, + "step": 2074624 + }, + { + "epoch": 1.0, + "learning_rate": 1.6026987027332295e-05, + "loss": 3.3868, + "step": 2075136 + }, + { + "epoch": 1.0, + "learning_rate": 1.6018617458625504e-05, + "loss": 3.3908, + "step": 2075648 + }, + { + "epoch": 1.01, + "learning_rate": 1.6010231511114984e-05, + "loss": 3.3928, + "step": 2076160 + }, + { + "epoch": 1.01, + "learning_rate": 1.6001845563604464e-05, + "loss": 3.3977, + "step": 2076672 + }, + { + "epoch": 1.01, + "learning_rate": 1.5993459616093944e-05, + "loss": 3.3937, + "step": 2077184 + }, + { + "epoch": 1.01, + "learning_rate": 1.5985090047387156e-05, + "loss": 3.4102, + "step": 2077696 + }, + { + "epoch": 1.01, + "learning_rate": 1.5976704099876636e-05, + "loss": 3.3885, + "step": 2078208 + }, + { + "epoch": 1.01, + "learning_rate": 1.5968318152366116e-05, + "loss": 3.3909, + "step": 2078720 + }, + { + "epoch": 1.01, + "learning_rate": 1.5959932204855596e-05, + "loss": 3.4066, + "step": 2079232 + }, + { + "epoch": 1.01, + "learning_rate": 1.5951562636148805e-05, + "loss": 3.3764, + "step": 2079744 + }, + { + "epoch": 1.01, + "learning_rate": 1.5943176688638285e-05, + "loss": 3.3892, + "step": 2080256 + }, + { + "epoch": 1.01, + "learning_rate": 1.5934790741127765e-05, + "loss": 3.3911, + "step": 2080768 + }, + { + "epoch": 1.01, + "learning_rate": 1.592640479361725e-05, + "loss": 3.3856, + "step": 2081280 + }, + { + "epoch": 1.01, + "learning_rate": 1.5918035224910458e-05, + "loss": 3.3948, + "step": 2081792 + }, + { + "epoch": 1.01, + "learning_rate": 1.5909649277399938e-05, + "loss": 3.3945, + "step": 2082304 + }, + { + "epoch": 1.01, + "learning_rate": 1.5901279708693147e-05, + "loss": 3.3946, + "step": 2082816 + }, + { + "epoch": 1.01, + "learning_rate": 1.589289376118263e-05, + "loss": 3.3929, + "step": 2083328 + }, + { + "epoch": 1.01, + "learning_rate": 1.588450781367211e-05, + "loss": 3.3959, + "step": 2083840 + }, + { + "epoch": 1.01, + "learning_rate": 1.587612186616159e-05, + "loss": 3.384, + "step": 2084352 + }, + { + "epoch": 1.01, + "learning_rate": 1.586773591865107e-05, + "loss": 3.3974, + "step": 2084864 + }, + { + "epoch": 1.01, + "learning_rate": 1.585934997114055e-05, + "loss": 3.3626, + "step": 2085376 + }, + { + "epoch": 1.01, + "learning_rate": 1.5850964023630026e-05, + "loss": 3.3966, + "step": 2085888 + }, + { + "epoch": 1.01, + "learning_rate": 1.5842578076119506e-05, + "loss": 3.3924, + "step": 2086400 + }, + { + "epoch": 1.01, + "learning_rate": 1.583420850741272e-05, + "loss": 3.4003, + "step": 2086912 + }, + { + "epoch": 1.01, + "learning_rate": 1.5825822559902202e-05, + "loss": 3.3865, + "step": 2087424 + }, + { + "epoch": 1.01, + "learning_rate": 1.581743661239168e-05, + "loss": 3.3931, + "step": 2087936 + }, + { + "epoch": 1.01, + "learning_rate": 1.580905066488116e-05, + "loss": 3.3793, + "step": 2088448 + }, + { + "epoch": 1.01, + "learning_rate": 1.580068109617437e-05, + "loss": 3.3844, + "step": 2088960 + }, + { + "epoch": 1.01, + "learning_rate": 1.579229514866385e-05, + "loss": 3.407, + "step": 2089472 + }, + { + "epoch": 1.01, + "learning_rate": 1.578390920115333e-05, + "loss": 3.3783, + "step": 2089984 + }, + { + "epoch": 1.01, + "learning_rate": 1.577552325364281e-05, + "loss": 3.3974, + "step": 2090496 + }, + { + "epoch": 1.01, + "learning_rate": 1.5767170063739753e-05, + "loss": 3.3978, + "step": 2091008 + }, + { + "epoch": 1.01, + "learning_rate": 1.5758784116229233e-05, + "loss": 3.372, + "step": 2091520 + }, + { + "epoch": 1.01, + "learning_rate": 1.5750398168718713e-05, + "loss": 3.4015, + "step": 2092032 + }, + { + "epoch": 1.01, + "learning_rate": 1.5742012221208193e-05, + "loss": 3.3803, + "step": 2092544 + }, + { + "epoch": 1.01, + "learning_rate": 1.5733626273697673e-05, + "loss": 3.3801, + "step": 2093056 + }, + { + "epoch": 1.01, + "learning_rate": 1.5725240326187153e-05, + "loss": 3.3949, + "step": 2093568 + }, + { + "epoch": 1.01, + "learning_rate": 1.5716854378676632e-05, + "loss": 3.3935, + "step": 2094080 + }, + { + "epoch": 1.01, + "learning_rate": 1.5708468431166112e-05, + "loss": 3.3809, + "step": 2094592 + }, + { + "epoch": 1.01, + "learning_rate": 1.5700098862459325e-05, + "loss": 3.3899, + "step": 2095104 + }, + { + "epoch": 1.01, + "learning_rate": 1.56917129149488e-05, + "loss": 3.3767, + "step": 2095616 + }, + { + "epoch": 1.01, + "learning_rate": 1.5683326967438285e-05, + "loss": 3.3934, + "step": 2096128 + }, + { + "epoch": 1.01, + "learning_rate": 1.5674941019927765e-05, + "loss": 3.3966, + "step": 2096640 + }, + { + "epoch": 1.01, + "learning_rate": 1.5666571451220974e-05, + "loss": 3.3924, + "step": 2097152 + }, + { + "epoch": 1.01, + "learning_rate": 1.5658185503710454e-05, + "loss": 3.394, + "step": 2097664 + }, + { + "epoch": 1.01, + "learning_rate": 1.5649799556199934e-05, + "loss": 3.3946, + "step": 2098176 + }, + { + "epoch": 1.01, + "learning_rate": 1.5641413608689414e-05, + "loss": 3.4067, + "step": 2098688 + }, + { + "epoch": 1.01, + "learning_rate": 1.5633044039982626e-05, + "loss": 3.3873, + "step": 2099200 + }, + { + "epoch": 1.01, + "learning_rate": 1.562467447127584e-05, + "loss": 3.399, + "step": 2099712 + }, + { + "epoch": 1.01, + "learning_rate": 1.561628852376532e-05, + "loss": 3.3873, + "step": 2100224 + }, + { + "epoch": 1.01, + "learning_rate": 1.5607902576254795e-05, + "loss": 3.379, + "step": 2100736 + }, + { + "epoch": 1.01, + "learning_rate": 1.5599516628744275e-05, + "loss": 3.3923, + "step": 2101248 + }, + { + "epoch": 1.01, + "learning_rate": 1.5591130681233755e-05, + "loss": 3.3943, + "step": 2101760 + }, + { + "epoch": 1.01, + "learning_rate": 1.558276111252697e-05, + "loss": 3.3926, + "step": 2102272 + }, + { + "epoch": 1.01, + "learning_rate": 1.5574375165016448e-05, + "loss": 3.4067, + "step": 2102784 + }, + { + "epoch": 1.01, + "learning_rate": 1.5565989217505928e-05, + "loss": 3.3767, + "step": 2103296 + }, + { + "epoch": 1.01, + "learning_rate": 1.5557603269995408e-05, + "loss": 3.3858, + "step": 2103808 + }, + { + "epoch": 1.01, + "learning_rate": 1.5549217322484887e-05, + "loss": 3.3907, + "step": 2104320 + }, + { + "epoch": 1.01, + "learning_rate": 1.55408477537781e-05, + "loss": 3.3923, + "step": 2104832 + }, + { + "epoch": 1.01, + "learning_rate": 1.553246180626758e-05, + "loss": 3.3887, + "step": 2105344 + }, + { + "epoch": 1.01, + "learning_rate": 1.552407585875706e-05, + "loss": 3.3852, + "step": 2105856 + }, + { + "epoch": 1.01, + "learning_rate": 1.551568991124654e-05, + "loss": 3.3875, + "step": 2106368 + }, + { + "epoch": 1.02, + "learning_rate": 1.550730396373602e-05, + "loss": 3.3888, + "step": 2106880 + }, + { + "epoch": 1.02, + "learning_rate": 1.54989180162255e-05, + "loss": 3.3918, + "step": 2107392 + }, + { + "epoch": 1.02, + "learning_rate": 1.5490532068714976e-05, + "loss": 3.3868, + "step": 2107904 + }, + { + "epoch": 1.02, + "learning_rate": 1.5482146121204456e-05, + "loss": 3.3986, + "step": 2108416 + }, + { + "epoch": 1.02, + "learning_rate": 1.5473776552497672e-05, + "loss": 3.397, + "step": 2108928 + }, + { + "epoch": 1.02, + "learning_rate": 1.5465390604987152e-05, + "loss": 3.3891, + "step": 2109440 + }, + { + "epoch": 1.02, + "learning_rate": 1.545700465747663e-05, + "loss": 3.3824, + "step": 2109952 + }, + { + "epoch": 1.02, + "learning_rate": 1.544861870996611e-05, + "loss": 3.3915, + "step": 2110464 + }, + { + "epoch": 1.02, + "learning_rate": 1.544024914125932e-05, + "loss": 3.3891, + "step": 2110976 + }, + { + "epoch": 1.02, + "learning_rate": 1.54318631937488e-05, + "loss": 3.3937, + "step": 2111488 + }, + { + "epoch": 1.02, + "learning_rate": 1.542347724623828e-05, + "loss": 3.3852, + "step": 2112000 + }, + { + "epoch": 1.02, + "learning_rate": 1.541509129872776e-05, + "loss": 3.3856, + "step": 2112512 + }, + { + "epoch": 1.02, + "learning_rate": 1.5406721730020973e-05, + "loss": 3.39, + "step": 2113024 + }, + { + "epoch": 1.02, + "learning_rate": 1.5398352161314183e-05, + "loss": 3.3899, + "step": 2113536 + }, + { + "epoch": 1.02, + "learning_rate": 1.5389966213803663e-05, + "loss": 3.3867, + "step": 2114048 + }, + { + "epoch": 1.02, + "learning_rate": 1.5381580266293142e-05, + "loss": 3.3845, + "step": 2114560 + }, + { + "epoch": 1.02, + "learning_rate": 1.5373194318782626e-05, + "loss": 3.3782, + "step": 2115072 + }, + { + "epoch": 1.02, + "learning_rate": 1.5364808371272102e-05, + "loss": 3.3942, + "step": 2115584 + }, + { + "epoch": 1.02, + "learning_rate": 1.5356422423761582e-05, + "loss": 3.3875, + "step": 2116096 + }, + { + "epoch": 1.02, + "learning_rate": 1.5348036476251062e-05, + "loss": 3.378, + "step": 2116608 + }, + { + "epoch": 1.02, + "learning_rate": 1.5339650528740542e-05, + "loss": 3.3754, + "step": 2117120 + }, + { + "epoch": 1.02, + "learning_rate": 1.5331280960033755e-05, + "loss": 3.3911, + "step": 2117632 + }, + { + "epoch": 1.02, + "learning_rate": 1.5322895012523235e-05, + "loss": 3.3922, + "step": 2118144 + }, + { + "epoch": 1.02, + "learning_rate": 1.5314509065012715e-05, + "loss": 3.3799, + "step": 2118656 + }, + { + "epoch": 1.02, + "learning_rate": 1.5306123117502195e-05, + "loss": 3.3941, + "step": 2119168 + }, + { + "epoch": 1.02, + "learning_rate": 1.5297753548795404e-05, + "loss": 3.4051, + "step": 2119680 + }, + { + "epoch": 1.02, + "learning_rate": 1.5289367601284884e-05, + "loss": 3.3923, + "step": 2120192 + }, + { + "epoch": 1.02, + "learning_rate": 1.5280981653774364e-05, + "loss": 3.3871, + "step": 2120704 + }, + { + "epoch": 1.02, + "learning_rate": 1.5272612085067576e-05, + "loss": 3.3869, + "step": 2121216 + }, + { + "epoch": 1.02, + "learning_rate": 1.5264226137557056e-05, + "loss": 3.3884, + "step": 2121728 + }, + { + "epoch": 1.02, + "learning_rate": 1.5255840190046536e-05, + "loss": 3.3946, + "step": 2122240 + }, + { + "epoch": 1.02, + "learning_rate": 1.5247454242536016e-05, + "loss": 3.3789, + "step": 2122752 + }, + { + "epoch": 1.02, + "learning_rate": 1.5239068295025496e-05, + "loss": 3.3794, + "step": 2123264 + }, + { + "epoch": 1.02, + "learning_rate": 1.5230682347514978e-05, + "loss": 3.3892, + "step": 2123776 + }, + { + "epoch": 1.02, + "learning_rate": 1.5222312778808187e-05, + "loss": 3.386, + "step": 2124288 + }, + { + "epoch": 1.02, + "learning_rate": 1.5213926831297667e-05, + "loss": 3.3922, + "step": 2124800 + }, + { + "epoch": 1.02, + "learning_rate": 1.5205540883787148e-05, + "loss": 3.3901, + "step": 2125312 + }, + { + "epoch": 1.02, + "learning_rate": 1.5197154936276628e-05, + "loss": 3.3801, + "step": 2125824 + }, + { + "epoch": 1.02, + "learning_rate": 1.5188768988766105e-05, + "loss": 3.3861, + "step": 2126336 + }, + { + "epoch": 1.02, + "learning_rate": 1.5180383041255586e-05, + "loss": 3.3998, + "step": 2126848 + }, + { + "epoch": 1.02, + "learning_rate": 1.5171997093745066e-05, + "loss": 3.3855, + "step": 2127360 + }, + { + "epoch": 1.02, + "learning_rate": 1.5163611146234546e-05, + "loss": 3.3974, + "step": 2127872 + }, + { + "epoch": 1.02, + "learning_rate": 1.5155241577527757e-05, + "loss": 3.3809, + "step": 2128384 + }, + { + "epoch": 1.02, + "learning_rate": 1.5146855630017237e-05, + "loss": 3.3931, + "step": 2128896 + }, + { + "epoch": 1.02, + "learning_rate": 1.5138469682506717e-05, + "loss": 3.3937, + "step": 2129408 + }, + { + "epoch": 1.02, + "learning_rate": 1.5130083734996197e-05, + "loss": 3.3901, + "step": 2129920 + }, + { + "epoch": 1.02, + "learning_rate": 1.5121714166289408e-05, + "loss": 3.3915, + "step": 2130432 + }, + { + "epoch": 1.02, + "learning_rate": 1.5113328218778888e-05, + "loss": 3.386, + "step": 2130944 + }, + { + "epoch": 1.02, + "learning_rate": 1.510494227126837e-05, + "loss": 3.3907, + "step": 2131456 + }, + { + "epoch": 1.02, + "learning_rate": 1.509655632375785e-05, + "loss": 3.4025, + "step": 2131968 + }, + { + "epoch": 1.02, + "learning_rate": 1.5088186755051058e-05, + "loss": 3.388, + "step": 2132480 + }, + { + "epoch": 1.02, + "learning_rate": 1.507980080754054e-05, + "loss": 3.3901, + "step": 2132992 + }, + { + "epoch": 1.02, + "learning_rate": 1.507141486003002e-05, + "loss": 3.3971, + "step": 2133504 + }, + { + "epoch": 1.02, + "learning_rate": 1.50630289125195e-05, + "loss": 3.3826, + "step": 2134016 + }, + { + "epoch": 1.02, + "learning_rate": 1.505465934381271e-05, + "loss": 3.3858, + "step": 2134528 + }, + { + "epoch": 1.02, + "learning_rate": 1.504627339630219e-05, + "loss": 3.3978, + "step": 2135040 + }, + { + "epoch": 1.02, + "learning_rate": 1.503788744879167e-05, + "loss": 3.3888, + "step": 2135552 + }, + { + "epoch": 1.02, + "learning_rate": 1.502950150128115e-05, + "loss": 3.3906, + "step": 2136064 + }, + { + "epoch": 1.02, + "learning_rate": 1.5021148311378094e-05, + "loss": 3.3896, + "step": 2136576 + }, + { + "epoch": 1.03, + "eval_loss": 3.8617653846740723, + "eval_runtime": 304.2419, + "eval_samples_per_second": 1254.236, + "eval_steps_per_second": 39.196, + "step": 2136960 + }, + { + "epoch": 0.0, + "learning_rate": 1.5012762363867574e-05, + "loss": 3.3899, + "step": 2137088 + }, + { + "epoch": 0.0, + "learning_rate": 1.5004376416357052e-05, + "loss": 3.3801, + "step": 2137600 + }, + { + "epoch": 0.0, + "learning_rate": 1.4995990468846532e-05, + "loss": 3.3857, + "step": 2138112 + }, + { + "epoch": 