diff --git "a/checkpoint-2900160/trainer_state.json" "b/checkpoint-2900160/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2900160/trainer_state.json" @@ -0,0 +1,34313 @@ +{ + "best_metric": 3.84504771232605, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/det-adj-noun/transformer/1/checkpoints/checkpoint-992160", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2900160, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 11.0484, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8231, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1887, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9796, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8076, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7017, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6021, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5261, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4485, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4057, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3524, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3114, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2653, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2144, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1763, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1401, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1109, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0873, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0499, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0212, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0132, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 4.97, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9591, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9332, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.924, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.8918, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8703, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8532, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8429, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8209, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8078, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7984, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7763, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 4.7702, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7544, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7446, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969820416244367e-05, + "loss": 4.731, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.6995, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.707, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6792, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6872, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6706, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6715, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6541, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.644, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6414, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6329, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6224, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6057, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.95892359812181e-05, + "loss": 4.5916, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.6018, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5889, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5831, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5605, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5656, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5446, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5658, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5346, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5471, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5309, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5135, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.519, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5117, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4896, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4899, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5028, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4809, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4733, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4636, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4683, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4828, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940482703000532e-05, + "loss": 4.4691, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396441082494794e-05, + "loss": 4.4539, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388055134984274e-05, + "loss": 4.4579, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.4594, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4422, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.4354, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.438, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4241, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.4259, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.424, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4208, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4236, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.414, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.3973, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.4026, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.3971, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.4014, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926231505873767e-05, + "loss": 4.3925, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925394549003088e-05, + "loss": 4.3906, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924555954252036e-05, + "loss": 4.3898, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923717359500984e-05, + "loss": 4.3824, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.3806, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3738, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.365, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920364618377149e-05, + "loss": 4.3725, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919526023626097e-05, + "loss": 4.36, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918687428875045e-05, + "loss": 4.3584, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917848834123993e-05, + "loss": 4.3569, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.3583, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.3597, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3484, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3411, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913657498249106e-05, + "loss": 4.3386, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912818903498054e-05, + "loss": 4.3364, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911980308747002e-05, + "loss": 4.3204, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911143351876323e-05, + "loss": 4.3192, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.3313, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3266, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.3135, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3102, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3141, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3246, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3183, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.90443623174828e-05, + "loss": 4.309, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903597636997228e-05, + "loss": 4.3139, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027606801265495e-05, + "loss": 4.3142, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019220853754975e-05, + "loss": 4.299, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010834906244455e-05, + "loss": 4.2944, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002448958733935e-05, + "loss": 4.2987, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994063011223415e-05, + "loss": 4.2982, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985677063712895e-05, + "loss": 4.2805, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977307495006104e-05, + "loss": 4.283, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968921547495584e-05, + "loss": 4.2819, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2793, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.2807, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.894378008376775e-05, + "loss": 4.2873, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893539413625723e-05, + "loss": 4.271, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.2726, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2625, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891025267252941e-05, + "loss": 4.2779, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890186672501889e-05, + "loss": 4.2706, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889348077750837e-05, + "loss": 4.2629, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888509482999785e-05, + "loss": 4.2631, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887672526129106e-05, + "loss": 4.268, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886833931378054e-05, + "loss": 4.2652, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885995336627002e-05, + "loss": 4.2601, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515674187595e-05, + "loss": 4.2548, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.8843197850052706e-05, + "loss": 4.2565, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.8834811902542186e-05, + "loss": 4.2567, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.8826425955031666e-05, + "loss": 4.2552, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.8818040007521146e-05, + "loss": 4.2382, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.8809654060010626e-05, + "loss": 4.2466, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.8801268112500106e-05, + "loss": 4.2348, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879289854379332e-05, + "loss": 4.2254, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.87845125962828e-05, + "loss": 4.2519, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877612664877228e-05, + "loss": 4.236, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876774070126176e-05, + "loss": 4.2375, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875937113255497e-05, + "loss": 4.2367, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875098518504445e-05, + "loss": 4.2179, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.200989246368408, + "eval_runtime": 303.1099, + "eval_samples_per_second": 1258.92, + "eval_steps_per_second": 39.342, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874259923753393e-05, + "loss": 4.2206, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873421329002341e-05, + "loss": 4.2154, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872582734251289e-05, + "loss": 4.2347, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.87174577738061e-05, + "loss": 4.2183, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870907182629558e-05, + "loss": 4.2267, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870068587878506e-05, + "loss": 4.2062, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869229993127454e-05, + "loss": 4.2073, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683930362567756e-05, + "loss": 4.2029, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675544415057236e-05, + "loss": 4.2093, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667158467546716e-05, + "loss": 4.2078, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658772520036196e-05, + "loss": 4.2138, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.8650402951329405e-05, + "loss": 4.2148, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642033382622614e-05, + "loss": 4.1937, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633647435112094e-05, + "loss": 4.1917, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.8625261487601574e-05, + "loss": 4.1904, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.8616875540091054e-05, + "loss": 4.1823, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608489592580534e-05, + "loss": 4.1923, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.8600103645070014e-05, + "loss": 4.18, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591717697559493e-05, + "loss": 4.1807, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858333175004898e-05, + "loss": 4.2034, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857496218134219e-05, + "loss": 4.1787, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856657623383167e-05, + "loss": 4.1796, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.855819028632115e-05, + "loss": 4.1809, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854980433881063e-05, + "loss": 4.185, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854143477010384e-05, + "loss": 4.1734, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853304882259332e-05, + "loss": 4.1691, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.85246628750828e-05, + "loss": 4.1669, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851627692757228e-05, + "loss": 4.1727, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850790735886549e-05, + "loss": 4.1548, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849952141135497e-05, + "loss": 4.1653, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849113546384445e-05, + "loss": 4.1647, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848276589513766e-05, + "loss": 4.1624, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847437994762714e-05, + "loss": 4.1634, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846599400011662e-05, + "loss": 4.1538, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.84576080526061e-05, + "loss": 4.1549, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844922210509558e-05, + "loss": 4.1568, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.8440836157585056e-05, + "loss": 4.1377, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.8432450210074536e-05, + "loss": 4.1478, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.8424064262564016e-05, + "loss": 4.1345, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.8415694693857225e-05, + "loss": 4.1438, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.8407308746346705e-05, + "loss": 4.1458, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398922798836185e-05, + "loss": 4.1513, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839053685132567e-05, + "loss": 4.1426, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838216728261888e-05, + "loss": 4.1381, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837378133510836e-05, + "loss": 4.1472, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836539538759784e-05, + "loss": 4.1407, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835700944008732e-05, + "loss": 4.1318, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834863987138053e-05, + "loss": 4.1281, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834025392387001e-05, + "loss": 4.1213, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833186797635949e-05, + "loss": 4.1348, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832348202884897e-05, + "loss": 4.1297, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831511246014218e-05, + "loss": 4.126, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830672651263166e-05, + "loss": 4.1202, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829834056512114e-05, + "loss": 4.1255, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289954617610625e-05, + "loss": 4.1096, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281585048903834e-05, + "loss": 4.1312, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273199101393314e-05, + "loss": 4.1131, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264813153882794e-05, + "loss": 4.1294, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256427206372274e-05, + "loss": 4.1176, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248057637665483e-05, + "loss": 4.104, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823967169015496e-05, + "loss": 4.1083, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823128574264444e-05, + "loss": 4.1133, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822289979513392e-05, + "loss": 4.0948, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821453022642713e-05, + "loss": 4.0991, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820614427891661e-05, + "loss": 4.1118, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819775833140609e-05, + "loss": 4.1016, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818937238389558e-05, + "loss": 4.0953, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818100281518879e-05, + "loss": 4.0929, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817261686767827e-05, + "loss": 4.0942, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816423092016775e-05, + "loss": 4.1115, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815584497265723e-05, + "loss": 4.1059, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814747540395044e-05, + "loss": 4.0986, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813908945643992e-05, + "loss": 4.1041, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.81307035089294e-05, + "loss": 4.1011, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812231756141888e-05, + "loss": 4.0969, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113947992712086e-05, + "loss": 4.0836, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105562045201566e-05, + "loss": 4.0975, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.8097176097691046e-05, + "loss": 4.0907, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808879015018053e-05, + "loss": 4.0873, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808042058147374e-05, + "loss": 4.0947, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807203463396322e-05, + "loss": 4.0892, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.80636486864527e-05, + "loss": 4.0975, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805526273894218e-05, + "loss": 4.0911, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804689317023539e-05, + "loss": 4.0717, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803850722272487e-05, + "loss": 4.0839, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803012127521435e-05, + "loss": 4.0803, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802173532770383e-05, + "loss": 4.0875, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801336575899704e-05, + "loss": 4.0811, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800497981148652e-05, + "loss": 4.0811, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996610242779736e-05, + "loss": 4.0823, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988224295269215e-05, + "loss": 4.0778, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979838347758695e-05, + "loss": 4.0803, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971452400248175e-05, + "loss": 4.0769, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7963066452737655e-05, + "loss": 4.0679, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954696884030864e-05, + "loss": 4.0814, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946310936520344e-05, + "loss": 4.0761, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.7937924989009824e-05, + "loss": 4.067, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.7929539041499304e-05, + "loss": 4.075, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.7921153093988784e-05, + "loss": 4.0735, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912767146478264e-05, + "loss": 4.08, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.7904381198967744e-05, + "loss": 4.0689, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895995251457224e-05, + "loss": 4.0602, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788762568275043e-05, + "loss": 4.064, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787923973523992e-05, + "loss": 4.0657, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.78708537877294e-05, + "loss": 4.043, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786248421902261e-05, + "loss": 4.0585, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785409827151209e-05, + "loss": 4.0619, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784571232400157e-05, + "loss": 4.0608, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783732637649105e-05, + "loss": 4.0496, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782894042898053e-05, + "loss": 4.0457, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782055448147001e-05, + "loss": 4.0556, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781216853395948e-05, + "loss": 4.0671, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780378258644896e-05, + "loss": 4.0595, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779541301774218e-05, + "loss": 4.059, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778702707023166e-05, + "loss": 4.0569, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777864112272114e-05, + "loss": 4.0696, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770271554014354e-05, + "loss": 4.0453, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761885606503834e-05, + "loss": 4.0461, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775349965899331e-05, + "loss": 4.0516, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774511371148279e-05, + "loss": 4.0536, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773672776397227e-05, + "loss": 4.0355, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772835819526548e-05, + "loss": 4.0377, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719972247754956e-05, + "loss": 4.0466, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.7711586300244436e-05, + "loss": 4.0431, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.7703200352733916e-05, + "loss": 4.0457, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.7694814405223396e-05, + "loss": 4.0517, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.7686428457712876e-05, + "loss": 4.0346, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767805888900609e-05, + "loss": 4.0403, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766967294149557e-05, + "loss": 4.0327, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766128699398505e-05, + "loss": 4.0509, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765290104647453e-05, + "loss": 4.0471, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764451509896401e-05, + "loss": 4.0335, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763612915145349e-05, + "loss": 4.0371, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.76277595827467e-05, + "loss": 4.0415, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761937363523618e-05, + "loss": 4.0454, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761098768772566e-05, + "loss": 4.0419, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760260174021514e-05, + "loss": 4.0368, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759421579270462e-05, + "loss": 4.0362, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.75858298451941e-05, + "loss": 4.0362, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757744389768358e-05, + "loss": 4.0386, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756905795017306e-05, + "loss": 4.0246, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560688381466276e-05, + "loss": 4.0328, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552302433955756e-05, + "loss": 4.0266, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543916486445236e-05, + "loss": 4.0139, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535530538934716e-05, + "loss": 4.0427, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527144591424196e-05, + "loss": 4.0259, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518775022717405e-05, + "loss": 4.0279, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510389075206885e-05, + "loss": 4.0295, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7502003127696365e-05, + "loss": 4.0153, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.030919075012207, + "eval_runtime": 302.8768, + "eval_samples_per_second": 1259.889, + "eval_steps_per_second": 39.372, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493617180185845e-05, + "loss": 4.0194, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748523123267532e-05, + "loss": 4.0104, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.74768452851648e-05, + "loss": 4.036, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746845933765428e-05, + "loss": 4.0148, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460073390143764e-05, + "loss": 4.0322, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451687442633244e-05, + "loss": 4.0109, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443301495122724e-05, + "loss": 4.0104, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434915547612204e-05, + "loss": 4.0034, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426545978905413e-05, + "loss": 4.0172, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741816003139489e-05, + "loss": 4.0136, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740977408388437e-05, + "loss": 4.0197, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740138813637385e-05, + "loss": 4.0226, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739301856766706e-05, + "loss": 4.0066, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738463262015654e-05, + "loss": 4.0061, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737624667264602e-05, + "loss": 4.0005, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.73678607251355e-05, + "loss": 3.9984, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735947477762498e-05, + "loss": 4.0044, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735108883011446e-05, + "loss": 3.9983, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734270288260394e-05, + "loss": 3.9967, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733433331389716e-05, + "loss": 4.0162, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732594736638664e-05, + "loss": 3.9989, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731756141887612e-05, + "loss": 3.9995, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.73091754713656e-05, + "loss": 4.0017, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730080590265881e-05, + "loss": 4.0059, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729241995514829e-05, + "loss": 3.9932, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728403400763777e-05, + "loss": 3.9959, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727564806012725e-05, + "loss": 3.9934, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267278491420456e-05, + "loss": 3.9928, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258892543909936e-05, + "loss": 3.9838, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250506596399416e-05, + "loss": 3.9941, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7242120648888896e-05, + "loss": 3.9932, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723375108018211e-05, + "loss": 3.9914, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722536513267159e-05, + "loss": 3.9973, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721697918516107e-05, + "loss": 3.9837, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720859323765055e-05, + "loss": 3.986, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720020729014003e-05, + "loss": 3.9893, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191821342629505e-05, + "loss": 3.9753, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183435395118985e-05, + "loss": 3.9795, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175049447608465e-05, + "loss": 3.9705, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716667987890168e-05, + "loss": 3.9769, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158293931391154e-05, + "loss": 3.985, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149907983880634e-05, + "loss": 3.9894, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714152203637012e-05, + "loss": 3.9825, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713315246766333e-05, + "loss": 3.9768, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712476652015281e-05, + "loss": 3.9906, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711638057264229e-05, + "loss": 3.9777, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710799462513177e-05, + "loss": 3.9767, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709960867762125e-05, + "loss": 3.975, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709122273011073e-05, + "loss": 3.9609, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708285316140394e-05, + "loss": 3.9784, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707446721389342e-05, + "loss": 3.9724, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.70660812663829e-05, + "loss": 3.9737, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705769531887238e-05, + "loss": 3.9679, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704930937136186e-05, + "loss": 3.9724, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704092342385134e-05, + "loss": 3.9554, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032553855144554e-05, + "loss": 3.9807, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024167907634034e-05, + "loss": 3.9599, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015781960123514e-05, + "loss": 3.9814, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007396012612994e-05, + "loss": 3.9667, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6999010065102474e-05, + "loss": 3.962, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699064049639568e-05, + "loss": 3.9567, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698225454888516e-05, + "loss": 3.9682, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697386860137464e-05, + "loss": 3.9478, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696548265386412e-05, + "loss": 3.9556, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695711308515733e-05, + "loss": 3.9642, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694872713764681e-05, + "loss": 3.9607, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694034119013629e-05, + "loss": 3.9516, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693195524262577e-05, + "loss": 3.948, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692356929511526e-05, + "loss": 3.9502, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691519972640847e-05, + "loss": 3.9713, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690681377889795e-05, + "loss": 3.9599, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689842783138743e-05, + "loss": 3.9555, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689004188387691e-05, + "loss": 3.9649, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688165593636639e-05, + "loss": 3.961, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687326998885587e-05, + "loss": 3.958, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686488404134534e-05, + "loss": 3.9424, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856514472638556e-05, + "loss": 3.9616, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848128525128036e-05, + "loss": 3.9557, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683974257761751e-05, + "loss": 3.9454, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831356630106996e-05, + "loss": 3.961, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822987061400205e-05, + "loss": 3.9528, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681460111388969e-05, + "loss": 3.9591, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806215166379165e-05, + "loss": 3.9558, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797829218868645e-05, + "loss": 3.94, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678945965016186e-05, + "loss": 3.9494, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678107370265134e-05, + "loss": 3.946, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772687755140814e-05, + "loss": 3.9523, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764301807630294e-05, + "loss": 3.9508, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755915860119774e-05, + "loss": 3.947, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674754629141298e-05, + "loss": 3.9516, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673916034390246e-05, + "loss": 3.9466, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673077439639194e-05, + "loss": 3.9471, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672238844888143e-05, + "loss": 3.9442, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671400250137091e-05, + "loss": 3.9456, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670563293266412e-05, + "loss": 3.954, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.66972469851536e-05, + "loss": 3.9446, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668886103764308e-05, + "loss": 3.9408, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668047509013256e-05, + "loss": 3.946, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667210552142577e-05, + "loss": 3.9466, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666371957391525e-05, + "loss": 3.955, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665533362640473e-05, + "loss": 3.9415, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664694767889421e-05, + "loss": 3.9363, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663857811018742e-05, + "loss": 3.9403, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.66301921626769e-05, + "loss": 3.9404, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.6621806215166383e-05, + "loss": 3.9182, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.6613420267655863e-05, + "loss": 3.9351, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660505069894907e-05, + "loss": 3.9398, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659666475143855e-05, + "loss": 3.9325, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658827880392803e-05, + "loss": 3.9314, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657989285641751e-05, + "loss": 3.927, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657150690890699e-05, + "loss": 3.9292, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.65631373402002e-05, + "loss": 3.9496, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655475139268968e-05, + "loss": 3.9352, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654636544517916e-05, + "loss": 3.9424, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653797949766864e-05, + "loss": 3.9358, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652960992896185e-05, + "loss": 3.9475, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652122398145134e-05, + "loss": 3.9289, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651283803394082e-05, + "loss": 3.9288, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.6504468465234026e-05, + "loss": 3.9297, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6496082517723506e-05, + "loss": 3.9367, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487696570212986e-05, + "loss": 3.9193, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479310622702466e-05, + "loss": 3.9214, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470924675191946e-05, + "loss": 3.9251, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462555106485155e-05, + "loss": 3.9295, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454169158974635e-05, + "loss": 3.9307, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445783211464115e-05, + "loss": 3.9375, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437397263953595e-05, + "loss": 3.9183, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429027695246804e-05, + "loss": 3.9237, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642064174773629e-05, + "loss": 3.9183, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641225580022577e-05, + "loss": 3.9372, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640386985271525e-05, + "loss": 3.9361, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639550028400846e-05, + "loss": 3.923, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638711433649794e-05, + "loss": 3.9195, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637872838898742e-05, + "loss": 3.9295, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.63703424414769e-05, + "loss": 3.9306, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636197287277011e-05, + "loss": 3.9315, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635358692525959e-05, + "loss": 3.9229, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634520097774907e-05, + "loss": 3.9254, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633681503023855e-05, + "loss": 3.9259, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632844546153176e-05, + "loss": 3.9314, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320059514021244e-05, + "loss": 3.9166, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311673566510724e-05, + "loss": 3.9202, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303287619000204e-05, + "loss": 3.9183, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294918050293413e-05, + "loss": 3.9001, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286532102782893e-05, + "loss": 3.9326, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6278146155272373e-05, + "loss": 3.9187, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626976020776185e-05, + "loss": 3.9185, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626139063905506e-05, + "loss": 3.9236, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625300469154454e-05, + "loss": 3.9071, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.955702543258667, + "eval_runtime": 332.6666, + "eval_samples_per_second": 1147.067, + "eval_steps_per_second": 35.847, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624461874403402e-05, + "loss": 3.9132, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.62362327965235e-05, + "loss": 3.9036, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622786322781671e-05, + "loss": 3.9266, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.62194772803062e-05, + "loss": 3.9089, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621109133279568e-05, + "loss": 3.9336, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620270538528516e-05, + "loss": 3.8994, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619433581657837e-05, + "loss": 3.9112, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618594986906785e-05, + "loss": 3.8926, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617756392155733e-05, + "loss": 3.9158, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616917797404681e-05, + "loss": 3.9105, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616079202653629e-05, + "loss": 3.9118, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.6152422457829496e-05, + "loss": 3.9244, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6144052889122705e-05, + "loss": 3.8999, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135666941612185e-05, + "loss": 3.904, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127280994101665e-05, + "loss": 3.8977, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611889504659115e-05, + "loss": 3.898, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611050909908063e-05, + "loss": 3.9013, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610212315157011e-05, + "loss": 3.8985, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609373720405959e-05, + "loss": 3.8976, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085351256549065e-05, + "loss": 3.9142, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607698168784228e-05, + "loss": 3.9004, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606859574033176e-05, + "loss": 3.8995, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606020979282124e-05, + "loss": 3.9042, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605184022411445e-05, + "loss": 3.9072, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604345427660393e-05, + "loss": 3.8939, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603506832909341e-05, + "loss": 3.8984, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602668238158289e-05, + "loss": 3.8964, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.60183128128761e-05, + "loss": 3.8911, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009926865365585e-05, + "loss": 3.8893, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.6001540917855065e-05, + "loss": 3.8919, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599315497034454e-05, + "loss": 3.9017, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.5984785401637754e-05, + "loss": 3.8929, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.5976399454127234e-05, + "loss": 3.905, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5968013506616714e-05, + "loss": 3.8904, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595962755910619e-05, + "loss": 3.8908, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595124161159567e-05, + "loss": 3.8915, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594285566408515e-05, + "loss": 3.8846, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593446971657463e-05, + "loss": 3.8822, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592608376906411e-05, + "loss": 3.8787, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591771420035732e-05, + "loss": 3.882, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.59093282528468e-05, + "loss": 3.8901, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590094230533628e-05, + "loss": 3.8923, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589257273662949e-05, + "loss": 3.8899, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588418678911897e-05, + "loss": 3.8854, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587580084160845e-05, + "loss": 3.8984, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586741489409793e-05, + "loss": 3.8848, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585904532539114e-05, + "loss": 3.8845, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585065937788062e-05, + "loss": 3.8807, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.58422734303701e-05, + "loss": 3.8698, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583388748285958e-05, + "loss": 3.891, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582551791415279e-05, + "loss": 3.8788, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581713196664228e-05, + "loss": 3.8822, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580874601913176e-05, + "loss": 3.8755, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580036007162124e-05, + "loss": 3.8864, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.5791990502914446e-05, + "loss": 3.862, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783604555403926e-05, + "loss": 3.8892, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.5775218607893406e-05, + "loss": 3.8738, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.5766832660382886e-05, + "loss": 3.8861, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758463091676095e-05, + "loss": 3.8822, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5750077144165575e-05, + "loss": 3.8716, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741691196655055e-05, + "loss": 3.8653, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733305249144535e-05, + "loss": 3.8857, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724935680437744e-05, + "loss": 3.8626, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571654973292723e-05, + "loss": 3.8617, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570816378541671e-05, + "loss": 3.8799, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569977783790619e-05, + "loss": 3.8746, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.56914082691994e-05, + "loss": 3.8611, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568302232168888e-05, + "loss": 3.8636, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567463637417836e-05, + "loss": 3.8636, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566625042666784e-05, + "loss": 3.8826, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565788085796105e-05, + "loss": 3.8732, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564949491045053e-05, + "loss": 3.8679, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564110896294001e-05, + "loss": 3.879, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563272301542949e-05, + "loss": 3.8778, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.56243534467227e-05, + "loss": 3.8755, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.5615967499212184e-05, + "loss": 3.8567, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.5607581551701664e-05, + "loss": 3.8742, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.5599195604191144e-05, + "loss": 3.869, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559082603548435e-05, + "loss": 3.8618, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558244008797383e-05, + "loss": 3.881, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557405414046331e-05, + "loss": 3.8672, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556566819295279e-05, + "loss": 3.8755, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557298624246e-05, + "loss": 3.8708, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554891267673548e-05, + "loss": 3.8586, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554052672922496e-05, + "loss": 3.866, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553214078171444e-05, + "loss": 3.8629, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552377121300765e-05, + "loss": 3.8672, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551538526549714e-05, + "loss": 3.8692, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550699931798662e-05, + "loss": 3.8605, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.54986133704761e-05, + "loss": 3.8701, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549024380176931e-05, + "loss": 3.8701, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548185785425879e-05, + "loss": 3.8626, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547347190674827e-05, + "loss": 3.8635, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546508595923775e-05, + "loss": 3.8626, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.5456716390530956e-05, + "loss": 3.8761, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.5448330443020436e-05, + "loss": 3.8614, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5439944495509916e-05, + "loss": 3.8608, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431558547999396e-05, + "loss": 3.8647, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.5423188979292605e-05, + "loss": 3.8627, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541480303178209e-05, + "loss": 3.8748, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540641708427157e-05, + "loss": 3.8612, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539803113676105e-05, + "loss": 3.86, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538966156805426e-05, + "loss": 3.8575, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538127562054374e-05, + "loss": 3.8641, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537288967303322e-05, + "loss": 3.8395, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.53645037255227e-05, + "loss": 3.852, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535613415681591e-05, + "loss": 3.8634, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534774820930539e-05, + "loss": 3.8548, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533936226179487e-05, + "loss": 3.8488, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533097631428435e-05, + "loss": 3.8493, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532260674557756e-05, + "loss": 3.8526, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314220798067045e-05, + "loss": 3.8746, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305834850556525e-05, + "loss": 3.8535, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297448903046005e-05, + "loss": 3.8626, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5289079334339214e-05, + "loss": 3.8577, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280693386828694e-05, + "loss": 3.8705, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.5272307439318174e-05, + "loss": 3.8551, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5263921491807654e-05, + "loss": 3.848, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525555192310086e-05, + "loss": 3.8573, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524716597559034e-05, + "loss": 3.8591, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523878002807982e-05, + "loss": 3.8424, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.52303940805693e-05, + "loss": 3.8437, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522202451186251e-05, + "loss": 3.8514, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213638564352e-05, + "loss": 3.8528, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520525261684148e-05, + "loss": 3.8496, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519686666933096e-05, + "loss": 