0.0, + "learning_rate": 1.4987604521336012e-05, + "loss": 3.3953, + "step": 2138624 + }, + { + "epoch": 0.0, + "learning_rate": 1.4979234952629226e-05, + "loss": 3.3909, + "step": 2139136 + }, + { + "epoch": 0.0, + "learning_rate": 1.4970849005118703e-05, + "loss": 3.39, + "step": 2139648 + }, + { + "epoch": 0.0, + "learning_rate": 1.4962463057608185e-05, + "loss": 3.3901, + "step": 2140160 + }, + { + "epoch": 0.0, + "learning_rate": 1.4954077110097664e-05, + "loss": 3.3867, + "step": 2140672 + }, + { + "epoch": 0.0, + "learning_rate": 1.4945707541390874e-05, + "loss": 3.3854, + "step": 2141184 + }, + { + "epoch": 0.0, + "learning_rate": 1.4937321593880355e-05, + "loss": 3.3902, + "step": 2141696 + }, + { + "epoch": 0.0, + "learning_rate": 1.4928935646369835e-05, + "loss": 3.3904, + "step": 2142208 + }, + { + "epoch": 0.0, + "learning_rate": 1.4920549698859315e-05, + "loss": 3.3771, + "step": 2142720 + }, + { + "epoch": 0.0, + "learning_rate": 1.4912196508956258e-05, + "loss": 3.3984, + "step": 2143232 + }, + { + "epoch": 0.0, + "learning_rate": 1.4903810561445738e-05, + "loss": 3.3799, + "step": 2143744 + }, + { + "epoch": 0.0, + "learning_rate": 1.4895424613935218e-05, + "loss": 3.3793, + "step": 2144256 + }, + { + "epoch": 0.0, + "learning_rate": 1.4887038666424698e-05, + "loss": 3.3754, + "step": 2144768 + }, + { + "epoch": 0.0, + "learning_rate": 1.4878652718914177e-05, + "loss": 3.381, + "step": 2145280 + }, + { + "epoch": 0.0, + "learning_rate": 1.4870266771403657e-05, + "loss": 3.3786, + "step": 2145792 + }, + { + "epoch": 0.0, + "learning_rate": 1.4861880823893136e-05, + "loss": 3.3751, + "step": 2146304 + }, + { + "epoch": 0.0, + "learning_rate": 1.4853494876382618e-05, + "loss": 3.3864, + "step": 2146816 + }, + { + "epoch": 0.0, + "learning_rate": 1.4845125307675827e-05, + "loss": 3.3949, + "step": 2147328 + }, + { + "epoch": 0.0, + "learning_rate": 1.4836755738969041e-05, + "loss": 3.3857, + "step": 2147840 + }, + { + "epoch": 0.0, + "learning_rate": 1.4828369791458521e-05, + "loss": 3.3804, + "step": 2148352 + }, + { + "epoch": 0.0, + "learning_rate": 1.4819983843947998e-05, + "loss": 3.3873, + "step": 2148864 + }, + { + "epoch": 0.0, + "learning_rate": 1.481159789643748e-05, + "loss": 3.3946, + "step": 2149376 + }, + { + "epoch": 0.0, + "learning_rate": 1.480321194892696e-05, + "loss": 3.3816, + "step": 2149888 + }, + { + "epoch": 0.0, + "learning_rate": 1.479482600141644e-05, + "loss": 3.3761, + "step": 2150400 + }, + { + "epoch": 0.0, + "learning_rate": 1.478644005390592e-05, + "loss": 3.3939, + "step": 2150912 + }, + { + "epoch": 0.0, + "learning_rate": 1.4778054106395401e-05, + "loss": 3.3788, + "step": 2151424 + }, + { + "epoch": 0.0, + "learning_rate": 1.476968453768861e-05, + "loss": 3.3778, + "step": 2151936 + }, + { + "epoch": 0.01, + "learning_rate": 1.476129859017809e-05, + "loss": 3.382, + "step": 2152448 + }, + { + "epoch": 0.01, + "learning_rate": 1.4752912642667572e-05, + "loss": 3.3862, + "step": 2152960 + }, + { + "epoch": 0.01, + "learning_rate": 1.4744526695157052e-05, + "loss": 3.3853, + "step": 2153472 + }, + { + "epoch": 0.01, + "learning_rate": 1.4736140747646528e-05, + "loss": 3.4005, + "step": 2153984 + }, + { + "epoch": 0.01, + "learning_rate": 1.472775480013601e-05, + "loss": 3.3752, + "step": 2154496 + }, + { + "epoch": 0.01, + "learning_rate": 1.471936885262549e-05, + "loss": 3.3878, + "step": 2155008 + }, + { + "epoch": 0.01, + "learning_rate": 1.4710999283918702e-05, + "loss": 3.3916, + "step": 2155520 + }, + { + "epoch": 0.01, + "learning_rate": 1.470261333640818e-05, + "loss": 3.3656, + "step": 2156032 + }, + { + "epoch": 0.01, + "learning_rate": 1.469422738889766e-05, + "loss": 3.3819, + "step": 2156544 + }, + { + "epoch": 0.01, + "learning_rate": 1.468584144138714e-05, + "loss": 3.3833, + "step": 2157056 + }, + { + "epoch": 0.01, + "learning_rate": 1.4677471872680355e-05, + "loss": 3.3707, + "step": 2157568 + }, + { + "epoch": 0.01, + "learning_rate": 1.4669085925169831e-05, + "loss": 3.3899, + "step": 2158080 + }, + { + "epoch": 0.01, + "learning_rate": 1.4660699977659311e-05, + "loss": 3.382, + "step": 2158592 + }, + { + "epoch": 0.01, + "learning_rate": 1.4652330408952525e-05, + "loss": 3.3882, + "step": 2159104 + }, + { + "epoch": 0.01, + "learning_rate": 1.4643944461442002e-05, + "loss": 3.381, + "step": 2159616 + }, + { + "epoch": 0.01, + "learning_rate": 1.4635558513931482e-05, + "loss": 3.3859, + "step": 2160128 + }, + { + "epoch": 0.01, + "learning_rate": 1.4627172566420964e-05, + "loss": 3.3719, + "step": 2160640 + }, + { + "epoch": 0.01, + "learning_rate": 1.4618786618910444e-05, + "loss": 3.3897, + "step": 2161152 + }, + { + "epoch": 0.01, + "learning_rate": 1.4610400671399924e-05, + "loss": 3.3546, + "step": 2161664 + }, + { + "epoch": 0.01, + "learning_rate": 1.4602014723889404e-05, + "loss": 3.3857, + "step": 2162176 + }, + { + "epoch": 0.01, + "learning_rate": 1.4593628776378883e-05, + "loss": 3.3806, + "step": 2162688 + }, + { + "epoch": 0.01, + "learning_rate": 1.4585259207672094e-05, + "loss": 3.3898, + "step": 2163200 + }, + { + "epoch": 0.01, + "learning_rate": 1.4576873260161574e-05, + "loss": 3.3753, + "step": 2163712 + }, + { + "epoch": 0.01, + "learning_rate": 1.4568487312651056e-05, + "loss": 3.3789, + "step": 2164224 + }, + { + "epoch": 0.01, + "learning_rate": 1.4560101365140536e-05, + "loss": 3.3736, + "step": 2164736 + }, + { + "epoch": 0.01, + "learning_rate": 1.4551731796433745e-05, + "loss": 3.3733, + "step": 2165248 + }, + { + "epoch": 0.01, + "learning_rate": 1.4543362227726956e-05, + "loss": 3.3969, + "step": 2165760 + }, + { + "epoch": 0.01, + "learning_rate": 1.4534976280216436e-05, + "loss": 3.366, + "step": 2166272 + }, + { + "epoch": 0.01, + "learning_rate": 1.4526590332705917e-05, + "loss": 3.392, + "step": 2166784 + }, + { + "epoch": 0.01, + "learning_rate": 1.4518204385195397e-05, + "loss": 3.3879, + "step": 2167296 + }, + { + "epoch": 0.01, + "learning_rate": 1.4509818437684877e-05, + "loss": 3.3643, + "step": 2167808 + }, + { + "epoch": 0.01, + "learning_rate": 1.4501432490174357e-05, + "loss": 3.39, + "step": 2168320 + }, + { + "epoch": 0.01, + "learning_rate": 1.4493046542663835e-05, + "loss": 3.3682, + "step": 2168832 + }, + { + "epoch": 0.01, + "learning_rate": 1.4484660595153315e-05, + "loss": 3.373, + "step": 2169344 + }, + { + "epoch": 0.01, + "learning_rate": 1.4476291026446528e-05, + "loss": 3.3827, + "step": 2169856 + }, + { + "epoch": 0.01, + "learning_rate": 1.446790507893601e-05, + "loss": 3.3846, + "step": 2170368 + }, + { + "epoch": 0.01, + "learning_rate": 1.4459519131425486e-05, + "loss": 3.3691, + "step": 2170880 + }, + { + "epoch": 0.01, + "learning_rate": 1.4451133183914966e-05, + "loss": 3.3835, + "step": 2171392 + }, + { + "epoch": 0.01, + "learning_rate": 1.444276361520818e-05, + "loss": 3.3669, + "step": 2171904 + }, + { + "epoch": 0.01, + "learning_rate": 1.4434377667697657e-05, + "loss": 3.3793, + "step": 2172416 + }, + { + "epoch": 0.01, + "learning_rate": 1.4425991720187137e-05, + "loss": 3.3908, + "step": 2172928 + }, + { + "epoch": 0.01, + "learning_rate": 1.4417605772676618e-05, + "loss": 3.3818, + "step": 2173440 + }, + { + "epoch": 0.01, + "learning_rate": 1.4409236203969831e-05, + "loss": 3.3854, + "step": 2173952 + }, + { + "epoch": 0.01, + "learning_rate": 1.4400850256459309e-05, + "loss": 3.3829, + "step": 2174464 + }, + { + "epoch": 0.01, + "learning_rate": 1.4392464308948789e-05, + "loss": 3.3946, + "step": 2174976 + }, + { + "epoch": 0.01, + "learning_rate": 1.4384078361438269e-05, + "loss": 3.3798, + "step": 2175488 + }, + { + "epoch": 0.01, + "learning_rate": 1.4375725171535212e-05, + "loss": 3.387, + "step": 2176000 + }, + { + "epoch": 0.01, + "learning_rate": 1.4367339224024692e-05, + "loss": 3.3798, + "step": 2176512 + }, + { + "epoch": 0.01, + "learning_rate": 1.4358953276514172e-05, + "loss": 3.3674, + "step": 2177024 + }, + { + "epoch": 0.01, + "learning_rate": 1.4350567329003652e-05, + "loss": 3.3825, + "step": 2177536 + }, + { + "epoch": 0.01, + "learning_rate": 1.434218138149313e-05, + "loss": 3.3852, + "step": 2178048 + }, + { + "epoch": 0.01, + "learning_rate": 1.4333811812786343e-05, + "loss": 3.3848, + "step": 2178560 + }, + { + "epoch": 0.01, + "learning_rate": 1.4325425865275825e-05, + "loss": 3.3955, + "step": 2179072 + }, + { + "epoch": 0.01, + "learning_rate": 1.4317039917765305e-05, + "loss": 3.3717, + "step": 2179584 + }, + { + "epoch": 0.01, + "learning_rate": 1.4308653970254781e-05, + "loss": 3.3737, + "step": 2180096 + }, + { + "epoch": 0.01, + "learning_rate": 1.4300268022744263e-05, + "loss": 3.3771, + "step": 2180608 + }, + { + "epoch": 0.01, + "learning_rate": 1.4291898454037475e-05, + "loss": 3.3888, + "step": 2181120 + }, + { + "epoch": 0.01, + "learning_rate": 1.4283512506526952e-05, + "loss": 3.3764, + "step": 2181632 + }, + { + "epoch": 0.01, + "learning_rate": 1.4275126559016434e-05, + "loss": 3.3755, + "step": 2182144 + }, + { + "epoch": 0.01, + "learning_rate": 1.4266740611505913e-05, + "loss": 3.3785, + "step": 2182656 + }, + { + "epoch": 0.02, + "learning_rate": 1.4258354663995393e-05, + "loss": 3.3777, + "step": 2183168 + }, + { + "epoch": 0.02, + "learning_rate": 1.4249968716484873e-05, + "loss": 3.3802, + "step": 2183680 + }, + { + "epoch": 0.02, + "learning_rate": 1.4241582768974353e-05, + "loss": 3.3764, + "step": 2184192 + }, + { + "epoch": 0.02, + "learning_rate": 1.4233196821463835e-05, + "loss": 3.3892, + "step": 2184704 + }, + { + "epoch": 0.02, + "learning_rate": 1.4224827252757044e-05, + "loss": 3.3878, + "step": 2185216 + }, + { + "epoch": 0.02, + "learning_rate": 1.4216441305246526e-05, + "loss": 3.3827, + "step": 2185728 + }, + { + "epoch": 0.02, + "learning_rate": 1.4208055357736006e-05, + "loss": 3.3713, + "step": 2186240 + }, + { + "epoch": 0.02, + "learning_rate": 1.4199669410225486e-05, + "loss": 3.3783, + "step": 2186752 + }, + { + "epoch": 0.02, + "learning_rate": 1.4191299841518696e-05, + "loss": 3.3772, + "step": 2187264 + }, + { + "epoch": 0.02, + "learning_rate": 1.4182913894008176e-05, + "loss": 3.3885, + "step": 2187776 + }, + { + "epoch": 0.02, + "learning_rate": 1.4174527946497656e-05, + "loss": 3.3748, + "step": 2188288 + }, + { + "epoch": 0.02, + "learning_rate": 1.4166141998987135e-05, + "loss": 3.3774, + "step": 2188800 + }, + { + "epoch": 0.02, + "learning_rate": 1.4157772430280347e-05, + "loss": 3.3804, + "step": 2189312 + }, + { + "epoch": 0.02, + "learning_rate": 1.4149402861573558e-05, + "loss": 3.3771, + "step": 2189824 + }, + { + "epoch": 0.02, + "learning_rate": 1.4141016914063038e-05, + "loss": 3.3787, + "step": 2190336 + }, + { + "epoch": 0.02, + "learning_rate": 1.4132630966552518e-05, + "loss": 3.3791, + "step": 2190848 + }, + { + "epoch": 0.02, + "learning_rate": 1.4124245019041998e-05, + "loss": 3.3652, + "step": 2191360 + }, + { + "epoch": 0.02, + "learning_rate": 1.411585907153148e-05, + "loss": 3.3858, + "step": 2191872 + }, + { + "epoch": 0.02, + "learning_rate": 1.410747312402096e-05, + "loss": 3.3751, + "step": 2192384 + }, + { + "epoch": 0.02, + "learning_rate": 1.4099087176510436e-05, + "loss": 3.3711, + "step": 2192896 + }, + { + "epoch": 0.02, + "learning_rate": 1.4090701228999918e-05, + "loss": 3.3653, + "step": 2193408 + }, + { + "epoch": 0.02, + "learning_rate": 1.408233166029313e-05, + "loss": 3.3798, + "step": 2193920 + }, + { + "epoch": 0.02, + "learning_rate": 1.4073945712782607e-05, + "loss": 3.3867, + "step": 2194432 + }, + { + "epoch": 0.02, + "learning_rate": 1.4065559765272088e-05, + "loss": 3.3688, + "step": 2194944 + }, + { + "epoch": 0.02, + "learning_rate": 1.4057173817761568e-05, + "loss": 3.3835, + "step": 2195456 + }, + { + "epoch": 0.02, + "learning_rate": 1.404880424905478e-05, + "loss": 3.3897, + "step": 2195968 + }, + { + "epoch": 0.02, + "learning_rate": 1.4040418301544259e-05, + "loss": 3.3908, + "step": 2196480 + }, + { + "epoch": 0.02, + "learning_rate": 1.4032032354033739e-05, + "loss": 3.3775, + "step": 2196992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4023646406523219e-05, + "loss": 3.3742, + "step": 2197504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4015276837816433e-05, + "loss": 3.374, + "step": 2198016 + }, + { + "epoch": 0.02, + "learning_rate": 1.400689089030591e-05, + "loss": 3.3855, + "step": 2198528 + }, + { + "epoch": 0.02, + "learning_rate": 1.399850494279539e-05, + "loss": 3.3676, + "step": 2199040 + }, + { + "epoch": 0.02, + "learning_rate": 1.3990118995284871e-05, + "loss": 3.3721, + "step": 2199552 + }, + { + "epoch": 0.02, + "learning_rate": 1.3981733047774351e-05, + "loss": 3.3716, + "step": 2200064 + }, + { + "epoch": 0.02, + "learning_rate": 1.3973347100263831e-05, + "loss": 3.3806, + "step": 2200576 + }, + { + "epoch": 0.02, + "learning_rate": 1.3964977531557042e-05, + "loss": 3.3809, + "step": 2201088 + }, + { + "epoch": 0.02, + "learning_rate": 1.3956591584046522e-05, + "loss": 3.3828, + "step": 2201600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3948205636536002e-05, + "loss": 3.3684, + "step": 2202112 + }, + { + "epoch": 0.02, + "learning_rate": 1.3939819689025482e-05, + "loss": 3.3767, + "step": 2202624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3931433741514963e-05, + "loss": 3.3929, + "step": 2203136 + }, + { + "epoch": 0.02, + "learning_rate": 1.392304779400444e-05, + "loss": 3.3739, + "step": 2203648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3914678225297653e-05, + "loss": 3.3901, + "step": 2204160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3906292277787134e-05, + "loss": 3.3662, + "step": 2204672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3897906330276614e-05, + "loss": 3.3874, + "step": 2205184 + }, + { + "epoch": 0.02, + "learning_rate": 1.388952038276609e-05, + "loss": 3.3828, + "step": 2205696 + }, + { + "epoch": 0.02, + "learning_rate": 1.3881134435255572e-05, + "loss": 3.3802, + "step": 2206208 + }, + { + "epoch": 0.02, + "learning_rate": 1.3872748487745052e-05, + "loss": 3.3813, + "step": 2206720 + }, + { + "epoch": 0.02, + "learning_rate": 1.3864362540234532e-05, + "loss": 3.3735, + "step": 2207232 + }, + { + "epoch": 0.02, + "learning_rate": 1.3855976592724012e-05, + "loss": 3.3885, + "step": 2207744 + }, + { + "epoch": 0.02, + "learning_rate": 1.3847607024017223e-05, + "loss": 3.3906, + "step": 2208256 + }, + { + "epoch": 0.02, + "learning_rate": 1.3839221076506703e-05, + "loss": 3.3787, + "step": 2208768 + }, + { + "epoch": 0.02, + "learning_rate": 1.3830835128996183e-05, + "loss": 3.38, + "step": 2209280 + }, + { + "epoch": 0.02, + "learning_rate": 1.3822449181485665e-05, + "loss": 3.3846, + "step": 2209792 + }, + { + "epoch": 0.02, + "learning_rate": 1.3814079612778874e-05, + "loss": 3.3736, + "step": 2210304 + }, + { + "epoch": 0.02, + "learning_rate": 1.3805693665268354e-05, + "loss": 3.3753, + "step": 2210816 + }, + { + "epoch": 0.02, + "learning_rate": 1.3797307717757835e-05, + "loss": 3.3915, + "step": 2211328 + }, + { + "epoch": 0.02, + "learning_rate": 1.3788921770247315e-05, + "loss": 3.3793, + "step": 2211840 + }, + { + "epoch": 0.02, + "learning_rate": 1.3780552201540526e-05, + "loss": 3.381, + "step": 2212352 + }, + { + "epoch": 0.02, + "learning_rate": 1.3772182632833735e-05, + "loss": 3.376, + "step": 2212864 + }, + { + "epoch": 0.03, + "eval_loss": 3.8634135723114014, + "eval_runtime": 314.4878, + "eval_samples_per_second": 1213.373, + "eval_steps_per_second": 37.919, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3763796685323215e-05, + "loss": 3.3827, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3755410737812697e-05, + "loss": 3.371, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3747024790302177e-05, + "loss": 3.3744, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3738638842791657e-05, + "loss": 3.3844, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3730269274084867e-05, + "loss": 3.3819, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3721883326574347e-05, + "loss": 3.3807, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3713497379063827e-05, + "loss": 3.378, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3705111431553307e-05, + "loss": 3.3789, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3696741862846518e-05, + "loss": 3.3734, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3688355915335998e-05, + "loss": 3.3856, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.367996996782548e-05, + "loss": 3.3748, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.367158402031496e-05, + "loss": 3.3724, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3663230830411903e-05, + "loss": 3.3896, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3654844882901383e-05, + "loss": 3.367, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.364645893539086e-05, + "loss": 3.3717, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3638072987880341e-05, + "loss": 3.3647, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3629687040369821e-05, + "loss": 3.3727, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3621301092859301e-05, + "loss": 3.3671, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3612915145348781e-05, + "loss": 3.3688, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3604529197838261e-05, + "loss": 3.3741, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3596159629131472e-05, + "loss": 3.3871, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3587790060424683e-05, + "loss": 3.3763, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3579404112914162e-05, + "loss": 3.3706, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3571018165403642e-05, + "loss": 3.3792, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3562632217893122e-05, + "loss": 3.3878, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3554246270382604e-05, + "loss": 3.3701, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3545860322872084e-05, + "loss": 3.3659, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3537474375361564e-05, + "loss": 3.384, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3529088427851042e-05, + "loss": 3.3671, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3520718859144255e-05, + "loss": 3.3691, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3512332911633735e-05, + "loss": 3.3732, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3503946964123213e-05, + "loss": 3.3702, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3495561016612693e-05, + "loss": 3.3824, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3487191447905905e-05, + "loss": 3.385, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3478805500395385e-05, + "loss": 3.37, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3470419552884864e-05, + "loss": 3.373, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3462033605374344e-05, + "loss": 3.3829, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3453664036667558e-05, + "loss": 3.358, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3445278089157038e-05, + "loss": 3.3788, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3436892141646514e-05, + "loss": 3.3676, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3428506194135996e-05, + "loss": 3.3608, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3420136625429208e-05, + "loss": 3.3773, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3411750677918687e-05, + "loss": 3.3768, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3403381109211899e-05, + "loss": 3.3754, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3394995161701379e-05, + "loss": 3.3704, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3386609214190859e-05, + "loss": 3.3741, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3378223266680337e-05, + "loss": 3.3676, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3369837319169817e-05, + "loss": 3.3748, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3361451371659297e-05, + "loss": 3.3504, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3353065424148777e-05, + "loss": 3.373, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3344679476638259e-05, + "loss": 3.3723, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3336309907931468e-05, + "loss": 3.3809, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.332792396042095e-05, + "loss": 3.3679, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.331953801291043e-05, + "loss": 3.3675, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.331115206539991e-05, + "loss": 3.3611, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.330278249669312e-05, + "loss": 3.3654, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.32943965491826e-05, + "loss": 3.3836, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.328601060167208e-05, + "loss": 3.3544, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.327762465416156e-05, + "loss": 3.3849, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3269255085454771e-05, + "loss": 3.3751, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3260885516747983e-05, + "loss": 3.3581, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3252499569237462e-05, + "loss": 3.3798, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3244113621726942e-05, + "loss": 3.3573, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3235727674216422e-05, + "loss": 3.3603, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3227341726705903e-05, + "loss": 3.372, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3218955779195383e-05, + "loss": 3.3761, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3210569831684863e-05, + "loss": 3.3573, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3202200262978074e-05, + "loss": 3.3769, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3193814315467554e-05, + "loss": 3.3554, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3185428367957034e-05, + "loss": 3.3668, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3177042420446514e-05, + "loss": 3.3823, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3168672851739725e-05, + "loss": 3.3709, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3160286904229205e-05, + "loss": 3.3742, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3151900956718684e-05, + "loss": 3.3746, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3143515009208166e-05, + "loss": 3.3873, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3135145440501375e-05, + "loss": 3.3696, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3126759492990857e-05, + "loss": 3.3804, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3118389924284066e-05, + "loss": 3.364, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3110003976773546e-05, + "loss": 3.3597, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3101618029263028e-05, + "loss": 3.3726, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3093232081752508e-05, + "loss": 3.3709, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3084862513045718e-05, + "loss": 3.3746, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3076476565535198e-05, + "loss": 3.3857, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3068090618024678e-05, + "loss": 3.3681, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3059704670514158e-05, + "loss": 3.3603, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3051318723003636e-05, + "loss": 3.3651, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3042949154296849e-05, + "loss": 3.3794, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3034563206786329e-05, + "loss": 3.3682, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3026177259275809e-05, + "loss": 3.3651, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3017791311765287e-05, + "loss": 3.3688, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3009405364254767e-05, + "loss": 3.3662, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3001019416744247e-05, + "loss": 3.3733, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2992633469233729e-05, + "loss": 3.3679, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2984263900526938e-05, + "loss": 3.3786, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.297587795301642e-05, + "loss": 3.3819, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.29674920055059e-05, + "loss": 3.3692, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.295910605799538e-05, + "loss": 3.3634, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.295072011048486e-05, + "loss": 3.3676, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.294233416297434e-05, + "loss": 3.3706, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2933948215463817e-05, + "loss": 3.3765, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2925562267953297e-05, + "loss": 3.366, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2917192699246512e-05, + "loss": 3.366, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2908806751735992e-05, + "loss": 3.3728, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2900420804225468e-05, + "loss": 3.3692, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2892051235518682e-05, + "loss": 3.3678, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2883665288008162e-05, + "loss": 3.3679, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2875279340497642e-05, + "loss": 3.3582, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.286689339298712e-05, + "loss": 3.3747, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.28585074454766e-05, + "loss": 3.3699, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.285012149796608e-05, + "loss": 3.3565, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.284173555045556e-05, + "loss": 3.355, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2833365981748771e-05, + "loss": 3.3674, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2824980034238251e-05, + "loss": 3.3771, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2816594086727731e-05, + "loss": 3.3621, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2808208139217213e-05, + "loss": 3.3711, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2799838570510422e-05, + "loss": 3.3762, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2791452622999903e-05, + "loss": 3.382, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2783066675489383e-05, + "loss": 3.3706, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2774680727978863e-05, + "loss": 