3.8649, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518849710062417e-05, + "loss": 3.8406, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.518011115311365e-05, + "loss": 3.8472, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517172520560313e-05, + "loss": 3.8414, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516333925809261e-05, + "loss": 3.8633, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515496968938582e-05, + "loss": 3.8621, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.51465837418753e-05, + "loss": 3.8497, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513819779436478e-05, + "loss": 3.8421, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512981184685426e-05, + "loss": 3.855, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.5121442278147466e-05, + "loss": 3.8557, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.5113056330636946e-05, + "loss": 3.8544, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510467038312643e-05, + "loss": 3.8516, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509628443561591e-05, + "loss": 3.8483, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508791486690912e-05, + "loss": 3.8531, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.50795289193986e-05, + "loss": 3.861, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507114297188808e-05, + "loss": 3.8418, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506275702437756e-05, + "loss": 3.844, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505438745567077e-05, + "loss": 3.8443, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504600150816025e-05, + "loss": 3.8338, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503761556064973e-05, + "loss": 3.8571, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502922961313921e-05, + "loss": 3.8462, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502086004443242e-05, + "loss": 3.8479, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.50124740969219e-05, + "loss": 3.8463, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.5004088149411386e-05, + "loss": 3.8411, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9141323566436768, + "eval_runtime": 322.8123, + "eval_samples_per_second": 1182.083, + "eval_steps_per_second": 36.941, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499570220190086e-05, + "loss": 3.8416, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498731625439034e-05, + "loss": 3.8319, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497893030687982e-05, + "loss": 3.8525, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.49705443593693e-05, + "loss": 3.8405, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496215841185878e-05, + "loss": 3.8604, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495377246434826e-05, + "loss": 3.8362, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494538651683774e-05, + "loss": 3.8373, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493700056932722e-05, + "loss": 3.8235, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492863100062043e-05, + "loss": 3.8399, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492024505310991e-05, + "loss": 3.844, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491185910559939e-05, + "loss": 3.8403, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490347315808887e-05, + "loss": 3.8492, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489511996818581e-05, + "loss": 3.8348, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488673402067529e-05, + "loss": 3.8342, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487834807316477e-05, + "loss": 3.8279, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486996212565425e-05, + "loss": 3.825, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486157617814373e-05, + "loss": 3.8331, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485319023063321e-05, + "loss": 3.8316, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484480428312269e-05, + "loss": 3.8267, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483641833561217e-05, + "loss": 3.8432, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482804876690538e-05, + "loss": 3.8336, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481966281939486e-05, + "loss": 3.8315, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481127687188434e-05, + "loss": 3.8343, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480289092437382e-05, + "loss": 3.8394, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479452135566704e-05, + "loss": 3.8223, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478613540815652e-05, + "loss": 3.837, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.4777749460646e-05, + "loss": 3.8226, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.4769379891939207e-05, + "loss": 3.8259, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.4760993944428687e-05, + "loss": 3.8221, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.4752607996918166e-05, + "loss": 3.8248, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.4744222049407646e-05, + "loss": 3.8333, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.4735852480700856e-05, + "loss": 3.83, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.4727466533190335e-05, + "loss": 3.8343, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4719080585679815e-05, + "loss": 3.8254, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710694638169295e-05, + "loss": 3.8196, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4702308690658775e-05, + "loss": 3.8266, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469392274314826e-05, + "loss": 3.8206, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468553679563774e-05, + "loss": 3.8137, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467715084812722e-05, + "loss": 3.8144, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466878127942043e-05, + "loss": 3.8156, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466039533190991e-05, + "loss": 3.8241, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465200938439939e-05, + "loss": 3.8296, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.46436398156926e-05, + "loss": 3.824, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463525386818208e-05, + "loss": 3.8169, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462686792067156e-05, + "loss": 3.8319, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461848197316104e-05, + "loss": 3.824, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.461011240445425e-05, + "loss": 3.8192, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460172645694373e-05, + "loss": 3.8153, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593340509433216e-05, + "loss": 3.8031, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584954561922696e-05, + "loss": 3.8277, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576584993215905e-05, + "loss": 3.8143, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568199045705385e-05, + "loss": 3.819, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559813098194865e-05, + "loss": 3.8164, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551427150684345e-05, + "loss": 3.8118, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4543057581977554e-05, + "loss": 3.8038, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534671634467034e-05, + "loss": 3.8188, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526285686956514e-05, + "loss": 3.8141, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517899739445994e-05, + "loss": 3.8256, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.45095301707392e-05, + "loss": 3.8174, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450114422322868e-05, + "loss": 3.8099, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449275827571816e-05, + "loss": 3.802, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448437232820764e-05, + "loss": 3.82, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447600275950086e-05, + "loss": 3.8024, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446761681199034e-05, + "loss": 3.7986, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445923086447982e-05, + "loss": 3.8142, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445084491696929e-05, + "loss": 3.8154, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444247534826251e-05, + "loss": 3.798, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443408940075199e-05, + "loss": 3.8004, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442570345324147e-05, + "loss": 3.7985, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441731750573094e-05, + "loss": 3.8177, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.4408947937024156e-05, + "loss": 3.813, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.4400561989513636e-05, + "loss": 3.8089, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.4392176042003116e-05, + "loss": 3.8165, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.4383790094492596e-05, + "loss": 3.8129, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437542052578581e-05, + "loss": 3.8182, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436703457827529e-05, + "loss": 3.7994, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.4358648630764765e-05, + "loss": 3.8094, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4350262683254245e-05, + "loss": 3.8088, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434189311454746e-05, + "loss": 3.7979, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333507167036934e-05, + "loss": 3.8221, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4325121219526414e-05, + "loss": 3.807, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316735272015894e-05, + "loss": 3.8136, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430836570330911e-05, + "loss": 3.8163, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429997975579859e-05, + "loss": 3.7993, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429159380828807e-05, + "loss": 3.8028, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428320786077755e-05, + "loss": 3.8023, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274838292070766e-05, + "loss": 3.8047, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426645234456024e-05, + "loss": 3.8073, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425806639704972e-05, + "loss": 3.8042, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.42496804495392e-05, + "loss": 3.8089, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424131088083241e-05, + "loss": 3.8093, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423292493332189e-05, + "loss": 3.8004, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224555364615104e-05, + "loss": 3.804, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216169417104584e-05, + "loss": 3.8028, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207783469594064e-05, + "loss": 3.8162, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199397522083544e-05, + "loss": 3.8058, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4191011574573024e-05, + "loss": 3.7998, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182625627062504e-05, + "loss": 3.8058, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174239679551984e-05, + "loss": 3.8037, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165853732041464e-05, + "loss": 3.8171, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415748416333467e-05, + "loss": 3.8041, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414909821582415e-05, + "loss": 3.8002, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414071226831363e-05, + "loss": 3.7982, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413232632080311e-05, + "loss": 3.8083, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412395675209632e-05, + "loss": 3.7827, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.41155708045858e-05, + "loss": 3.7942, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410718485707528e-05, + "loss": 3.8034, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409879890956476e-05, + "loss": 3.8017, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409042934085798e-05, + "loss": 3.7904, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4082059772151186e-05, + "loss": 3.7902, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073673824640666e-05, + "loss": 3.7966, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4065287877130146e-05, + "loss": 3.813, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056901929619626e-05, + "loss": 3.8012, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.4048515982109106e-05, + "loss": 3.8017, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4040130034598586e-05, + "loss": 3.8018, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031744087088066e-05, + "loss": 3.8087, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.4023358139577546e-05, + "loss": 3.8021, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.4014988570870755e-05, + "loss": 3.7891, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.4006602623360235e-05, + "loss": 3.799, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.3998216675849715e-05, + "loss": 3.8028, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.39898307283392e-05, + "loss": 3.7849, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398146115963241e-05, + "loss": 3.7897, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397307521212189e-05, + "loss": 3.7914, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396468926461137e-05, + "loss": 3.7976, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395630331710085e-05, + "loss": 3.7941, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394793374839406e-05, + "loss": 3.8068, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393954780088354e-05, + "loss": 3.7833, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393116185337302e-05, + "loss": 3.7931, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.39227759058625e-05, + "loss": 3.7862, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391440633715571e-05, + "loss": 3.8095, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390602038964519e-05, + "loss": 3.8, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389763444213467e-05, + "loss": 3.8004, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889248494624155e-05, + "loss": 3.7832, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880878925917365e-05, + "loss": 3.7999, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872492978406845e-05, + "loss": 3.8044, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3864107030896325e-05, + "loss": 3.7964, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855721083385804e-05, + "loss": 3.7922, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847351514679014e-05, + "loss": 3.7994, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838965567168494e-05, + "loss": 3.7953, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830579619657973e-05, + "loss": 3.8065, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822193672147453e-05, + "loss": 3.7827, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381382410344066e-05, + "loss": 3.7917, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380543815593014e-05, + "loss": 3.788, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379705220841962e-05, + "loss": 3.781, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378866626090911e-05, + "loss": 3.7993, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378028031339859e-05, + "loss": 3.7927, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377189436588807e-05, + "loss": 3.7947, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376350841837754e-05, + "loss": 3.7903, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375512247086702e-05, + "loss": 3.7899, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8890888690948486, + "eval_runtime": 303.1724, + "eval_samples_per_second": 1258.66, + "eval_steps_per_second": 39.334, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374675290216024e-05, + "loss": 3.7866, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373836695464972e-05, + "loss": 3.7761, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372998100713919e-05, + "loss": 3.7992, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372159505962867e-05, + "loss": 3.7879, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371322549092189e-05, + "loss": 3.8029, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370483954341137e-05, + "loss": 3.7848, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369645359590085e-05, + "loss": 3.7779, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368808402719406e-05, + "loss": 3.773, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367969807968354e-05, + "loss": 3.7845, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.3671312132173016e-05, + "loss": 3.7931, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.3662926184662496e-05, + "loss": 3.7869, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365455661595571e-05, + "loss": 3.7966, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364618704724892e-05, + "loss": 3.7816, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.36378010997384e-05, + "loss": 3.7852, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362941515222788e-05, + "loss": 3.776, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362102920471736e-05, + "loss": 3.7702, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361264325720684e-05, + "loss": 3.7804, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.3604257309696314e-05, + "loss": 3.7799, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.35958713621858e-05, + "loss": 3.7745, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358748541467528e-05, + "loss": 3.7898, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357911584596849e-05, + "loss": 3.7855, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357072989845797e-05, + "loss": 3.7806, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356234395094745e-05, + "loss": 3.7796, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355395800343693e-05, + "loss": 3.7852, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354558843473014e-05, + "loss": 3.7715, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353720248721962e-05, + "loss": 3.7856, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.35288165397091e-05, + "loss": 3.7727, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3520446971002314e-05, + "loss": 3.7747, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351206102349179e-05, + "loss": 3.7747, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350367507598127e-05, + "loss": 3.7715, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349528912847075e-05, + "loss": 3.7824, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486919559763963e-05, + "loss": 3.7814, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347853361225344e-05, + "loss": 3.7814, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.347014766474292e-05, + "loss": 3.7748, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.34617617172324e-05, + "loss": 3.7683, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345337576972188e-05, + "loss": 3.7815, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344498982221136e-05, + "loss": 3.7711, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343660387470084e-05, + "loss": 3.7599, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342821792719032e-05, + "loss": 3.7668, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341984835848353e-05, + "loss": 3.764, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341146241097301e-05, + "loss": 3.7714, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340307646346249e-05, + "loss": 3.7809, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339469051595197e-05, + "loss": 3.7719, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338632094724519e-05, + "loss": 3.7718, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337793499973467e-05, + "loss": 3.7793, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336954905222415e-05, + "loss": 3.7716, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336117948351736e-05, + "loss": 3.7726, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335279353600684e-05, + "loss": 3.7661, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334440758849632e-05, + "loss": 3.7497, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.33360216409858e-05, + "loss": 3.7797, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.3327652072279006e-05, + "loss": 3.7643, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.3319266124768486e-05, + "loss": 3.7718, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.3310880177257966e-05, + "loss": 3.7652, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.3302494229747446e-05, + "loss": 3.7622, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3294124661040655e-05, + "loss": 3.7588, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328573871353014e-05, + "loss": 3.7662, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327735276601962e-05, + "loss": 3.7677, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.32689668185091e-05, + "loss": 3.7754, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326059724980231e-05, + "loss": 3.7666, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325221130229179e-05, + "loss": 3.7657, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324382535478127e-05, + "loss": 3.75, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323543940727075e-05, + "loss": 3.7754, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322706983856396e-05, + "loss": 3.754, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321868389105344e-05, + "loss": 3.751, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321029794354292e-05, + "loss": 3.7642, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.32019119960324e-05, + "loss": 3.7679, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319354242732561e-05, + "loss": 3.7474, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3185156479815095e-05, + "loss": 3.7572, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.3176770532304575e-05, + "loss": 3.7473, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3168384584794055e-05, + "loss": 3.7724, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.3160015016087264e-05, + "loss": 3.7629, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151629068576744e-05, + "loss": 3.7628, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314325949986995e-05, + "loss": 3.768, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313487355235943e-05, + "loss": 3.7613, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312648760484891e-05, + "loss": 3.7751, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311810165733839e-05, + "loss": 3.7493, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310971570982787e-05, + "loss": 3.7659, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310132976231735e-05, + "loss": 3.7597, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309294381480683e-05, + "loss": 3.7512, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308455786729631e-05, + "loss": 3.7686, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307618829858953e-05, + "loss": 3.7658, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306780235107901e-05, + "loss": 3.7642, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305941640356849e-05, + "loss": 3.7702, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305103045605797e-05, + "loss": 3.7516, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304266088735118e-05, + "loss": 3.7556, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303427493984066e-05, + "loss": 3.7528, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302588899233014e-05, + "loss": 3.7582, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301750304481962e-05, + "loss": 3.7593, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300913347611283e-05, + "loss": 3.759, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300074752860231e-05, + "loss": 3.7581, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299236158109179e-05, + "loss": 3.7653, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298397563358127e-05, + "loss": 3.7533, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297562244367821e-05, + "loss": 3.757, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296723649616769e-05, + "loss": 3.7594, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295885054865717e-05, + "loss": 3.7688, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295046460114665e-05, + "loss": 3.763, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294207865363613e-05, + "loss": 3.7499, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293369270612561e-05, + "loss": 3.7605, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292530675861509e-05, + "loss": 3.7593, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.2916920811104565e-05, + "loss": 3.7652, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290855124239778e-05, + "loss": 3.7597, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.290018167369099e-05, + "loss": 3.7547, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289179572618047e-05, + "loss": 3.7472, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.2883409778669956e-05, + "loss": 3.7668, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.2875023831159436e-05, + "loss": 3.7362, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.2866637883648916e-05, + "loss": 3.7531, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858251936138396e-05, + "loss": 3.7554, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284986598862787e-05, + "loss": 3.7519, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.2841496419921085e-05, + "loss": 3.7469, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2833110472410565e-05, + "loss": 3.7462, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282472452490004e-05, + "loss": 3.7515, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281633857738952e-05, + "loss": 3.7661, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807952629879e-05, + "loss": 3.7573, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279956668236848e-05, + "loss": 3.7531, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2791197113661694e-05, + "loss": 3.7595, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782811166151174e-05, + "loss": 3.763, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2774425218640654e-05, + "loss": 3.7578, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2766039271130134e-05, + "loss": 3.7439, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757653323619614e-05, + "loss": 3.7554, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2749267376109094e-05, + "loss": 3.7551, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.2740881428598574e-05, + "loss": 3.7399, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.2732495481088054e-05, + "loss": 3.7441, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272412591238126e-05, + "loss": 3.7505, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271573996487074e-05, + "loss": 3.7498, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270735401736022e-05, + "loss": 3.7507, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.26989680698497e-05, + "loss": 3.76, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269059850114291e-05, + "loss": 3.7416, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268221255363239e-05, + "loss": 3.746, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267382660612187e-05, + "loss": 3.7462, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266544065861136e-05, + "loss": 3.7626, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265707108990457e-05, + "loss": 3.7538, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264868514239405e-05, + "loss": 3.7562, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.264029919488353e-05, + "loss": 3.7426, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263191324737301e-05, + "loss": 3.7558, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623543678666216e-05, + "loss": 3.759, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2615157731155696e-05, + "loss": 3.7516, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606771783645176e-05, + "loss": 3.749, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2598385836134656e-05, + "loss": 3.7546, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2590016267427865e-05, + "loss": 3.75, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581630319917345e-05, + "loss": 3.7651, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.2573244372406825e-05, + "loss": 3.7386, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256487480370004e-05, + "loss": 3.7528, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255648885618952e-05, + "loss": 3.7392, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.2548102908679e-05, + "loss": 3.7408, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253971696116848e-05, + "loss": 3.7571, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253133101365796e-05, + "loss": 3.7436, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252294506614744e-05, + "loss": 3.7594, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251455911863692e-05, + "loss": 3.7398, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.25061731711264e-05, + "loss": 3.7523, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.8726401329040527, + "eval_runtime": 302.2559, + "eval_samples_per_second": 1262.477, + "eval_steps_per_second": 39.453, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249780360241961e-05, + "loss": 3.7567, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248941765490909e-05, + "loss": 3.7283, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248103170739857e-05, + "loss": 3.7523, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247264575988805e-05, + "loss": 3.7484, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246425981237753e-05, + "loss": 3.7593, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245587386486701e-05, + "loss": 3.7397, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244748791735649e-05, + "loss": 3.7372, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243910196984597e-05, + "loss": 3.7347, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243073240113918e-05, + "loss": 3.7408, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242234645362866e-05, + "loss": 3.7481, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241396050611814e-05, + "loss": 3.7466, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240557455860762e-05, + "loss": 3.7526, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.2397221368704564e-05, + "loss": 3.7434, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388835421194044e-05, + "loss": 3.7404, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380449473683524e-05, + "loss": 3.7335, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2372063526173004e-05, + "loss": 3.7258, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363677578662484e-05, + "loss": 3.7406, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355291631151963e-05, + "loss": 3.7341, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346905683641443e-05, + "loss": 3.7352, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233851973613092e-05, + "loss": 3.7448, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233015016742413e-05, + "loss": 3.7468, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232176421991361e-05, + "loss": 3.7382, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231337827240309e-05, + "loss": 3.7374, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230499232489257e-05, + "loss": 3.742, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229662275618578e-05, + "loss": 3.7341, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228823680867526e-05, + "loss": 3.7397, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227985086116474e-05, + "loss": 3.7316, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227146491365422e-05, + "loss": 3.7356, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226309534494744e-05, + "loss": 3.7336, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225470939743692e-05, + "loss": 3.7323, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.22463234499264e-05, + "loss": 3.7353, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237953881219606e-05, + "loss": 3.7409, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2229567933709086e-05, + "loss": 3.7386, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2221181986198566e-05, + "loss": 3.7367, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212796038688046e-05, + "loss": 3.7273, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2204426469981255e-05, + "loss": 3.739, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2196040522470735e-05, + "loss": 3.7338, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187654574960215e-05, + "loss": 3.7225, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2179268627449695e-05, + "loss": 3.7227, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170882679939175e-05, + "loss": 3.7227, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2162496732428655e-05, + "loss": 3.7286, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2154110784918135e-05, + "loss": 3.7381, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214574121621135e-05, + "loss": 3.7315, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213735526870083e-05, + "loss": 3.7352, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212896932119031e-05, + "loss": 3.7401, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212058337367979e-05, + "loss": 3.7288, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211219742616927e-05, + "loss": 3.7319, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210382785746248e-05, + "loss": 3.7286, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209544190995196e-05, + "loss": 3.7038, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208705596244144e-05, + "loss": 3.7417, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207867001493092e-05, + "loss": 3.7235, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.20702840674204e-05, + "loss": 3.737, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206191449871361e-05, + "loss": 3.7232, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205352855120309e-05, + "loss": 3.7276, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045142603692575e-05, + "loss": 3.7168, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036756656182055e-05, + "loss": 3.7258, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028370708671535e-05, + "loss": 3.7275, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201998476116101e-05, + "loss": 3.7372, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201159881365049e-05, + "loss": 3.7345, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200321286613997e-05, + "loss": 3.7206, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994843297433184e-05, + "loss": 3.7099, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198645734992266e-05, + "loss": 3.74, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197807140241214e-05, + "loss": 3.712, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196968545490162e-05, + "loss": 3.708, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196131588619483e-05, + "loss": 3.7271, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195292993868431e-05, + "loss": 3.7316, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194454399117379e-05, + "loss": 3.706, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193615804366327e-05, + "loss": 3.7171, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192778847495648e-05, + "loss": 3.7122, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191940252744596e-05, + "loss": 3.7298, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191101657993544e-05, + "loss": 3.7256, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190263063242492e-05, + "loss": 3.7251, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189427744252187e-05, + "loss": 3.7254, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188589149501135e-05, + "loss": 3.7255, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187750554750083e-05, + "loss": 3.736, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.18691195999903e-05, + "loss": 3.7088, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186073365247978e-05, + "loss": 3.729, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185234770496927e-05, + "loss": 3.7238, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184397813626248e-05, + "loss": 3.7125, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835592188751956e-05, + "loss": 3.7279, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1827206241241436e-05, + "loss": 3.7289, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818820293730916e-05, + "loss": 3.7262, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.1810434346220396e-05, + "loss": 3.7306, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1802048398709876e-05, + "loss": 3.7101, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793662451199356e-05, + "loss": 3.7152, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1785276503688836e-05, + "loss": 3.7163, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776906934982045e-05, + "loss": 3.7216, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1768520987471525e-05, + "loss": 3.7216, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760135039961005e-05, + "loss": 3.7259, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175176547125422e-05, + "loss": 3.7114, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.17433795237437e-05, + "loss": 3.7293, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173499357623318e-05, + "loss": 3.7158, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172660762872266e-05, + "loss": 3.719, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171822168121214e-05, + "loss": 3.722, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170985211250535e-05, + "loss": 3.7281, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170146616499483e-05, + "loss": 3.7278, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169308021748431e-05, + "loss": 3.7114, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168469426997379e-05, + "loss": 3.7218, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167630832246327e-05, + "loss": 3.7225, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166793875375648e-05, + "loss": 3.7248, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165955280624596e-05, + "loss": 3.7238, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165116685873544e-05, + "loss": 3.7169, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164278091122492e-05, + "loss": 3.7149, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1634394963714405e-05, + "loss": 3.7258, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1626009016203885e-05, + "loss": 3.7004, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617623068693365e-05, + "loss": 3.713, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609237121182845e-05, + "loss": 3.7163, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.1600867552476054e-05, + "loss": 3.7169, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159249798376926e-05, + "loss": 3.7081, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158411203625874e-05, + "loss": 3.7121, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157572608874822e-05, + "loss": 3.7157, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.15673401412377e-05, + "loss": 3.7273, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155895419372718e-05, + "loss": 3.7216, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155056824621666e-05, + "loss": 3.7144, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154219867750987e-05, + "loss": 3.7241, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153381272999936e-05, + "loss": 3.7272, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152542678248884e-05, + "loss": 3.7231, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151704083497832e-05, + "loss": 3.706, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150865488746779e-05, + "loss": 3.718, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150026893995727e-05, + "loss": 3.7178, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149189937125049e-05, + "loss": 3.7025, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148351342373997e-05, + "loss": 3.7078, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147512747622944e-05, + "loss": 3.7133, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146674152871892e-05, + "loss": 3.7097, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.14583555812084e-05, + "loss": 3.7162, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144996963369788e-05, + "loss": 3.7234, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144158368618736e-05, + "loss": 3.7081, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143319773867684e-05, + "loss": 3.7079, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424828169970056e-05, + "loss": 3.7135, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1416442222459536e-05, + "loss": 3.7234, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1408056274949016e-05, + "loss": 3.7168, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399670327438496e-05, + "loss": 3.7235, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1391300758731705e-05, + "loss": 3.7049, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382931190024914e-05, + "loss": 3.7203, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1374545242514394e-05, + "loss": 3.7225, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1366159295003874e-05, + "loss": 3.7143, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357773347493354e-05, + "loss": 3.7174, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349387399982834e-05, + "loss": 3.7153, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1341001452472314e-05, + "loss": 3.7152, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1332615504961794e-05, + "loss": 3.7294, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324229557451274e-05, + "loss": 3.7058, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131585998874449e-05, + "loss": 3.7144, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130747404123397e-05, + "loss": 3.7048, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129908809372345e-05, + "loss": 3.7064, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129070214621293e-05, + "loss": 3.7161, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128231619870241e-05, + "loss": 3.711, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127393025119189e-05, + "loss": 3.7203, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126554430368137e-05, + "loss": 3.705, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125717473497458e-05, + "loss": 3.7189, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.8624958992004395, + "eval_runtime": 303.3265, + "eval_samples_per_second": 1258.021, + "eval_steps_per_second": 39.314, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124878878746406e-05, + "loss": 3.7061, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.124040283995354e-05, + "loss": 3.6947, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123201689244302e-05, + "loss": 3.7139, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.12236309449325e-05, + "loss": 3.7115, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1215261376225714e-05, + "loss": 3.722, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.1206875428715194e-05, + "loss": 3.7079, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.1198489481204674e-05, + "loss": 3.7033, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.1190103533694154e-05, + "loss": 3.7028, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118171758618363e-05, + "loss": 3.7067, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117333163867311e-05, + "loss": 3.7103, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116494569116259e-05, + "loss": 3.7106, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115655974365207e-05, + "loss": 3.7161, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1148190174945276e-05, + "loss": 3.7067, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139804227434756e-05, + "loss": 3.7066, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.1131418279924236e-05, + "loss": 3.7019, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.1123032332413716e-05, + "loss": 3.6916, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.1114646384903196e-05, + "loss": 3.7036, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110626043739268e-05, + "loss": 3.704, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109789086868589e-05, + "loss": 3.7004, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108950492117537e-05, + "loss": 3.7021, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108111897366485e-05, + "loss": 3.719, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107273302615433e-05, + "loss": 3.7041, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106434707864381e-05, + "loss": 3.7032, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105596113113329e-05, + "loss": 3.704, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.10475915624265e-05, + "loss": 3.7019, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103920561491598e-05, + "loss": 3.7059, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103081966740546e-05, + "loss": 3.6997, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102243371989494e-05, + "loss": 3.7041, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101404777238442e-05, + "loss": 3.696, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.10056618248739e-05, + "loss": 3.6943, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099727587736338e-05, + "loss": 3.7003, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988906308656597e-05, + "loss": 3.7085, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0980520361146076e-05, + "loss": 3.7073, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0972134413635556e-05, + "loss": 3.7047, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963748466125036e-05, + "loss": 3.6928, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0955378897418245e-05, + "loss": 3.6985, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0946992949907725e-05, + "loss": 3.6989, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0938607002397205e-05, + "loss": 3.6922, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930221054886685e-05, + "loss": 3.6891, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092183510737616e-05, + "loss": 3.6879, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091344915986564e-05, + "loss": 3.6963, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090506321235512e-05, + "loss": 3.701, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.0896693643648334e-05, + "loss": 3.6973, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0888307696137814e-05, + "loss": 3.7035, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.0879921748627294e-05, + "loss": 3.7015, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.0871535801116774e-05, + "loss": 3.6973, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.0863149853606254e-05, + "loss": 3.6994, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.0854763906095734e-05, + "loss": 3.6942, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.0846377958585214e-05, + "loss": 3.6726, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.0837992011074694e-05, + "loss": 3.7067, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.08296224423679e-05, + "loss": 3.6885, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082125287366111e-05, + "loss": 3.7041, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081286692615059e-05, + "loss": 3.6939, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080448097864007e-05, + "loss": 3.6918, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079609503112955e-05, + "loss": 3.6824, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078770908361904e-05, + "loss": 3.6891, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077932313610852e-05, + "loss": 3.6988, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0770937188598e-05, + "loss": 3.6991, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076256761989121e-05, + "loss": 3.7007, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075418167238069e-05, + "loss": 3.69, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074579572487017e-05, + "loss": 3.6773, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073740977735965e-05, + "loss": 3.7061, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072902382984913e-05, + "loss": 3.6824, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072063788233861e-05, + "loss": 3.6724, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071225193482809e-05, + "loss": 3.6938, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070386598731757e-05, + "loss": 3.6996, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.0695496418610777e-05, + "loss": 3.6765, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.0687110471100257e-05, + "loss": 3.6863, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.0678724523589736e-05, + "loss": 