3.3626, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2766311159272074e-05, + "loss": 3.3688, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2757925211761554e-05, + "loss": 3.376, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2749539264251034e-05, + "loss": 3.3569, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2741153316740514e-05, + "loss": 3.3649, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2732767369229994e-05, + "loss": 3.3645, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2724397800523205e-05, + "loss": 3.3685, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2716011853012685e-05, + "loss": 3.3697, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2707625905502166e-05, + "loss": 3.3774, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2699239957991646e-05, + "loss": 3.358, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2690854010481123e-05, + "loss": 3.368, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2682468062970605e-05, + "loss": 3.3841, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2674082115460085e-05, + "loss": 3.368, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2665712546753297e-05, + "loss": 3.3791, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2657326599242775e-05, + "loss": 3.3571, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2648940651732255e-05, + "loss": 3.3747, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2640554704221735e-05, + "loss": 3.3768, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2632168756711215e-05, + "loss": 3.3733, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2623782809200697e-05, + "loss": 3.3666, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2615396861690177e-05, + "loss": 3.3665, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2607010914179653e-05, + "loss": 3.3823, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2598641345472867e-05, + "loss": 3.3747, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2590255397962347e-05, + "loss": 3.3756, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2581869450451827e-05, + "loss": 3.368, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2573483502941306e-05, + "loss": 3.3761, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2565113934234518e-05, + "loss": 3.3673, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2556727986723998e-05, + "loss": 3.3613, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2548342039213478e-05, + "loss": 3.3829, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2539956091702956e-05, + "loss": 3.3666, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2531586522996169e-05, + "loss": 3.3778, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.252321695428938e-05, + "loss": 3.3626, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.8645238876342773, + "eval_runtime": 302.1686, + "eval_samples_per_second": 1262.841, + "eval_steps_per_second": 39.465, + "step": 2289600 + }, + { + "epoch": 0.0, + "learning_rate": 1.251483100677886e-05, + "loss": 3.3553, + "step": 2289664 + }, + { + "epoch": 0.0, + "learning_rate": 1.250644505926834e-05, + "loss": 3.3647, + "step": 2290176 + }, + { + "epoch": 0.0, + "learning_rate": 1.249805911175782e-05, + "loss": 3.365, + "step": 2290688 + }, + { + "epoch": 0.0, + "learning_rate": 1.24896731642473e-05, + "loss": 3.3715, + "step": 2291200 + }, + { + "epoch": 0.0, + "learning_rate": 1.2481303595540512e-05, + "loss": 3.3742, + "step": 2291712 + }, + { + "epoch": 0.0, + "learning_rate": 1.2472917648029992e-05, + "loss": 3.369, + "step": 2292224 + }, + { + "epoch": 0.0, + "learning_rate": 1.246453170051947e-05, + "loss": 3.3655, + "step": 2292736 + }, + { + "epoch": 0.0, + "learning_rate": 1.245614575300895e-05, + "loss": 3.3664, + "step": 2293248 + }, + { + "epoch": 0.0, + "learning_rate": 1.2447776184302163e-05, + "loss": 3.3688, + "step": 2293760 + }, + { + "epoch": 0.0, + "learning_rate": 1.243939023679164e-05, + "loss": 3.3764, + "step": 2294272 + }, + { + "epoch": 0.0, + "learning_rate": 1.243100428928112e-05, + "loss": 3.3645, + "step": 2294784 + }, + { + "epoch": 0.0, + "learning_rate": 1.2422618341770602e-05, + "loss": 3.3639, + "step": 2295296 + }, + { + "epoch": 0.0, + "learning_rate": 1.2414265151867544e-05, + "loss": 3.3795, + "step": 2295808 + }, + { + "epoch": 0.0, + "learning_rate": 1.2405879204357024e-05, + "loss": 3.3574, + "step": 2296320 + }, + { + "epoch": 0.0, + "learning_rate": 1.2397493256846504e-05, + "loss": 3.3606, + "step": 2296832 + }, + { + "epoch": 0.0, + "learning_rate": 1.2389107309335984e-05, + "loss": 3.3607, + "step": 2297344 + }, + { + "epoch": 0.0, + "learning_rate": 1.2380721361825464e-05, + "loss": 3.3653, + "step": 2297856 + }, + { + "epoch": 0.0, + "learning_rate": 1.2372335414314944e-05, + "loss": 3.3536, + "step": 2298368 + }, + { + "epoch": 0.0, + "learning_rate": 1.2363949466804424e-05, + "loss": 3.3582, + "step": 2298880 + }, + { + "epoch": 0.0, + "learning_rate": 1.2355563519293904e-05, + "loss": 3.3668, + "step": 2299392 + }, + { + "epoch": 0.0, + "learning_rate": 1.2347193950587115e-05, + "loss": 3.3729, + "step": 2299904 + }, + { + "epoch": 0.0, + "learning_rate": 1.2338824381880327e-05, + "loss": 3.3677, + "step": 2300416 + }, + { + "epoch": 0.0, + "learning_rate": 1.2330438434369807e-05, + "loss": 3.3581, + "step": 2300928 + }, + { + "epoch": 0.0, + "learning_rate": 1.2322052486859287e-05, + "loss": 3.3713, + "step": 2301440 + }, + { + "epoch": 0.0, + "learning_rate": 1.2313666539348765e-05, + "loss": 3.3786, + "step": 2301952 + }, + { + "epoch": 0.0, + "learning_rate": 1.2305280591838247e-05, + "loss": 3.3595, + "step": 2302464 + }, + { + "epoch": 0.0, + "learning_rate": 1.2296894644327727e-05, + "loss": 3.3568, + "step": 2302976 + }, + { + "epoch": 0.0, + "learning_rate": 1.2288508696817205e-05, + "loss": 3.3747, + "step": 2303488 + }, + { + "epoch": 0.0, + "learning_rate": 1.2280122749306685e-05, + "loss": 3.3533, + "step": 2304000 + }, + { + "epoch": 0.0, + "learning_rate": 1.2271753180599897e-05, + "loss": 3.3613, + "step": 2304512 + }, + { + "epoch": 0.01, + "learning_rate": 1.2263367233089377e-05, + "loss": 3.361, + "step": 2305024 + }, + { + "epoch": 0.01, + "learning_rate": 1.2254981285578856e-05, + "loss": 3.3602, + "step": 2305536 + }, + { + "epoch": 0.01, + "learning_rate": 1.2246595338068337e-05, + "loss": 3.3674, + "step": 2306048 + }, + { + "epoch": 0.01, + "learning_rate": 1.2238225769361548e-05, + "loss": 3.3752, + "step": 2306560 + }, + { + "epoch": 0.01, + "learning_rate": 1.2229839821851028e-05, + "loss": 3.3655, + "step": 2307072 + }, + { + "epoch": 0.01, + "learning_rate": 1.2221453874340508e-05, + "loss": 3.3619, + "step": 2307584 + }, + { + "epoch": 0.01, + "learning_rate": 1.2213067926829988e-05, + "loss": 3.3726, + "step": 2308096 + }, + { + "epoch": 0.01, + "learning_rate": 1.22046983581232e-05, + "loss": 3.3489, + "step": 2308608 + }, + { + "epoch": 0.01, + "learning_rate": 1.2196312410612679e-05, + "loss": 3.3689, + "step": 2309120 + }, + { + "epoch": 0.01, + "learning_rate": 1.2187926463102159e-05, + "loss": 3.3561, + "step": 2309632 + }, + { + "epoch": 0.01, + "learning_rate": 1.2179540515591639e-05, + "loss": 3.355, + "step": 2310144 + }, + { + "epoch": 0.01, + "learning_rate": 1.2171170946884851e-05, + "loss": 3.3663, + "step": 2310656 + }, + { + "epoch": 0.01, + "learning_rate": 1.216278499937433e-05, + "loss": 3.3728, + "step": 2311168 + }, + { + "epoch": 0.01, + "learning_rate": 1.215439905186381e-05, + "loss": 3.3592, + "step": 2311680 + }, + { + "epoch": 0.01, + "learning_rate": 1.2146029483157022e-05, + "loss": 3.3624, + "step": 2312192 + }, + { + "epoch": 0.01, + "learning_rate": 1.2137643535646502e-05, + "loss": 3.3637, + "step": 2312704 + }, + { + "epoch": 0.01, + "learning_rate": 1.2129257588135982e-05, + "loss": 3.3581, + "step": 2313216 + }, + { + "epoch": 0.01, + "learning_rate": 1.2120871640625462e-05, + "loss": 3.3658, + "step": 2313728 + }, + { + "epoch": 0.01, + "learning_rate": 1.2112485693114942e-05, + "loss": 3.3428, + "step": 2314240 + }, + { + "epoch": 0.01, + "learning_rate": 1.210409974560442e-05, + "loss": 3.3632, + "step": 2314752 + }, + { + "epoch": 0.01, + "learning_rate": 1.2095713798093902e-05, + "loss": 3.363, + "step": 2315264 + }, + { + "epoch": 0.01, + "learning_rate": 1.2087344229387112e-05, + "loss": 3.3706, + "step": 2315776 + }, + { + "epoch": 0.01, + "learning_rate": 1.2078958281876592e-05, + "loss": 3.3573, + "step": 2316288 + }, + { + "epoch": 0.01, + "learning_rate": 1.2070572334366072e-05, + "loss": 3.3573, + "step": 2316800 + }, + { + "epoch": 0.01, + "learning_rate": 1.2062186386855552e-05, + "loss": 3.3539, + "step": 2317312 + }, + { + "epoch": 0.01, + "learning_rate": 1.2053816818148763e-05, + "loss": 3.3535, + "step": 2317824 + }, + { + "epoch": 0.01, + "learning_rate": 1.2045430870638243e-05, + "loss": 3.377, + "step": 2318336 + }, + { + "epoch": 0.01, + "learning_rate": 1.2037044923127723e-05, + "loss": 3.3481, + "step": 2318848 + }, + { + "epoch": 0.01, + "learning_rate": 1.2028658975617203e-05, + "loss": 3.3712, + "step": 2319360 + }, + { + "epoch": 0.01, + "learning_rate": 1.2020289406910415e-05, + "loss": 3.3651, + "step": 2319872 + }, + { + "epoch": 0.01, + "learning_rate": 1.2011919838203624e-05, + "loss": 3.3523, + "step": 2320384 + }, + { + "epoch": 0.01, + "learning_rate": 1.2003533890693106e-05, + "loss": 3.369, + "step": 2320896 + }, + { + "epoch": 0.01, + "learning_rate": 1.1995147943182586e-05, + "loss": 3.3487, + "step": 2321408 + }, + { + "epoch": 0.01, + "learning_rate": 1.1986761995672066e-05, + "loss": 3.3507, + "step": 2321920 + }, + { + "epoch": 0.01, + "learning_rate": 1.1978376048161544e-05, + "loss": 3.3603, + "step": 2322432 + }, + { + "epoch": 0.01, + "learning_rate": 1.1969990100651026e-05, + "loss": 3.3687, + "step": 2322944 + }, + { + "epoch": 0.01, + "learning_rate": 1.1961604153140506e-05, + "loss": 3.3483, + "step": 2323456 + }, + { + "epoch": 0.01, + "learning_rate": 1.1953234584433717e-05, + "loss": 3.3675, + "step": 2323968 + }, + { + "epoch": 0.01, + "learning_rate": 1.1944848636923197e-05, + "loss": 3.3439, + "step": 2324480 + }, + { + "epoch": 0.01, + "learning_rate": 1.1936462689412677e-05, + "loss": 3.36, + "step": 2324992 + }, + { + "epoch": 0.01, + "learning_rate": 1.1928076741902157e-05, + "loss": 3.3725, + "step": 2325504 + }, + { + "epoch": 0.01, + "learning_rate": 1.1919707173195367e-05, + "loss": 3.365, + "step": 2326016 + }, + { + "epoch": 0.01, + "learning_rate": 1.1911321225684847e-05, + "loss": 3.3628, + "step": 2326528 + }, + { + "epoch": 0.01, + "learning_rate": 1.1902935278174327e-05, + "loss": 3.3651, + "step": 2327040 + }, + { + "epoch": 0.01, + "learning_rate": 1.1894549330663807e-05, + "loss": 3.3752, + "step": 2327552 + }, + { + "epoch": 0.01, + "learning_rate": 1.1886179761957018e-05, + "loss": 3.3619, + "step": 2328064 + }, + { + "epoch": 0.01, + "learning_rate": 1.1877793814446498e-05, + "loss": 3.3738, + "step": 2328576 + }, + { + "epoch": 0.01, + "learning_rate": 1.186942424573971e-05, + "loss": 3.3532, + "step": 2329088 + }, + { + "epoch": 0.01, + "learning_rate": 1.1861038298229189e-05, + "loss": 3.3474, + "step": 2329600 + }, + { + "epoch": 0.01, + "learning_rate": 1.185265235071867e-05, + "loss": 3.3594, + "step": 2330112 + }, + { + "epoch": 0.01, + "learning_rate": 1.184426640320815e-05, + "loss": 3.3638, + "step": 2330624 + }, + { + "epoch": 0.01, + "learning_rate": 1.1835880455697629e-05, + "loss": 3.3644, + "step": 2331136 + }, + { + "epoch": 0.01, + "learning_rate": 1.1827510886990841e-05, + "loss": 3.3767, + "step": 2331648 + }, + { + "epoch": 0.01, + "learning_rate": 1.1819124939480321e-05, + "loss": 3.3593, + "step": 2332160 + }, + { + "epoch": 0.01, + "learning_rate": 1.1810738991969801e-05, + "loss": 3.3476, + "step": 2332672 + }, + { + "epoch": 0.01, + "learning_rate": 1.180235304445928e-05, + "loss": 3.3574, + "step": 2333184 + }, + { + "epoch": 0.01, + "learning_rate": 1.1793983475752492e-05, + "loss": 3.3672, + "step": 2333696 + }, + { + "epoch": 0.01, + "learning_rate": 1.1785597528241972e-05, + "loss": 3.3595, + "step": 2334208 + }, + { + "epoch": 0.01, + "learning_rate": 1.1777211580731452e-05, + "loss": 3.357, + "step": 2334720 + }, + { + "epoch": 0.01, + "learning_rate": 1.1768825633220932e-05, + "loss": 3.3621, + "step": 2335232 + }, + { + "epoch": 0.02, + "learning_rate": 1.1760439685710412e-05, + "loss": 3.3544, + "step": 2335744 + }, + { + "epoch": 0.02, + "learning_rate": 1.1752053738199892e-05, + "loss": 3.3649, + "step": 2336256 + }, + { + "epoch": 0.02, + "learning_rate": 1.1743667790689371e-05, + "loss": 3.3552, + "step": 2336768 + }, + { + "epoch": 0.02, + "learning_rate": 1.1735298221982582e-05, + "loss": 3.3672, + "step": 2337280 + }, + { + "epoch": 0.02, + "learning_rate": 1.1726912274472062e-05, + "loss": 3.3739, + "step": 2337792 + }, + { + "epoch": 0.02, + "learning_rate": 1.1718526326961544e-05, + "loss": 3.362, + "step": 2338304 + }, + { + "epoch": 0.02, + "learning_rate": 1.1710140379451022e-05, + "loss": 3.3515, + "step": 2338816 + }, + { + "epoch": 0.02, + "learning_rate": 1.1701754431940502e-05, + "loss": 3.3599, + "step": 2339328 + }, + { + "epoch": 0.02, + "learning_rate": 1.1693368484429982e-05, + "loss": 3.3589, + "step": 2339840 + }, + { + "epoch": 0.02, + "learning_rate": 1.1684982536919462e-05, + "loss": 3.3674, + "step": 2340352 + }, + { + "epoch": 0.02, + "learning_rate": 1.1676596589408942e-05, + "loss": 3.3573, + "step": 2340864 + }, + { + "epoch": 0.02, + "learning_rate": 1.1668227020702153e-05, + "loss": 3.3586, + "step": 2341376 + }, + { + "epoch": 0.02, + "learning_rate": 1.1659841073191634e-05, + "loss": 3.3579, + "step": 2341888 + }, + { + "epoch": 0.02, + "learning_rate": 1.1651455125681113e-05, + "loss": 3.3594, + "step": 2342400 + }, + { + "epoch": 0.02, + "learning_rate": 1.1643085556974325e-05, + "loss": 3.3604, + "step": 2342912 + }, + { + "epoch": 0.02, + "learning_rate": 1.1634699609463805e-05, + "loss": 3.3584, + "step": 2343424 + }, + { + "epoch": 0.02, + "learning_rate": 1.1626313661953283e-05, + "loss": 3.3497, + "step": 2343936 + }, + { + "epoch": 0.02, + "learning_rate": 1.1617927714442763e-05, + "loss": 3.3614, + "step": 2344448 + }, + { + "epoch": 0.02, + "learning_rate": 1.1609541766932245e-05, + "loss": 3.3589, + "step": 2344960 + }, + { + "epoch": 0.02, + "learning_rate": 1.1601155819421725e-05, + "loss": 3.3488, + "step": 2345472 + }, + { + "epoch": 0.02, + "learning_rate": 1.1592769871911203e-05, + "loss": 3.3472, + "step": 2345984 + }, + { + "epoch": 0.02, + "learning_rate": 1.1584400303204416e-05, + "loss": 3.3537, + "step": 2346496 + }, + { + "epoch": 0.02, + "learning_rate": 1.1576014355693896e-05, + "loss": 3.3722, + "step": 2347008 + }, + { + "epoch": 0.02, + "learning_rate": 1.1567628408183374e-05, + "loss": 3.3558, + "step": 2347520 + }, + { + "epoch": 0.02, + "learning_rate": 1.1559242460672856e-05, + "loss": 3.3604, + "step": 2348032 + }, + { + "epoch": 0.02, + "learning_rate": 1.1550872891966066e-05, + "loss": 3.3633, + "step": 2348544 + }, + { + "epoch": 0.02, + "learning_rate": 1.1542486944455546e-05, + "loss": 3.3782, + "step": 2349056 + }, + { + "epoch": 0.02, + "learning_rate": 1.1534100996945026e-05, + "loss": 3.3582, + "step": 2349568 + }, + { + "epoch": 0.02, + "learning_rate": 1.1525715049434506e-05, + "loss": 3.3525, + "step": 2350080 + }, + { + "epoch": 0.02, + "learning_rate": 1.1517345480727717e-05, + "loss": 3.3596, + "step": 2350592 + }, + { + "epoch": 0.02, + "learning_rate": 1.1508959533217199e-05, + "loss": 3.3611, + "step": 2351104 + }, + { + "epoch": 0.02, + "learning_rate": 1.1500573585706677e-05, + "loss": 3.3474, + "step": 2351616 + }, + { + "epoch": 0.02, + "learning_rate": 1.1492187638196157e-05, + "loss": 3.3547, + "step": 2352128 + }, + { + "epoch": 0.02, + "learning_rate": 1.1483801690685637e-05, + "loss": 3.3534, + "step": 2352640 + }, + { + "epoch": 0.02, + "learning_rate": 1.1475432121978848e-05, + "loss": 3.3586, + "step": 2353152 + }, + { + "epoch": 0.02, + "learning_rate": 1.1467046174468328e-05, + "loss": 3.3533, + "step": 2353664 + }, + { + "epoch": 0.02, + "learning_rate": 1.1458660226957808e-05, + "loss": 3.3663, + "step": 2354176 + }, + { + "epoch": 0.02, + "learning_rate": 1.1450274279447289e-05, + "loss": 3.3538, + "step": 2354688 + }, + { + "epoch": 0.02, + "learning_rate": 1.1441888331936767e-05, + "loss": 3.3561, + "step": 2355200 + }, + { + "epoch": 0.02, + "learning_rate": 1.1433502384426247e-05, + "loss": 3.3707, + "step": 2355712 + }, + { + "epoch": 0.02, + "learning_rate": 1.1425116436915729e-05, + "loss": 3.36, + "step": 2356224 + }, + { + "epoch": 0.02, + "learning_rate": 1.1416746868208938e-05, + "loss": 3.3667, + "step": 2356736 + }, + { + "epoch": 0.02, + "learning_rate": 1.1408360920698418e-05, + "loss": 3.3516, + "step": 2357248 + }, + { + "epoch": 0.02, + "learning_rate": 1.13999749731879e-05, + "loss": 3.3636, + "step": 2357760 + }, + { + "epoch": 0.02, + "learning_rate": 1.139158902567738e-05, + "loss": 3.3673, + "step": 2358272 + }, + { + "epoch": 0.02, + "learning_rate": 1.1383203078166858e-05, + "loss": 3.3603, + "step": 2358784 + }, + { + "epoch": 0.02, + "learning_rate": 1.1374817130656338e-05, + "loss": 3.3597, + "step": 2359296 + }, + { + "epoch": 0.02, + "learning_rate": 1.136643118314582e-05, + "loss": 3.3533, + "step": 2359808 + }, + { + "epoch": 0.02, + "learning_rate": 1.1358045235635298e-05, + "loss": 3.3724, + "step": 2360320 + }, + { + "epoch": 0.02, + "learning_rate": 1.134967566692851e-05, + "loss": 3.3638, + "step": 2360832 + }, + { + "epoch": 0.02, + "learning_rate": 1.134128971941799e-05, + "loss": 3.3645, + "step": 2361344 + }, + { + "epoch": 0.02, + "learning_rate": 1.133290377190747e-05, + "loss": 3.36, + "step": 2361856 + }, + { + "epoch": 0.02, + "learning_rate": 1.1324517824396948e-05, + "loss": 3.3649, + "step": 2362368 + }, + { + "epoch": 0.02, + "learning_rate": 1.1316148255690161e-05, + "loss": 3.3553, + "step": 2362880 + }, + { + "epoch": 0.02, + "learning_rate": 1.1307762308179641e-05, + "loss": 3.3513, + "step": 2363392 + }, + { + "epoch": 0.02, + "learning_rate": 1.129937636066912e-05, + "loss": 3.3734, + "step": 2363904 + }, + { + "epoch": 0.02, + "learning_rate": 1.12909904131586e-05, + "loss": 3.3579, + "step": 2364416 + }, + { + "epoch": 0.02, + "learning_rate": 1.1282620844451812e-05, + "loss": 3.3666, + "step": 2364928 + }, + { + "epoch": 0.02, + "learning_rate": 1.1274251275745024e-05, + "loss": 3.3583, + "step": 2365440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8649256229400635, + "eval_runtime": 309.0576, + "eval_samples_per_second": 1234.692, + "eval_steps_per_second": 38.585, + "step": 2365920 + }, + { + "epoch": 1.0, + "learning_rate": 1.1265865328234502e-05, + "loss": 3.3509, + "step": 2365952 + }, + { + "epoch": 1.0, + "learning_rate": 1.1257479380723982e-05, + "loss": 3.3514, + "step": 2366464 + }, + { + "epoch": 1.0, + "learning_rate": 1.1249093433213464e-05, + "loss": 3.3542, + "step": 2366976 + }, + { + "epoch": 1.0, + "learning_rate": 1.1240707485702942e-05, + "loss": 3.3651, + "step": 2367488 + }, + { + "epoch": 1.0, + "learning_rate": 1.1232321538192422e-05, + "loss": 3.3605, + "step": 2368000 + }, + { + "epoch": 1.0, + "learning_rate": 1.1223935590681902e-05, + "loss": 3.3652, + "step": 2368512 + }, + { + "epoch": 1.0, + "learning_rate": 1.1215549643171384e-05, + "loss": 3.358, + "step": 2369024 + }, + { + "epoch": 1.0, + "learning_rate": 1.1207180074464593e-05, + "loss": 3.3567, + "step": 2369536 + }, + { + "epoch": 1.0, + "learning_rate": 1.1198794126954073e-05, + "loss": 3.3603, + "step": 2370048 + }, + { + "epoch": 1.0, + "learning_rate": 1.1190408179443554e-05, + "loss": 3.3693, + "step": 2370560 + }, + { + "epoch": 1.0, + "learning_rate": 1.1182022231933033e-05, + "loss": 3.3497, + "step": 2371072 + }, + { + "epoch": 1.0, + "learning_rate": 1.1173652663226245e-05, + "loss": 3.356, + "step": 2371584 + }, + { + "epoch": 1.0, + "learning_rate": 1.1165283094519456e-05, + "loss": 3.3657, + "step": 2372096 + }, + { + "epoch": 1.0, + "learning_rate": 1.1156897147008936e-05, + "loss": 3.353, + "step": 2372608 + }, + { + "epoch": 1.0, + "learning_rate": 1.1148511199498416e-05, + "loss": 3.3499, + "step": 2373120 + }, + { + "epoch": 1.0, + "learning_rate": 1.1140125251987896e-05, + "loss": 3.3511, + "step": 2373632 + }, + { + "epoch": 1.0, + "learning_rate": 1.1131739304477376e-05, + "loss": 3.35, + "step": 2374144 + }, + { + "epoch": 1.0, + "learning_rate": 1.1123353356966856e-05, + "loss": 3.3482, + "step": 2374656 + }, + { + "epoch": 1.0, + "learning_rate": 1.1114967409456336e-05, + "loss": 3.3502, + "step": 2375168 + }, + { + "epoch": 1.0, + "learning_rate": 1.1106581461945816e-05, + "loss": 3.3513, + "step": 2375680 + }, + { + "epoch": 1.0, + "learning_rate": 1.1098211893239026e-05, + "loss": 3.3656, + "step": 2376192 + }, + { + "epoch": 1.0, + "learning_rate": 1.1089825945728506e-05, + "loss": 3.3569, + "step": 2376704 + }, + { + "epoch": 1.0, + "learning_rate": 1.1081456377021717e-05, + "loss": 3.3515, + "step": 2377216 + }, + { + "epoch": 1.0, + "learning_rate": 1.1073070429511199e-05, + "loss": 3.3586, + "step": 2377728 + }, + { + "epoch": 1.0, + "learning_rate": 1.1064684482000679e-05, + "loss": 3.3713, + "step": 2378240 + }, + { + "epoch": 1.0, + "learning_rate": 1.1056298534490157e-05, + "loss": 3.3468, + "step": 2378752 + }, + { + "epoch": 1.0, + "learning_rate": 1.1047912586979637e-05, + "loss": 3.3497, + "step": 2379264 + }, + { + "epoch": 1.0, + "learning_rate": 1.1039526639469119e-05, + "loss": 3.3625, + "step": 2379776 + }, + { + "epoch": 1.0, + "learning_rate": 1.1031140691958597e-05, + "loss": 3.3478, + "step": 2380288 + }, + { + "epoch": 1.0, + "learning_rate": 1.1022771123251808e-05, + "loss": 3.35, + "step": 2380800 + }, + { + "epoch": 1.01, + "learning_rate": 1.101438517574129e-05, + "loss": 3.351, + "step": 2381312 + }, + { + "epoch": 1.01, + "learning_rate": 1.100599922823077e-05, + "loss": 3.357, + "step": 2381824 + }, + { + "epoch": 1.01, + "learning_rate": 1.0997613280720248e-05, + "loss": 3.3614, + "step": 2382336 + }, + { + "epoch": 1.01, + "learning_rate": 1.0989227333209728e-05, + "loss": 3.3629, + "step": 2382848 + }, + { + "epoch": 1.01, + "learning_rate": 1.098084138569921e-05, + "loss": 3.3575, + "step": 2383360 + }, + { + "epoch": 1.01, + "learning_rate": 1.0972455438188688e-05, + "loss": 3.3511, + "step": 2383872 + }, + { + "epoch": 1.01, + "learning_rate": 1.0964069490678167e-05, + "loss": 3.3623, + "step": 2384384 + }, + { + "epoch": 1.01, + "learning_rate": 1.095569992197138e-05, + "loss": 3.3398, + "step": 2384896 + }, + { + "epoch": 1.01, + "learning_rate": 1.094731397446086e-05, + "loss": 3.3627, + "step": 2385408 + }, + { + "epoch": 1.01, + "learning_rate": 1.0938928026950338e-05, + "loss": 3.3463, + "step": 2385920 + }, + { + "epoch": 1.01, + "learning_rate": 1.093055845824355e-05, + "loss": 3.3468, + "step": 2386432 + }, + { + "epoch": 1.01, + "learning_rate": 1.092217251073303e-05, + "loss": 3.3536, + "step": 2386944 + }, + { + "epoch": 1.01, + "learning_rate": 1.0913802942026243e-05, + "loss": 3.3611, + "step": 2387456 + }, + { + "epoch": 1.01, + "learning_rate": 1.0905416994515721e-05, + "loss": 3.3517, + "step": 2387968 + }, + { + "epoch": 1.01, + "learning_rate": 1.0897031047005201e-05, + "loss": 3.3533, + "step": 2388480 + }, + { + "epoch": 1.01, + "learning_rate": 1.0888645099494681e-05, + "loss": 3.3516, + "step": 2388992 + }, + { + "epoch": 1.01, + "learning_rate": 1.0880259151984161e-05, + "loss": 3.3497, + "step": 2389504 + }, + { + "epoch": 1.01, + "learning_rate": 1.0871873204473641e-05, + "loss": 3.361, + "step": 2390016 + }, + { + "epoch": 1.01, + "learning_rate": 1.0863487256963121e-05, + "loss": 3.3271, + "step": 2390528 + }, + { + "epoch": 1.01, + "learning_rate": 1.0855101309452601e-05, + "loss": 3.3501, + "step": 2391040 + }, + { + "epoch": 1.01, + "learning_rate": 1.0846731740745812e-05, + "loss": 3.3592, + "step": 2391552 + }, + { + "epoch": 1.01, + "learning_rate": 1.0838345793235292e-05, + "loss": 3.3572, + "step": 2392064 + }, + { + "epoch": 1.01, + "learning_rate": 1.0829959845724773e-05, + "loss": 3.3448, + "step": 2392576 + }, + { + "epoch": 1.01, + "learning_rate": 1.0821573898214252e-05, + "loss": 3.3502, + "step": 2393088 + }, + { + "epoch": 1.01, + "learning_rate": 1.0813204329507463e-05, + "loss": 3.3476, + "step": 2393600 + }, + { + "epoch": 1.01, + "learning_rate": 1.0804818381996944e-05, + "loss": 3.3432, + "step": 2394112 + }, + { + "epoch": 1.01, + "learning_rate": 1.0796432434486424e-05, + "loss": 3.3685, + "step": 2394624 + }, + { + "epoch": 1.01, + "learning_rate": 1.0788046486975902e-05, + "loss": 3.3383, + "step": 2395136 + }, + { + "epoch": 1.01, + "learning_rate": 1.0779676918269115e-05, + "loss": 3.3605, + "step": 2395648 + }, + { + "epoch": 1.01, + "learning_rate": 1.0771290970758595e-05, + "loss": 3.3521, + "step": 2396160 + }, + { + "epoch": 1.01, + "learning_rate": 1.0762921402051807e-05, + "loss": 3.3452, + "step": 2396672 + }, + { + "epoch": 1.01, + "learning_rate": 1.0754535454541286e-05, + "loss": 3.3563, + "step": 2397184 + }, + { + "epoch": 1.01, + "learning_rate": 1.0746149507030766e-05, + "loss": 3.3412, + "step": 2397696 + }, + { + "epoch": 1.01, + "learning_rate": 1.0737763559520245e-05, + "loss": 3.3466, + "step": 2398208 + }, + { + "epoch": 1.01, + "learning_rate": 1.0729377612009725e-05, + "loss": 3.3471, + "step": 2398720 + }, + { + "epoch": 1.01, + "learning_rate": 1.0720991664499205e-05, + "loss": 3.3629, + "step": 2399232 + }, + { + "epoch": 1.01, + "learning_rate": 1.0712605716988685e-05, + "loss": 3.3382, + "step": 2399744 + }, + { + "epoch": 1.01, + "learning_rate": 1.0704219769478165e-05, + "loss": 3.3564, + "step": 2400256 + }, + { + "epoch": 1.01, + "learning_rate": 1.0695850200771376e-05, + "loss": 3.3361, + "step": 2400768 + }, + { + "epoch": 1.01, + "learning_rate": 1.0687464253260856e-05, + "loss": 3.3494, + "step": 2401280 + }, + { + "epoch": 1.01, + "learning_rate": 1.0679078305750336e-05, + "loss": 3.3601, + "step": 2401792 + }, + { + "epoch": 1.01, + "learning_rate": 1.0670708737043549e-05, + "loss": 3.3614, + "step": 2402304 + }, + { + "epoch": 1.01, + "learning_rate": 1.0662322789533027e-05, + "loss": 3.3515, + "step": 2402816 + }, + { + "epoch": 