3.6775, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067033857607922e-05, + "loss": 3.6957, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066196900737243e-05, + "loss": 3.6948, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065358305986191e-05, + "loss": 3.6883, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064521349115512e-05, + "loss": 3.692, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.06368275436446e-05, + "loss": 3.6927, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062844159613408e-05, + "loss": 3.7028, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.062005564862356e-05, + "loss": 3.6782, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061166970111304e-05, + "loss": 3.6978, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060330013240625e-05, + "loss": 3.6859, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059491418489573e-05, + "loss": 3.6842, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.058652823738521e-05, + "loss": 3.695, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.057814228987469e-05, + "loss": 3.6985, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056975634236418e-05, + "loss": 3.6916, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0561386773657386e-05, + "loss": 3.701, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0553000826146866e-05, + "loss": 3.6774, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0544614878636346e-05, + "loss": 3.6822, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053622893112582e-05, + "loss": 3.6852, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.05278429836153e-05, + "loss": 3.6924, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051945703610478e-05, + "loss": 3.685, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051107108859426e-05, + "loss": 3.6934, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050268514108374e-05, + "loss": 3.6812, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049431557237695e-05, + "loss": 3.6985, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048592962486643e-05, + "loss": 3.688, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.0477543677355915e-05, + "loss": 3.6849, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.0469157729845395e-05, + "loss": 3.6896, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.0460788161138604e-05, + "loss": 3.6966, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.0452402213628084e-05, + "loss": 3.6954, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.0444016266117564e-05, + "loss": 3.6826, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.0435630318607044e-05, + "loss": 3.6872, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.0427244371096524e-05, + "loss": 3.6906, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041887480238973e-05, + "loss": 3.6937, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.041048885487921e-05, + "loss": 3.6924, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040210290736869e-05, + "loss": 3.6832, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039371695985817e-05, + "loss": 3.6824, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038534739115138e-05, + "loss": 3.6935, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037696144364087e-05, + "loss": 3.6675, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036857549613035e-05, + "loss": 3.6841, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036018954861983e-05, + "loss": 3.6827, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035181997991304e-05, + "loss": 3.6883, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034343403240252e-05, + "loss": 3.6747, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.0335048084892e-05, + "loss": 3.683, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032666213738148e-05, + "loss": 3.6865, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031827618987096e-05, + "loss": 3.6909, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030989024236044e-05, + "loss": 3.6886, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030150429484992e-05, + "loss": 3.6842, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0293134726143126e-05, + "loss": 3.6916, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284748778632606e-05, + "loss": 3.6985, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0276362831122086e-05, + "loss": 3.6901, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0267976883611566e-05, + "loss": 3.6738, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0259590936101046e-05, + "loss": 3.6867, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025120498859053e-05, + "loss": 3.6885, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024281904108001e-05, + "loss": 3.669, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023444947237322e-05, + "loss": 3.6775, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.02260635248627e-05, + "loss": 3.6812, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021767757735218e-05, + "loss": 3.6814, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0209291629841655e-05, + "loss": 3.6803, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200905682331135e-05, + "loss": 3.6933, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0192519734820615e-05, + "loss": 3.6804, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0184133787310095e-05, + "loss": 3.6754, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175764218603304e-05, + "loss": 3.6795, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0167378271092784e-05, + "loss": 3.6961, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015899232358227e-05, + "loss": 3.6833, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0150622754875486e-05, + "loss": 3.6939, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014223680736496e-05, + "loss": 3.6725, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013385085985444e-05, + "loss": 3.6889, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012546491234392e-05, + "loss": 3.6921, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011709534363713e-05, + "loss": 3.687, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010870939612661e-05, + "loss": 3.6842, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010032344861609e-05, + "loss": 3.6851, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009193750110557e-05, + "loss": 3.6844, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008355155359505e-05, + "loss": 3.6997, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007516560608453e-05, + "loss": 3.6755, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006679603737774e-05, + "loss": 3.6843, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.0058410089867224e-05, + "loss": 3.6774, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.0050024142356704e-05, + "loss": 3.6766, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.0041638194846184e-05, + "loss": 3.6779, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0033252247335664e-05, + "loss": 3.6817, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0024866299825144e-05, + "loss": 3.6924, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001649673111835e-05, + "loss": 3.6749, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000811078360783e-05, + "loss": 3.6871, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.855154275894165, + "eval_runtime": 302.1496, + "eval_samples_per_second": 1262.921, + "eval_steps_per_second": 39.467, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999972483609731e-05, + "loss": 3.6872, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999133888858679e-05, + "loss": 3.665, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998295294107627e-05, + "loss": 3.686, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997456699356575e-05, + "loss": 3.6832, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996619742485896e-05, + "loss": 3.6897, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995781147734844e-05, + "loss": 3.6751, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994942552983792e-05, + "loss": 3.6764, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994103958232741e-05, + "loss": 3.6695, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993265363481689e-05, + "loss": 3.675, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.99242840661101e-05, + "loss": 3.6837, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991589811859958e-05, + "loss": 3.6776, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990751217108906e-05, + "loss": 3.6858, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989914260238227e-05, + "loss": 3.6857, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989075665487175e-05, + "loss": 3.6669, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882370707361227e-05, + "loss": 3.669, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9873984759850707e-05, + "loss": 3.6677, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865598812340187e-05, + "loss": 3.6744, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857212864829666e-05, + "loss": 3.6719, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848826917319146e-05, + "loss": 3.669, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9840440969808626e-05, + "loss": 3.6763, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983207140110184e-05, + "loss": 3.6865, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823685453591315e-05, + "loss": 3.6755, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9815299506080795e-05, + "loss": 3.6734, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9806913558570275e-05, + "loss": 3.6716, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979854398986349e-05, + "loss": 3.6737, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9790158042352964e-05, + "loss": 3.6767, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781772094842444e-05, + "loss": 3.6681, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9773386147331924e-05, + "loss": 3.6809, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976501657862514e-05, + "loss": 3.6658, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975663063111461e-05, + "loss": 3.6629, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974824468360409e-05, + "loss": 3.674, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973985873609358e-05, + "loss": 3.6734, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973147278858306e-05, + "loss": 3.6756, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972310321987627e-05, + "loss": 3.6749, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971471727236575e-05, + "loss": 3.6637, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970633132485523e-05, + "loss": 3.6671, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969794537734471e-05, + "loss": 3.6764, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968955942983419e-05, + "loss": 3.6592, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.96811898611274e-05, + "loss": 3.662, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967280391361688e-05, + "loss": 3.6601, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966441796610636e-05, + "loss": 3.664, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965603201859584e-05, + "loss": 3.6703, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964766244988905e-05, + "loss": 3.6708, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9639276502378534e-05, + "loss": 3.6785, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9630890554868014e-05, + "loss": 3.6667, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9622504607357494e-05, + "loss": 3.6726, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.96141350386507e-05, + "loss": 3.6668, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960574909114018e-05, + "loss": 3.6679, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959736314362966e-05, + "loss": 3.6422, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958897719611914e-05, + "loss": 3.677, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958059124860862e-05, + "loss": 3.6614, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957222167990183e-05, + "loss": 3.6742, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956383573239131e-05, + "loss": 3.6653, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955544978488079e-05, + "loss": 3.6645, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954706383737027e-05, + "loss": 3.6497, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953869426866349e-05, + "loss": 3.6614, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953030832115297e-05, + "loss": 3.6725, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952192237364245e-05, + "loss": 3.6639, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951353642613193e-05, + "loss": 3.6726, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.9505166857425136e-05, + "loss": 3.6668, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.9496780909914616e-05, + "loss": 3.644, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9488394962404096e-05, + "loss": 3.6752, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9480009014893576e-05, + "loss": 3.6568, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471639446186785e-05, + "loss": 3.6462, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9463253498676265e-05, + "loss": 3.6682, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454867551165745e-05, + "loss": 3.6635, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446481603655225e-05, + "loss": 3.648, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9438095656144705e-05, + "loss": 3.6569, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942972608743792e-05, + "loss": 3.653, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.94213401399274e-05, + "loss": 3.6643, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941295419241688e-05, + "loss": 3.6657, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940456824490636e-05, + "loss": 3.6614, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939619867619957e-05, + "loss": 3.6665, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938781272868905e-05, + "loss": 3.6625, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937942678117853e-05, + "loss": 3.676, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937104083366801e-05, + "loss": 3.6484, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936267126496122e-05, + "loss": 3.6681, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.93542853174507e-05, + "loss": 3.657, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934589936994018e-05, + "loss": 3.6541, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933751342242966e-05, + "loss": 3.6671, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329143853722875e-05, + "loss": 3.6687, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9320757906212355e-05, + "loss": 3.6641, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9312371958701835e-05, + "loss": 3.673, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9303986011191315e-05, + "loss": 3.6478, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295616442484524e-05, + "loss": 3.6556, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9287230494974004e-05, + "loss": 3.6559, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.9278844547463484e-05, + "loss": 3.6631, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.9270458599952964e-05, + "loss": 3.6559, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.9262072652442443e-05, + "loss": 3.6645, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925370308373565e-05, + "loss": 3.6571, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924531713622513e-05, + "loss": 3.6667, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923693118871461e-05, + "loss": 3.6607, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922854524120409e-05, + "loss": 3.6581, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922017567249731e-05, + "loss": 3.6634, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921178972498679e-05, + "loss": 3.6676, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920340377747627e-05, + "loss": 3.6713, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919501782996575e-05, + "loss": 3.6556, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918664826125896e-05, + "loss": 3.6553, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917826231374844e-05, + "loss": 3.6633, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916987636623792e-05, + "loss": 3.6694, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916149041872739e-05, + "loss": 3.6632, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915310447121687e-05, + "loss": 3.6608, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144734902510086e-05, + "loss": 3.658, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9136348954999566e-05, + "loss": 3.6642, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.9127963007489046e-05, + "loss": 3.6415, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.9119577059978526e-05, + "loss": 3.6591, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911120749127174e-05, + "loss": 3.6458, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910282154376122e-05, + "loss": 3.6598, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9094435596250695e-05, + "loss": 3.6494, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9086049648740175e-05, + "loss": 3.6596, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907768008003339e-05, + "loss": 3.6567, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9069294132522864e-05, + "loss": 3.6642, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060908185012344e-05, + "loss": 3.6602, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9052522237501824e-05, + "loss": 3.6594, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9044136289991304e-05, + "loss": 3.6643, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903576672128452e-05, + "loss": 3.6671, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027380773774e-05, + "loss": 3.6623, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901899482626348e-05, + "loss": 3.6517, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901060887875296e-05, + "loss": 3.6552, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900223931004617e-05, + "loss": 3.6616, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899385336253565e-05, + "loss": 3.6484, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898546741502513e-05, + "loss": 3.6479, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897708146751461e-05, + "loss": 3.6524, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896869552000409e-05, + "loss": 3.6547, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.89603259512973e-05, + "loss": 3.65, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895194000378678e-05, + "loss": 3.6685, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894355405627626e-05, + "loss": 3.6542, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893516810876574e-05, + "loss": 3.6505, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892678216125522e-05, + "loss": 3.6502, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891841259254843e-05, + "loss": 3.6664, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891002664503791e-05, + "loss": 3.659, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890164069752739e-05, + "loss": 3.6623, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889325475001687e-05, + "loss": 3.6463, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888486880250635e-05, + "loss": 3.6633, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887649923379956e-05, + "loss": 3.665, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886811328628904e-05, + "loss": 3.6599, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885972733877852e-05, + "loss": 3.6575, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8851341391268e-05, + "loss": 3.6525, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884297182256121e-05, + "loss": 3.6584, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883458587505069e-05, + "loss": 3.6726, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882619992754017e-05, + "loss": 3.6494, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881781398002966e-05, + "loss": 3.6569, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880944441132287e-05, + "loss": 3.6517, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880105846381235e-05, + "loss": 3.6512, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879267251630183e-05, + "loss": 3.6507, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878428656879131e-05, + "loss": 3.6555, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8775917000084516e-05, + "loss": 3.6638, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.8767531052573996e-05, + "loss": 3.6538, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8759145105063476e-05, + "loss": 3.6572, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.850785255432129, + "eval_runtime": 304.0309, + "eval_samples_per_second": 1255.106, + "eval_steps_per_second": 39.223, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750759157552956e-05, + "loss": 3.6457, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742373210042436e-05, + "loss": 3.6406, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8734003641335645e-05, + "loss": 3.6571, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.8725617693825125e-05, + "loss": 3.655, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871723174631461e-05, + "loss": 3.6666, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870884579880409e-05, + "loss": 3.6481, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.87004762300973e-05, + "loss": 3.6515, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869209028258678e-05, + "loss": 3.6404, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868370433507626e-05, + "loss": 3.6494, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867531838756574e-05, + "loss": 3.6569, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866693244005522e-05, + "loss": 3.6507, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865856287134843e-05, + "loss": 3.6573, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865017692383791e-05, + "loss": 3.664, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864179097632739e-05, + "loss": 3.6399, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863340502881687e-05, + "loss": 3.6437, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862503546011008e-05, + "loss": 3.64, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616649512599565e-05, + "loss": 3.6494, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8608263565089045e-05, + "loss": 3.6421, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599877617578525e-05, + "loss": 3.6457, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8591491670068e-05, + "loss": 3.6484, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.8583122101361214e-05, + "loss": 3.6568, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.8574736153850694e-05, + "loss": 3.6514, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8566350206340174e-05, + "loss": 3.6457, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855796425882965e-05, + "loss": 3.6468, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854959469012286e-05, + "loss": 3.6492, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854120874261234e-05, + "loss": 3.6524, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853282279510182e-05, + "loss": 3.6367, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.85244368475913e-05, + "loss": 3.6565, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851606727888452e-05, + "loss": 3.6409, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8507681331374e-05, + "loss": 3.6377, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849929538386347e-05, + "loss": 3.6502, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849090943635295e-05, + "loss": 3.6488, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848253986764617e-05, + "loss": 3.6468, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847415392013565e-05, + "loss": 3.6552, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846576797262512e-05, + "loss": 3.6397, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.84573820251146e-05, + "loss": 3.6429, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844899607760408e-05, + "loss": 3.6474, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.844061013009356e-05, + "loss": 3.632, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843224056138677e-05, + "loss": 3.6397, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842385461387626e-05, + "loss": 3.6326, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841546866636574e-05, + "loss": 3.6383, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840708271885522e-05, + "loss": 3.6457, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.8398713150148426e-05, + "loss": 3.6429, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.8390327202637906e-05, + "loss": 3.6513, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8381941255127386e-05, + "loss": 3.6423, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8373555307616866e-05, + "loss": 3.6483, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8365185738910075e-05, + "loss": 3.6437, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356799791399555e-05, + "loss": 3.6418, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8348413843889035e-05, + "loss": 3.6221, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8340027896378515e-05, + "loss": 3.6475, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331658327671724e-05, + "loss": 3.6358, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832327238016121e-05, + "loss": 3.6488, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831488643265069e-05, + "loss": 3.637, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830650048514017e-05, + "loss": 3.638, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829813091643338e-05, + "loss": 3.6278, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828974496892286e-05, + "loss": 3.6364, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828135902141234e-05, + "loss": 3.6477, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827297307390182e-05, + "loss": 3.6371, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826460350519503e-05, + "loss": 3.6517, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825621755768451e-05, + "loss": 3.642, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824783161017399e-05, + "loss": 3.6131, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823944566266347e-05, + "loss": 3.6511, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823105971515295e-05, + "loss": 3.6312, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822269014644616e-05, + "loss": 3.6232, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.8214304198935644e-05, + "loss": 3.6387, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8205918251425124e-05, + "loss": 3.6416, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8197532303914604e-05, + "loss": 3.6242, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818916273520781e-05, + "loss": 3.6314, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818077678769729e-05, + "loss": 3.6238, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817239084018677e-05, + "loss": 3.643, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816400489267625e-05, + "loss": 3.6397, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815563532396946e-05, + "loss": 3.634, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814724937645894e-05, + "loss": 3.6449, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813886342894842e-05, + "loss": 3.6372, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.81304774814379e-05, + "loss": 3.65, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812210791273111e-05, + "loss": 3.6275, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.81137219652206e-05, + "loss": 3.6407, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810533601771008e-05, + "loss": 3.633, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809695007019956e-05, + "loss": 3.6335, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808856412268904e-05, + "loss": 3.6396, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808019455398225e-05, + "loss": 3.6401, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071808606471727e-05, + "loss": 3.6437, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.8063422658961207e-05, + "loss": 3.6459, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.8055036711450686e-05, + "loss": 3.6294, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.8046667142743896e-05, + "loss": 3.6292, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8038281195233376e-05, + "loss": 3.6301, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029895247722855e-05, + "loss": 3.6413, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8021509300212335e-05, + "loss": 3.6304, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801313973150555e-05, + "loss": 3.6358, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800475378399503e-05, + "loss": 3.6391, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799636783648451e-05, + "loss": 3.6393, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798798188897399e-05, + "loss": 3.6355, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.79796123202672e-05, + "loss": 3.6341, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797122637275668e-05, + "loss": 3.6389, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796284042524616e-05, + "loss": 3.6425, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795445447773564e-05, + "loss": 3.6462, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794608490902885e-05, + "loss": 3.6275, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793769896151833e-05, + "loss": 3.6368, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792931301400781e-05, + "loss": 3.6368, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792092706649729e-05, + "loss": 3.6429, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7912557497790505e-05, + "loss": 3.6392, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7904171550279985e-05, + "loss": 3.6391, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895785602769465e-05, + "loss": 3.6323, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.7887399655258945e-05, + "loss": 3.6352, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7879030086552154e-05, + "loss": 3.6199, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.7870644139041634e-05, + "loss": 3.6319, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.7862258191531114e-05, + "loss": 3.6225, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.7853872244020594e-05, + "loss": 3.6394, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.78455026753138e-05, + "loss": 3.6273, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783711672780328e-05, + "loss": 3.631, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782873078029276e-05, + "loss": 3.6353, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782034483278224e-05, + "loss": 3.6373, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781197526407546e-05, + "loss": 3.6384, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780358931656494e-05, + "loss": 3.6335, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779520336905442e-05, + "loss": 3.6391, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.77868174215439e-05, + "loss": 3.6409, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777844785283711e-05, + "loss": 3.6363, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777006190532659e-05, + "loss": 3.6328, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776167595781607e-05, + "loss": 3.6289, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775329001030555e-05, + "loss": 3.6352, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.7744920441598757e-05, + "loss": 3.6306, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.7736534494088237e-05, + "loss": 3.6178, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.7728148546577716e-05, + "loss": 3.6279, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719762599067196e-05, + "loss": 3.6279, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771139303036041e-05, + "loss": 3.6304, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770300708284989e-05, + "loss": 3.6411, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769462113533937e-05, + "loss": 3.6313, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768623518782885e-05, + "loss": 3.6238, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.7677849240318325e-05, + "loss": 3.6292, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766947967161154e-05, + "loss": 3.6442, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766109372410102e-05, + "loss": 3.6321, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.7652707776590494e-05, + "loss": 3.6404, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.7644321829079974e-05, + "loss": 3.6196, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763595226037319e-05, + "loss": 3.6452, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762756631286267e-05, + "loss": 3.6371, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761918036535215e-05, + "loss": 3.6353, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.761079441784163e-05, + "loss": 3.6332, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760240847033111e-05, + "loss": 3.6295, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759402252282059e-05, + "loss": 3.6327, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.75856529541138e-05, + "loss": 3.6557, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757726700660328e-05, + "loss": 3.6229, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756888105909276e-05, + "loss": 3.6357, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756049511158224e-05, + "loss": 3.6301, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755212554287545e-05, + "loss": 3.621, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754373959536493e-05, + "loss": 3.6293, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753535364785441e-05, + "loss": 3.6331, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752698407914762e-05, + "loss": 3.6386, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.7518598131637104e-05, + "loss": 3.6308, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.7510212184126584e-05, + "loss": 3.632, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.847637891769409, + "eval_runtime": 304.0055, + "eval_samples_per_second": 1255.211, + "eval_steps_per_second": 39.226, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.7501826236616064e-05, + "loss": 3.6339, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.7493440289105544e-05, + "loss": 3.6172, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7485054341595024e-05, + "loss": 3.6334, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7476668394084504e-05, + "loss": 3.6348, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746829882537771e-05, + "loss": 3.643, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745991287786719e-05, + "loss": 3.6295, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745152693035667e-05, + "loss": 3.6263, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744314098284615e-05, + "loss": 3.6201, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743475503533563e-05, + "loss": 3.6229, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742638546662884e-05, + "loss": 3.634, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741799951911832e-05, + "loss": 3.6293, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.74096135716078e-05, + "loss": 3.6368, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740124400290102e-05, + "loss": 3.6362, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.73928580553905e-05, + "loss": 3.6179, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738447210787998e-05, + "loss": 3.6186, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737608616036946e-05, + "loss": 3.6154, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736770021285894e-05, + "loss": 3.6314, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735931426534842e-05, + "loss": 3.6206, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.73509283178379e-05, + "loss": 3.6205, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734254237032738e-05, + "loss": 3.6231, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7334172801620586e-05, + "loss": 3.6362, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7325786854110066e-05, + "loss": 3.6244, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7317400906599546e-05, + "loss": 3.6279, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7309014959089026e-05, + "loss": 3.6235, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.7300645390382235e-05, + "loss": 3.629, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729225944287172e-05, + "loss": 3.626, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.72838734953612e-05, + "loss": 3.6141, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727548754785068e-05, + "loss": 3.6331, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726711797914389e-05, + "loss": 3.6149, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725873203163337e-05, + "loss": 3.6129, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725034608412285e-05, + "loss": 3.6324, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724196013661233e-05, + "loss": 3.6234, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723359056790554e-05, + "loss": 3.6239, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722520462039502e-05, + "loss": 3.6315, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.72168186728845e-05, + "loss": 3.6174, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720843272537398e-05, + "loss": 3.6223, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.720006315666719e-05, + "loss": 3.6254, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191677209156676e-05, + "loss": 3.6082, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7183291261646155e-05, + "loss": 3.6176, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717490531413563e-05, + "loss": 3.6115, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7166535745428845e-05, + "loss": 3.6149, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.7158149797918324e-05, + "loss": 3.6256, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7149763850407804e-05, + "loss": 3.6203, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714137790289728e-05, + "loss": 3.6287, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.7133008334190493e-05, + "loss": 3.6185, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.7124622386679973e-05, + "loss": 3.6248, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7116236439169453e-05, + "loss": 3.6183, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7107850491658927e-05, + "loss": 3.6178, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709948092295214e-05, + "loss": 3.5993, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709109497544163e-05, + "loss": 3.6261, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.70827090279311e-05, + "loss": 3.6144, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707432308042058e-05, + "loss": 3.6263, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.70659535117138e-05, + "loss": 3.6155, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705756756420328e-05, + "loss": 3.6106, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704918161669275e-05, + "loss": 3.6077, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704079566918223e-05, + "loss": 3.6128, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703240972167171e-05, + "loss": 3.6256, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702404015296493e-05, + "loss": 3.6137, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.70156542054544e-05, + "loss": 3.6317, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700726825794388e-05, + "loss": 3.6205, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699888231043337e-05, + "loss": 3.5897, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6990512741726576e-05, + "loss": 3.6292, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6982126794216056e-05, + "loss": 3.61, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6973740846705536e-05, + "loss": 3.6019, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.6965354899195016e-05, + "loss": 3.6136, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6956985330488225e-05, + "loss": 3.6219, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.6948599382977705e-05, + "loss": 3.6025, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.6940213435467185e-05, + "loss": 3.6112, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.6931827487956665e-05, + "loss": 3.6029, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923457919249874e-05, + "loss": 3.6144, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.6915071971739354e-05, + "loss": 3.6218, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6906686024228834e-05, + "loss": 3.61, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689830007671832e-05, + "loss": 3.6221, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688993050801153e-05, + "loss": 3.6117, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688154456050101e-05, + "loss": 3.6272, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687315861299049e-05, + "loss": 3.606, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686477266547997e-05, + "loss": 3.6222, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685638671796945e-05, + "loss": 3.6099, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684801714926266e-05, + "loss": 3.6095, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683963120175214e-05, + "loss": 3.6182, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683124525424162e-05, + "loss": 3.6154, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.68228593067311e-05, + "loss": 3.6191, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681448973802431e-05, + "loss": 3.6283, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680610379051379e-05, + "loss": 3.6107, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.6797717843003274e-05, + "loss": 3.6047, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.6789331895492754e-05, + "loss": 3.6064, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678096232678596e-05, + "loss": 3.6191, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677257637927544e-05, + "loss": 3.607, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676419043176492e-05, + "loss": 3.6167, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.67558044842544e-05, + "loss": 3.6173, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674743491554761e-05, + "loss": 3.616, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673904896803709e-05, + "loss": 3.6118, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673066302052657e-05, + "loss": 3.6107, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672227707301605e-05, + "loss": 3.6201, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671390750430926e-05, + "loss": 3.6183, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670552155679874e-05, + "loss": 3.6219, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669713560928822e-05, + "loss": 3.6099, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668874966177771e-05, + "loss": 3.611, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668038009307092e-05, + "loss": 3.6186, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.66719941455604e-05, + "loss": 3.6199, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666360819804988e-05, + "loss": 3.6168, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665522225053936e-05, + "loss": 3.6145, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.6646852681832566e-05, + "loss": 3.6139, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6638466734322046e-05, + "loss": 3.6103, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6630080786811526e-05, + "loss": 3.6028, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6621694839301006e-05, + "loss": 3.6079, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6613325270594215e-05, + "loss": 3.6017, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604939323083695e-05, + "loss": 3.6191, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6596553375573175e-05, + "loss": 3.6065, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658816742806266e-05, + "loss": 3.6099, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657979785935587e-05, + "loss": 3.6097, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657141191184535e-05, + "loss": 3.6206, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656302596433483e-05, + "loss": 3.6135, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655464001682431e-05, + "loss": 3.6125, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654627044811752e-05, + "loss": 3.6203, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.6537884500607e-05, + "loss": 3.6201, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652949855309648e-05, + "loss": 3.6144, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652111260558596e-05, + "loss": 3.6092, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651274303687917e-05, + "loss": 3.607, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650435708936865e-05, + "loss": 3.6143, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649597114185813e-05, + "loss": 3.6117, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.6487585194347615e-05, + "loss": 3.5915, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6479215625640824e-05, + "loss": 3.6106, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6470829678130304e-05, + "loss": 3.6077, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6462443730619784e-05, + "loss": 3.6081, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6454057783109264e-05, + "loss": 3.6189, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644568821440247e-05, + "loss": 3.6094, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643730226689195e-05, + "loss": 3.6048, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642891631938143e-05, + "loss": 3.6045, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642053037187091e-05, + "loss": 3.6252, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641214442436039e-05, + "loss": 3.6133, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.64037748556536e-05, + "loss": 3.6199, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639538890814308e-05, + "loss": 3.5993, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638700296063257e-05, + "loss": 3.6202, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637861701312205e-05, + "loss": 3.6148, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637024744441526e-05, + "loss": 3.6158, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636186149690474e-05, + "loss": 3.6128, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635347554939422e-05, + "loss": 3.6033, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634510598068743e-05, + "loss": 3.6131, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633672003317691e-05, + "loss": 3.6329, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632833408566639e-05, + "loss": 3.6027, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631994813815587e-05, + "loss": 3.6119, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631156219064535e-05, + "loss": 3.6069, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.6303192621938556e-05, + "loss": 3.6065, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6294806674428036e-05, + "loss": 3.6046, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628642072691752e-05, + "loss": 3.6115, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6278034779407e-05, + "loss": 3.6146, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626966521070021e-05, + "loss": 3.616, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626127926318969e-05, + "loss": 3.6086, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.845874071121216, + "eval_runtime": 310.4534, + "eval_samples_per_second": 1229.141, + "eval_steps_per_second": 38.412, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625289331567917e-05, + "loss": 3.6006, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624450736816865e-05, + "loss": 3.5962, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623613779946186e-05, + "loss": 3.6132, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622775185195134e-05, + "loss": 3.6135, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621936590444082e-05, + "loss": 3.6189, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.62109799569303e-05, + "loss": 3.6112, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620261038822351e-05, + "loss": 3.6059, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619422444071299e-05, + "loss": 3.5989, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6185838493202476e-05, + "loss": 3.6016, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617745254569195e-05, + "loss": 3.6048, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.6169082976985165e-05, + "loss": 3.6157, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6160697029474645e-05, + "loss": 3.6177, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6152327460767854e-05, + "loss": 3.6219, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6143941513257334e-05, + "loss": 3.5904, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6135555565746814e-05, + "loss": 3.6021, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6127169618236294e-05, + "loss": 3.5898, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6118783670725774e-05, + "loss": 3.6109, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611039772321525e-05, + "loss": 3.5997, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610201177570473e-05, + "loss": 3.5968, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.6093625828194214e-05, + "loss": 3.6041, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608525625948742e-05, + "loss": 3.6184, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.60768703119769e-05, + "loss": 3.5997, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606848436446638e-05, + "loss": 3.6071, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.606009841695586e-05, + "loss": 3.6022, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605172884824907e-05, + "loss": 3.6098, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604334290073855e-05, + "loss": 3.6023, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603495695322803e-05, + "loss": 3.5946, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602657100571751e-05, + "loss": 3.6101, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601820143701072e-05, + "loss": 3.5972, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.60098154895002e-05, + "loss": 3.5937, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600142954198968e-05, + "loss": 3.6092, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599304359447917e-05, + "loss": 3.6033, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598467402577238e-05, + "loss": 3.6061, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597628807826186e-05, + "loss": 3.61, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596790213075134e-05, + "loss": 3.5969, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595951618324082e-05, + "loss": 3.6032, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.5951146614534026e-05, + "loss": 3.6037, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.5942760667023506e-05, + "loss": 3.5858, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5934374719512986e-05, + "loss": 3.5982, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.5925988772002466e-05, + "loss": 3.5886, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.5917619203295675e-05, + "loss": 3.5932, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5909233255785155e-05, + "loss": 3.6041, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5900847308274635e-05, + "loss": 3.6056, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589246136076412e-05, + "loss": 3.6018, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588409179205733e-05, + "loss": 3.6026, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587570584454681e-05, + "loss": 3.6002, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586731989703629e-05, + "loss": 3.6011, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585893394952577e-05, + "loss": 3.5946, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.585056438081898e-05, + "loss": 3.5832, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584217843330846e-05, + "loss": 3.6014, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583379248579794e-05, + "loss": 3.596, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582540653828742e-05, + "loss": 3.6042, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581703696958063e-05, + "loss": 3.5994, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580865102207011e-05, + "loss": 3.5915, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580026507455959e-05, + "loss": 3.5879, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579187912704907e-05, + "loss": 3.5902, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5783493179538555e-05, + "loss": 3.6062, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.5775123610831764e-05, + "loss": 3.5883, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5766737663321244e-05, + "loss": 3.6139, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.5758351715810724e-05, + "loss": 3.6001, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.5749965768300204e-05, + "loss": 3.5742, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574159619959341e-05, + "loss": 3.6046, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573321025208289e-05, + "loss": 3.5891, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572482430457237e-05, + "loss": 3.5829, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571643835706185e-05, + "loss": 3.5928, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570806878835506e-05, + "loss": 3.5997, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569968284084454e-05, + "loss": 3.5818, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569129689333402e-05, + "loss": 3.5926, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568291094582351e-05, + "loss": 3.5811, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567454137711672e-05, + "loss": 3.5957, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.56661554296062e-05, + "loss": 3.6014, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565776948209568e-05, + "loss": 3.5923, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564938353458516e-05, + "loss": 3.6014, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564101396587837e-05, + "loss": 3.5916, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563262801836785e-05, + "loss": 3.6069, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562424207085733e-05, + "loss": 3.5894, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5615856123346807e-05, + "loss": 3.5994, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5607486554640016e-05, + "loss": 3.5859, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5599100607129496e-05, + "loss": 3.5908, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5590714659618976e-05, + "loss": 3.6019, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558232871210846e-05, + "loss": 3.5933, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557395914340167e-05, + "loss": 3.5996, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556557319589115e-05, + "loss": 3.6084, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555718724838063e-05, + "loss": 3.5915, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554880130087011e-05, + "loss": 3.5772, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554043173216332e-05, + "loss": 3.59, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.55320457846528e-05, + "loss": 3.5988, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552365983714228e-05, + "loss": 3.5924, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551527388963176e-05, + "loss": 3.5932, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550690432092497e-05, + "loss": 3.6002, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549851837341445e-05, + "loss": 3.5939, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549013242590393e-05, + "loss": 3.5929, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.5481746478393416e-05, + "loss": 3.5915, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473376909686625e-05, + "loss": 3.5993, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5464990962176105e-05, + "loss": 3.601, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5456605014665585e-05, + "loss": 3.6063, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5448219067155065e-05, + "loss": 3.5852, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5439849498448274e-05, + "loss": 3.5966, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5431463550937754e-05, + "loss": 3.5967, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.5423077603427234e-05, + "loss": 3.5973, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.5414691655916714e-05, + "loss": 3.5991, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540632208720992e-05, + "loss": 3.5939, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.53979361396994e-05, + "loss": 3.5956, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538955019218888e-05, + "loss": 3.5885, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538116424467837e-05, + "loss": 3.5908, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537279467597158e-05, + "loss": 3.5843, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536440872846106e-05, + "loss": 3.5848, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535602278095054e-05, + "loss": 3.5971, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534763683344002e-05, + "loss": 3.5898, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533926726473323e-05, + "loss": 3.5836, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533088131722271e-05, + "loss": 3.587, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532249536971219e-05, + "loss": 3.6021, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531410942220167e-05, + "loss": 3.598, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530573985349488e-05, + "loss": 3.5932, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529735390598436e-05, + "loss": 3.6009, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528896795847384e-05, + "loss": 3.6009, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528058201096332e-05, + "loss": 3.5929, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527221244225653e-05, + "loss": 3.5881, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526382649474601e-05, + "loss": 3.5901, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525544054723549e-05, + "loss": 3.5911, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524705459972497e-05, + "loss": 3.5973, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523868503101818e-05, + "loss": 3.5685, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523029908350766e-05, + "loss": 3.5908, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522191313599714e-05, + "loss": 3.5883, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521352718848662e-05, + "loss": 3.5924, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520515761977983e-05, + "loss": 3.5972, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519677167226931e-05, + "loss": 3.5911, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518838572475879e-05, + "loss": 3.5861, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517999977724828e-05, + "loss": 3.5817, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517161382973775e-05, + "loss": 3.606, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5163244261030966e-05, + "loss": 3.5898, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5154858313520446e-05, + "loss": 3.6034, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514647236600992e-05, + "loss": 3.5797, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.51380864184994e-05, + "loss": 3.5963, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5129716849792615e-05, + "loss": 3.5998, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5121330902282095e-05, + "loss": 3.5922, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511294495477157e-05, + "loss": 3.5963, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510455900726105e-05, + "loss": 3.5848, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5096189438554264e-05, + "loss": 3.5948, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.5087803491043744e-05, + "loss": 3.609, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.5079417543533224e-05, + "loss": 3.5882, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.5071031596022704e-05, + "loss": 3.5912, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506266202731592e-05, + "loss": 3.5908, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505427607980539e-05, + "loss": 3.5848, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504589013229487e-05, + "loss": 3.586, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503750418478435e-05, + "loss": 3.5972, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502913461607757e-05, + "loss": 3.5887, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502074866856704e-05, + "loss": 3.5967, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501236272105652e-05, + "loss": 3.5901, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.8455843925476074, + "eval_runtime": 311.3215, + "eval_samples_per_second": 1225.714, + "eval_steps_per_second": 38.304, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5003976773546e-05, + "loss": 3.6109, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499559082603548e-05, + "loss": 3.5736, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498720487852497e-05, + "loss": 3.5903, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497881893101445e-05, + "loss": 3.5977, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.497044936230766e-05, + "loss": 3.5965, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496206341479714e-05, + "loss": 3.5931, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495367746728662e-05, + "loss": 3.5881, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.49452915197761e-05, + "loss": 3.5801, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.4936921951069306e-05, + "loss": 3.5816, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.4928536003558786e-05, + "loss": 3.5865, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4920150056048266e-05, + "loss": 3.5947, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4911764108537746e-05, + "loss": 3.596, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490341091863469e-05, + "loss": 3.6065, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489502497112417e-05, + "loss": 3.5695, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488663902361365e-05, + "loss": 3.5806, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487825307610313e-05, + "loss": 3.5696, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486986712859261e-05, + "loss": 3.5925, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486148118108209e-05, + "loss": 3.5812, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485309523357157e-05, + "loss": 3.5785, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484470928606105e-05, + "loss": 3.5807, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483633971735426e-05, + "loss": 3.6, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482795376984374e-05, + "loss": 3.5815, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481956782233322e-05, + "loss": 3.5878, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.48111818748227e-05, + "loss": 3.5844, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480281230611591e-05, + "loss": 3.5975, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479442635860539e-05, + "loss": 3.583, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478604041109487e-05, + "loss": 3.5755, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4777654463584356e-05, + "loss": 3.5929, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4769284894877565e-05, + "loss": 3.5725, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760898947367045e-05, + "loss": 3.5741, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4752512999856525e-05, + "loss": 3.591, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4744127052346005e-05, + "loss": 3.5844, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4735757483639214e-05, + "loss": 3.5848, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4727371536128694e-05, + "loss": 3.5928, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4718985588618174e-05, + "loss": 3.5775, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4710599641107654e-05, + "loss": 3.5831, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470223007240086e-05, + "loss": 3.5855, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469384412489034e-05, + "loss": 3.5695, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468545817737982e-05, + "loss": 3.5806, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467707222986931e-05, + "loss": 3.5686, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466870266116252e-05, + "loss": 3.576, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.4660316713652e-05, + "loss": 3.5824, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465193076614148e-05, + "loss": 3.5897, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464354481863096e-05, + "loss": 3.5842, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463517524992417e-05, + "loss": 3.583, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462678930241365e-05, + "loss": 3.5843, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461840335490313e-05, + "loss": 3.5805, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.461001740739261e-05, + "loss": 3.5774, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4601647838685816e-05, + "loss": 3.5634, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4593261891175296e-05, + "loss": 3.5811, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4584875943664776e-05, + "loss": 3.5806, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457648999615426e-05, + "loss": 3.5829, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456810404864374e-05, + "loss": 3.5818, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455973447993695e-05, + "loss": 3.5727, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455134853242643e-05, + "loss": 3.5681, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454296258491591e-05, + "loss": 3.5711, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453457663740539e-05, + "loss": 3.588, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.45262070686986e-05, + "loss": 3.5734, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451782112118808e-05, + "loss": 3.5929, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450943517367756e-05, + "loss": 3.5796, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450104922616704e-05, + "loss": 3.5611, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449267965746025e-05, + "loss": 3.5832, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448429370994973e-05, + "loss": 3.5715, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447590776243922e-05, + "loss": 3.5643, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.44675218149287e-05, + "loss": 3.5705, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4459152246221906e-05, + "loss": 3.582, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4450766298711386e-05, + "loss": 3.5638, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.4442380351200866e-05, + "loss": 3.5795, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.4433994403690346e-05, + "loss": 3.5585, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.4425624834983555e-05, + "loss": 3.5778, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4417238887473035e-05, + "loss": 3.5819, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4408852939962515e-05, + "loss": 3.574, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4400466992451995e-05, + "loss": 3.5812, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4392097423745204e-05, + "loss": 3.5731, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.4383711476234684e-05, + "loss": 3.5879, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437532552872417e-05, + "loss": 3.5717, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436693958121365e-05, + "loss": 3.5832, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435857001250686e-05, + "loss": 3.5719, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435018406499634e-05, + "loss": 3.5712, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434179811748582e-05, + "loss": 3.5796, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433341216997529e-05, + "loss": 3.5734, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432504260126851e-05, + "loss": 3.5825, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431665665375799e-05, + "loss": 3.5868, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430827070624747e-05, + "loss": 3.5778, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429988475873694e-05, + "loss": 3.5589, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429151519003016e-05, + "loss": 3.571, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428312924251964e-05, + "loss": 3.5772, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.4274743295009124e-05, + "loss": 3.576, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.42663573474986e-05, + "loss": 3.5731, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425798777879181e-05, + "loss": 3.5807, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424960183128129e-05, + "loss": 3.5764, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.4241215883770766e-05, + "loss": 3.5732, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.4232829936260246e-05, + "loss": 3.5742, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422446036755346e-05, + "loss": 3.5814, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421607442004294e-05, + "loss": 3.5808, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.4207688472532415e-05, + "loss": 3.5872, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4199302525021895e-05, + "loss": 3.5659, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419093295631511e-05, + "loss": 3.5773, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418254700880459e-05, + "loss": 3.5792, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417416106129407e-05, + "loss": 3.5796, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416577511378355e-05, + "loss": 3.5825, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415740554507677e-05, + "loss": 3.5752, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414901959756624e-05, + "loss": 3.5762, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414063365005572e-05, + "loss": 3.5715, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.41322477025452e-05, + "loss": 3.5733, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4123878133838416e-05, + "loss": 3.5641, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411549218632789e-05, + "loss": 3.5668, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410710623881737e-05, + "loss": 3.5779, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409872029130685e-05, + "loss": 3.5752, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4090350722600065e-05, + "loss": 3.5673, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.4081964775089545e-05, + "loss": 3.5657, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.4073578827579025e-05, + "loss": 3.5842, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.4065192880068505e-05, + "loss": 3.5796, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4056823311361714e-05, + "loss": 3.5757, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4048437363851194e-05, + "loss": 3.5821, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4040051416340674e-05, + "loss": 3.5847, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.4031665468830154e-05, + "loss": 3.5753, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402329590012336e-05, + "loss": 3.5709, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401490995261284e-05, + "loss": 3.5743, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400652400510232e-05, + "loss": 3.5749, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.39981380575918e-05, + "loss": 3.5793, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398976848888502e-05, + "loss": 3.552, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.39813825413745e-05, + "loss": 3.5722, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397299659386398e-05, + "loss": 3.5697, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396462702515719e-05, + "loss": 3.5713, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395624107764667e-05, + "loss": 3.5801, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394785513013615e-05, + "loss": 3.5733, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393946918262563e-05, + "loss": 3.5672, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.393108323511511e-05, + "loss": 3.5647, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3922713666408316e-05, + "loss": 3.5878, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3914327718897796e-05, + "loss": 3.5717, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3905941771387276e-05, + "loss": 3.5839, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897555823876756e-05, + "loss": 3.5644, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388918625516997e-05, + "loss": 3.578, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388080030765945e-05, + "loss": 3.5817, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387241436014893e-05, + "loss": 3.5753, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386402841263841e-05, + "loss": 3.5748, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385565884393162e-05, + "loss": 3.5688, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.38472728964211e-05, + "loss": 3.5773, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383888694891058e-05, + "loss": 3.593, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383050100140006e-05, + "loss": 3.5713, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382213143269327e-05, + "loss": 3.5693, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381374548518275e-05, + "loss": 3.5747, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380535953767223e-05, + "loss": 3.5679, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379697359016171e-05, + "loss": 3.565, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788604021454926e-05, + "loss": 3.5837, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3780218073944406e-05, + "loss": 3.5679, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3771832126433886e-05, + "loss": 3.5759, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3763446178923366e-05, + "loss": 3.5753, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.84504771232605, + "eval_runtime": 307.6838, + "eval_samples_per_second": 1240.205, + "eval_steps_per_second": 38.757, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.3755076610216575e-05, + "loss": 3.5918, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.3746690662706055e-05, + "loss": 3.5613, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.3738304715195535e-05, + "loss": 3.5699, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.3729918767685015e-05, + "loss": 3.5818, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.3721549198978224e-05, + "loss": 3.5774, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.3713163251467704e-05, + "loss": 3.5763, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.3704777303957184e-05, + "loss": 3.5662, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.3696391356446664e-05, + "loss": 3.5633, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.368802178773988e-05, + "loss": 3.5643, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367963584022936e-05, + "loss": 3.5729, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.367124989271884e-05, + "loss": 3.57, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.366286394520832e-05, + "loss": 3.585, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.365449437650153e-05, + "loss": 3.583, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364610842899101e-05, + "loss": 3.5531, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.363772248148049e-05, + "loss": 3.5649, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362933653396997e-05, + "loss": 3.5541, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.362096696526318e-05, + "loss": 3.5761, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361258101775266e-05, + "loss": 3.5602, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360419507024214e-05, + "loss": 3.5623, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359580912273162e-05, + "loss": 3.5658, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358743955402483e-05, + "loss": 3.5772, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.357905360651431e-05, + "loss": 3.5674, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.357066765900379e-05, + "loss": 3.5681, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.356228171149327e-05, + "loss": 3.5693, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.355391214278648e-05, + "loss": 3.5765, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.354552619527596e-05, + "loss": 3.5687, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353714024776544e-05, + "loss": 3.5588, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.352875430025492e-05, + "loss": 3.5734, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.352038473154813e-05, + "loss": 3.5549, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351199878403761e-05, + "loss": 3.5611, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350361283652709e-05, + "loss": 3.5701, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.349522688901657e-05, + "loss": 3.5653, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348685732030979e-05, + "loss": 3.5688, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347847137279927e-05, + "loss": 3.5738, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.347008542528875e-05, + "loss": 3.5632, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346169947777823e-05, + "loss": 3.5663, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.3453329909071436e-05, + "loss": 3.5678, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.3444943961560916e-05, + "loss": 3.5523, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.3436558014050396e-05, + "loss": 3.5645, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.3428172066539876e-05, + "loss": 3.5521, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.3419802497833085e-05, + "loss": 3.5625, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.3411416550322565e-05, + "loss": 3.5584, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.3403030602812045e-05, + "loss": 3.5733, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.3394644655301525e-05, + "loss": 3.5657, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.338627508659474e-05, + "loss": 3.5666, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.337788913908422e-05, + "loss": 3.5668, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.33695031915737e-05, + "loss": 3.5631, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.336111724406318e-05, + "loss": 3.5604, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.335274767535639e-05, + "loss": 3.5461, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.334436172784587e-05, + "loss": 3.5625, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.333597578033535e-05, + "loss": 3.5668, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332758983282483e-05, + "loss": 3.5667, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331922026411804e-05, + "loss": 3.5603, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.331083431660752e-05, + "loss": 3.5545, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.3302448369097e-05, + "loss": 3.5548, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329406242158648e-05, + "loss": 3.55, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.3285692852879694e-05, + "loss": 3.578, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.3277306905369174e-05, + "loss": 3.5549, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.3268920957858654e-05, + "loss": 3.5738, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.3260535010348134e-05, + "loss": 3.563, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325216544164134e-05, + "loss": 3.5441, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.324377949413082e-05, + "loss": 3.5653, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.32353935466203e-05, + "loss": 3.5519, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.322700759910978e-05, + "loss": 3.5514, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.321863803040299e-05, + "loss": 3.5517, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.321025208289247e-05, + "loss": 3.5661, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.320186613538195e-05, + "loss": 3.5475, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319348018787143e-05, + "loss": 3.5597, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.318511061916465e-05, + "loss": 3.5434, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.317672467165413e-05, + "loss": 3.5586, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.316833872414361e-05, + "loss": 3.5651, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.315995277663309e-05, + "loss": 3.5602, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.31515832079263e-05, + "loss": 3.5628, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314319726041578e-05, + "loss": 3.5575, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.313481131290526e-05, + "loss": 3.5697, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.3126425365394737e-05, + "loss": 3.5523, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.3118055796687946e-05, + "loss": 3.564, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.3109669849177426e-05, + "loss": 3.558, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.3101283901666906e-05, + "loss": 3.5526, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.3092897954156386e-05, + "loss": 3.5616, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.3084528385449595e-05, + "loss": 3.5596, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.307614243793908e-05, + "loss": 3.5674, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.306775649042856e-05, + "loss": 3.5713, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.305937054291804e-05, + "loss": 3.5566, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.305100097421125e-05, + "loss": 3.5471, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.304261502670073e-05, + "loss": 3.5534, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.303422907919021e-05, + "loss": 3.5606, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.3025843131679683e-05, + "loss": 3.5596, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.30174735629729e-05, + "loss": 3.5575, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.300908761546238e-05, + "loss": 3.5651, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.300070166795186e-05, + "loss": 3.5588, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299231572044133e-05, + "loss": 3.5543, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.298394615173455e-05, + "loss": 3.5598, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.2975560204224035e-05, + "loss": 3.5661, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.296717425671351e-05, + "loss": 3.5611, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295878830920299e-05, + "loss": 3.5719, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.2950418740496204e-05, + "loss": 3.5453, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.2942032792985684e-05, + "loss": 3.5668, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293364684547516e-05, + "loss": 3.5645, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292526089796464e-05, + "loss": 3.5591, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291689132925785e-05, + "loss": 3.5648, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290850538174733e-05, + "loss": 3.5592, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.2900119434236806e-05, + "loss": 3.5591, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.2891733486726286e-05, + "loss": 3.5552, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.28833639180195e-05, + "loss": 3.5573, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287497797050898e-05, + "loss": 3.5473, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.286659202299846e-05, + "loss": 3.5541, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285820607548794e-05, + "loss": 3.5584, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.284983650678116e-05, + "loss": 3.5577, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.284145055927063e-05, + "loss": 3.5484, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.283306461176011e-05, + "loss": 3.5516, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.282467866424959e-05, + "loss": 3.5616, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.281630909554281e-05, + "loss": 3.5647, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280792314803228e-05, + "loss": 3.5574, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279953720052176e-05, + "loss": 3.5681, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.279115125301124e-05, + "loss": 3.566, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.2782781684304456e-05, + "loss": 3.5628, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.2774395736793936e-05, + "loss": 3.5519, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.2766009789283416e-05, + "loss": 3.557, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.2757623841772896e-05, + "loss": 3.5558, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.2749254273066105e-05, + "loss": 3.5641, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.2740868325555585e-05, + "loss": 3.5374, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.2732482378045065e-05, + "loss": 3.5543, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.2724096430534544e-05, + "loss": 3.5491, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.2715726861827754e-05, + "loss": 3.5558, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.2707340914317234e-05, + "loss": 3.5654, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.2698954966806713e-05, + "loss": 3.5558, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.2690569019296193e-05, + "loss": 3.5477, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.268219945058941e-05, + "loss": 3.55, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.267381350307889e-05, + "loss": 3.5713, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.266542755556837e-05, + "loss": 3.556, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.265704160805785e-05, + "loss": 3.5701, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.264867203935106e-05, + "loss": 3.5467, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.264028609184054e-05, + "loss": 3.5623, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.263190014433002e-05, + "loss": 3.5643, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.26235141968195e-05, + "loss": 3.5586, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261514462811271e-05, + "loss": 3.5533, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260675868060219e-05, + "loss": 3.5551, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.259837273309167e-05, + "loss": 3.5644, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.258998678558115e-05, + "loss": 3.5707, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258161721687436e-05, + "loss": 3.5589, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257323126936384e-05, + "loss": 3.5507, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.256484532185332e-05, + "loss": 3.5617, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.25564593743428e-05, + "loss": 3.55, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254808980563601e-05, + "loss": 3.5466, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253970385812549e-05, + "loss": 3.5679, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.253131791061497e-05, + "loss": 3.5507, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.252293196310445e-05, + "loss": 3.5637, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251456239439766e-05, + "loss": 3.5527, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.84675669670105, + "eval_runtime": 304.0271, + "eval_samples_per_second": 1255.122, + "eval_steps_per_second": 39.223, + "step": 1068480 + }, + { + "epoch": 1.0, + "learning_rate": 3.250617644688714e-05, + "loss": 3.5502, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.249779049937662e-05, + "loss": 3.5469, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.24894045518661e-05, + "loss": 3.5524, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.248103498315932e-05, + "loss": 3.5649, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.2472649035648797e-05, + "loss": 3.5649, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.2464263088138277e-05, + "loss": 3.5594, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.2455877140627757e-05, + "loss": 3.5495, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.2447507571920966e-05, + "loss": 3.5468, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.2439121624410446e-05, + "loss": 3.5474, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.2430735676899926e-05, + "loss": 3.5553, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.2422349729389405e-05, + "loss": 3.5579, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.2413980160682615e-05, + "loss": 3.5658, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.2405610591975824e-05, + "loss": 3.5694, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.239722464446531e-05, + "loss": 3.539, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.238883869695479e-05, + "loss": 3.5467, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.238045274944427e-05, + "loss": 3.5398, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.237206680193375e-05, + "loss": 3.5584, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.236368085442323e-05, + "loss": 3.5451, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.235529490691271e-05, + "loss": 3.5476, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.234690895940219e-05, + "loss": 3.5464, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.23385393906954e-05, + "loss": 3.5599, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.233015344318488e-05, + "loss": 3.55, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.232176749567436e-05, + "loss": 3.5524, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.231338154816384e-05, + "loss": 3.553, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.230501197945705e-05, + "loss": 3.5621, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.229662603194653e-05, + "loss": 3.5487, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.228824008443601e-05, + "loss": 3.5453, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.227985413692549e-05, + "loss": 3.5566, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.2271468189414975e-05, + "loss": 3.5392, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.2263098620708184e-05, + "loss": 3.5446, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.2254712673197664e-05, + "loss": 3.5529, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.2246326725687144e-05, + "loss": 3.5522, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.2237940778176624e-05, + "loss": 3.5504, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.222957120946983e-05, + "loss": 3.5569, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.222118526195931e-05, + "loss": 3.5493, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.221279931444879e-05, + "loss": 3.549, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.2204429745742e-05, + "loss": 3.5493, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.219604379823148e-05, + "loss": 3.5368, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.218765785072096e-05, + "loss": 3.5479, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.217927190321044e-05, + "loss": 3.5386, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.217088595569993e-05, + "loss": 3.5447, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.216251638699314e-05, + "loss": 3.5444, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.215413043948262e-05, + "loss": 3.5587, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.21457444919721e-05, + "loss": 3.5474, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.2137374923265307e-05, + "loss": 3.5514, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.2128988975754787e-05, + "loss": 3.55, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.2120603028244266e-05, + "loss": 3.5495, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.2112217080733746e-05, + "loss": 3.5428, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.2103847512026956e-05, + "loss": 3.5332, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.2095461564516435e-05, + "loss": 3.5443, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.2087075617005915e-05, + "loss": 3.5496, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.2078689669495395e-05, + "loss": 3.5503, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.207032010078861e-05, + "loss": 3.5469, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.206193415327809e-05, + "loss": 3.534, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.205354820576757e-05, + "loss": 3.5434, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.204516225825705e-05, + "loss": 3.5327, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.203679268955026e-05, + "loss": 3.5625, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.202840674203974e-05, + "loss": 3.5367, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.202002079452922e-05, + "loss": 3.5574, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.20116348470187e-05, + "loss": 3.5428, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.200326527831191e-05, + "loss": 3.5309, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.199487933080139e-05, + "loss": 3.5438, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.198649338329087e-05, + "loss": 3.5419, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.197810743578035e-05, + "loss": 3.5376, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.1969737867073565e-05, + "loss": 3.5309, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.1961351919563045e-05, + "loss": 3.5529, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.1952965972052525e-05, + "loss": 3.5348, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.1944580024542005e-05, + "loss": 3.5373, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.1936210455835214e-05, + "loss": 3.528, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.1927824508324694e-05, + "loss": 3.5441, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.1919438560814174e-05, + "loss": 3.5475, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.1911052613303654e-05, + "loss": 3.5421, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.190268304459686e-05, + "loss": 3.544, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189429709708634e-05, + "loss": 3.546, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.188591114957582e-05, + "loss": 3.5513, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.18775252020653e-05, + "loss": 3.5407, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.186915563335852e-05, + "loss": 3.5443, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.1860769685848e-05, + "loss": 3.5419, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.185238373833748e-05, + "loss": 3.542, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.184399779082695e-05, + "loss": 3.5446, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.183562822212017e-05, + "loss": 3.546, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.182724227460965e-05, + "loss": 3.5471, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.181885632709913e-05, + "loss": 3.5535, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.18104703795886e-05, + "loss": 3.5433, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.1802100810881817e-05, + "loss": 3.5304, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.1793714863371296e-05, + "loss": 3.5375, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.1785328915860776e-05, + "loss": 3.5481, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.1776942968350256e-05, + "loss": 3.541, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.176857339964347e-05, + "loss": 3.5411, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.176018745213295e-05, + "loss": 3.5502, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.1751801504622425e-05, + "loss": 3.5438, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.1743415557111905e-05, + "loss": 3.539, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.173504598840512e-05, + "loss": 3.5412, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.17266600408946e-05, + "loss": 3.5514, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.1718274093384074e-05, + "loss": 3.5474, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.1709888145873554e-05, + "loss": 3.5566, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.170151857716677e-05, + "loss": 3.5297, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.169313262965625e-05, + "loss": 3.5483, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.168474668214573e-05, + "loss": 3.5464, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.167636073463521e-05, + "loss": 3.5458, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.1667991165928426e-05, + "loss": 3.5486, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.16596052184179e-05, + "loss": 3.5455, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.165121927090738e-05, + "loss": 