1.01, + "learning_rate": 1.0653936842022508e-05, + "loss": 3.3554, + "step": 2403328 + }, + { + "epoch": 1.01, + "learning_rate": 1.064556727331572e-05, + "loss": 3.366, + "step": 2403840 + }, + { + "epoch": 1.01, + "learning_rate": 1.06371813258052e-05, + "loss": 3.3518, + "step": 2404352 + }, + { + "epoch": 1.01, + "learning_rate": 1.0628795378294679e-05, + "loss": 3.3626, + "step": 2404864 + }, + { + "epoch": 1.01, + "learning_rate": 1.0620409430784159e-05, + "loss": 3.3472, + "step": 2405376 + }, + { + "epoch": 1.01, + "learning_rate": 1.0612023483273637e-05, + "loss": 3.3427, + "step": 2405888 + }, + { + "epoch": 1.01, + "learning_rate": 1.0603637535763119e-05, + "loss": 3.3488, + "step": 2406400 + }, + { + "epoch": 1.01, + "learning_rate": 1.059526796705633e-05, + "loss": 3.3513, + "step": 2406912 + }, + { + "epoch": 1.01, + "learning_rate": 1.058688201954581e-05, + "loss": 3.3559, + "step": 2407424 + }, + { + "epoch": 1.01, + "learning_rate": 1.057849607203529e-05, + "loss": 3.3649, + "step": 2407936 + }, + { + "epoch": 1.01, + "learning_rate": 1.057011012452477e-05, + "loss": 3.3574, + "step": 2408448 + }, + { + "epoch": 1.01, + "learning_rate": 1.056172417701425e-05, + "loss": 3.3368, + "step": 2408960 + }, + { + "epoch": 1.01, + "learning_rate": 1.0553338229503728e-05, + "loss": 3.3472, + "step": 2409472 + }, + { + "epoch": 1.01, + "learning_rate": 1.054496866079694e-05, + "loss": 3.3575, + "step": 2409984 + }, + { + "epoch": 1.01, + "learning_rate": 1.053658271328642e-05, + "loss": 3.3504, + "step": 2410496 + }, + { + "epoch": 1.01, + "learning_rate": 1.05281967657759e-05, + "loss": 3.3463, + "step": 2411008 + }, + { + "epoch": 1.01, + "learning_rate": 1.051981081826538e-05, + "loss": 3.3539, + "step": 2411520 + }, + { + "epoch": 1.02, + "learning_rate": 1.051142487075486e-05, + "loss": 3.3461, + "step": 2412032 + }, + { + "epoch": 1.02, + "learning_rate": 1.050303892324434e-05, + "loss": 3.3526, + "step": 2412544 + }, + { + "epoch": 1.02, + "learning_rate": 1.049465297573382e-05, + "loss": 3.3479, + "step": 2413056 + }, + { + "epoch": 1.02, + "learning_rate": 1.04862670282233e-05, + "loss": 3.3572, + "step": 2413568 + }, + { + "epoch": 1.02, + "learning_rate": 1.047789745951651e-05, + "loss": 3.359, + "step": 2414080 + }, + { + "epoch": 1.02, + "learning_rate": 1.0469511512005992e-05, + "loss": 3.3549, + "step": 2414592 + }, + { + "epoch": 1.02, + "learning_rate": 1.0461141943299202e-05, + "loss": 3.3429, + "step": 2415104 + }, + { + "epoch": 1.02, + "learning_rate": 1.0452755995788682e-05, + "loss": 3.3531, + "step": 2415616 + }, + { + "epoch": 1.02, + "learning_rate": 1.0444370048278163e-05, + "loss": 3.351, + "step": 2416128 + }, + { + "epoch": 1.02, + "learning_rate": 1.0435984100767643e-05, + "loss": 3.3564, + "step": 2416640 + }, + { + "epoch": 1.02, + "learning_rate": 1.0427598153257121e-05, + "loss": 3.3481, + "step": 2417152 + }, + { + "epoch": 1.02, + "learning_rate": 1.0419212205746601e-05, + "loss": 3.3459, + "step": 2417664 + }, + { + "epoch": 1.02, + "learning_rate": 1.0410842637039814e-05, + "loss": 3.348, + "step": 2418176 + }, + { + "epoch": 1.02, + "learning_rate": 1.0402456689529292e-05, + "loss": 3.3523, + "step": 2418688 + }, + { + "epoch": 1.02, + "learning_rate": 1.0394070742018774e-05, + "loss": 3.3529, + "step": 2419200 + }, + { + "epoch": 1.02, + "learning_rate": 1.0385684794508254e-05, + "loss": 3.3472, + "step": 2419712 + }, + { + "epoch": 1.02, + "learning_rate": 1.0377298846997734e-05, + "loss": 3.3402, + "step": 2420224 + }, + { + "epoch": 1.02, + "learning_rate": 1.0368912899487212e-05, + "loss": 3.3546, + "step": 2420736 + }, + { + "epoch": 1.02, + "learning_rate": 1.0360526951976694e-05, + "loss": 3.351, + "step": 2421248 + }, + { + "epoch": 1.02, + "learning_rate": 1.0352141004466174e-05, + "loss": 3.335, + "step": 2421760 + }, + { + "epoch": 1.02, + "learning_rate": 1.0343771435759383e-05, + "loss": 3.3397, + "step": 2422272 + }, + { + "epoch": 1.02, + "learning_rate": 1.0335385488248864e-05, + "loss": 3.3421, + "step": 2422784 + }, + { + "epoch": 1.02, + "learning_rate": 1.0326999540738344e-05, + "loss": 3.3605, + "step": 2423296 + }, + { + "epoch": 1.02, + "learning_rate": 1.0318613593227824e-05, + "loss": 3.3479, + "step": 2423808 + }, + { + "epoch": 1.02, + "learning_rate": 1.0310244024521035e-05, + "loss": 3.3491, + "step": 2424320 + }, + { + "epoch": 1.02, + "learning_rate": 1.0301874455814246e-05, + "loss": 3.3565, + "step": 2424832 + }, + { + "epoch": 1.02, + "learning_rate": 1.0293488508303727e-05, + "loss": 3.3688, + "step": 2425344 + }, + { + "epoch": 1.02, + "learning_rate": 1.0285102560793207e-05, + "loss": 3.349, + "step": 2425856 + }, + { + "epoch": 1.02, + "learning_rate": 1.0276716613282686e-05, + "loss": 3.3412, + "step": 2426368 + }, + { + "epoch": 1.02, + "learning_rate": 1.0268347044575898e-05, + "loss": 3.3537, + "step": 2426880 + }, + { + "epoch": 1.02, + "learning_rate": 1.0259961097065378e-05, + "loss": 3.3496, + "step": 2427392 + }, + { + "epoch": 1.02, + "learning_rate": 1.0251575149554856e-05, + "loss": 3.3435, + "step": 2427904 + }, + { + "epoch": 1.02, + "learning_rate": 1.0243189202044336e-05, + "loss": 3.3434, + "step": 2428416 + }, + { + "epoch": 1.02, + "learning_rate": 1.0234803254533818e-05, + "loss": 3.3482, + "step": 2428928 + }, + { + "epoch": 1.02, + "learning_rate": 1.0226417307023298e-05, + "loss": 3.3512, + "step": 2429440 + }, + { + "epoch": 1.02, + "learning_rate": 1.0218047738316509e-05, + "loss": 3.3457, + "step": 2429952 + }, + { + "epoch": 1.02, + "learning_rate": 1.0209661790805989e-05, + "loss": 3.3565, + "step": 2430464 + }, + { + "epoch": 1.02, + "learning_rate": 1.0201275843295469e-05, + "loss": 3.3447, + "step": 2430976 + }, + { + "epoch": 1.02, + "learning_rate": 1.0192889895784947e-05, + "loss": 3.3497, + "step": 2431488 + }, + { + "epoch": 1.02, + "learning_rate": 1.0184503948274429e-05, + "loss": 3.3543, + "step": 2432000 + }, + { + "epoch": 1.02, + "learning_rate": 1.0176118000763908e-05, + "loss": 3.357, + "step": 2432512 + }, + { + "epoch": 1.02, + "learning_rate": 1.016774843205712e-05, + "loss": 3.3592, + "step": 2433024 + }, + { + "epoch": 1.02, + "learning_rate": 1.01593624845466e-05, + "loss": 3.3398, + "step": 2433536 + }, + { + "epoch": 1.02, + "learning_rate": 1.015097653703608e-05, + "loss": 3.3507, + "step": 2434048 + }, + { + "epoch": 1.02, + "learning_rate": 1.0142590589525559e-05, + "loss": 3.3611, + "step": 2434560 + }, + { + "epoch": 1.02, + "learning_rate": 1.0134204642015039e-05, + "loss": 3.3511, + "step": 2435072 + }, + { + "epoch": 1.02, + "learning_rate": 1.0125818694504519e-05, + "loss": 3.3538, + "step": 2435584 + }, + { + "epoch": 1.02, + "learning_rate": 1.0117432746993999e-05, + "loss": 3.3446, + "step": 2436096 + }, + { + "epoch": 1.02, + "learning_rate": 1.0109046799483479e-05, + "loss": 3.3652, + "step": 2436608 + }, + { + "epoch": 1.02, + "learning_rate": 1.010067723077669e-05, + "loss": 3.3528, + "step": 2437120 + }, + { + "epoch": 1.02, + "learning_rate": 1.009229128326617e-05, + "loss": 3.3556, + "step": 2437632 + }, + { + "epoch": 1.02, + "learning_rate": 1.008390533575565e-05, + "loss": 3.3489, + "step": 2438144 + }, + { + "epoch": 1.02, + "learning_rate": 1.007551938824513e-05, + "loss": 3.3568, + "step": 2438656 + }, + { + "epoch": 1.02, + "learning_rate": 1.006714981953834e-05, + "loss": 3.346, + "step": 2439168 + }, + { + "epoch": 1.02, + "learning_rate": 1.0058780250831553e-05, + "loss": 3.3382, + "step": 2439680 + }, + { + "epoch": 1.02, + "learning_rate": 1.0050394303321033e-05, + "loss": 3.3648, + "step": 2440192 + }, + { + "epoch": 1.02, + "learning_rate": 1.0042008355810511e-05, + "loss": 3.3494, + "step": 2440704 + }, + { + "epoch": 1.02, + "learning_rate": 1.0033622408299993e-05, + "loss": 3.355, + "step": 2441216 + }, + { + "epoch": 1.02, + "learning_rate": 1.0025236460789473e-05, + "loss": 3.3488, + "step": 2441728 + }, + { + "epoch": 1.03, + "learning_rate": 1.0016866892082683e-05, + "loss": 3.3415, + "step": 2442240 + }, + { + "epoch": 1.03, + "eval_loss": 3.8662655353546143, + "eval_runtime": 303.385, + "eval_samples_per_second": 1257.778, + "eval_steps_per_second": 39.306, + "step": 2442240 + }, + { + "epoch": 0.0, + "learning_rate": 1.0008480944572163e-05, + "loss": 3.3432, + "step": 2442752 + }, + { + "epoch": 0.0, + "learning_rate": 1.0000094997061643e-05, + "loss": 3.3463, + "step": 2443264 + }, + { + "epoch": 0.0, + "learning_rate": 9.991709049551123e-06, + "loss": 3.3552, + "step": 2443776 + }, + { + "epoch": 0.0, + "learning_rate": 9.983339480844334e-06, + "loss": 3.3518, + "step": 2444288 + }, + { + "epoch": 0.0, + "learning_rate": 9.974953533333814e-06, + "loss": 3.3556, + "step": 2444800 + }, + { + "epoch": 0.0, + "learning_rate": 9.966567585823294e-06, + "loss": 3.3476, + "step": 2445312 + }, + { + "epoch": 0.0, + "learning_rate": 9.958181638312774e-06, + "loss": 3.3472, + "step": 2445824 + }, + { + "epoch": 0.0, + "learning_rate": 9.949812069605985e-06, + "loss": 3.345, + "step": 2446336 + }, + { + "epoch": 0.0, + "learning_rate": 9.941426122095465e-06, + "loss": 3.3617, + "step": 2446848 + }, + { + "epoch": 0.0, + "learning_rate": 9.933040174584945e-06, + "loss": 3.3428, + "step": 2447360 + }, + { + "epoch": 0.0, + "learning_rate": 9.924654227074425e-06, + "loss": 3.3488, + "step": 2447872 + }, + { + "epoch": 0.0, + "learning_rate": 9.916301037171368e-06, + "loss": 3.3581, + "step": 2448384 + }, + { + "epoch": 0.0, + "learning_rate": 9.907915089660848e-06, + "loss": 3.3462, + "step": 2448896 + }, + { + "epoch": 0.0, + "learning_rate": 9.899529142150328e-06, + "loss": 3.3372, + "step": 2449408 + }, + { + "epoch": 0.0, + "learning_rate": 9.891143194639806e-06, + "loss": 3.3406, + "step": 2449920 + }, + { + "epoch": 0.0, + "learning_rate": 9.882757247129288e-06, + "loss": 3.3384, + "step": 2450432 + }, + { + "epoch": 0.0, + "learning_rate": 9.874387678422499e-06, + "loss": 3.341, + "step": 2450944 + }, + { + "epoch": 0.0, + "learning_rate": 9.866001730911979e-06, + "loss": 3.3426, + "step": 2451456 + }, + { + "epoch": 0.0, + "learning_rate": 9.857615783401459e-06, + "loss": 3.3407, + "step": 2451968 + }, + { + "epoch": 0.0, + "learning_rate": 9.849229835890938e-06, + "loss": 3.3615, + "step": 2452480 + }, + { + "epoch": 0.0, + "learning_rate": 9.840843888380418e-06, + "loss": 3.3453, + "step": 2452992 + }, + { + "epoch": 0.0, + "learning_rate": 9.832474319673631e-06, + "loss": 3.3408, + "step": 2453504 + }, + { + "epoch": 0.0, + "learning_rate": 9.82408837216311e-06, + "loss": 3.3508, + "step": 2454016 + }, + { + "epoch": 0.0, + "learning_rate": 9.815702424652589e-06, + "loss": 3.3608, + "step": 2454528 + }, + { + "epoch": 0.0, + "learning_rate": 9.80731647714207e-06, + "loss": 3.3349, + "step": 2455040 + }, + { + "epoch": 0.0, + "learning_rate": 9.798930529631549e-06, + "loss": 3.345, + "step": 2455552 + }, + { + "epoch": 0.0, + "learning_rate": 9.790544582121029e-06, + "loss": 3.3475, + "step": 2456064 + }, + { + "epoch": 0.0, + "learning_rate": 9.782158634610509e-06, + "loss": 3.3467, + "step": 2456576 + }, + { + "epoch": 0.0, + "learning_rate": 9.773789065903721e-06, + "loss": 3.3393, + "step": 2457088 + }, + { + "epoch": 0.01, + "learning_rate": 9.7654031183932e-06, + "loss": 3.3391, + "step": 2457600 + }, + { + "epoch": 0.01, + "learning_rate": 9.75701717088268e-06, + "loss": 3.3497, + "step": 2458112 + }, + { + "epoch": 0.01, + "learning_rate": 9.748631223372161e-06, + "loss": 3.3503, + "step": 2458624 + }, + { + "epoch": 0.01, + "learning_rate": 9.74024527586164e-06, + "loss": 3.352, + "step": 2459136 + }, + { + "epoch": 0.01, + "learning_rate": 9.73185932835112e-06, + "loss": 3.3501, + "step": 2459648 + }, + { + "epoch": 0.01, + "learning_rate": 9.723473380840601e-06, + "loss": 3.3455, + "step": 2460160 + }, + { + "epoch": 0.01, + "learning_rate": 9.71508743333008e-06, + "loss": 3.3496, + "step": 2460672 + }, + { + "epoch": 0.01, + "learning_rate": 9.70671786462329e-06, + "loss": 3.3337, + "step": 2461184 + }, + { + "epoch": 0.01, + "learning_rate": 9.698331917112772e-06, + "loss": 3.3501, + "step": 2461696 + }, + { + "epoch": 0.01, + "learning_rate": 9.689945969602252e-06, + "loss": 3.337, + "step": 2462208 + }, + { + "epoch": 0.01, + "learning_rate": 9.68156002209173e-06, + "loss": 3.3401, + "step": 2462720 + }, + { + "epoch": 0.01, + "learning_rate": 9.673190453384943e-06, + "loss": 3.3411, + "step": 2463232 + }, + { + "epoch": 0.01, + "learning_rate": 9.664820884678153e-06, + "loss": 3.3563, + "step": 2463744 + }, + { + "epoch": 0.01, + "learning_rate": 9.656434937167633e-06, + "loss": 3.3416, + "step": 2464256 + }, + { + "epoch": 0.01, + "learning_rate": 9.648048989657113e-06, + "loss": 3.3416, + "step": 2464768 + }, + { + "epoch": 0.01, + "learning_rate": 9.639663042146593e-06, + "loss": 3.3483, + "step": 2465280 + }, + { + "epoch": 0.01, + "learning_rate": 9.631277094636073e-06, + "loss": 3.3379, + "step": 2465792 + }, + { + "epoch": 0.01, + "learning_rate": 9.622891147125553e-06, + "loss": 3.3536, + "step": 2466304 + }, + { + "epoch": 0.01, + "learning_rate": 9.614505199615033e-06, + "loss": 3.3216, + "step": 2466816 + }, + { + "epoch": 