3.5408, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.164283332339686e-05, + "loss": 3.5443, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.1634463754690075e-05, + "loss": 3.5375, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.162607780717955e-05, + "loss": 3.5372, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.161769185966903e-05, + "loss": 3.5351, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.160930591215851e-05, + "loss": 3.5421, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.160093634345172e-05, + "loss": 3.5429, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.1592550395941204e-05, + "loss": 3.5294, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.1584164448430684e-05, + "loss": 3.532, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.1575778500920164e-05, + "loss": 3.5456, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.156740893221337e-05, + "loss": 3.553, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.155902298470285e-05, + "loss": 3.5455, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.155063703719233e-05, + "loss": 3.5448, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.154225108968181e-05, + "loss": 3.5497, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.153388152097502e-05, + "loss": 3.5461, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.15254955734645e-05, + "loss": 3.5388, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.151710962595398e-05, + "loss": 3.5397, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.150872367844346e-05, + "loss": 3.5426, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.150035410973667e-05, + "loss": 3.5485, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.149196816222616e-05, + "loss": 3.5205, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.148358221471564e-05, + "loss": 3.543, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.147519626720512e-05, + "loss": 3.5312, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.1466826698498326e-05, + "loss": 3.5418, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.1458440750987806e-05, + "loss": 3.5457, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.1450054803477286e-05, + "loss": 3.5434, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.1441668855966766e-05, + "loss": 3.5304, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.1433299287259975e-05, + "loss": 3.5368, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.1424913339749455e-05, + "loss": 3.5513, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.1416527392238935e-05, + "loss": 3.5415, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.1408141444728415e-05, + "loss": 3.5514, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.1399755497217895e-05, + "loss": 3.5371, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.139138592851111e-05, + "loss": 3.5431, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.138299998100059e-05, + "loss": 3.5492, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.137461403349007e-05, + "loss": 3.5452, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.136624446478328e-05, + "loss": 3.5391, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.135785851727276e-05, + "loss": 3.5393, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.134947256976224e-05, + "loss": 3.5513, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.134108662225172e-05, + "loss": 3.5538, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.133271705354493e-05, + "loss": 3.5429, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.132433110603441e-05, + "loss": 3.5338, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.131594515852389e-05, + "loss": 3.543, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.130755921101337e-05, + "loss": 3.5347, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.129918964230658e-05, + "loss": 3.5294, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.1290803694796065e-05, + "loss": 3.5535, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.1282417747285545e-05, + "loss": 3.5366, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.1274031799775025e-05, + "loss": 3.5469, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.1265662231068234e-05, + "loss": 3.5373, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 3.847018003463745, + "eval_runtime": 304.3354, + "eval_samples_per_second": 1253.85, + "eval_steps_per_second": 39.184, + "step": 1144800 + }, + { + "epoch": 0.0, + "learning_rate": 3.1257276283557714e-05, + "loss": 3.526, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.1248890336047194e-05, + "loss": 3.5351, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.1240504388536674e-05, + "loss": 3.5386, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.1232118441026154e-05, + "loss": 3.5471, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.122374887231936e-05, + "loss": 3.5499, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.121536292480884e-05, + "loss": 3.5431, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.120697697729832e-05, + "loss": 3.5367, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.11985910297878e-05, + "loss": 3.5304, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.119022146108101e-05, + "loss": 3.5322, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.11818355135705e-05, + "loss": 3.5425, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.117344956605998e-05, + "loss": 3.537, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.116506361854946e-05, + "loss": 3.555, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.1156710428646397e-05, + "loss": 3.5532, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.1148324481135877e-05, + "loss": 3.5258, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.1139938533625357e-05, + "loss": 3.5274, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.1131552586114836e-05, + "loss": 3.5254, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.1123166638604316e-05, + "loss": 3.542, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.1114780691093796e-05, + "loss": 3.5332, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.1106394743583276e-05, + "loss": 3.5331, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.1098008796072756e-05, + "loss": 3.5263, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.1089639227365965e-05, + "loss": 3.5523, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.108125327985545e-05, + "loss": 3.5314, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.107286733234493e-05, + "loss": 3.5382, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.106448138483441e-05, + "loss": 3.5391, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.105611181612762e-05, + "loss": 3.5491, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.10477258686171e-05, + "loss": 3.529, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.103933992110658e-05, + "loss": 3.5318, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.103095397359606e-05, + "loss": 3.5353, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.102256802608554e-05, + "loss": 3.5343, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.101419845737875e-05, + "loss": 3.5266, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.100581250986823e-05, + "loss": 3.5342, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.099742656235771e-05, + "loss": 3.5383, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.098905699365092e-05, + "loss": 3.5349, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.0980671046140406e-05, + "loss": 3.5399, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.0972285098629886e-05, + "loss": 3.533, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.0963899151119366e-05, + "loss": 3.536, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.0955529582412575e-05, + "loss": 3.533, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.0947143634902055e-05, + "loss": 3.5259, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.0938757687391535e-05, + "loss": 3.5325, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.0930371739881015e-05, + "loss": 3.5195, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.0922002171174224e-05, + "loss": 3.5324, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.0913616223663704e-05, + "loss": 3.5286, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.0905230276153184e-05, + "loss": 3.546, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.0896844328642664e-05, + "loss": 3.5334, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.0888458381132144e-05, + "loss": 3.5329, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.088008881242536e-05, + "loss": 3.5404, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.087170286491484e-05, + "loss": 3.5294, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.086331691740432e-05, + "loss": 3.5267, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.085494734869753e-05, + "loss": 3.519, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.084656140118701e-05, + "loss": 3.5334, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.083817545367649e-05, + "loss": 3.533, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.082978950616597e-05, + "loss": 3.5323, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.082140355865545e-05, + "loss": 3.5356, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.081303398994866e-05, + "loss": 3.5179, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.080464804243814e-05, + "loss": 3.5275, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.079626209492762e-05, + "loss": 3.5164, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.07878761474171e-05, + "loss": 3.5452, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.077950657871031e-05, + "loss": 3.521, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.077112063119979e-05, + "loss": 3.5454, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.076273468368927e-05, + "loss": 3.531, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.0754348736178746e-05, + "loss": 3.5131, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.074597916747196e-05, + "loss": 3.5287, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.073759321996144e-05, + "loss": 3.5283, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.072920727245092e-05, + "loss": 3.5195, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.0720821324940395e-05, + "loss": 3.516, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.071245175623361e-05, + "loss": 3.5377, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.070406580872309e-05, + "loss": 3.5228, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.069567986121257e-05, + "loss": 3.5204, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.068729391370205e-05, + "loss": 3.5142, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.067892434499527e-05, + "loss": 3.5274, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.067053839748475e-05, + "loss": 3.5344, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.066215244997422e-05, + "loss": 3.5276, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.06537665024637e-05, + "loss": 3.5265, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.0645396933756916e-05, + "loss": 3.5311, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.0637010986246396e-05, + "loss": 3.5355, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.062862503873587e-05, + "loss": 3.5243, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.062023909122535e-05, + "loss": 3.5304, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.0611869522518565e-05, + "loss": 3.5302, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.0603483575008045e-05, + "loss": 3.5246, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.059509762749752e-05, + "loss": 3.5299, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.0586711679987005e-05, + "loss": 3.5299, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.057834211128022e-05, + "loss": 3.5323, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.0569956163769694e-05, + "loss": 3.5401, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.0561570216259174e-05, + "loss": 3.5252, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.0553184268748654e-05, + "loss": 3.5175, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.054481470004187e-05, + "loss": 3.5227, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.053642875253134e-05, + "loss": 3.5354, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.052804280502082e-05, + "loss": 3.532, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.05196568575103e-05, + "loss": 3.5237, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.051128728880352e-05, + "loss": 3.5338, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.0502901341292995e-05, + "loss": 3.5327, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.0494515393782475e-05, + "loss": 3.5221, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.048614582507569e-05, + "loss": 3.5254, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0477759877565164e-05, + "loss": 3.5402, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.0469373930054644e-05, + "loss": 3.5266, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.0460987982544127e-05, + "loss": 3.5393, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.0452618413837343e-05, + "loss": 3.5201, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.0444232466326816e-05, + "loss": 3.5333, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.0435846518816296e-05, + "loss": 3.5335, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.0427460571305776e-05, + "loss": 3.5276, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.0419091002598992e-05, + "loss": 3.5369, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.041070505508847e-05, + "loss": 3.5297, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.040231910757795e-05, + "loss": 3.5253, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.039393316006743e-05, + "loss": 3.5235, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.0385563591360638e-05, + "loss": 3.527, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.0377177643850118e-05, + "loss": 3.5198, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.0368791696339598e-05, + "loss": 3.5213, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.036040574882908e-05, + "loss": 3.5336, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.035203618012229e-05, + "loss": 3.5273, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.034365023261177e-05, + "loss": 3.5139, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.033526428510125e-05, + "loss": 3.5185, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.032687833759073e-05, + "loss": 3.5286, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.0318508768883942e-05, + "loss": 3.5383, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.0310122821373422e-05, + "loss": 3.5287, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.0301736873862902e-05, + "loss": 3.5307, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.0293350926352382e-05, + "loss": 3.5332, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.028498135764559e-05, + "loss": 3.5396, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.027659541013507e-05, + "loss": 3.5213, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.026820946262455e-05, + "loss": 3.5261, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0259823515114035e-05, + "loss": 3.5283, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0251453946407244e-05, + "loss": 3.531, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.0243067998896724e-05, + "loss": 3.5107, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.0234682051386204e-05, + "loss": 3.5243, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.0226296103875684e-05, + "loss": 3.5195, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0217926535168896e-05, + "loss": 3.5238, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0209540587658376e-05, + "loss": 3.5263, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0201154640147856e-05, + "loss": 3.5375, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.0192768692637336e-05, + "loss": 3.5175, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0184399123930545e-05, + "loss": 3.5215, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.0176013176420025e-05, + "loss": 3.5308, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.0167627228909505e-05, + "loss": 3.532, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.0159241281398988e-05, + "loss": 3.5345, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.0150871712692197e-05, + "loss": 3.5227, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.0142485765181677e-05, + "loss": 3.5276, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0134099817671157e-05, + "loss": 3.5344, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.0125713870160637e-05, + "loss": 3.5331, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.011734430145385e-05, + "loss": 3.5233, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.010895835394333e-05, + "loss": 3.5267, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.010057240643281e-05, + "loss": 3.5364, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.009218645892229e-05, + "loss": 3.5339, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.00838168902155e-05, + "loss": 3.5332, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.007543094270498e-05, + "loss": 3.5207, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.006704499519446e-05, + "loss": 3.5268, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.0058659047683942e-05, + "loss": 3.5159, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.005028947897715e-05, + "loss": 3.5163, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.004190353146663e-05, + "loss": 3.5393, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.003351758395611e-05, + "loss": 3.5237, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.002513163644559e-05, + "loss": 3.5295, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.0016762067738803e-05, + "loss": 3.5247, + "step": 1220608 + }, + { + "epoch": 0.03, + "learning_rate": 3.0008376120228283e-05, + "loss": 3.5199, + "step": 1221120 + }, + { + "epoch": 0.03, + "eval_loss": 3.8478143215179443, + "eval_runtime": 305.5063, + "eval_samples_per_second": 1249.045, + "eval_steps_per_second": 39.034, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 2.9999990172717763e-05, + "loss": 3.5224, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.9991604225207243e-05, + "loss": 3.5202, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.9983234656500452e-05, + "loss": 3.5353, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.9974848708989932e-05, + "loss": 3.5322, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.9966462761479412e-05, + "loss": 3.5315, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9958076813968892e-05, + "loss": 3.5181, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.9949707245262105e-05, + "loss": 3.5169, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.9941321297751585e-05, + "loss": 3.5134, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.9932935350241065e-05, + "loss": 3.5299, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.9924549402730545e-05, + "loss": 3.5234, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.9916179834023757e-05, + "loss": 3.5367, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.9907793886513237e-05, + "loss": 3.5325, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.9899424317806446e-05, + "loss": 3.519, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.9891038370295926e-05, + "loss": 3.5153, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.9882652422785406e-05, + "loss": 3.5143, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.9874266475274886e-05, + "loss": 3.5183, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.9865880527764366e-05, + "loss": 3.5192, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.9857494580253846e-05, + "loss": 3.5166, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.984910863274333e-05, + "loss": 3.5145, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.9840739064036538e-05, + "loss": 3.5401, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.9832353116526018e-05, + "loss": 3.5144, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9823967169015498e-05, + "loss": 3.5275, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.9815581221504978e-05, + "loss": 3.5238, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.980721165279819e-05, + "loss": 3.5321, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.979882570528767e-05, + "loss": 3.5138, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.979043975777715e-05, + "loss": 3.5191, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.978205381026663e-05, + "loss": 3.5193, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.977366786275611e-05, + "loss": 3.5215, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.976529829404932e-05, + "loss": 3.5123, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.97569123465388e-05, + "loss": 3.5198, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.9748526399028283e-05, + "loss": 3.5256, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.9740140451517763e-05, + "loss": 3.5206, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.9731770882810972e-05, + "loss": 3.5257, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.9723384935300452e-05, + "loss": 3.5206, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9714998987789932e-05, + "loss": 3.5187, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.9706629419083144e-05, + "loss": 3.5167, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9698243471572624e-05, + "loss": 3.5101, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.9689857524062104e-05, + "loss": 3.5209, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.9681471576551584e-05, + "loss": 3.5041, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.9673102007844793e-05, + "loss": 3.5169, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.9664716060334273e-05, + "loss": 3.5148, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.9656330112823753e-05, + "loss": 3.5275, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.9647944165313237e-05, + "loss": 3.5213, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.9639558217802716e-05, + "loss": 3.5144, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.9631188649095926e-05, + "loss": 3.5251, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.9622802701585406e-05, + "loss": 3.5191, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.9614416754074886e-05, + "loss": 3.5135, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.9606030806564365e-05, + "loss": 3.5067, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.9597661237857578e-05, + "loss": 3.5106, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.9589275290347058e-05, + "loss": 3.523, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.9580889342836538e-05, + "loss": 3.5174, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.957250339532601e-05, + "loss": 3.5174, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.9564133826619227e-05, + "loss": 3.5076, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.9555747879108707e-05, + "loss": 3.5124, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.954736193159819e-05, + "loss": 3.5023, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.9538975984087663e-05, + "loss": 3.5283, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.953060641538088e-05, + "loss": 3.5111, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.952222046787036e-05, + "loss": 3.5277, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.951383452035984e-05, + "loss": 3.5168, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9505448572849316e-05, + "loss": 3.502, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.949707900414253e-05, + "loss": 3.5146, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.948869305663201e-05, + "loss": 3.5142, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.9480307109121485e-05, + "loss": 3.5045, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.9471921161610965e-05, + "loss": 3.5002, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.946355159290418e-05, + "loss": 3.5254, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.945516564539366e-05, + "loss": 3.5112, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.9446779697883137e-05, + "loss": 3.5055, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.9438393750372617e-05, + "loss": 3.5, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.9430024181665833e-05, + "loss": 3.5142, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.9421638234155313e-05, + "loss": 3.5201, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.941325228664479e-05, + "loss": 3.5158, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.940486633913427e-05, + "loss": 3.5119, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.9396496770427485e-05, + "loss": 3.5169, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.938811082291696e-05, + "loss": 3.5189, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.937972487540644e-05, + "loss": 3.5121, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.937133892789592e-05, + "loss": 3.5137, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.9362969359189134e-05, + "loss": 3.5187, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.935458341167861e-05, + "loss": 3.5099, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.934619746416809e-05, + "loss": 3.5183, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.933781151665757e-05, + "loss": 3.515, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.9329441947950787e-05, + "loss": 3.52, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.932105600044026e-05, + "loss": 3.5228, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.9312670052929743e-05, + "loss": 3.5119, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.9304284105419223e-05, + "loss": 3.5042, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.9295914536712432e-05, + "loss": 3.5089, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.9287528589201912e-05, + "loss": 3.5176, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.9279142641691392e-05, + "loss": 3.5195, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.9270756694180872e-05, + "loss": 3.5125, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.9262387125474085e-05, + "loss": 3.5178, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9254001177963564e-05, + "loss": 3.5179, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9245615230453044e-05, + "loss": 3.5124, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9237229282942524e-05, + "loss": 3.5132, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.9228859714235733e-05, + "loss": 3.5157, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.9220473766725213e-05, + "loss": 3.5161, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.9212087819214697e-05, + "loss": 3.5223, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.9203701871704177e-05, + "loss": 3.5116, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9195332302997386e-05, + "loss": 3.5176, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.9186946355486866e-05, + "loss": 3.5206, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.9178560407976346e-05, + "loss": 3.5188, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.9170174460465826e-05, + "loss": 3.5179, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.9161804891759038e-05, + "loss": 3.5184, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.9153418944248518e-05, + "loss": 3.5086, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.9145032996737998e-05, + "loss": 3.5129, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.9136647049227478e-05, + "loss": 3.5149, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.9128277480520687e-05, + "loss": 3.502, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.9119891533010167e-05, + "loss": 3.502, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.911150558549965e-05, + "loss": 3.5219, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.910311963798913e-05, + "loss": 3.5135, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.909475006928234e-05, + "loss": 3.4975, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.908636412177182e-05, + "loss": 3.5061, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.90779781742613e-05, + "loss": 3.5135, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.906959222675078e-05, + "loss": 3.5248, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.9061222658043992e-05, + "loss": 3.5198, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9052836710533472e-05, + "loss": 3.512, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.9044450763022952e-05, + "loss": 3.5224, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.9036064815512432e-05, + "loss": 3.5223, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.902769524680564e-05, + "loss": 3.5058, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.901930929929512e-05, + "loss": 3.5111, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.90109233517846e-05, + "loss": 3.5178, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.9002537404274084e-05, + "loss": 3.5127, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.8994167835567293e-05, + "loss": 3.5018, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.8985781888056773e-05, + "loss": 3.5044, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.8977395940546253e-05, + "loss": 3.5057, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.8969009993035733e-05, + "loss": 3.5081, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.8960640424328946e-05, + "loss": 3.5135, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.8952254476818425e-05, + "loss": 3.5228, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.8943868529307905e-05, + "loss": 3.5059, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8935482581797385e-05, + "loss": 3.5102, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.8927113013090594e-05, + "loss": 3.5103, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.8918727065580074e-05, + "loss": 3.5206, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.8910341118069554e-05, + "loss": 3.5198, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.8901955170559038e-05, + "loss": 3.5118, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.8893585601852247e-05, + "loss": 3.511, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.8885199654341727e-05, + "loss": 3.518, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.8876813706831207e-05, + "loss": 3.52, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.8868427759320687e-05, + "loss": 3.5122, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.88600581906139e-05, + "loss": 3.5106, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.885167224310338e-05, + "loss": 3.5217, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.884328629559286e-05, + "loss": 3.5185, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.883490034808234e-05, + "loss": 3.5193, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.8826530779375548e-05, + "loss": 3.5069, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.8818144831865028e-05, + "loss": 3.5136, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.8809758884354508e-05, + "loss": 3.5065, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.880137293684399e-05, + "loss": 3.4978, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.87930033681372e-05, + "loss": 3.5259, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.878461742062668e-05, + "loss": 3.5123, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.877623147311616e-05, + "loss": 3.5184, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.876784552560564e-05, + "loss": 3.5115, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.8759475956898853e-05, + "loss": 3.5015, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 3.849015712738037, + "eval_runtime": 305.1963, + "eval_samples_per_second": 1250.313, + "eval_steps_per_second": 39.073, + "step": 1297440 + }, + { + "epoch": 0.0, + "learning_rate": 2.8751090009388333e-05, + "loss": 3.5079, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8742704061877813e-05, + "loss": 3.5082, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8734318114367293e-05, + "loss": 3.5238, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8725932166856773e-05, + "loss": 3.5124, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.8717562598149982e-05, + "loss": 3.5208, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8709176650639462e-05, + "loss": 3.5033, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8700790703128945e-05, + "loss": 3.5059, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8692421134422154e-05, + "loss": 3.5041, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.8684035186911634e-05, + "loss": 3.5111, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.8675649239401114e-05, + "loss": 3.5134, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.8667263291890594e-05, + "loss": 3.5206, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.8658877344380074e-05, + "loss": 3.5175, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650524154477016e-05, + "loss": 3.5073, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8642138206966496e-05, + "loss": 3.5034, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.8633752259455976e-05, + "loss": 3.5036, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.8625366311945455e-05, + "loss": 3.4997, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8616980364434935e-05, + "loss": 3.5067, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.8608594416924415e-05, + "loss": 3.5011, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.86002084694139e-05, + "loss": 3.5008, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.859182252190338e-05, + "loss": 3.529, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8583452953196588e-05, + "loss": 3.5022, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8575067005686068e-05, + "loss": 3.5077, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.8566681058175548e-05, + "loss": 3.5091, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.855831148946876e-05, + "loss": 3.515, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.854992554195824e-05, + "loss": 3.5021, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.854153959444772e-05, + "loss": 3.5073, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.85331536469372e-05, + "loss": 3.5036, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.852476769942668e-05, + "loss": 3.5122, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.851639813071989e-05, + "loss": 3.4928, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.850801218320937e-05, + "loss": 3.5065, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8499626235698852e-05, + "loss": 3.5108, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.8491240288188332e-05, + "loss": 3.5088, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.848287071948154e-05, + "loss": 3.5152, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.847448477197102e-05, + "loss": 3.5052, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.84660988244605e-05, + "loss": 3.5032, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.845771287694998e-05, + "loss": 3.5044, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8449343308243194e-05, + "loss": 3.4957, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8440957360732674e-05, + "loss": 3.505, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.8432571413222154e-05, + "loss": 3.4921, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.8424185465711634e-05, + "loss": 3.4993, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.8415815897004843e-05, + "loss": 3.5057, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.8407429949494323e-05, + "loss": 3.5155, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.8399044001983806e-05, + "loss": 3.5072, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.839065805447328e-05, + "loss": 3.5028, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8382288485766495e-05, + "loss": 3.5156, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.8373902538255975e-05, + "loss": 3.5059, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.8365516590745455e-05, + "loss": 3.4977, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.835713064323493e-05, + "loss": 3.498, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.8348761074528147e-05, + "loss": 3.494, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.8340375127017627e-05, + "loss": 3.5094, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331989179507107e-05, + "loss": 3.5028, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.832360323199658e-05, + "loss": 3.4995, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.8315233663289796e-05, + "loss": 3.497, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8306847715779276e-05, + "loss": 3.5018, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.8298461768268753e-05, + "loss": 3.488, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.8290075820758233e-05, + "loss": 3.5124, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.828170625205145e-05, + "loss": 3.4993, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.827332030454093e-05, + "loss": 3.5147, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8264934357030405e-05, + "loss": 3.5055, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.8256548409519885e-05, + "loss": 3.4894, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.82481788408131e-05, + "loss": 3.4991, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.823979289330258e-05, + "loss": 3.503, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8231406945792054e-05, + "loss": 3.4896, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8223020998281534e-05, + "loss": 3.4894, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.821465142957475e-05, + "loss": 3.5064, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8206265482064227e-05, + "loss": 3.4995, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8197879534553707e-05, + "loss": 3.4929, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8189493587043187e-05, + "loss": 3.4907, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8181124018336402e-05, + "loss": 3.496, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8172738070825876e-05, + "loss": 3.5047, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.816435212331536e-05, + "loss": 3.5021, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.815596617580484e-05, + "loss": 3.4984, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.8147596607098055e-05, + "loss": 3.5064, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.8139210659587528e-05, + "loss": 3.5025, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8130824712077008e-05, + "loss": 3.5047, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.8122438764566488e-05, + "loss": 3.4914, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.81140691958597e-05, + "loss": 3.5061, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.810568324834918e-05, + "loss": 3.4993, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.809729730083866e-05, + "loss": 3.5013, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.808891135332814e-05, + "loss": 3.5064, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.808054178462135e-05, + "loss": 3.5044, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.807215583711083e-05, + "loss": 3.5075, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.806376988960031e-05, + "loss": 3.4997, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8055383942089793e-05, + "loss": 3.4863, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8047014373383002e-05, + "loss": 3.4969, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.803862842587248e-05, + "loss": 3.5013, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.803024247836196e-05, + "loss": 3.5056, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.802185653085144e-05, + "loss": 3.5002, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8013486962144654e-05, + "loss": 3.5034, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8005101014634134e-05, + "loss": 3.5005, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7996715067123614e-05, + "loss": 3.499, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.7988329119613094e-05, + "loss": 3.5007, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7979959550906303e-05, + "loss": 3.5026, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7971573603395783e-05, + "loss": 3.4972, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7963187655885263e-05, + "loss": 3.509, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7954801708374746e-05, + "loss": 3.5052, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7946432139667955e-05, + "loss": 3.4985, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7938046192157435e-05, + "loss": 3.5091, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7929660244646915e-05, + "loss": 3.5051, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7921274297136395e-05, + "loss": 3.5085, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7912904728429608e-05, + "loss": 3.5034, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.7904518780919088e-05, + "loss": 3.4928, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.7896132833408568e-05, + "loss": 3.5011, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7887763264701777e-05, + "loss": 3.5023, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.7879377317191257e-05, + "loss": 3.4846, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.7870991369680737e-05, + "loss": 3.4969, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7862605422170217e-05, + "loss": 3.5053, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.785423585346343e-05, + "loss": 3.5023, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.784584990595291e-05, + "loss": 3.4877, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.783746395844239e-05, + "loss": 3.4888, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.782907801093187e-05, + "loss": 3.5013, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.7820708442225078e-05, + "loss": 3.5103, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.781232249471456e-05, + "loss": 3.5023, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.780393654720404e-05, + "loss": 3.5021, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.779555059969352e-05, + "loss": 3.5048, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.778718103098673e-05, + "loss": 3.5138, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.777879508347621e-05, + "loss": 3.4914, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.777040913596569e-05, + "loss": 3.4961, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.776202318845517e-05, + "loss": 3.5042, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.7753653619748383e-05, + "loss": 3.5032, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7745267672237863e-05, + "loss": 3.486, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7736881724727343e-05, + "loss": 3.4885, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.7728495777216823e-05, + "loss": 3.4984, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7720126208510032e-05, + "loss": 3.4962, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7711740260999515e-05, + "loss": 3.5024, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7703354313488995e-05, + "loss": 3.5061, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7694968365978475e-05, + "loss": 3.4902, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7686598797271684e-05, + "loss": 3.4974, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.7678212849761164e-05, + "loss": 3.4948, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.7669826902250644e-05, + "loss": 3.5116, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.7661440954740124e-05, + "loss": 3.5095, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.7653071386033336e-05, + "loss": 3.4953, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.7644685438522816e-05, + "loss": 3.4975, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7636299491012296e-05, + "loss": 3.5009, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.7627913543501776e-05, + "loss": 3.5103, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7619543974794985e-05, + "loss": 3.5023, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.761115802728447e-05, + "loss": 3.4986, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.760277207977395e-05, + "loss": 3.5059, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.759438613226343e-05, + "loss": 3.5032, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.7586016563556638e-05, + "loss": 3.5061, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.7577630616046118e-05, + "loss": 3.4944, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.7569244668535598e-05, + "loss": 3.4992, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7560858721025078e-05, + "loss": 3.4954, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.755248915231829e-05, + "loss": 3.4851, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.754410320480777e-05, + "loss": 3.5148, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.753571725729725e-05, + "loss": 3.4979, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.752733130978673e-05, + "loss": 3.5039, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.751896174107994e-05, + "loss": 3.4984, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.7510575793569422e-05, + "loss": 3.4899, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.8509576320648193, + "eval_runtime": 303.5355, + "eval_samples_per_second": 1257.155, + "eval_steps_per_second": 39.287, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7502189846058902e-05, + "loss": 3.4971, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493803898548382e-05, + "loss": 3.4908, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485417951037862e-05, + "loss": 3.5109, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7477032003527342e-05, + "loss": 3.4975, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.746866243482055e-05, + "loss": 3.51, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.746027648731003e-05, + "loss": 3.4904, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451890539799515e-05, + "loss": 3.4918, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443504592288995e-05, + "loss": 3.4865, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7435135023582204e-05, + "loss": 3.5008, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426749076071684e-05, + "loss": 3.4976, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7418363128561164e-05, + "loss": 3.5051, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409977181050644e-05, + "loss": 3.504, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401623991147585e-05, + "loss": 3.4945, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7393238043637065e-05, + "loss": 3.4916, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384852096126545e-05, + "loss": 3.4899, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7376466148616025e-05, + "loss": 3.4905, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7368080201105505e-05, + "loss": 3.4894, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359694253594985e-05, + "loss": 3.4911, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7351308306084468e-05, + "loss": 3.4913, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342938737377677e-05, + "loss": 3.5085, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7334552789867157e-05, + "loss": 3.4925, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7326166842356637e-05, + "loss": 3.4923, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317780894846117e-05, + "loss": 3.4992, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7309394947335597e-05, + "loss": 3.5003, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.730102537862881e-05, + "loss": 3.4929, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.729263943111829e-05, + "loss": 3.4957, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.728425348360777e-05, + "loss": 3.4928, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.727586753609725e-05, + "loss": 3.4936, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.726749796739046e-05, + "loss": 3.4826, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725911201987994e-05, + "loss": 3.4935, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.725072607236942e-05, + "loss": 3.4968, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.724235650366263e-05, + "loss": 3.4968, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.723397055615211e-05, + "loss": 3.5016, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.722558460864159e-05, + "loss": 3.4922, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.721719866113107e-05, + "loss": 3.4876, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.720882909242428e-05, + "loss": 3.4932, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7200443144913763e-05, + "loss": 3.4857, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7192057197403243e-05, + "loss": 3.4868, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183671249892723e-05, + "loss": 3.4796, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7175301681185932e-05, + "loss": 3.4857, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166915733675412e-05, + "loss": 3.4943, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158529786164892e-05, + "loss": 3.5006, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7150143838654372e-05, + "loss": 3.4949, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141774269947585e-05, + "loss": 3.4873, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7133388322437065e-05, + "loss": 3.5047, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7125002374926545e-05, + "loss": 3.4893, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116616427416018e-05, + "loss": 3.4869, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7108246858709234e-05, + "loss": 3.4899, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099860911198717e-05, + "loss": 3.4765, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7091474963688197e-05, + "loss": 3.4971, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.708308901617767e-05, + "loss": 3.486, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074719447470886e-05, + "loss": 3.4894, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7066333499960366e-05, + "loss": 3.4864, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057947552449846e-05, + "loss": 3.4888, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049561604939322e-05, + "loss": 3.4751, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.704119203623254e-05, + "loss": 3.5001, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.703280608872202e-05, + "loss": 3.483, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.702442014121149e-05, + "loss": 3.5012, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.701603419370097e-05, + "loss": 3.488, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007664624994187e-05, + "loss": 3.4825, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.699927867748367e-05, + "loss": 3.4828, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990892729973144e-05, + "loss": 3.4912, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982506782462624e-05, + "loss": 3.4747, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.697413721375584e-05, + "loss": 3.4803, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.696575126624532e-05, + "loss": 3.491, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6957365318734796e-05, + "loss": 3.4901, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6948979371224276e-05, + "loss": 3.4808, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940609802517492e-05, + "loss": 3.4751, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6932223855006965e-05, + "loss": 3.4817, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923837907496445e-05, + "loss": 3.4972, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6915451959985925e-05, + "loss": 3.4859, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.690708239127914e-05, + "loss": 3.4843, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898696443768618e-05, + "loss": 3.4944, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6890310496258098e-05, + "loss": 3.4893, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881924548747577e-05, + "loss": 3.4934, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873554980040793e-05, + "loss": 3.4757, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.686516903253027e-05, + "loss": 3.4944, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.685678308501975e-05, + "loss": 3.4898, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.684839713750923e-05, + "loss": 3.4838, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.684002756880244e-05, + "loss": 3.4971, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.683164162129192e-05, + "loss": 3.4914, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.68232556737814e-05, + "loss": 3.4932, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.681486972627088e-05, + "loss": 3.4891, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.680650015756409e-05, + "loss": 3.4746, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.679811421005357e-05, + "loss": 3.4853, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.678972826254305e-05, + "loss": 3.4863, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.678134231503253e-05, + "loss": 3.4925, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.677297274632574e-05, + "loss": 3.4901, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764586798815224e-05, + "loss": 3.4888, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6756200851304704e-05, + "loss": 3.4881, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747814903794184e-05, + "loss": 3.4875, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739445335087393e-05, + "loss": 3.4868, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6731059387576873e-05, + "loss": 3.4873, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722673440066353e-05, + "loss": 3.4887, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6714287492555832e-05, + "loss": 3.4964, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705917923849045e-05, + "loss": 3.4884, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697531976338525e-05, + "loss": 3.487, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6689146028828005e-05, + "loss": 3.4942, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680760081317485e-05, + "loss": 3.4914, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6672390512610694e-05, + "loss": 3.4965, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6664004565100177e-05, + "loss": 3.4886, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6655618617589657e-05, + "loss": 3.4843, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6647232670079137e-05, + "loss": 3.4872, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638863101372346e-05, + "loss": 3.4893, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6630477153861826e-05, + "loss": 3.4699, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6622091206351306e-05, + "loss": 3.4851, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613705258840786e-05, + "loss": 3.4918, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6605335690134e-05, + "loss": 3.4837, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.659694974262348e-05, + "loss": 3.4781, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.658856379511296e-05, + "loss": 3.4797, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.658017784760244e-05, + "loss": 3.4831, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571808278895648e-05, + "loss": 3.5017, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.656342233138513e-05, + "loss": 3.4857, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.655503638387461e-05, + "loss": 3.496, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.654665043636409e-05, + "loss": 3.4902, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.65382808676573e-05, + "loss": 3.5013, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.652989492014678e-05, + "loss": 3.4816, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.652150897263626e-05, + "loss": 3.4853, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.651312302512574e-05, + "loss": 3.4893, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504753456418952e-05, + "loss": 3.4875, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6496367508908432e-05, + "loss": 3.4751, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487981561397912e-05, + "loss": 3.4759, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479595613887392e-05, + "loss": 3.4816, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.64712260451806e-05, + "loss": 3.4873, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462840097670085e-05, + "loss": 3.49, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454454150159565e-05, + "loss": 3.4961, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6446068202649045e-05, + "loss": 3.4763, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437698633942254e-05, + "loss": 3.4818, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6429312686431734e-05, + "loss": 3.4819, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6420926738921214e-05, + "loss": 3.4975, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6412540791410693e-05, + "loss": 3.4998, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6404171222703906e-05, + "loss": 3.486, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395785275193386e-05, + "loss": 3.4795, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6387399327682866e-05, + "loss": 3.4888, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6379013380172346e-05, + "loss": 3.4934, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370643811465555e-05, + "loss": 3.4924, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6362257863955038e-05, + "loss": 3.4839, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353871916444518e-05, + "loss": 3.4911, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6345485968933998e-05, + "loss": 3.4899, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6337116400227207e-05, + "loss": 3.4973, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328730452716687e-05, + "loss": 3.484, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320344505206167e-05, + "loss": 3.4852, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311958557695647e-05, + "loss": 3.4865, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.630358898898886e-05, + "loss": 3.4686, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.629520304147834e-05, + "loss": 3.5005, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.628681709396782e-05, + "loss": 3.4882, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.62784311464573e-05, + "loss": 3.4887, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.627006157775051e-05, + "loss": 3.4886, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.626167563023999e-05, + "loss": 3.4739, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.8521366119384766, + "eval_runtime": 304.8739, + "eval_samples_per_second": 1251.636, + "eval_steps_per_second": 39.115, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6253289682729472e-05, + "loss": 3.4849, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244903735218952e-05, + "loss": 3.4792, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.623653416651216e-05, + "loss": 3.4947, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.622814821900164e-05, + "loss": 3.4836, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.621976227149112e-05, + "loss": 3.5064, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.62113763239806e-05, + "loss": 3.4721, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6203006755273813e-05, + "loss": 3.4831, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6194620807763293e-05, + "loss": 3.4708, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6186234860252773e-05, + "loss": 3.4883, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6177848912742253e-05, + "loss": 3.4858, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6169479344035462e-05, + "loss": 3.488, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6161093396524942e-05, + "loss": 3.4987, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152723827818155e-05, + "loss": 3.479, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6144337880307635e-05, + "loss": 3.4814, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135951932797115e-05, + "loss": 3.4751, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127565985286595e-05, + "loss": 3.477, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6119180037776075e-05, + "loss": 3.4787, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6110794090265554e-05, + "loss": 3.4773, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6102408142755034e-05, + "loss": 3.4808, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6094022195244518e-05, + "loss": 3.4939, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085652626537727e-05, + "loss": 3.4802, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6077266679027207e-05, + "loss": 3.4795, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6068880731516687e-05, + "loss": 3.4871, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6060494784006167e-05, + "loss": 3.4892, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.605212521529938e-05, + "loss": 3.4799, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.604373926778886e-05, + "loss": 3.4827, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.603535332027834e-05, + "loss": 3.4802, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.602696737276782e-05, + "loss": 3.4772, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018597804061028e-05, + "loss": 3.4729, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6010211856550508e-05, + "loss": 3.4773, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.6001825909039988e-05, + "loss": 3.4891, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5993439961529465e-05, + "loss": 3.4823, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.598507039282268e-05, + "loss": 3.4918, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.597668444531216e-05, + "loss": 3.4827, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.596829849780164e-05, + "loss": 3.4768, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.595992892909485e-05, + "loss": 3.4806, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5951542981584333e-05, + "loss": 3.475, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5943157034073813e-05, + "loss": 3.4719, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5934771086563293e-05, + "loss": 3.4676, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5926385139052766e-05, + "loss": 3.4722, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5918015570345982e-05, + "loss": 3.4834, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5909629622835462e-05, + "loss": 3.4843, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.590124367532494e-05, + "loss": 3.4801, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5892874106618154e-05, + "loss": 3.4777, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5884488159107634e-05, + "loss": 3.4925, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5876102211597114e-05, + "loss": 3.4755, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5867716264086587e-05, + "loss": 3.4753, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5859346695379803e-05, + "loss": 3.474, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5850960747869287e-05, + "loss": 3.4632, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842574800358767e-05, + "loss": 3.4862, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.583418885284824e-05, + "loss": 3.4736, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5825819284141456e-05, + "loss": 3.4776, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5817433336630936e-05, + "loss": 3.4722, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5809047389120412e-05, + "loss": 3.4805, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800661441609892e-05, + "loss": 3.4588, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5792275494099372e-05, + "loss": 3.4865, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783905925392588e-05, + "loss": 3.4749, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.577551997788206e-05, + "loss": 3.4858, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.576713403037154e-05, + "loss": 3.4797, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5758748082861024e-05, + "loss": 3.4668, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5750378514154233e-05, + "loss": 3.4683, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741992566643713e-05, + "loss": 3.4842, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5733606619133193e-05, + "loss": 3.464, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5725220671622673e-05, + "loss": 3.4633, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716851102915886e-05, + "loss": 3.4779, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5708465155405366e-05, + "loss": 3.477, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5700079207894846e-05, + "loss": 3.4656, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5691693260384326e-05, + "loss": 3.4659, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5683323691677535e-05, + "loss": 3.466, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5674937744167015e-05, + "loss": 3.4829, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666551796656495e-05, + "loss": 3.4741, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5658165849145978e-05, + "loss": 3.471, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5649796280439187e-05, + "loss": 3.4833, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5641410332928667e-05, + "loss": 3.4798, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5633024385418147e-05, + "loss": 3.4836, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624638437907627e-05, + "loss": 3.4655, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.561626886920084e-05, + "loss": 3.481, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.560788292169032e-05, + "loss": 3.4744, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.55994969741798e-05, + "loss": 3.4714, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.559111102666928e-05, + "loss": 3.4877, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.558274145796249e-05, + "loss": 3.4776, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.557435551045197e-05, + "loss": 3.4802, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.556596956294145e-05, + "loss": 3.4775, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.555758361543093e-05, + "loss": 3.468, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.554921404672414e-05, + "loss": 3.471, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.554082809921362e-05, + "loss": 3.472, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.55324421517031e-05, + "loss": 3.4774, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.552405620419258e-05, + "loss": 3.4773, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5515686635485793e-05, + "loss": 3.4748, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5507300687975273e-05, + "loss": 3.4774, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5498914740464753e-05, + "loss": 3.4791, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5490528792954233e-05, + "loss": 3.4709, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5482159224247442e-05, + "loss": 3.4749, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473773276736922e-05, + "loss": 3.4749, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5465387329226402e-05, + "loss": 3.4874, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5457001381715885e-05, + "loss": 3.4756, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5448631813009094e-05, + "loss": 3.4759, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5440245865498574e-05, + "loss": 3.4815, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431859917988054e-05, + "loss": 3.4763, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5423473970477534e-05, + "loss": 3.4845, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5415104401770747e-05, + "loss": 3.4771, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406718454260227e-05, + "loss": 3.474, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5398332506749707e-05, + "loss": 3.4719, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5389946559239187e-05, + "loss": 3.4814, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5381576990532396e-05, + "loss": 3.457, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5373191043021876e-05, + "loss": 3.4718, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5364805095511356e-05, + "loss": 3.4797, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5356419148000836e-05, + "loss": 3.4744, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5348049579294048e-05, + "loss": 3.4633, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5339663631783528e-05, + "loss": 3.4676, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5331277684273008e-05, + "loss": 3.4721, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5322891736762488e-05, + "loss": 3.4909, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5314522168055697e-05, + "loss": 3.4702, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.530613622054518e-05, + "loss": 3.4821, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.529775027303466e-05, + "loss": 3.4779, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.528936432552414e-05, + "loss": 3.4903, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.528099475681735e-05, + "loss": 3.4722, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.527260880930683e-05, + "loss": 3.4663, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.526422286179631e-05, + "loss": 3.4809, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.525583691428579e-05, + "loss": 3.476, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5247467345579002e-05, + "loss": 3.4621, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5239081398068482e-05, + "loss": 3.464, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.523069545055796e-05, + "loss": 3.471, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.522230950304744e-05, + "loss": 3.4745, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.521393993434065e-05, + "loss": 3.4737, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5205553986830134e-05, + "loss": 3.4875, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5197168039319614e-05, + "loss": 3.4627, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188782091809094e-05, + "loss": 3.4695, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5180412523102303e-05, + "loss": 3.4686, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5172026575591783e-05, + "loss": 3.4868, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163640628081263e-05, + "loss": 3.4865, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5155254680570743e-05, + "loss": 3.4727, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146868733060226e-05, + "loss": 3.4655, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138499164353435e-05, + "loss": 3.479, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5130113216842915e-05, + "loss": 3.481, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5121727269332395e-05, + "loss": 3.4761, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5113357700625604e-05, + "loss": 3.4753, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104971753115088e-05, + "loss": 3.4761, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096585805604568e-05, + "loss": 3.4784, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5088199858094048e-05, + "loss": 3.4874, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5079813910583528e-05, + "loss": 3.4716, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5071444341876737e-05, + "loss": 3.471, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5063058394366217e-05, + "loss": 3.4723, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5054672446855697e-05, + "loss": 3.4626, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.504628649934518e-05, + "loss": 3.484, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.503791693063839e-05, + "loss": 3.477, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.502953098312787e-05, + "loss": 3.4782, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.502114503561735e-05, + "loss": 3.4707, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.501275908810683e-05, + "loss": 3.4693, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.85332989692688, + "eval_runtime": 304.4549, + "eval_samples_per_second": 1253.358, + "eval_steps_per_second": 39.168, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500438951940004e-05, + "loss": 3.4718, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499600357188952e-05, + "loss": 3.4648, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4987617624378998e-05, + "loss": 3.4805, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4979231676868478e-05, + "loss": 3.4744, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.497086210816169e-05, + "loss": 3.488, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.496247616065117e-05, + "loss": 3.47, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.495409021314065e-05, + "loss": 3.4678, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494570426563013e-05, + "loss": 3.4591, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4937334696923343e-05, + "loss": 3.4736, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492894874941282e-05, + "loss": 3.4776, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.49205628019023e-05, + "loss": 3.4755, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.491217685439178e-05, + "loss": 3.4815, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903807285684995e-05, + "loss": 3.4697, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.489542133817447e-05, + "loss": 3.4672, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.488703539066395e-05, + "loss": 3.4652, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.487864944315343e-05, + "loss": 3.4644, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.487027987444664e-05, + "loss": 3.4669, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.486189392693612e-05, + "loss": 3.467, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853507979425604e-05, + "loss": 3.4663, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4845122031915084e-05, + "loss": 3.4797, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836752463208293e-05, + "loss": 3.4715, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4828366515697773e-05, + "loss": 3.4693, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819980568187253e-05, + "loss": 3.4725, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811594620676733e-05, + "loss": 3.4781, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4803225051969945e-05, + "loss": 3.4642, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794839104459425e-05, + "loss": 3.4773, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786453156948905e-05, + "loss": 3.4633, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4778067209438385e-05, + "loss": 3.4658, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4769697640731594e-05, + "loss": 3.4603, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4761311693221074e-05, + "loss": 3.4671, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752925745710558e-05, + "loss": 3.4749, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744539798200038e-05, + "loss": 3.472, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4736170229493247e-05, + "loss": 3.4786, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727784281982727e-05, + "loss": 3.4698, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719398334472207e-05, + "loss": 3.461, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4711012386961687e-05, + "loss": 3.4703, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.47026428182549e-05, + "loss": 3.4663, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469425687074438e-05, + "loss": 3.4589, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.468587092323386e-05, + "loss": 3.4575, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.467748497572334e-05, + "loss": 3.4582, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4669115407016548e-05, + "loss": 3.4704, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660729459506028e-05, + "loss": 3.4729, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.465234351199551e-05, + "loss": 3.4699, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464395756448499e-05, + "loss": 3.4622, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.46355879957782e-05, + "loss": 3.4805, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.462720204826768e-05, + "loss": 3.4679, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.461881610075716e-05, + "loss": 3.4617, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610446532050373e-05, + "loss": 3.4601, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4602060584539853e-05, + "loss": 3.4486, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593674637029333e-05, + "loss": 3.4773, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4585288689518813e-05, + "loss": 3.4625, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576902742008293e-05, + "loss": 3.4663, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.45685331733015e-05, + "loss": 3.4648, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.456014722579098e-05, + "loss": 3.4604, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551761278280465e-05, + "loss": 3.4525, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4543375330769945e-05, + "loss": 3.4669, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4535005762063154e-05, + "loss": 3.4644, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526619814552634e-05, + "loss": 3.4749, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4518233867042114e-05, + "loss": 3.467, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509847919531594e-05, + "loss": 3.4575, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501478350824806e-05, + "loss": 3.4561, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4493092403314286e-05, + "loss": 3.4716, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484706455803766e-05, + "loss": 3.4547, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4476320508293243e-05, + "loss": 3.4519, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467950939586455e-05, + "loss": 3.4666, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459564992075935e-05, + "loss": 3.4686, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.445117904456542e-05, + "loss": 3.4535, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442793097054895e-05, + "loss": 3.4525, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434423528348108e-05, + "loss": 3.4512, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4426037580837588e-05, + "loss": 3.4686, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417651633327064e-05, + "loss": 3.4638, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4409265685816544e-05, + "loss": 3.4622, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.440089611710976e-05, + "loss": 3.4701, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439251016959924e-05, + "loss": 3.4638, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4384124222088717e-05, + "loss": 3.4746, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375738274578197e-05, + "loss": 3.456, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.436736870587141e-05, + "loss": 3.4642, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435898275836089e-05, + "loss": 3.4623, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.435059681085037e-05, + "loss": 3.4552, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.434221086333985e-05, + "loss": 3.4776, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.433384129463306e-05, + "loss": 3.4669, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325455347122538e-05, + "loss": 3.4688, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4317069399612018e-05, + "loss": 3.4693, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308683452101498e-05, + "loss": 3.4536, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4300313883394714e-05, + "loss": 3.4562, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.429192793588419e-05, + "loss": 3.4603, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428354198837367e-05, + "loss": 3.4618, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.427515604086315e-05, + "loss": 3.465, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266786472156363e-05, + "loss": 3.463, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258400524645843e-05, + "loss": 3.4645, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4250014577135323e-05, + "loss": 3.4699, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241628629624803e-05, + "loss": 3.456, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.423325906091801e-05, + "loss": 3.4634, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422487311340749e-05, + "loss": 3.4633, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.421648716589697e-05, + "loss": 3.4766, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.420810121838645e-05, + "loss": 3.4654, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199731649679664e-05, + "loss": 3.4617, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4191345702169144e-05, + "loss": 3.4695, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182959754658624e-05, + "loss": 3.4631, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174573807148104e-05, + "loss": 3.4753, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4166204238441313e-05, + "loss": 3.4658, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157818290930796e-05, + "loss": 3.4598, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4149432343420276e-05, + "loss": 3.4554, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4141046395909756e-05, + "loss": 3.4709, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132676827202965e-05, + "loss": 3.4455, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4124290879692445e-05, + "loss": 3.4604, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115904932181925e-05, + "loss": 3.4649, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107518984671405e-05, + "loss": 3.4654, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4099149415964618e-05, + "loss": 3.4521, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090763468454098e-05, + "loss": 3.4547, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4082377520943578e-05, + "loss": 3.4596, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073991573433058e-05, + "loss": 3.4778, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065622004726267e-05, + "loss": 3.4638, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.405723605721575e-05, + "loss": 3.4684, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404885010970523e-05, + "loss": 3.4705, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.404046416219471e-05, + "loss": 3.4747, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.403209459348792e-05, + "loss": 3.4649, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.40237086459774e-05, + "loss": 3.4531, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.401532269846688e-05, + "loss": 3.4657, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.400693675095636e-05, + "loss": 3.4674, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.399856718224957e-05, + "loss": 3.4518, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.399018123473905e-05, + "loss": 3.454, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.398179528722853e-05, + "loss": 3.4563, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.397340933971801e-05, + "loss": 3.4617, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.396503977101122e-05, + "loss": 3.4623, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956653823500704e-05, + "loss": 3.4745, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3948267875990184e-05, + "loss": 3.449, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939881928479664e-05, + "loss": 3.4578, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3931512359772873e-05, + "loss": 3.4565, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3923126412262353e-05, + "loss": 3.4775, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914740464751833e-05, + "loss": 3.4681, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3906354517241312e-05, + "loss": 3.4685, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897984948534525e-05, + "loss": 3.4501, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889599001024005e-05, + "loss": 3.469, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3881213053513485e-05, + "loss": 3.4733, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872827106002965e-05, + "loss": 3.4627, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3864457537296174e-05, + "loss": 3.461, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3856071589785657e-05, + "loss": 3.4682, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847685642275137e-05, + "loss": 3.464, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3839299694764614e-05, + "loss": 3.4782, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830930126057826e-05, + "loss": 3.4564, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822544178547306e-05, + "loss": 3.459, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3814158231036786e-05, + "loss": 3.4572, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3805772283526266e-05, + "loss": 3.4527, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.379740271481948e-05, + "loss": 3.4675, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.378901676730896e-05, + "loss": 3.4666, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780630819798435e-05, + "loss": 3.466, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3772244872287915e-05, + "loss": 3.4582, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763875303581128e-05, + "loss": 3.4617, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8545687198638916, + "eval_runtime": 308.4769, + "eval_samples_per_second": 1237.017, + "eval_steps_per_second": 38.658, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.375548935607061e-05, + "loss": 3.4594, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3747103408560088e-05, + "loss": 3.4508, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3738717461049567e-05, + "loss": 3.472, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.373034789234278e-05, + "loss": 3.4623, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.372196194483226e-05, + "loss": 3.4746, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713575997321736e-05, + "loss": 3.459, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.370519004981122e-05, + "loss": 3.4515, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.3696820481104432e-05, + "loss": 3.4494, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.368843453359391e-05, + "loss": 3.4604, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.368004858608339e-05, + "loss": 3.4662, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.367166263857287e-05, + "loss": 3.4639, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.366329306986608e-05, + "loss": 3.471, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3654923501159294e-05, + "loss": 3.4584, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3646537553648774e-05, + "loss": 3.4584, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.3638151606138254e-05, + "loss": 3.4538, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3629765658627734e-05, + "loss": 3.4491, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.362137971111721e-05, + "loss": 3.457, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.361299376360669e-05, + "loss": 3.456, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604607816096173e-05, + "loss": 3.4537, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3596221868585653e-05, + "loss": 3.4666, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3587852299878863e-05, + "loss": 3.4615, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.3579466352368343e-05, + "loss": 3.4588, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.3571080404857822e-05, + "loss": 3.4601, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3562694457347302e-05, + "loss": 3.4629, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3554324888640515e-05, + "loss": 3.452, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545938941129995e-05, + "loss": 3.466, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537552993619475e-05, + "loss": 3.4492, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3529167046108955e-05, + "loss": 3.4574, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3520797477402164e-05, + "loss": 3.4527, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3512411529891644e-05, + "loss": 3.4524, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3504025582381127e-05, + "loss": 3.4636, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3495639634870607e-05, + "loss": 3.4625, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3487270066163816e-05, + "loss": 3.4629, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478884118653296e-05, + "loss": 3.4578, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3470498171142776e-05, + "loss": 3.4488, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.3462112223632256e-05, + "loss": 3.4621, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345374265492547e-05, + "loss": 3.4571, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.344535670741495e-05, + "loss": 3.4429, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.343697075990443e-05, + "loss": 3.4478, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.342858481239391e-05, + "loss": 3.446, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3420215243687118e-05, + "loss": 3.4536, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3411829296176597e-05, + "loss": 3.4648, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.340344334866608e-05, + "loss": 3.4581, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.339505740115556e-05, + "loss": 3.4557, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.338668783244877e-05, + "loss": 3.4651, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.337830188493825e-05, + "loss": 3.453, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.336991593742773e-05, + "loss": 3.4558, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.336152998991721e-05, + "loss": 3.4497, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3353160421210422e-05, + "loss": 3.4345, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.3344774473699902e-05, + "loss": 3.4656, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.3336388526189382e-05, + "loss": 3.4501, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.3328002578678862e-05, + "loss": 3.4559, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.331963300997207e-05, + "loss": 3.4525, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.331124706246155e-05, + "loss": 3.4476, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3302861114951034e-05, + "loss": 3.4447, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.329447516744051e-05, + "loss": 3.4534, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3286105598733724e-05, + "loss": 3.4539, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.3277719651223204e-05, + "loss": 3.4626, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3269333703712683e-05, + "loss": 3.4542, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.326094775620216e-05, + "loss": 3.4527, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252578187495376e-05, + "loss": 3.44, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3244192239984856e-05, + "loss": 3.4616, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3235806292474336e-05, + "loss": 3.4424, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.3227420344963812e-05, + "loss": 3.4393, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.3219050776257025e-05, + "loss": 3.4542, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.3210664828746505e-05, + "loss": 3.4552, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3202278881235985e-05, + "loss": 3.4393, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193892933725465e-05, + "loss": 3.4459, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3185523365018677e-05, + "loss": 3.4372, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3177137417508157e-05, + "loss": 3.4612, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.3168751469997634e-05, + "loss": 3.4501, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.3160365522487114e-05, + "loss": 3.4509, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.315199595378033e-05, + "loss": 3.4561, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3143610006269806e-05, + "loss": 3.4515, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3135224058759286e-05, + "loss": 3.4671, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.31268544900525e-05, + "loss": 3.4422, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.311846854254198e-05, + "loss": 3.4587, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.311008259503146e-05, + "loss": 3.4498, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.310169664752094e-05, + "loss": 3.4441, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.309332707881415e-05, + "loss": 3.4607, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.308494113130363e-05, + "loss": 3.4588, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076555183793107e-05, + "loss": 3.4574, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3068169236282587e-05, + "loss": 3.4593, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.30597996675758e-05, + "loss": 3.4438, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.305141372006528e-05, + "loss": 3.4456, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.304302777255476e-05, + "loss": 3.4469, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.303464182504424e-05, + "loss": 3.4504, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3026272256337452e-05, + "loss": 3.4546, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.301788630882693e-05, + "loss": 3.4552, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3009500361316412e-05, + "loss": 3.4483, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3001114413805892e-05, + "loss": 3.4609, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.2992744845099105e-05, + "loss": 3.4441, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.298435889758858e-05, + "loss": 3.4508, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.297597295007806e-05, + "loss": 3.4536, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.296758700256754e-05, + "loss": 3.462, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2959217433860754e-05, + "loss": 3.4569, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2950831486350234e-05, + "loss": 3.4473, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2942445538839713e-05, + "loss": 3.459, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2934059591329193e-05, + "loss": 3.4539, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2925690022622403e-05, + "loss": 3.4584, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.2917304075111882e-05, + "loss": 3.4545, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908918127601366e-05, + "loss": 3.4496, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900532180090846e-05, + "loss": 3.444, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2892162611384055e-05, + "loss": 3.4631, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883776663873535e-05, + "loss": 3.4341, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2875390716363015e-05, + "loss": 3.4507, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.2867004768852495e-05, + "loss": 3.4517, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2858635200145707e-05, + "loss": 3.4493, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2850249252635187e-05, + "loss": 3.4429, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2841863305124667e-05, + "loss": 3.4426, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2833477357614147e-05, + "loss": 3.4492, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2825107788907356e-05, + "loss": 3.4637, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.2816721841396836e-05, + "loss": 3.4538, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.280833589388632e-05, + "loss": 3.451, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.27999499463758e-05, + "loss": 3.4587, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.279158037766901e-05, + "loss": 3.4637, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.278319443015849e-05, + "loss": 3.4528, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.277480848264797e-05, + "loss": 3.442, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.276642253513745e-05, + "loss": 3.455, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.275805296643066e-05, + "loss": 3.4537, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.274966701892014e-05, + "loss": 3.4388, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.274128107140962e-05, + "loss": 3.4429, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.27328951238991e-05, + "loss": 3.448, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.272452555519231e-05, + "loss": 3.4476, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.271613960768179e-05, + "loss": 3.4528, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707753660171273e-05, + "loss": 3.4612, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2699367712660753e-05, + "loss": 3.4417, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2690998143953962e-05, + "loss": 3.445, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.2682612196443442e-05, + "loss": 3.447, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2674226248932922e-05, + "loss": 