0.01, + "learning_rate": 9.606119252104513e-06, + "loss": 3.3379, + "step": 2467328 + }, + { + "epoch": 0.01, + "learning_rate": 9.597749683397726e-06, + "loss": 3.3475, + "step": 2467840 + }, + { + "epoch": 0.01, + "learning_rate": 9.589363735887204e-06, + "loss": 3.3493, + "step": 2468352 + }, + { + "epoch": 0.01, + "learning_rate": 9.580977788376684e-06, + "loss": 3.3395, + "step": 2468864 + }, + { + "epoch": 0.01, + "learning_rate": 9.572591840866164e-06, + "loss": 3.3366, + "step": 2469376 + }, + { + "epoch": 0.01, + "learning_rate": 9.564222272159376e-06, + "loss": 3.3401, + "step": 2469888 + }, + { + "epoch": 0.01, + "learning_rate": 9.555836324648854e-06, + "loss": 3.3289, + "step": 2470400 + }, + { + "epoch": 0.01, + "learning_rate": 9.547450377138336e-06, + "loss": 3.3584, + "step": 2470912 + }, + { + "epoch": 0.01, + "learning_rate": 9.539080808431547e-06, + "loss": 3.337, + "step": 2471424 + }, + { + "epoch": 0.01, + "learning_rate": 9.530694860921025e-06, + "loss": 3.3492, + "step": 2471936 + }, + { + "epoch": 0.01, + "learning_rate": 9.522308913410507e-06, + "loss": 3.3426, + "step": 2472448 + }, + { + "epoch": 0.01, + "learning_rate": 9.513922965899987e-06, + "loss": 3.3331, + "step": 2472960 + }, + { + "epoch": 0.01, + "learning_rate": 9.505537018389467e-06, + "loss": 3.3458, + "step": 2473472 + }, + { + "epoch": 0.01, + "learning_rate": 9.497151070878945e-06, + "loss": 3.3348, + "step": 2473984 + }, + { + "epoch": 0.01, + "learning_rate": 9.488765123368427e-06, + "loss": 3.3375, + "step": 2474496 + }, + { + "epoch": 0.01, + "learning_rate": 9.480379175857907e-06, + "loss": 3.3319, + "step": 2475008 + }, + { + "epoch": 0.01, + "learning_rate": 9.472009607151117e-06, + "loss": 3.3554, + "step": 2475520 + }, + { + "epoch": 0.01, + "learning_rate": 9.463623659640597e-06, + "loss": 3.3326, + "step": 2476032 + }, + { + "epoch": 0.01, + "learning_rate": 9.455237712130077e-06, + "loss": 3.3432, + "step": 2476544 + }, + { + "epoch": 0.01, + "learning_rate": 9.446868143423288e-06, + "loss": 3.3275, + "step": 2477056 + }, + { + "epoch": 0.01, + "learning_rate": 9.438482195912768e-06, + "loss": 3.3414, + "step": 2477568 + }, + { + "epoch": 0.01, + "learning_rate": 9.430096248402248e-06, + "loss": 3.3491, + "step": 2478080 + }, + { + "epoch": 0.01, + "learning_rate": 9.421710300891728e-06, + "loss": 3.3482, + "step": 2478592 + }, + { + "epoch": 0.01, + "learning_rate": 9.41334073218494e-06, + "loss": 3.3421, + "step": 2479104 + }, + { + "epoch": 0.01, + "learning_rate": 9.404954784674419e-06, + "loss": 3.3506, + "step": 2479616 + }, + { + "epoch": 0.01, + "learning_rate": 9.396568837163899e-06, + "loss": 3.3546, + "step": 2480128 + }, + { + "epoch": 0.01, + "learning_rate": 9.38818288965338e-06, + "loss": 3.3392, + "step": 2480640 + }, + { + "epoch": 0.01, + "learning_rate": 9.37981332094659e-06, + "loss": 3.3506, + "step": 2481152 + }, + { + "epoch": 0.01, + "learning_rate": 9.371443752239802e-06, + "loss": 3.3422, + "step": 2481664 + }, + { + "epoch": 0.01, + "learning_rate": 9.363057804729282e-06, + "loss": 3.3339, + "step": 2482176 + }, + { + "epoch": 0.01, + "learning_rate": 9.354671857218762e-06, + "loss": 3.3396, + "step": 2482688 + }, + { + "epoch": 0.01, + "learning_rate": 9.346285909708242e-06, + "loss": 3.3414, + "step": 2483200 + }, + { + "epoch": 0.01, + "learning_rate": 9.337899962197722e-06, + "loss": 3.3484, + "step": 2483712 + }, + { + "epoch": 0.01, + "learning_rate": 9.329530393490932e-06, + "loss": 3.358, + "step": 2484224 + }, + { + "epoch": 0.01, + "learning_rate": 9.321144445980412e-06, + "loss": 3.3475, + "step": 2484736 + }, + { + "epoch": 0.01, + "learning_rate": 9.312758498469892e-06, + "loss": 3.3254, + "step": 2485248 + }, + { + "epoch": 0.01, + "learning_rate": 9.304372550959372e-06, + "loss": 3.339, + "step": 2485760 + }, + { + "epoch": 0.01, + "learning_rate": 9.295986603448852e-06, + "loss": 3.3446, + "step": 2486272 + }, + { + "epoch": 0.01, + "learning_rate": 9.287617034742063e-06, + "loss": 3.3433, + "step": 2486784 + }, + { + "epoch": 0.01, + "learning_rate": 9.279231087231543e-06, + "loss": 3.3367, + "step": 2487296 + }, + { + "epoch": 0.01, + "learning_rate": 9.270845139721025e-06, + "loss": 3.3418, + "step": 2487808 + }, + { + "epoch": 0.02, + "learning_rate": 9.262459192210503e-06, + "loss": 3.3349, + "step": 2488320 + }, + { + "epoch": 0.02, + "learning_rate": 9.254073244699983e-06, + "loss": 3.3435, + "step": 2488832 + }, + { + "epoch": 0.02, + "learning_rate": 9.245687297189463e-06, + "loss": 3.341, + "step": 2489344 + }, + { + "epoch": 0.02, + "learning_rate": 9.237317728482675e-06, + "loss": 3.3503, + "step": 2489856 + }, + { + "epoch": 0.02, + "learning_rate": 9.228931780972154e-06, + "loss": 3.3461, + "step": 2490368 + }, + { + "epoch": 0.02, + "learning_rate": 9.220545833461634e-06, + "loss": 3.3503, + "step": 2490880 + }, + { + "epoch": 0.02, + "learning_rate": 9.212159885951115e-06, + "loss": 3.3304, + "step": 2491392 + }, + { + "epoch": 0.02, + "learning_rate": 9.203773938440593e-06, + "loss": 3.3428, + "step": 2491904 + }, + { + "epoch": 0.02, + "learning_rate": 9.195387990930073e-06, + "loss": 3.3444, + "step": 2492416 + }, + { + "epoch": 0.02, + "learning_rate": 9.187002043419553e-06, + "loss": 3.3466, + "step": 2492928 + }, + { + "epoch": 0.02, + "learning_rate": 9.178616095909035e-06, + "loss": 3.3436, + "step": 2493440 + }, + { + "epoch": 0.02, + "learning_rate": 9.170246527202244e-06, + "loss": 3.3342, + "step": 2493952 + }, + { + "epoch": 0.02, + "learning_rate": 9.161860579691726e-06, + "loss": 3.3386, + "step": 2494464 + }, + { + "epoch": 0.02, + "learning_rate": 9.153474632181206e-06, + "loss": 3.3405, + "step": 2494976 + }, + { + "epoch": 0.02, + "learning_rate": 9.145105063474417e-06, + "loss": 3.345, + "step": 2495488 + }, + { + "epoch": 0.02, + "learning_rate": 9.136719115963896e-06, + "loss": 3.3363, + "step": 2496000 + }, + { + "epoch": 0.02, + "learning_rate": 9.128333168453376e-06, + "loss": 3.3313, + "step": 2496512 + }, + { + "epoch": 0.02, + "learning_rate": 9.119947220942856e-06, + "loss": 3.3485, + "step": 2497024 + }, + { + "epoch": 0.02, + "learning_rate": 9.111561273432335e-06, + "loss": 3.3358, + "step": 2497536 + }, + { + "epoch": 0.02, + "learning_rate": 9.103175325921816e-06, + "loss": 3.33, + "step": 2498048 + }, + { + "epoch": 0.02, + "learning_rate": 9.094789378411296e-06, + "loss": 3.3313, + "step": 2498560 + }, + { + "epoch": 0.02, + "learning_rate": 9.086403430900775e-06, + "loss": 3.3322, + "step": 2499072 + }, + { + "epoch": 0.02, + "learning_rate": 9.078033862193987e-06, + "loss": 3.3505, + "step": 2499584 + }, + { + "epoch": 0.02, + "learning_rate": 9.069647914683467e-06, + "loss": 3.3374, + "step": 2500096 + }, + { + "epoch": 0.02, + "learning_rate": 9.061261967172947e-06, + "loss": 3.3405, + "step": 2500608 + }, + { + "epoch": 0.02, + "learning_rate": 9.052892398466158e-06, + "loss": 3.345, + "step": 2501120 + }, + { + "epoch": 0.02, + "learning_rate": 9.044506450955638e-06, + "loss": 3.3594, + "step": 2501632 + }, + { + "epoch": 0.02, + "learning_rate": 9.036120503445118e-06, + "loss": 3.339, + "step": 2502144 + }, + { + "epoch": 0.02, + "learning_rate": 9.0277345559346e-06, + "loss": 3.3351, + "step": 2502656 + }, + { + "epoch": 0.02, + "learning_rate": 9.019364987227808e-06, + "loss": 3.3424, + "step": 2503168 + }, + { + "epoch": 0.02, + "learning_rate": 9.010979039717288e-06, + "loss": 3.3408, + "step": 2503680 + }, + { + "epoch": 0.02, + "learning_rate": 9.00259309220677e-06, + "loss": 3.3314, + "step": 2504192 + }, + { + "epoch": 0.02, + "learning_rate": 8.994207144696248e-06, + "loss": 3.3371, + "step": 2504704 + }, + { + "epoch": 0.02, + "learning_rate": 8.985821197185728e-06, + "loss": 3.3346, + "step": 2505216 + }, + { + "epoch": 0.02, + "learning_rate": 8.977435249675208e-06, + "loss": 3.3416, + "step": 2505728 + }, + { + "epoch": 0.02, + "learning_rate": 8.96906568096842e-06, + "loss": 3.338, + "step": 2506240 + }, + { + "epoch": 0.02, + "learning_rate": 8.960679733457899e-06, + "loss": 3.346, + "step": 2506752 + }, + { + "epoch": 0.02, + "learning_rate": 8.95229378594738e-06, + "loss": 3.3366, + "step": 2507264 + }, + { + "epoch": 0.02, + "learning_rate": 8.94390783843686e-06, + "loss": 3.3391, + "step": 2507776 + }, + { + "epoch": 0.02, + "learning_rate": 8.935521890926339e-06, + "loss": 3.3402, + "step": 2508288 + }, + { + "epoch": 0.02, + "learning_rate": 8.927135943415819e-06, + "loss": 3.3515, + "step": 2508800 + }, + { + "epoch": 0.02, + "learning_rate": 8.9187499959053e-06, + "loss": 3.3469, + "step": 2509312 + }, + { + "epoch": 0.02, + "learning_rate": 8.910380427198511e-06, + "loss": 3.3378, + "step": 2509824 + }, + { + "epoch": 0.02, + "learning_rate": 8.901994479687991e-06, + "loss": 3.3343, + "step": 2510336 + }, + { + "epoch": 0.02, + "learning_rate": 8.893608532177471e-06, + "loss": 3.3509, + "step": 2510848 + }, + { + "epoch": 0.02, + "learning_rate": 8.885222584666951e-06, + "loss": 3.3413, + "step": 2511360 + }, + { + "epoch": 0.02, + "learning_rate": 8.876853015960162e-06, + "loss": 3.344, + "step": 2511872 + }, + { + "epoch": 0.02, + "learning_rate": 8.868467068449642e-06, + "loss": 3.3368, + "step": 2512384 + }, + { + "epoch": 0.02, + "learning_rate": 8.860081120939122e-06, + "loss": 3.3528, + "step": 2512896 + }, + { + "epoch": 0.02, + "learning_rate": 8.851695173428602e-06, + "loss": 3.3417, + "step": 2513408 + }, + { + "epoch": 0.02, + "learning_rate": 8.843325604721812e-06, + "loss": 3.3417, + "step": 2513920 + }, + { + "epoch": 0.02, + "learning_rate": 8.834939657211292e-06, + "loss": 3.3423, + "step": 2514432 + }, + { + "epoch": 0.02, + "learning_rate": 8.826570088504505e-06, + "loss": 3.3495, + "step": 2514944 + }, + { + "epoch": 0.02, + "learning_rate": 8.818184140993985e-06, + "loss": 3.3416, + "step": 2515456 + }, + { + "epoch": 0.02, + "learning_rate": 8.809798193483463e-06, + "loss": 3.3262, + "step": 2515968 + }, + { + "epoch": 0.02, + "learning_rate": 8.801412245972945e-06, + "loss": 3.3538, + "step": 2516480 + }, + { + "epoch": 0.02, + "learning_rate": 8.793026298462425e-06, + "loss": 3.344, + "step": 2516992 + }, + { + "epoch": 0.02, + "learning_rate": 8.784640350951903e-06, + "loss": 3.344, + "step": 2517504 + }, + { + "epoch": 0.02, + "learning_rate": 8.776254403441383e-06, + "loss": 3.3409, + "step": 2518016 + }, + { + "epoch": 0.02, + "learning_rate": 8.767884834734595e-06, + "loss": 3.3306, + "step": 2518528 + }, + { + "epoch": 0.03, + "eval_loss": 3.8663790225982666, + "eval_runtime": 305.3832, + "eval_samples_per_second": 1249.548, + "eval_steps_per_second": 39.049, + "step": 2518560 + }, + { + "epoch": 1.0, + "learning_rate": 8.759498887224075e-06, + "loss": 3.3333, + "step": 2519040 + }, + { + "epoch": 1.0, + "learning_rate": 8.751112939713554e-06, + "loss": 3.3398, + "step": 2519552 + }, + { + "epoch": 1.0, + "learning_rate": 8.742726992203035e-06, + "loss": 3.3451, + "step": 2520064 + }, + { + "epoch": 1.0, + "learning_rate": 8.734341044692515e-06, + "loss": 3.3378, + "step": 2520576 + }, + { + "epoch": 1.0, + "learning_rate": 8.725971475985726e-06, + "loss": 3.3475, + "step": 2521088 + }, + { + "epoch": 1.0, + "learning_rate": 8.717585528475206e-06, + "loss": 3.3376, + "step": 2521600 + }, + { + "epoch": 1.0, + "learning_rate": 8.709199580964686e-06, + "loss": 3.3394, + "step": 2522112 + }, + { + "epoch": 1.0, + "learning_rate": 8.700813633454166e-06, + "loss": 3.3354, + "step": 2522624 + }, + { + "epoch": 1.0, + "learning_rate": 8.692444064747377e-06, + "loss": 3.3502, + "step": 2523136 + }, + { + "epoch": 1.0, + "learning_rate": 8.684058117236857e-06, + "loss": 3.3363, + "step": 2523648 + }, + { + "epoch": 1.0, + "learning_rate": 8.675672169726337e-06, + "loss": 3.3368, + "step": 2524160 + }, + { + "epoch": 1.0, + "learning_rate": 8.667286222215817e-06, + "loss": 3.3411, + "step": 2524672 + }, + { + "epoch": 1.0, + "learning_rate": 8.658916653509027e-06, + "loss": 3.3425, + "step": 2525184 + }, + { + "epoch": 1.0, + "learning_rate": 8.650530705998507e-06, + "loss": 3.33, + "step": 2525696 + }, + { + "epoch": 1.0, + "learning_rate": 8.642144758487989e-06, + "loss": 3.3379, + "step": 2526208 + }, + { + "epoch": 1.0, + "learning_rate": 8.633758810977467e-06, + "loss": 3.3222, + "step": 2526720 + }, + { + "epoch": 1.0, + "learning_rate": 8.625372863466947e-06, + "loss": 3.332, + "step": 2527232 + }, + { + "epoch": 1.0, + "learning_rate": 8.616986915956427e-06, + "loss": 3.3323, + "step": 2527744 + }, + { + "epoch": 1.0, + "learning_rate": 8.608600968445907e-06, + "loss": 3.3284, + "step": 2528256 + }, + { + "epoch": 1.0, + "learning_rate": 8.600215020935387e-06, + "loss": 3.3574, + "step": 2528768 + }, + { + "epoch": 1.0, + "learning_rate": 8.591829073424867e-06, + "loss": 3.3308, + "step": 2529280 + }, + { + "epoch": 1.0, + "learning_rate": 8.58345950471808e-06, + "loss": 3.3379, + "step": 2529792 + }, + { + "epoch": 1.0, + "learning_rate": 8.575073557207558e-06, + "loss": 3.3375, + "step": 2530304 + }, + { + "epoch": 1.0, + "learning_rate": 8.566687609697038e-06, + "loss": 3.352, + "step": 2530816 + }, + { + "epoch": 1.0, + "learning_rate": 8.55830166218652e-06, + "loss": 