3.463, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665840301422402e-05, + "loss": 3.4554, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2657470732715615e-05, + "loss": 3.4557, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2649084785205095e-05, + "loss": 3.4426, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2640698837694574e-05, + "loss": 3.4573, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2632312890184054e-05, + "loss": 3.4608, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.2623943321477264e-05, + "loss": 3.4532, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2615557373966743e-05, + "loss": 3.4501, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2607171426456223e-05, + "loss": 3.4558, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598785478945707e-05, + "loss": 3.4533, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2590415910238916e-05, + "loss": 3.4668, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.2582029962728396e-05, + "loss": 3.4434, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.2573644015217876e-05, + "loss": 3.452, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.2565258067707352e-05, + "loss": 3.4418, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.2556888499000568e-05, + "loss": 3.445, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2548502551490048e-05, + "loss": 3.4595, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2540116603979528e-05, + "loss": 3.4505, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531730656469005e-05, + "loss": 3.462, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2523361087762217e-05, + "loss": 3.4423, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.2514975140251697e-05, + "loss": 3.4553, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.8568434715270996, + "eval_runtime": 306.3885, + "eval_samples_per_second": 1245.448, + "eval_steps_per_second": 38.921, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2506589192741177e-05, + "loss": 3.4607, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2498203245230657e-05, + "loss": 3.4353, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2489817297720137e-05, + "loss": 3.4575, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2481431350209617e-05, + "loss": 3.4554, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2473061781502826e-05, + "loss": 3.4641, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464675833992306e-05, + "loss": 3.4482, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.245628988648179e-05, + "loss": 3.4393, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244790393897127e-05, + "loss": 3.4425, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243953437026448e-05, + "loss": 3.447, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.243114842275396e-05, + "loss": 3.4533, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.242276247524344e-05, + "loss": 3.4518, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2414376527732918e-05, + "loss": 3.4572, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.240600695902613e-05, + "loss": 3.45, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.239762101151561e-05, + "loss": 3.4478, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.238923506400509e-05, + "loss": 3.4426, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.238084911649457e-05, + "loss": 3.4343, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.237247954778778e-05, + "loss": 3.4475, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.236409360027726e-05, + "loss": 3.4404, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355707652766743e-05, + "loss": 3.446, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2347321705256223e-05, + "loss": 3.4525, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338952136549432e-05, + "loss": 3.4556, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2330566189038912e-05, + "loss": 3.4469, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2322180241528392e-05, + "loss": 3.4476, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313794294017872e-05, + "loss": 3.4495, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2305424725311084e-05, + "loss": 3.447, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2297038777800564e-05, + "loss": 3.4509, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2288652830290044e-05, + "loss": 3.4399, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2280266882779524e-05, + "loss": 3.4486, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2271897314072733e-05, + "loss": 3.4442, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2263511366562213e-05, + "loss": 3.4415, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2255125419051697e-05, + "loss": 3.4479, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246739471541177e-05, + "loss": 3.4514, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2238369902834386e-05, + "loss": 3.4514, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2229983955323866e-05, + "loss": 3.4503, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2221598007813346e-05, + "loss": 3.4365, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2213212060302826e-05, + "loss": 3.4492, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2204842491596038e-05, + "loss": 3.4468, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2196456544085518e-05, + "loss": 3.4359, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2188070596574998e-05, + "loss": 3.4338, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179684649064478e-05, + "loss": 3.4342, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2171315080357687e-05, + "loss": 3.4416, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2162929132847167e-05, + "loss": 3.4511, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2154543185336647e-05, + "loss": 3.446, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.214615723782613e-05, + "loss": 3.4487, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.213778766911934e-05, + "loss": 3.454, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.212940172160882e-05, + "loss": 3.4388, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.21210157740983e-05, + "loss": 3.4427, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2112629826587776e-05, + "loss": 3.4417, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2104260257880992e-05, + "loss": 3.4181, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2095874310370472e-05, + "loss": 3.4571, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.208748836285995e-05, + "loss": 3.4367, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2079102415349428e-05, + "loss": 3.4512, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.207073284664264e-05, + "loss": 3.4367, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.206234689913212e-05, + "loss": 3.4414, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.20539609516216e-05, + "loss": 3.431, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.204557500411108e-05, + "loss": 3.4391, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2037205435404293e-05, + "loss": 3.4453, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028819487893773e-05, + "loss": 3.4532, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.202043354038325e-05, + "loss": 3.4502, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.201204759287273e-05, + "loss": 3.4342, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003678024165945e-05, + "loss": 3.4294, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1995292076655425e-05, + "loss": 3.4553, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986906129144902e-05, + "loss": 3.4287, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1978520181634382e-05, + "loss": 3.4239, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1970150612927594e-05, + "loss": 3.4451, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961764665417074e-05, + "loss": 3.4489, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1953378717906554e-05, + "loss": 3.4267, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944992770396034e-05, + "loss": 3.433, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936623201689247e-05, + "loss": 3.4293, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1928237254178723e-05, + "loss": 3.4445, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.1919851306668203e-05, + "loss": 3.4405, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.1911465359157683e-05, + "loss": 3.4412, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.19030957904509e-05, + "loss": 3.4415, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894709842940376e-05, + "loss": 3.4409, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1886323895429856e-05, + "loss": 3.4575, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877937947919336e-05, + "loss": 3.4293, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1869568379212545e-05, + "loss": 3.4489, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1861182431702028e-05, + "loss": 3.4404, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1852796484191508e-05, + "loss": 3.4323, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1844410536680988e-05, + "loss": 3.447, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1836040967974197e-05, + "loss": 3.4484, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827655020463677e-05, + "loss": 3.4469, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1819269072953157e-05, + "loss": 3.4488, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1810883125442637e-05, + "loss": 3.4291, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.180251355673585e-05, + "loss": 3.4337, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179412760922533e-05, + "loss": 3.4348, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.178574166171481e-05, + "loss": 3.4429, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.177735571420429e-05, + "loss": 3.4406, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.17689861454975e-05, + "loss": 3.4472, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.176060019798698e-05, + "loss": 3.4312, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.175221425047646e-05, + "loss": 3.4515, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.174382830296594e-05, + "loss": 3.4366, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173545873425915e-05, + "loss": 3.44, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.172707278674863e-05, + "loss": 3.4451, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.171868683923811e-05, + "loss": 3.4482, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.171030089172759e-05, + "loss": 3.4519, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701931323020803e-05, + "loss": 3.4335, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693545375510283e-05, + "loss": 3.4459, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1685159427999763e-05, + "loss": 3.4437, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1676773480489243e-05, + "loss": 3.4441, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1668403911782452e-05, + "loss": 3.4459, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1660017964271932e-05, + "loss": 3.4393, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651632016761415e-05, + "loss": 3.4384, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1643246069250895e-05, + "loss": 3.4469, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634876500544104e-05, + "loss": 3.4243, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1626490553033584e-05, + "loss": 3.4369, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1618104605523064e-05, + "loss": 3.438, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1609718658012544e-05, + "loss": 3.4422, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1601349089305757e-05, + "loss": 3.43, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592963141795237e-05, + "loss": 3.4352, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584577194284717e-05, + "loss": 3.4377, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1576191246774197e-05, + "loss": 3.45, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1567821678067406e-05, + "loss": 3.4431, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1559435730556886e-05, + "loss": 3.4371, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.155104978304637e-05, + "loss": 3.4477, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1542680214339578e-05, + "loss": 3.4537, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1534294266829058e-05, + "loss": 3.4453, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525908319318538e-05, + "loss": 3.4296, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517522371808018e-05, + "loss": 3.444, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.150915280310123e-05, + "loss": 3.4434, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.150076685559071e-05, + "loss": 3.4255, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.149238090808019e-05, + "loss": 3.4312, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.148399496056967e-05, + "loss": 3.4386, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1475609013059147e-05, + "loss": 3.4322, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.146723944435236e-05, + "loss": 3.4432, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.145885349684184e-05, + "loss": 3.4499, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1450467549331323e-05, + "loss": 3.4337, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.1442097980624532e-05, + "loss": 3.4324, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1433712033114012e-05, + "loss": 3.4402, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.142532608560349e-05, + "loss": 3.4489, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.141694013809297e-05, + "loss": 3.4461, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.140855419058245e-05, + "loss": 3.4479, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1400184621875664e-05, + "loss": 3.4304, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1391798674365144e-05, + "loss": 3.4458, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.138341272685462e-05, + "loss": 3.4489, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1375043158147833e-05, + "loss": 3.4413, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1366657210637313e-05, + "loss": 3.4441, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1358271263126793e-05, + "loss": 3.4418, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349885315616273e-05, + "loss": 3.4403, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1341515746909485e-05, + "loss": 3.4559, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1333129799398965e-05, + "loss": 3.4352, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1324743851888445e-05, + "loss": 3.4401, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1316357904377922e-05, + "loss": 3.4322, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307971956867405e-05, + "loss": 3.4355, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299602388160618e-05, + "loss": 3.442, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1291216440650094e-05, + "loss": 3.4424, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282830493139574e-05, + "loss": 3.4473, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1274444545629054e-05, + "loss": 3.4335, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1266074976922267e-05, + "loss": 3.4457, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.858046531677246, + "eval_runtime": 310.1115, + "eval_samples_per_second": 1230.496, + "eval_steps_per_second": 38.454, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.1257689029411747e-05, + "loss": 3.4345, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1249303081901227e-05, + "loss": 3.4271, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1240917134390707e-05, + "loss": 3.4442, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.123254756568392e-05, + "loss": 3.4415, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.1224161618173396e-05, + "loss": 3.4506, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.1215775670662876e-05, + "loss": 3.4391, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.120740610195609e-05, + "loss": 3.4325, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.1199020154445568e-05, + "loss": 3.4317, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.1190634206935048e-05, + "loss": 3.4364, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.1182248259424528e-05, + "loss": 3.4387, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.117387869071774e-05, + "loss": 3.4424, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.1165492743207217e-05, + "loss": 3.4459, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.11571067956967e-05, + "loss": 3.438, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.114872084818618e-05, + "loss": 3.4351, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.114035127947939e-05, + "loss": 3.4328, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.113196533196887e-05, + "loss": 3.4237, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.112357938445835e-05, + "loss": 3.4348, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.111519343694783e-05, + "loss": 3.4354, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.1106823868241042e-05, + "loss": 3.4331, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.109843792073052e-05, + "loss": 3.4352, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.109005197322e-05, + "loss": 3.4497, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.108166602570948e-05, + "loss": 3.4348, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.107329645700269e-05, + "loss": 3.437, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.106491050949217e-05, + "loss": 3.4373, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1056524561981654e-05, + "loss": 3.4372, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1048138614471134e-05, + "loss": 3.4409, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1039769045764343e-05, + "loss": 3.4288, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.1031383098253823e-05, + "loss": 3.4383, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.1022997150743303e-05, + "loss": 3.4287, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.1014611203232783e-05, + "loss": 3.4268, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1006241634525995e-05, + "loss": 3.4346, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0997855687015475e-05, + "loss": 3.4418, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0989469739504955e-05, + "loss": 3.4433, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.0981083791994435e-05, + "loss": 3.4395, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.0972714223287644e-05, + "loss": 3.4278, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0964328275777124e-05, + "loss": 3.4327, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0955942328266608e-05, + "loss": 3.4363, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0947556380756088e-05, + "loss": 3.4276, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0939186812049297e-05, + "loss": 3.4225, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0930800864538777e-05, + "loss": 3.4214, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.0922414917028257e-05, + "loss": 3.4341, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0914028969517737e-05, + "loss": 3.437, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.090565940081095e-05, + "loss": 3.435, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.089727345330043e-05, + "loss": 3.4382, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.088888750578991e-05, + "loss": 3.4391, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.088050155827939e-05, + "loss": 3.4308, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.0872131989572598e-05, + "loss": 3.4327, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.0863746042062078e-05, + "loss": 3.4312, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.085536009455156e-05, + "loss": 3.4088, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.084697414704104e-05, + "loss": 3.4445, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.083860457833425e-05, + "loss": 3.4243, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.083021863082373e-05, + "loss": 3.4401, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.082183268331321e-05, + "loss": 3.4307, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.081344673580269e-05, + "loss": 3.4257, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.0805077167095903e-05, + "loss": 3.419, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.0796691219585383e-05, + "loss": 3.4247, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.0788305272074863e-05, + "loss": 3.4366, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.0779919324564343e-05, + "loss": 3.4392, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.077154975585755e-05, + "loss": 3.4393, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.076316380834703e-05, + "loss": 3.4254, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.0754777860836515e-05, + "loss": 3.417, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.074639191332599e-05, + "loss": 3.4447, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.0738022344619204e-05, + "loss": 3.4194, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.0729636397108684e-05, + "loss": 3.4093, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.0721250449598164e-05, + "loss": 3.4342, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.071286450208764e-05, + "loss": 3.4359, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0704494933380856e-05, + "loss": 3.4173, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0696108985870336e-05, + "loss": 3.4243, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0687723038359816e-05, + "loss": 3.4153, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.0679337090849293e-05, + "loss": 3.4318, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.0670967522142505e-05, + "loss": 3.4312, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0662581574631985e-05, + "loss": 3.4268, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0654195627121465e-05, + "loss": 3.4308, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0645809679610945e-05, + "loss": 3.4299, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0637440110904158e-05, + "loss": 3.444, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.0629054163393638e-05, + "loss": 3.4195, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.0620668215883114e-05, + "loss": 3.4394, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.0612282268372594e-05, + "loss": 3.4239, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.060391269966581e-05, + "loss": 3.4238, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.059552675215529e-05, + "loss": 3.4367, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0587140804644767e-05, + "loss": 3.4414, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0578754857134247e-05, + "loss": 3.4307, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.057038528842746e-05, + "loss": 3.44, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.056199934091694e-05, + "loss": 3.4163, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.055361339340642e-05, + "loss": 3.421, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.05452274458959e-05, + "loss": 3.424, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.053685787718911e-05, + "loss": 3.4316, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0528471929678588e-05, + "loss": 3.4286, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0520085982168068e-05, + "loss": 3.4364, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.0511700034657548e-05, + "loss": 3.4215, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.050333046595076e-05, + "loss": 3.4414, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.049494451844024e-05, + "loss": 3.4294, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.048655857092972e-05, + "loss": 3.4281, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.04781726234192e-05, + "loss": 3.433, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.046980305471241e-05, + "loss": 3.4377, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0461417107201893e-05, + "loss": 3.4384, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0453031159691373e-05, + "loss": 3.4254, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.0444645212180853e-05, + "loss": 3.4298, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.043627564347406e-05, + "loss": 3.4325, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.042788969596354e-05, + "loss": 3.4366, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.041950374845302e-05, + "loss": 3.4334, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.04111178009425e-05, + "loss": 3.4268, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.0402748232235714e-05, + "loss": 3.427, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.0394362284725194e-05, + "loss": 3.4349, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.0385976337214674e-05, + "loss": 3.4124, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.0377590389704154e-05, + "loss": 3.4288, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.0369220820997363e-05, + "loss": 3.4265, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.0360834873486846e-05, + "loss": 3.4318, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0352448925976326e-05, + "loss": 3.4182, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.0344062978465806e-05, + "loss": 3.4246, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0335693409759015e-05, + "loss": 3.4324, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.0327307462248495e-05, + "loss": 3.4361, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.0318921514737975e-05, + "loss": 3.4322, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.0310535567227455e-05, + "loss": 3.4266, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0302165998520668e-05, + "loss": 3.4368, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0293780051010148e-05, + "loss": 3.4448, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.0285394103499628e-05, + "loss": 3.4318, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.0277008155989108e-05, + "loss": 3.4176, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.0268638587282317e-05, + "loss": 3.4335, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.02602526397718e-05, + "loss": 3.4347, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.025186669226128e-05, + "loss": 3.4129, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.024348074475076e-05, + "loss": 3.4217, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.023511117604397e-05, + "loss": 3.4265, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.022672522853345e-05, + "loss": 3.4241, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.021833928102293e-05, + "loss": 3.4255, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.020995333351241e-05, + "loss": 3.4404, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.020158376480562e-05, + "loss": 3.4251, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.01931978172951e-05, + "loss": 3.4214, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.018481186978458e-05, + "loss": 3.4262, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.017642592227406e-05, + "loss": 3.4414, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.016805635356727e-05, + "loss": 3.431, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.0159670406056754e-05, + "loss": 3.4379, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.0151284458546234e-05, + "loss": 3.4187, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.0142898511035714e-05, + "loss": 3.4341, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.0134528942328923e-05, + "loss": 3.436, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0126142994818403e-05, + "loss": 3.4324, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0117757047307883e-05, + "loss": 3.4301, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0109371099797363e-05, + "loss": 3.431, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0101001531090575e-05, + "loss": 3.4317, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0092615583580055e-05, + "loss": 3.4459, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0084229636069535e-05, + "loss": 3.4233, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.007584368855901e-05, + "loss": 3.4293, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0067474119852224e-05, + "loss": 3.4246, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.0059088172341707e-05, + "loss": 3.4247, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0050702224831187e-05, + "loss": 3.4255, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0042316277320664e-05, + "loss": 3.4318, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.0033946708613876e-05, + "loss": 3.4395, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.0025560761103356e-05, + "loss": 3.4203, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.0017174813592833e-05, + "loss": 3.4323, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.8589096069335938, + "eval_runtime": 307.9145, + "eval_samples_per_second": 1239.276, + "eval_steps_per_second": 38.728, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0008788866082316e-05, + "loss": 3.4319, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 2.0000402918571796e-05, + "loss": 3.4157, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.9992016971061276e-05, + "loss": 3.4342, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.9983631023550756e-05, + "loss": 3.4315, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.9975261454843965e-05, + "loss": 3.4404, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.9966875507333445e-05, + "loss": 3.4263, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.9958489559822925e-05, + "loss": 3.4258, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.995010361231241e-05, + "loss": 3.4186, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9941734043605617e-05, + "loss": 3.4239, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9933348096095097e-05, + "loss": 3.4318, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9924962148584577e-05, + "loss": 3.428, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9916576201074057e-05, + "loss": 3.4343, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.990820663236727e-05, + "loss": 3.4351, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.989982068485675e-05, + "loss": 3.4181, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.989143473734623e-05, + "loss": 3.4176, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.988304878983571e-05, + "loss": 3.4165, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.987467922112892e-05, + "loss": 3.4223, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.98662932736184e-05, + "loss": 3.4242, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.985790732610788e-05, + "loss": 3.4218, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.9849521378597362e-05, + "loss": 3.4271, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.984115180989057e-05, + "loss": 3.4376, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.983276586238005e-05, + "loss": 3.4264, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.982437991486953e-05, + "loss": 3.4249, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.981599396735901e-05, + "loss": 3.4244, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9807624398652224e-05, + "loss": 3.4258, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9799238451141703e-05, + "loss": 3.4311, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.9790852503631183e-05, + "loss": 3.4165, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9782466556120663e-05, + "loss": 3.4307, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9774096987413872e-05, + "loss": 3.4166, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9765711039903352e-05, + "loss": 3.417, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9757325092392832e-05, + "loss": 3.4286, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9748939144882312e-05, + "loss": 3.4255, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.9740569576175525e-05, + "loss": 3.4308, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.9732183628665005e-05, + "loss": 3.4315, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.9723797681154485e-05, + "loss": 3.415, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.971541173364396e-05, + "loss": 3.4229, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.9707042164937177e-05, + "loss": 3.4298, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.9698656217426657e-05, + "loss": 3.4135, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9690270269916137e-05, + "loss": 3.4155, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.9681884322405614e-05, + "loss": 3.4135, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.9673514753698826e-05, + "loss": 3.4183, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.9665128806188306e-05, + "loss": 3.4243, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.9656742858677786e-05, + "loss": 3.4261, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9648356911167266e-05, + "loss": 3.4308, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.963998734246048e-05, + "loss": 3.423, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.963160139494996e-05, + "loss": 3.4235, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.9623215447439435e-05, + "loss": 3.42, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.9614829499928915e-05, + "loss": 3.4208, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.960645993122213e-05, + "loss": 3.398, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.959807398371161e-05, + "loss": 3.4319, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.9589688036201087e-05, + "loss": 3.4162, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9581302088690567e-05, + "loss": 3.4267, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.957293251998378e-05, + "loss": 3.4198, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9564546572473256e-05, + "loss": 3.4202, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.955616062496274e-05, + "loss": 3.4059, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.954777467745222e-05, + "loss": 3.4159, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.9539405108745432e-05, + "loss": 3.4298, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.953101916123491e-05, + "loss": 3.4235, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.952263321372439e-05, + "loss": 3.4286, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.951424726621387e-05, + "loss": 3.4206, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.9505877697507085e-05, + "loss": 3.4037, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.949749174999656e-05, + "loss": 3.4321, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.948910580248604e-05, + "loss": 3.4104, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.948071985497552e-05, + "loss": 3.4016, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.947235028626873e-05, + "loss": 3.4256, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.946396433875821e-05, + "loss": 3.4211, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9455578391247693e-05, + "loss": 3.4076, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9447192443737173e-05, + "loss": 3.4131, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9438822875030382e-05, + "loss": 3.4106, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.9430436927519862e-05, + "loss": 3.4187, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9422050980009342e-05, + "loss": 3.4214, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9413665032498822e-05, + "loss": 3.4173, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9405295463792035e-05, + "loss": 3.4239, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9396909516281515e-05, + "loss": 3.4186, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9388523568770995e-05, + "loss": 3.4357, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9380137621260475e-05, + "loss": 3.4089, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9371768052553684e-05, + "loss": 3.4266, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9363382105043164e-05, + "loss": 3.4144, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9354996157532647e-05, + "loss": 3.4147, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9346610210022127e-05, + "loss": 3.4261, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9338240641315336e-05, + "loss": 3.4275, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.9329854693804816e-05, + "loss": 3.4224, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.9321468746294296e-05, + "loss": 3.4304, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.9313082798783776e-05, + "loss": 3.4057, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.930471323007699e-05, + "loss": 3.4139, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.929632728256647e-05, + "loss": 3.414, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.928794133505595e-05, + "loss": 3.4227, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9279571766349157e-05, + "loss": 3.4152, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9271185818838637e-05, + "loss": 3.4234, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.9262799871328117e-05, + "loss": 3.4154, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.92544139238176e-05, + "loss": 3.4252, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.924602797630708e-05, + "loss": 3.4204, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.923765840760029e-05, + "loss": 3.4166, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.922927246008977e-05, + "loss": 3.4244, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.922088651257925e-05, + "loss": 3.4252, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.9212516943872462e-05, + "loss": 3.431, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.9204130996361942e-05, + "loss": 3.4147, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.9195745048851422e-05, + "loss": 3.4156, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9187359101340902e-05, + "loss": 3.4245, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.917898953263411e-05, + "loss": 3.4261, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.917060358512359e-05, + "loss": 3.4209, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.916221763761307e-05, + "loss": 3.421, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9153831690102554e-05, + "loss": 3.4178, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9145462121395763e-05, + "loss": 3.4219, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.9137076173885243e-05, + "loss": 3.4049, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.9128690226374723e-05, + "loss": 3.4223, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9120304278864203e-05, + "loss": 3.4054, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.9111934710157416e-05, + "loss": 3.4218, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9103548762646896e-05, + "loss": 3.4107, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.9095162815136376e-05, + "loss": 3.4198, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.9086776867625856e-05, + "loss": 3.4178, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9078407298919065e-05, + "loss": 3.4275, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9070021351408545e-05, + "loss": 3.4198, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9061635403898025e-05, + "loss": 3.4194, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9053249456387508e-05, + "loss": 3.4265, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9044879887680717e-05, + "loss": 3.4301, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9036493940170197e-05, + "loss": 3.4223, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9028107992659677e-05, + "loss": 3.4132, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.9019722045149154e-05, + "loss": 3.4191, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.901135247644237e-05, + "loss": 3.4233, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.900296652893185e-05, + "loss": 3.4105, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.899458058142133e-05, + "loss": 3.4063, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8986194633910806e-05, + "loss": 3.4149, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.897782506520402e-05, + "loss": 3.4137, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.89694391176935e-05, + "loss": 3.4131, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.896105317018298e-05, + "loss": 3.4284, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.895266722267246e-05, + "loss": 3.4167, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.894429765396567e-05, + "loss": 3.4113, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.893591170645515e-05, + "loss": 3.4144, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8927525758944627e-05, + "loss": 3.4295, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8919139811434107e-05, + "loss": 3.4223, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.891077024272732e-05, + "loss": 3.4236, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.8902384295216803e-05, + "loss": 3.4095, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.889399834770628e-05, + "loss": 3.4272, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.888561240019576e-05, + "loss": 3.4251, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.8877242831488972e-05, + "loss": 3.4229, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8868856883978452e-05, + "loss": 3.4196, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8860470936467932e-05, + "loss": 3.4162, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8852084988957412e-05, + "loss": 3.4211, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.8843715420250624e-05, + "loss": 3.4357, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.88353294727401e-05, + "loss": 3.4121, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.882694352522958e-05, + "loss": 3.4196, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.881855757771906e-05, + "loss": 3.4163, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8810188009012273e-05, + "loss": 3.4145, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8801802061501753e-05, + "loss": 3.4149, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8793416113991233e-05, + "loss": 3.4206, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8785030166480713e-05, + "loss": 3.4261, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8776660597773926e-05, + "loss": 3.4154, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8768274650263402e-05, + "loss": 3.4196, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.8605642318725586, + "eval_runtime": 304.9604, + "eval_samples_per_second": 1251.28, + "eval_steps_per_second": 39.103, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8759888702752886e-05, + "loss": 3.4209, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8751502755242366e-05, + "loss": 3.4069, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8743116807731846e-05, + "loss": 3.4244, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734730860221326e-05, + "loss": 3.4186, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8726361291514535e-05, + "loss": 3.4331, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8717975344004015e-05, + "loss": 3.4144, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8709589396493495e-05, + "loss": 3.4147, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8701203448982978e-05, + "loss": 3.4073, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8692833880276187e-05, + "loss": 3.4155, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8684447932765667e-05, + "loss": 3.4213, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8676061985255147e-05, + "loss": 3.4165, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667676037744627e-05, + "loss": 3.4237, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.865930646903784e-05, + "loss": 3.4292, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.865092052152732e-05, + "loss": 3.4059, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.86425345740168e-05, + "loss": 3.4089, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.863414862650628e-05, + "loss": 3.4062, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.862577905779949e-05, + "loss": 3.4163, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8617393110288968e-05, + "loss": 3.4064, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8609007162778448e-05, + "loss": 3.4136, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8600621215267928e-05, + "loss": 3.4144, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.859225164656114e-05, + "loss": 3.4252, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.858386569905062e-05, + "loss": 3.4184, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.85754797515401e-05, + "loss": 3.4142, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8567093804029577e-05, + "loss": 3.4134, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8558724235322793e-05, + "loss": 3.4151, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8550338287812273e-05, + "loss": 3.4212, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8541952340301753e-05, + "loss": 3.4032, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.853356639279123e-05, + "loss": 3.4219, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8525196824084442e-05, + "loss": 3.41, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8516810876573922e-05, + "loss": 3.4023, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8508424929063402e-05, + "loss": 3.4189, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.8500038981552882e-05, + "loss": 3.4164, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8491669412846094e-05, + "loss": 3.4159, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8483283465335574e-05, + "loss": 3.4229, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.847489751782505e-05, + "loss": 3.4064, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.846651157031453e-05, + "loss": 3.4119, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8458142001607743e-05, + "loss": 3.4177, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8449756054097227e-05, + "loss": 3.3999, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8441370106586703e-05, + "loss": 3.4091, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8432984159076183e-05, + "loss": 3.4018, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8424614590369396e-05, + "loss": 3.4072, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8416228642858876e-05, + "loss": 3.4159, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8407842695348356e-05, + "loss": 3.4122, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8399456747837836e-05, + "loss": 3.4224, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8391087179131048e-05, + "loss": 3.4109, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8382701231620525e-05, + "loss": 3.4143, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8374315284110005e-05, + "loss": 3.4106, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8365929336599484e-05, + "loss": 3.4105, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8357559767892697e-05, + "loss": 3.391, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.8349173820382177e-05, + "loss": 3.4186, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8340787872871657e-05, + "loss": 3.4041, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8332401925361137e-05, + "loss": 3.4182, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.832403235665435e-05, + "loss": 3.4062, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.8315646409143826e-05, + "loss": 3.4103, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.830726046163331e-05, + "loss": 3.3966, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.829887451412279e-05, + "loss": 3.4056, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.8290504945415998e-05, + "loss": 3.4191, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8282118997905478e-05, + "loss": 3.4081, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.8273733050394958e-05, + "loss": 3.4231, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.826536348168817e-05, + "loss": 3.4117, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.825697753417765e-05, + "loss": 3.3886, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.824859158666713e-05, + "loss": 3.4216, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.824020563915661e-05, + "loss": 3.4025, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8231836070449823e-05, + "loss": 3.392, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.82234501229393e-05, + "loss": 3.4118, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.821506417542878e-05, + "loss": 3.4135, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8206678227918263e-05, + "loss": 3.3977, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8198308659211472e-05, + "loss": 3.4011, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8189922711700952e-05, + "loss": 