3.3267, + "step": 2531328 + }, + { + "epoch": 1.0, + "learning_rate": 8.549915714675998e-06, + "loss": 3.3358, + "step": 2531840 + }, + { + "epoch": 1.0, + "learning_rate": 8.541529767165478e-06, + "loss": 3.3364, + "step": 2532352 + }, + { + "epoch": 1.0, + "learning_rate": 8.533143819654958e-06, + "loss": 3.3361, + "step": 2532864 + }, + { + "epoch": 1.0, + "learning_rate": 8.52477425094817e-06, + "loss": 3.3308, + "step": 2533376 + }, + { + "epoch": 1.01, + "learning_rate": 8.516388303437648e-06, + "loss": 3.3297, + "step": 2533888 + }, + { + "epoch": 1.01, + "learning_rate": 8.508002355927128e-06, + "loss": 3.34, + "step": 2534400 + }, + { + "epoch": 1.01, + "learning_rate": 8.49961640841661e-06, + "loss": 3.3421, + "step": 2534912 + }, + { + "epoch": 1.01, + "learning_rate": 8.491230460906088e-06, + "loss": 3.3438, + "step": 2535424 + }, + { + "epoch": 1.01, + "learning_rate": 8.482844513395568e-06, + "loss": 3.3417, + "step": 2535936 + }, + { + "epoch": 1.01, + "learning_rate": 8.47445856588505e-06, + "loss": 3.3316, + "step": 2536448 + }, + { + "epoch": 1.01, + "learning_rate": 8.46607261837453e-06, + "loss": 3.3426, + "step": 2536960 + }, + { + "epoch": 1.01, + "learning_rate": 8.457703049667739e-06, + "loss": 3.322, + "step": 2537472 + }, + { + "epoch": 1.01, + "learning_rate": 8.44931710215722e-06, + "loss": 3.3428, + "step": 2537984 + }, + { + "epoch": 1.01, + "learning_rate": 8.4409311546467e-06, + "loss": 3.3263, + "step": 2538496 + }, + { + "epoch": 1.01, + "learning_rate": 8.432545207136179e-06, + "loss": 3.331, + "step": 2539008 + }, + { + "epoch": 1.01, + "learning_rate": 8.424175638429391e-06, + "loss": 3.3283, + "step": 2539520 + }, + { + "epoch": 1.01, + "learning_rate": 8.415789690918871e-06, + "loss": 3.3453, + "step": 2540032 + }, + { + "epoch": 1.01, + "learning_rate": 8.407403743408351e-06, + "loss": 3.3354, + "step": 2540544 + }, + { + "epoch": 1.01, + "learning_rate": 8.399034174701562e-06, + "loss": 3.3306, + "step": 2541056 + }, + { + "epoch": 1.01, + "learning_rate": 8.390648227191042e-06, + "loss": 3.341, + "step": 2541568 + }, + { + "epoch": 1.01, + "learning_rate": 8.382262279680522e-06, + "loss": 3.3318, + "step": 2542080 + }, + { + "epoch": 1.01, + "learning_rate": 8.373876332170002e-06, + "loss": 3.3407, + "step": 2542592 + }, + { + "epoch": 1.01, + "learning_rate": 8.365490384659482e-06, + "loss": 3.3145, + "step": 2543104 + }, + { + "epoch": 1.01, + "learning_rate": 8.357104437148962e-06, + "loss": 3.3281, + "step": 2543616 + }, + { + "epoch": 1.01, + "learning_rate": 8.348718489638442e-06, + "loss": 3.337, + "step": 2544128 + }, + { + "epoch": 1.01, + "learning_rate": 8.340332542127922e-06, + "loss": 3.3418, + "step": 2544640 + }, + { + "epoch": 1.01, + "learning_rate": 8.331962973421132e-06, + "loss": 3.3308, + "step": 2545152 + }, + { + "epoch": 1.01, + "learning_rate": 8.323577025910612e-06, + "loss": 3.3257, + "step": 2545664 + }, + { + "epoch": 1.01, + "learning_rate": 8.315191078400094e-06, + "loss": 3.3374, + "step": 2546176 + }, + { + "epoch": 1.01, + "learning_rate": 8.306805130889572e-06, + "loss": 3.3175, + "step": 2546688 + }, + { + "epoch": 1.01, + "learning_rate": 8.298435562182785e-06, + "loss": 3.3451, + "step": 2547200 + }, + { + "epoch": 1.01, + "learning_rate": 8.290065993475995e-06, + "loss": 3.3309, + "step": 2547712 + }, + { + "epoch": 1.01, + "learning_rate": 8.281680045965475e-06, + "loss": 3.3393, + "step": 2548224 + }, + { + "epoch": 1.01, + "learning_rate": 8.273294098454955e-06, + "loss": 3.3353, + "step": 2548736 + }, + { + "epoch": 1.01, + "learning_rate": 8.264908150944435e-06, + "loss": 3.3236, + "step": 2549248 + }, + { + "epoch": 1.01, + "learning_rate": 8.256522203433915e-06, + "loss": 3.3391, + "step": 2549760 + }, + { + "epoch": 1.01, + "learning_rate": 8.248136255923394e-06, + "loss": 3.3262, + "step": 2550272 + }, + { + "epoch": 1.01, + "learning_rate": 8.239750308412875e-06, + "loss": 3.3273, + "step": 2550784 + }, + { + "epoch": 1.01, + "learning_rate": 8.231364360902355e-06, + "loss": 3.3235, + "step": 2551296 + }, + { + "epoch": 1.01, + "learning_rate": 8.222994792195566e-06, + "loss": 3.3458, + "step": 2551808 + }, + { + "epoch": 1.01, + "learning_rate": 8.214608844685046e-06, + "loss": 3.3273, + "step": 2552320 + }, + { + "epoch": 1.01, + "learning_rate": 8.206222897174526e-06, + "loss": 3.3299, + "step": 2552832 + }, + { + "epoch": 1.01, + "learning_rate": 8.197853328467737e-06, + "loss": 3.3217, + "step": 2553344 + }, + { + "epoch": 1.01, + "learning_rate": 8.189467380957217e-06, + "loss": 3.332, + "step": 2553856 + }, + { + "epoch": 1.01, + "learning_rate": 8.181081433446697e-06, + "loss": 3.3402, + "step": 2554368 + }, + { + "epoch": 1.01, + "learning_rate": 8.172695485936177e-06, + "loss": 3.3405, + "step": 2554880 + }, + { + "epoch": 1.01, + "learning_rate": 8.164325917229389e-06, + "loss": 3.3336, + "step": 2555392 + }, + { + "epoch": 1.01, + "learning_rate": 8.155939969718867e-06, + "loss": 3.3386, + "step": 2555904 + }, + { + "epoch": 1.01, + "learning_rate": 8.147554022208347e-06, + "loss": 3.342, + "step": 2556416 + }, + { + "epoch": 1.01, + "learning_rate": 8.139168074697829e-06, + "loss": 3.3359, + "step": 2556928 + }, + { + "epoch": 1.01, + "learning_rate": 8.130798505991038e-06, + "loss": 3.341, + "step": 2557440 + }, + { + "epoch": 1.01, + "learning_rate": 8.12242893728425e-06, + "loss": 3.3343, + "step": 2557952 + }, + { + "epoch": 1.01, + "learning_rate": 8.11404298977373e-06, + "loss": 3.3231, + "step": 2558464 + }, + { + "epoch": 1.01, + "learning_rate": 8.10565704226321e-06, + "loss": 3.3314, + "step": 2558976 + }, + { + "epoch": 1.01, + "learning_rate": 8.09727109475269e-06, + "loss": 3.3346, + "step": 2559488 + }, + { + "epoch": 1.01, + "learning_rate": 8.08888514724217e-06, + "loss": 3.3355, + "step": 2560000 + }, + { + "epoch": 1.01, + "learning_rate": 8.080515578535381e-06, + "loss": 3.3489, + "step": 2560512 + }, + { + "epoch": 1.01, + "learning_rate": 8.072129631024863e-06, + "loss": 3.3386, + "step": 2561024 + }, + { + "epoch": 1.01, + "learning_rate": 8.063743683514341e-06, + "loss": 3.3191, + "step": 2561536 + }, + { + "epoch": 1.01, + "learning_rate": 8.055357736003821e-06, + "loss": 3.3285, + "step": 2562048 + }, + { + "epoch": 1.01, + "learning_rate": 8.046971788493301e-06, + "loss": 3.3376, + "step": 2562560 + }, + { + "epoch": 1.01, + "learning_rate": 8.038602219786512e-06, + "loss": 3.337, + "step": 2563072 + }, + { + "epoch": 1.01, + "learning_rate": 8.030216272275992e-06, + "loss": 3.3253, + "step": 2563584 + }, + { + "epoch": 1.01, + "learning_rate": 8.021830324765473e-06, + "loss": 3.3326, + "step": 2564096 + }, + { + "epoch": 1.02, + "learning_rate": 8.013444377254953e-06, + "loss": 3.3298, + "step": 2564608 + }, + { + "epoch": 1.02, + "learning_rate": 8.005074808548162e-06, + "loss": 3.3322, + "step": 2565120 + }, + { + "epoch": 1.02, + "learning_rate": 7.996688861037644e-06, + "loss": 3.3291, + "step": 2565632 + }, + { + "epoch": 1.02, + "learning_rate": 7.988302913527124e-06, + "loss": 3.341, + "step": 2566144 + }, + { + "epoch": 1.02, + "learning_rate": 7.979916966016602e-06, + "loss": 3.3362, + "step": 2566656 + }, + { + "epoch": 1.02, + "learning_rate": 7.971531018506082e-06, + "loss": 3.3396, + "step": 2567168 + }, + { + "epoch": 1.02, + "learning_rate": 7.963145070995564e-06, + "loss": 3.3207, + "step": 2567680 + }, + { + "epoch": 1.02, + "learning_rate": 7.954759123485044e-06, + "loss": 3.335, + "step": 2568192 + }, + { + "epoch": 1.02, + "learning_rate": 7.946373175974522e-06, + "loss": 3.3343, + "step": 2568704 + }, + { + "epoch": 1.02, + "learning_rate": 7.938003607267735e-06, + "loss": 3.3343, + "step": 2569216 + }, + { + "epoch": 1.02, + "learning_rate": 7.929634038560945e-06, + "loss": 3.3302, + "step": 2569728 + }, + { + "epoch": 1.02, + "learning_rate": 7.921248091050425e-06, + "loss": 3.3305, + "step": 2570240 + }, + { + "epoch": 1.02, + "learning_rate": 7.912862143539905e-06, + "loss": 3.3271, + "step": 2570752 + }, + { + "epoch": 1.02, + "learning_rate": 7.904476196029385e-06, + "loss": 3.3355, + "step": 2571264 + }, + { + "epoch": 1.02, + "learning_rate": 7.896090248518865e-06, + "loss": 3.3359, + "step": 2571776 + }, + { + "epoch": 1.02, + "learning_rate": 7.887704301008345e-06, + "loss": 3.3228, + "step": 2572288 + }, + { + "epoch": 1.02, + "learning_rate": 7.879318353497825e-06, + "loss": 3.3233, + "step": 2572800 + }, + { + "epoch": 1.02, + "learning_rate": 7.870932405987305e-06, + "loss": 3.3375, + "step": 2573312 + }, + { + "epoch": 1.02, + "learning_rate": 7.862562837280517e-06, + "loss": 3.3275, + "step": 2573824 + }, + { + "epoch": 1.02, + "learning_rate": 7.854176889769996e-06, + "loss": 3.3231, + "step": 2574336 + }, + { + "epoch": 1.02, + "learning_rate": 7.845790942259476e-06, + "loss": 3.3228, + "step": 2574848 + }, + { + "epoch": 1.02, + "learning_rate": 7.837404994748956e-06, + "loss": 3.3213, + "step": 2575360 + }, + { + "epoch": 1.02, + "learning_rate": 7.829035426042166e-06, + "loss": 3.3429, + "step": 2575872 + }, + { + "epoch": 1.02, + "learning_rate": 7.820649478531646e-06, + "loss": 3.3271, + "step": 2576384 + }, + { + "epoch": 1.02, + "learning_rate": 7.812263531021128e-06, + "loss": 3.3341, + "step": 2576896 + }, + { + "epoch": 1.02, + "learning_rate": 7.803893962314339e-06, + "loss": 3.3343, + "step": 2577408 + }, + { + "epoch": 1.02, + "learning_rate": 7.795508014803817e-06, + "loss": 3.3503, + "step": 2577920 + }, + { + "epoch": 1.02, + "learning_rate": 7.787122067293299e-06, + "loss": 3.3311, + "step": 2578432 + }, + { + "epoch": 1.02, + "learning_rate": 7.778736119782779e-06, + "loss": 3.3255, + "step": 2578944 + }, + { + "epoch": 1.02, + "learning_rate": 7.77036655107599e-06, + "loss": 3.3321, + "step": 2579456 + }, + { + "epoch": 1.02, + "learning_rate": 7.76198060356547e-06, + "loss": 3.331, + "step": 2579968 + }, + { + "epoch": 1.02, + "learning_rate": 7.75359465605495e-06, + "loss": 3.3208, + "step": 2580480 + }, + { + "epoch": 1.02, + "learning_rate": 7.74520870854443e-06, + "loss": 3.3283, + "step": 2580992 + }, + { + "epoch": 1.02, + "learning_rate": 7.73682276103391e-06, + "loss": 3.3244, + "step": 2581504 + }, + { + "epoch": 1.02, + "learning_rate": 7.72843681352339e-06, + "loss": 3.3362, + "step": 2582016 + }, + { + "epoch": 1.02, + "learning_rate": 7.7200672448166e-06, + "loss": 3.3239, + "step": 2582528 + }, + { + "epoch": 1.02, + "learning_rate": 7.711681297306082e-06, + "loss": 3.3376, + "step": 2583040 + }, + { + "epoch": 1.02, + "learning_rate": 7.70329534979556e-06, + "loss": 3.3287, + "step": 2583552 + }, + { + "epoch": 1.02, + "learning_rate": 7.69490940228504e-06, + "loss": 3.3321, + "step": 2584064 + }, + { + "epoch": 1.02, + "learning_rate": 7.68652345477452e-06, + "loss": 3.3283, + "step": 2584576 + }, + { + "epoch": 1.02, + "learning_rate": 7.678137507264e-06, + "loss": 3.3443, + "step": 2585088 + }, + { + "epoch": 1.02, + "learning_rate": 7.66976793855721e-06, + "loss": 3.338, + "step": 2585600 + }, + { + "epoch": 1.02, + "learning_rate": 7.66138199104669e-06, + "loss": 3.327, + "step": 2586112 + }, + { + "epoch": 1.02, + "learning_rate": 7.652996043536172e-06, + "loss": 3.328, + "step": 2586624 + }, + { + "epoch": 1.02, + "learning_rate": 7.64461009602565e-06, + "loss": 3.3379, + "step": 2587136 + }, + { + "epoch": 1.02, + "learning_rate": 7.63622414851513e-06, + "loss": 3.3364, + "step": 2587648 + }, + { + "epoch": 1.02, + "learning_rate": 7.627838201004611e-06, + "loss": 3.3371, + "step": 2588160 + }, + { + "epoch": 1.02, + "learning_rate": 7.61945225349409e-06, + "loss": 3.3264, + "step": 2588672 + }, + { + "epoch": 1.02, + "learning_rate": 7.61106630598357e-06, + "loss": 3.3425, + "step": 2589184 + }, + { + "epoch": 1.02, + "learning_rate": 7.602696737276782e-06, + "loss": 3.3314, + "step": 2589696 + }, + { + "epoch": 1.02, + "learning_rate": 7.594310789766263e-06, + "loss": 3.3356, + "step": 2590208 + }, + { + "epoch": 1.02, + "learning_rate": 7.585924842255741e-06, + "loss": 3.3336, + "step": 2590720 + }, + { + "epoch": 1.02, + "learning_rate": 7.577555273548953e-06, + "loss": 3.3377, + "step": 2591232 + }, + { + "epoch": 1.02, + "learning_rate": 7.5691693260384335e-06, + "loss": 3.331, + "step": 2591744 + }, + { + "epoch": 1.02, + "learning_rate": 7.560783378527913e-06, + "loss": 3.3209, + "step": 2592256 + }, + { + "epoch": 1.02, + "learning_rate": 7.5523974310173925e-06, + "loss": 3.345, + "step": 2592768 + }, + { + "epoch": 1.02, + "learning_rate": 7.544027862310604e-06, + "loss": 3.3382, + "step": 2593280 + }, + { + "epoch": 1.02, + "learning_rate": 7.535641914800084e-06, + "loss": 3.3336, + "step": 2593792 + }, + { + "epoch": 1.02, + "learning_rate": 7.527255967289563e-06, + "loss": 3.3304, + "step": 2594304 + }, + { + "epoch": 1.02, + "learning_rate": 7.518870019779044e-06, + "loss": 3.3246, + "step": 2594816 + }, + { + "epoch": 1.03, + "eval_loss": 3.8665130138397217, + "eval_runtime": 305.5328, + "eval_samples_per_second": 1248.936, + "eval_steps_per_second": 39.03, + "step": 2594880 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.7934808236848456e+18, + "trial_name": null, + "trial_params": null +}