3.3977, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8181536764190432e-05, + "loss": 3.4132, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8173150816679912e-05, + "loss": 3.4094, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8164781247973124e-05, + "loss": 3.4048, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8156395300462604e-05, + "loss": 3.4156, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8148009352952084e-05, + "loss": 3.4073, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8139623405441564e-05, + "loss": 3.4224, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8131253836734773e-05, + "loss": 3.3993, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8122867889224253e-05, + "loss": 3.4138, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8114481941713733e-05, + "loss": 3.4041, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8106095994203217e-05, + "loss": 3.4063, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097726425496426e-05, + "loss": 3.4122, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8089340477985906e-05, + "loss": 3.415, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8080954530475386e-05, + "loss": 3.4163, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8072568582964866e-05, + "loss": 3.4185, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8064199014258078e-05, + "loss": 3.4019, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8055813066747558e-05, + "loss": 3.4007, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8047427119237038e-05, + "loss": 3.4008, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8039041171726518e-05, + "loss": 3.4108, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8030671603019727e-05, + "loss": 3.403, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8022285655509207e-05, + "loss": 3.4088, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8013899707998687e-05, + "loss": 3.4124, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8005513760488167e-05, + "loss": 3.4116, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.799714419178138e-05, + "loss": 3.4083, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.798875824427086e-05, + "loss": 3.4071, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.798037229676034e-05, + "loss": 3.4126, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.797198634924982e-05, + "loss": 3.4139, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.796361678054303e-05, + "loss": 3.4177, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.795523083303251e-05, + "loss": 3.4015, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.794684488552199e-05, + "loss": 3.4106, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.793845893801147e-05, + "loss": 3.4122, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.793008936930468e-05, + "loss": 3.4176, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.792170342179416e-05, + "loss": 3.4109, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.791331747428364e-05, + "loss": 3.4132, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.790493152677312e-05, + "loss": 3.4078, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7896561958066333e-05, + "loss": 3.4102, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7888176010555813e-05, + "loss": 3.3959, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7879790063045293e-05, + "loss": 3.4051, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7871404115534773e-05, + "loss": 3.3981, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7863034546827982e-05, + "loss": 3.4139, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7854648599317465e-05, + "loss": 3.4024, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7846262651806945e-05, + "loss": 3.4054, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7837876704296422e-05, + "loss": 3.41, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.7829507135589634e-05, + "loss": 3.4135, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.7821121188079114e-05, + "loss": 3.4123, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.7812735240568594e-05, + "loss": 3.4061, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7804349293058074e-05, + "loss": 3.4155, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7795979724351287e-05, + "loss": 3.4171, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7787593776840767e-05, + "loss": 3.4085, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7779207829330247e-05, + "loss": 3.4065, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7770821881819723e-05, + "loss": 3.4065, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7762452313112936e-05, + "loss": 3.4098, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.775406636560242e-05, + "loss": 3.406, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7745680418091896e-05, + "loss": 3.3929, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7737294470581376e-05, + "loss": 3.4065, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7728924901874588e-05, + "loss": 3.4028, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7720538954364068e-05, + "loss": 3.4042, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7712153006853548e-05, + "loss": 3.4184, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7703767059343028e-05, + "loss": 3.4063, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.769539749063624e-05, + "loss": 3.3992, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.768701154312572e-05, + "loss": 3.4051, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7678625595615197e-05, + "loss": 3.4184, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.767025602690841e-05, + "loss": 3.4116, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.766187007939789e-05, + "loss": 3.4159, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.765348413188737e-05, + "loss": 3.3959, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.764509818437685e-05, + "loss": 3.4211, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7636728615670062e-05, + "loss": 3.4115, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.762834266815954e-05, + "loss": 3.4139, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7619956720649018e-05, + "loss": 3.4105, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.76115707731385e-05, + "loss": 3.4045, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7603217583235443e-05, + "loss": 3.4112, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7594831635724923e-05, + "loss": 3.4316, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7586445688214403e-05, + "loss": 3.3974, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.7578059740703883e-05, + "loss": 3.4088, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7569673793193363e-05, + "loss": 3.4081, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7561287845682843e-05, + "loss": 3.3971, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7552901898172323e-05, + "loss": 3.4042, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7544515950661803e-05, + "loss": 3.4119, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7536146381955015e-05, + "loss": 3.4163, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7527760434444492e-05, + "loss": 3.407, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7519374486933972e-05, + "loss": 3.4065, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.8633737564086914, + "eval_runtime": 306.4565, + "eval_samples_per_second": 1245.172, + "eval_steps_per_second": 38.913, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.7510988539423452e-05, + "loss": 3.4013, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.7502618970716668e-05, + "loss": 3.3973, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7494233023206144e-05, + "loss": 3.4126, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7485847075695624e-05, + "loss": 3.4126, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7477461128185104e-05, + "loss": 3.4209, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.7469091559478313e-05, + "loss": 3.4063, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.7460705611967797e-05, + "loss": 3.4037, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.7452319664457277e-05, + "loss": 3.3994, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7443933716946757e-05, + "loss": 3.4012, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7435564148239966e-05, + "loss": 3.4116, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7427178200729446e-05, + "loss": 3.4081, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.7418792253218926e-05, + "loss": 3.4164, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.7410406305708406e-05, + "loss": 3.414, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.7402036737001618e-05, + "loss": 3.3965, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.7393650789491098e-05, + "loss": 3.396, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7385264841980578e-05, + "loss": 3.3961, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.7376878894470058e-05, + "loss": 3.4073, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.7368509325763267e-05, + "loss": 3.4004, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.736012337825275e-05, + "loss": 3.3998, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.735173743074223e-05, + "loss": 3.4026, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.734335148323171e-05, + "loss": 3.414, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.733498191452492e-05, + "loss": 3.4047, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.73265959670144e-05, + "loss": 3.4088, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.731821001950388e-05, + "loss": 3.4006, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.730982407199336e-05, + "loss": 3.4109, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.730145450328657e-05, + "loss": 3.4087, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.729306855577605e-05, + "loss": 3.3929, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.728468260826553e-05, + "loss": 3.4138, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.727629666075501e-05, + "loss": 3.3946, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.726792709204822e-05, + "loss": 3.3928, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7259541144537704e-05, + "loss": 3.414, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7251155197027184e-05, + "loss": 3.4025, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7242769249516664e-05, + "loss": 3.4069, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.7234399680809873e-05, + "loss": 3.413, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.7226013733299353e-05, + "loss": 3.397, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.7217627785788833e-05, + "loss": 3.4043, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.7209241838278313e-05, + "loss": 3.4046, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.7200888648375258e-05, + "loss": 3.3885, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.7192502700864734e-05, + "loss": 3.3968, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7184116753354214e-05, + "loss": 3.3924, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.7175730805843694e-05, + "loss": 3.3971, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.7167344858333174e-05, + "loss": 3.408, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.7158958910822658e-05, + "loss": 3.4031, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.7150572963312138e-05, + "loss": 3.4103, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7142187015801618e-05, + "loss": 3.4021, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7133817447094827e-05, + "loss": 3.4055, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7125431499584307e-05, + "loss": 3.4005, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.7117045552073787e-05, + "loss": 3.3991, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.7108659604563267e-05, + "loss": 3.3794, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.710029003585648e-05, + "loss": 3.4051, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.709190408834596e-05, + "loss": 3.3974, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.708351814083544e-05, + "loss": 3.4055, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.7075132193324915e-05, + "loss": 3.3993, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.7066762624618128e-05, + "loss": 3.3932, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.705837667710761e-05, + "loss": 3.3902, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.704999072959709e-05, + "loss": 3.3946, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.7041604782086568e-05, + "loss": 3.4086, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.703323521337978e-05, + "loss": 3.3981, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.702484926586926e-05, + "loss": 3.4153, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7016463318358737e-05, + "loss": 3.4026, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.700807737084822e-05, + "loss": 3.3748, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6999707802141433e-05, + "loss": 3.4125, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.6991321854630913e-05, + "loss": 3.3923, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.698293590712039e-05, + "loss": 3.3854, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.697454995960987e-05, + "loss": 3.3965, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.696618039090308e-05, + "loss": 3.4035, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6957794443392565e-05, + "loss": 3.3864, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.694940849588204e-05, + "loss": 3.3924, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.694102254837152e-05, + "loss": 3.3881, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.6932652979664734e-05, + "loss": 3.3973, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.692426703215421e-05, + "loss": 3.4025, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.691588108464369e-05, + "loss": 3.394, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.6907495137133174e-05, + "loss": 3.4049, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.6899125568426386e-05, + "loss": 3.3941, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6890739620915863e-05, + "loss": 3.4132, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.6882353673405343e-05, + "loss": 3.3898, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.6873967725894823e-05, + "loss": 3.4087, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.6865598157188035e-05, + "loss": 3.3926, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.6857212209677515e-05, + "loss": 3.3927, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.6848826262166995e-05, + "loss": 3.4041, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6840440314656475e-05, + "loss": 3.4002, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6832070745949684e-05, + "loss": 3.404, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.6823684798439164e-05, + "loss": 3.4124, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.6815298850928644e-05, + "loss": 3.3952, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.6806912903418128e-05, + "loss": 3.3872, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.6798543334711337e-05, + "loss": 3.391, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.6790157387200817e-05, + "loss": 3.4032, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.6781771439690297e-05, + "loss": 3.3919, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.677340187098351e-05, + "loss": 3.4029, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.676501592347299e-05, + "loss": 3.4029, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.675662997596247e-05, + "loss": 3.3987, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.674824402845195e-05, + "loss": 3.3951, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.6739874459745158e-05, + "loss": 3.396, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.6731488512234638e-05, + "loss": 3.4055, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.6723102564724118e-05, + "loss": 3.402, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6714716617213598e-05, + "loss": 3.4077, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.670634704850681e-05, + "loss": 3.3936, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.669796110099629e-05, + "loss": 3.3967, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.668957515348577e-05, + "loss": 3.4044, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.668118920597525e-05, + "loss": 3.4068, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.667281963726846e-05, + "loss": 3.3989, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.6664433689757943e-05, + "loss": 3.4005, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.6656047742247423e-05, + "loss": 3.3997, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.6647661794736903e-05, + "loss": 3.394, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.663929222603011e-05, + "loss": 3.3905, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.663090627851959e-05, + "loss": 3.3926, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.662252033100907e-05, + "loss": 3.3875, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.661413438349855e-05, + "loss": 3.407, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6605764814791764e-05, + "loss": 3.3916, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.6597378867281244e-05, + "loss": 3.3947, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.6588992919770724e-05, + "loss": 3.3961, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6580606972260204e-05, + "loss": 3.4059, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.6572237403553413e-05, + "loss": 3.3997, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.6563851456042896e-05, + "loss": 3.398, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.6555465508532376e-05, + "loss": 3.4049, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.6547079561021856e-05, + "loss": 3.4091, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.6538709992315065e-05, + "loss": 3.3974, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.6530324044804545e-05, + "loss": 3.3973, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.6521938097294025e-05, + "loss": 3.3942, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.6513552149783505e-05, + "loss": 3.4016, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.6505182581076718e-05, + "loss": 3.3965, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6496796633566198e-05, + "loss": 3.3782, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6488410686055678e-05, + "loss": 3.3998, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6480024738545158e-05, + "loss": 3.3948, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6471655169838367e-05, + "loss": 3.3937, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.646326922232785e-05, + "loss": 3.4074, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.645488327481733e-05, + "loss": 3.3968, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.644649732730681e-05, + "loss": 3.3934, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.643812775860002e-05, + "loss": 3.3907, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.64297418110895e-05, + "loss": 3.4127, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.642135586357898e-05, + "loss": 3.4013, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.641296991606846e-05, + "loss": 3.4068, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.640458396855794e-05, + "loss": 3.3876, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.639619802104742e-05, + "loss": 3.4063, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.63878120735369e-05, + "loss": 3.4022, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.637942612602638e-05, + "loss": 3.4042, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6371056557319588e-05, + "loss": 3.3996, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6362670609809068e-05, + "loss": 3.391, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.635428466229855e-05, + "loss": 3.4016, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.634589871478803e-05, + "loss": 3.4192, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.633752914608124e-05, + "loss": 3.3907, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.632914319857072e-05, + "loss": 3.3973, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.63207572510602e-05, + "loss": 3.3952, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.631237130354968e-05, + "loss": 3.3937, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.6304001734842892e-05, + "loss": 3.3934, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.6295615787332372e-05, + "loss": 3.4007, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.6287229839821852e-05, + "loss": 3.4035, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.627886027111506e-05, + "loss": 3.404, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.627047432360454e-05, + "loss": 3.3952, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.863755702972412, + "eval_runtime": 313.0657, + "eval_samples_per_second": 1218.885, + "eval_steps_per_second": 38.091, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.626208837609402e-05, + "loss": 3.4007, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.6253702428583505e-05, + "loss": 3.3848, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6245316481072985e-05, + "loss": 3.4035, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6236930533562465e-05, + "loss": 3.4036, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6228560964855674e-05, + "loss": 3.4091, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6220175017345154e-05, + "loss": 3.396, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.6211789069834634e-05, + "loss": 3.3959, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.6203403122324114e-05, + "loss": 3.3884, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6195033553617326e-05, + "loss": 3.3921, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.6186647606106806e-05, + "loss": 3.3921, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.6178261658596286e-05, + "loss": 3.4021, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.6169875711085763e-05, + "loss": 3.4058, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.6161506142378975e-05, + "loss": 3.4079, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.615312019486846e-05, + "loss": 3.3822, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.614473424735794e-05, + "loss": 3.3888, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6136348299847415e-05, + "loss": 3.3799, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.6127978731140627e-05, + "loss": 3.3999, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6119592783630107e-05, + "loss": 3.3898, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6111206836119587e-05, + "loss": 3.3889, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6102820888609067e-05, + "loss": 3.3948, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.609445131990228e-05, + "loss": 3.4074, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.608606537239176e-05, + "loss": 3.3922, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6077679424881236e-05, + "loss": 3.4002, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6069293477370716e-05, + "loss": 3.3921, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.606092390866393e-05, + "loss": 3.4013, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6052537961153412e-05, + "loss": 3.3939, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.604415201364289e-05, + "loss": 3.3856, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.603576606613237e-05, + "loss": 3.4008, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.602739649742558e-05, + "loss": 3.387, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.601901054991506e-05, + "loss": 3.3828, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6010624602404538e-05, + "loss": 3.3998, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.600223865489402e-05, + "loss": 3.3906, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5993869086187233e-05, + "loss": 3.3994, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.598548313867671e-05, + "loss": 3.401, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.597709719116619e-05, + "loss": 3.3869, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.596871124365567e-05, + "loss": 3.3945, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5960341674948882e-05, + "loss": 3.3956, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.5951972106242095e-05, + "loss": 3.3789, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.5943586158731575e-05, + "loss": 3.3903, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5935200211221055e-05, + "loss": 3.3823, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.592681426371053e-05, + "loss": 3.3852, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.591842831620001e-05, + "loss": 3.3946, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.591004236868949e-05, + "loss": 3.3995, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.5901656421178975e-05, + "loss": 3.3956, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5893270473668455e-05, + "loss": 3.3957, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5884900904961664e-05, + "loss": 3.3919, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.5876514957451144e-05, + "loss": 3.3918, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5868129009940624e-05, + "loss": 3.3838, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.5859743062430104e-05, + "loss": 3.376, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5851373493723316e-05, + "loss": 3.3938, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5842987546212796e-05, + "loss": 3.3893, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5834601598702276e-05, + "loss": 3.3933, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5826215651191756e-05, + "loss": 3.3902, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5817846082484965e-05, + "loss": 3.3848, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.5809460134974445e-05, + "loss": 3.3793, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5801074187463928e-05, + "loss": 3.382, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5792688239953408e-05, + "loss": 3.3994, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5784318671246617e-05, + "loss": 3.3836, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.5775932723736097e-05, + "loss": 3.4076, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5767546776225577e-05, + "loss": 3.3919, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5759160828715057e-05, + "loss": 3.368, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.575079126000827e-05, + "loss": 3.3983, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.574240531249775e-05, + "loss": 3.3816, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.573401936498723e-05, + "loss": 3.3757, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.572563341747671e-05, + "loss": 3.3868, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.571726384876992e-05, + "loss": 3.3935, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.57088779012594e-05, + "loss": 3.3744, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5700491953748882e-05, + "loss": 3.3872, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5692106006238362e-05, + "loss": 3.3763, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.568373643753157e-05, + "loss": 3.3873, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.567535049002105e-05, + "loss": 3.3928, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.566696454251053e-05, + "loss": 3.3849, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.565857859500001e-05, + "loss": 3.395, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5650209026293223e-05, + "loss": 3.3847, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5641823078782703e-05, + "loss": 3.4024, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5633437131272183e-05, + "loss": 3.3819, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.562505118376166e-05, + "loss": 3.3952, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.5616681615054872e-05, + "loss": 3.3833, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.5608295667544352e-05, + "loss": 3.3848, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5599909720033836e-05, + "loss": 3.397, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5591523772523312e-05, + "loss": 3.3874, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5583154203816525e-05, + "loss": 3.395, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5574768256306005e-05, + "loss": 3.4009, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5566382308795485e-05, + "loss": 3.3868, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.555799636128496e-05, + "loss": 3.3731, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5549626792578177e-05, + "loss": 3.3826, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5541240845067657e-05, + "loss": 3.3906, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5532854897557134e-05, + "loss": 3.3869, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5524485328850346e-05, + "loss": 3.3873, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5516099381339826e-05, + "loss": 3.3975, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.5507713433829306e-05, + "loss": 3.3893, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.5499327486318786e-05, + "loss": 3.3851, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.5490957917612e-05, + "loss": 3.3853, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.548257197010148e-05, + "loss": 3.3933, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.5474186022590958e-05, + "loss": 3.3944, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5465800075080435e-05, + "loss": 3.4015, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.545743050637365e-05, + "loss": 3.3777, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.544904455886313e-05, + "loss": 3.3922, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.5440658611352607e-05, + "loss": 3.3931, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5432272663842087e-05, + "loss": 3.3905, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.54239030951353e-05, + "loss": 3.3923, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.541551714762478e-05, + "loss": 3.387, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.540713120011426e-05, + "loss": 3.3895, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.539874525260374e-05, + "loss": 3.383, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5390375683896952e-05, + "loss": 3.3896, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5381989736386432e-05, + "loss": 3.3787, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.537360378887591e-05, + "loss": 3.3806, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.536521784136539e-05, + "loss": 3.3942, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5356848272658604e-05, + "loss": 3.3858, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.534846232514808e-05, + "loss": 3.3783, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.534007637763756e-05, + "loss": 3.3843, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.533169043012704e-05, + "loss": 3.3987, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5323320861420253e-05, + "loss": 3.3922, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.531493491390973e-05, + "loss": 3.3873, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5306548966399213e-05, + "loss": 3.3965, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5298163018888693e-05, + "loss": 3.4002, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5289793450181902e-05, + "loss": 3.3875, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5281407502671382e-05, + "loss": 3.3828, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.5273021555160862e-05, + "loss": 3.3852, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.5264635607650342e-05, + "loss": 3.3881, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5256266038943553e-05, + "loss": 3.3936, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5247880091433035e-05, + "loss": 3.3639, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5239494143922515e-05, + "loss": 3.3866, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5231108196411995e-05, + "loss": 3.3828, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5222738627705205e-05, + "loss": 3.3881, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5214352680194685e-05, + "loss": 3.3944, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5205966732684165e-05, + "loss": 3.3872, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5197580785173645e-05, + "loss": 3.3817, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5189211216466856e-05, + "loss": 3.3778, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5180825268956336e-05, + "loss": 3.4018, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5172439321445816e-05, + "loss": 3.3867, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5164053373935298e-05, + "loss": 3.3986, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5155667426424778e-05, + "loss": 3.377, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5147281478914257e-05, + "loss": 3.3939, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5138895531403736e-05, + "loss": 3.3972, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5130509583893216e-05, + "loss": 3.3891, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5122140015186428e-05, + "loss": 3.3915, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5113754067675908e-05, + "loss": 3.3827, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5105368120165386e-05, + "loss": 3.3916, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5096982172654866e-05, + "loss": 3.4044, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5088612603948079e-05, + "loss": 3.3852, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5080226656437557e-05, + "loss": 3.387, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5071840708927037e-05, + "loss": 3.3878, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5063471140220251e-05, + "loss": 3.3812, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5055085192709731e-05, + "loss": 3.3823, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5046699245199208e-05, + "loss": 3.3951, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.503831329768869e-05, + "loss": 3.3866, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5029943728981902e-05, + "loss": 3.3916, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5021557781471382e-05, + "loss": 3.3877, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.865595817565918, + "eval_runtime": 306.0377, + "eval_samples_per_second": 1246.876, + "eval_steps_per_second": 38.966, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.501317183396086e-05, + "loss": 3.3847, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.500478588645034e-05, + "loss": 3.3732, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4996416317743553e-05, + "loss": 3.39, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.498803037023303e-05, + "loss": 3.3936, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.497964442272251e-05, + "loss": 3.3968, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.497125847521199e-05, + "loss": 3.3885, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4962888906505205e-05, + "loss": 3.3876, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4954502958994681e-05, + "loss": 3.3786, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4946117011484161e-05, + "loss": 3.3804, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4937731063973643e-05, + "loss": 3.3853, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4929361495266856e-05, + "loss": 3.3913, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4920975547756332e-05, + "loss": 3.3966, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4912589600245814e-05, + "loss": 3.4025, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4904203652735294e-05, + "loss": 3.3682, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4895834084028505e-05, + "loss": 3.3807, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4887448136517984e-05, + "loss": 3.3705, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4879062189007464e-05, + "loss": 3.3921, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4870676241496944e-05, + "loss": 3.3816, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4862306672790155e-05, + "loss": 3.3796, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4853920725279635e-05, + "loss": 3.3817, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4845534777769115e-05, + "loss": 3.395, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4837148830258597e-05, + "loss": 3.382, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4828779261551806e-05, + "loss": 3.3877, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4820393314041286e-05, + "loss": 3.3818, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4812007366530767e-05, + "loss": 3.3949, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4803621419020247e-05, + "loss": 3.3831, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4795251850313458e-05, + "loss": 3.3745, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4786865902802938e-05, + "loss": 3.3926, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4778479955292418e-05, + "loss": 3.3721, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4770094007781898e-05, + "loss": 3.3748, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4761724439075109e-05, + "loss": 3.3904, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4753338491564589e-05, + "loss": 3.3832, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4744952544054069e-05, + "loss": 3.388, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.473656659654355e-05, + "loss": 3.3924, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.472819702783676e-05, + "loss": 3.3778, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.471981108032624e-05, + "loss": 3.3814, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4711425132815721e-05, + "loss": 3.3852, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4703039185305201e-05, + "loss": 3.3701, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4694669616598412e-05, + "loss": 3.3815, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4686283669087892e-05, + "loss": 3.3691, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4677897721577372e-05, + "loss": 3.3764, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4669511774066852e-05, + "loss": 3.3813, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4661142205360062e-05, + "loss": 3.3894, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4652756257849542e-05, + "loss": 3.3838, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4644370310339022e-05, + "loss": 3.3846, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4635984362828502e-05, + "loss": 3.3852, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4627614794121713e-05, + "loss": 3.3806, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4619228846611193e-05, + "loss": 3.3769, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4610842899100675e-05, + "loss": 3.3627, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4602456951590155e-05, + "loss": 3.3838, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4594087382883364e-05, + "loss": 3.3809, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4585701435372845e-05, + "loss": 3.384, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4577315487862325e-05, + "loss": 3.3811, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4568929540351805e-05, + "loss": 3.3732, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4560559971645016e-05, + "loss": 3.3682, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4552174024134496e-05, + "loss": 3.3714, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4543788076623976e-05, + "loss": 3.3892, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4535402129113454e-05, + "loss": 3.3773, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4527032560406667e-05, + "loss": 3.3957, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4518646612896147e-05, + "loss": 3.378, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4510260665385628e-05, + "loss": 3.3657, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4501874717875105e-05, + "loss": 3.3838, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4493505149168317e-05, + "loss": 3.3732, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4485119201657799e-05, + "loss": 3.3664, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4476733254147279e-05, + "loss": 3.375, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.446836368544049e-05, + "loss": 3.3831, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.445997773792997e-05, + "loss": 3.3656, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.445159179041945e-05, + "loss": 3.3812, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4443205842908928e-05, + "loss": 3.362, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.443483627420214e-05, + "loss": 3.3775, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.442645032669162e-05, + "loss": 3.3826, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.44180643791811e-05, + "loss": 3.376, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4409678431670579e-05, + "loss": 3.3809, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4401308862963791e-05, + "loss": 3.3755, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4392922915453271e-05, + "loss": 3.391, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4384536967942753e-05, + "loss": 3.3744, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.437615102043223e-05, + "loss": 3.3871, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4367781451725444e-05, + "loss": 3.3746, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4359395504214923e-05, + "loss": 3.3725, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.43510095567044e-05, + "loss": 3.3853, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4342623609193882e-05, + "loss": 3.3753, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4334254040487094e-05, + "loss": 3.3871, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4325884471780305e-05, + "loss": 3.3892, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4317498524269785e-05, + "loss": 3.3805, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4309112576759265e-05, + "loss": 3.3638, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4300726629248745e-05, + "loss": 3.3723, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4292340681738225e-05, + "loss": 3.3799, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4283971113031436e-05, + "loss": 3.379, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4275585165520916e-05, + "loss": 3.3754, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4267199218010397e-05, + "loss": 3.3846, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4258813270499874e-05, + "loss": 3.3811, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4250427322989354e-05, + "loss": 3.3759, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4242041375478835e-05, + "loss": 3.3774, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4233655427968315e-05, + "loss": 3.3842, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4225269480457795e-05, + "loss": 3.3836, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4216899911751006e-05, + "loss": 3.3898, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4208513964240486e-05, + "loss": 3.3672, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4200128016729966e-05, + "loss": 3.3808, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4191758448023177e-05, + "loss": 3.3838, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4183372500512657e-05, + "loss": 3.3821, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4174986553002137e-05, + "loss": 3.3858, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4166600605491617e-05, + "loss": 3.3781, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4158231036784827e-05, + "loss": 3.3762, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4149845089274307e-05, + "loss": 3.3742, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4141459141763787e-05, + "loss": 3.3784, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4133073194253269e-05, + "loss": 3.3695, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4124703625546478e-05, + "loss": 3.3699, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.411631767803596e-05, + "loss": 3.3824, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.410793173052544e-05, + "loss": 3.3763, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.409954578301492e-05, + "loss": 3.3702, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.409117621430813e-05, + "loss": 3.3706, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.408279026679761e-05, + "loss": 3.3872, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.407440431928709e-05, + "loss": 3.3832, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.406601837177657e-05, + "loss": 3.379, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4057648803069781e-05, + "loss": 3.3866, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4049262855559261e-05, + "loss": 3.3901, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4040876908048741e-05, + "loss": 3.3779, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4032490960538223e-05, + "loss": 3.3733, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4024121391831432e-05, + "loss": 3.3766, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4015735444320913e-05, + "loss": 3.3812, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4007349496810393e-05, + "loss": 3.3822, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.3998963549299873e-05, + "loss": 3.3561, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3990593980593084e-05, + "loss": 3.3777, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3982208033082564e-05, + "loss": 3.372, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3973822085572044e-05, + "loss": 3.3754, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3965436138061524e-05, + "loss": 3.3857, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3957066569354735e-05, + "loss": 3.3757, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3948680621844215e-05, + "loss": 3.3726, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3940311053137426e-05, + "loss": 3.3692, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3931925105626905e-05, + "loss": 3.3914, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3923539158116385e-05, + "loss": 3.3784, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3915153210605867e-05, + "loss": 3.388, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3906767263095347e-05, + "loss": 3.3695, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3898381315584824e-05, + "loss": 3.382, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3889995368074305e-05, + "loss": 3.3835, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3881609420563785e-05, + "loss": 3.382, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3873239851856998e-05, + "loss": 3.3794, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3864853904346476e-05, + "loss": 3.3724, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3856467956835956e-05, + "loss": 3.3818, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3848082009325436e-05, + "loss": 3.397, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3839712440618648e-05, + "loss": 3.3746, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3831326493108127e-05, + "loss": 3.3741, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3822940545597607e-05, + "loss": 3.3793, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3814554598087087e-05, + "loss": 3.3727, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3806185029380297e-05, + "loss": 3.3688, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3797799081869777e-05, + "loss": 3.3907, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3789413134359259e-05, + "loss": 3.373, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3781027186848739e-05, + "loss": 3.3813, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3772657618141948e-05, + "loss": 3.3789, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.8665547370910645, + "eval_runtime": 309.118, + "eval_samples_per_second": 1234.451, + "eval_steps_per_second": 38.578, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.376427167063143e-05, + "loss": 3.3908, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.375588572312091e-05, + "loss": 3.3672, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.374749977561039e-05, + "loss": 3.3775, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.373911382809987e-05, + "loss": 3.3881, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.373074425939308e-05, + "loss": 3.3836, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.372235831188256e-05, + "loss": 3.3805, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.371397236437204e-05, + "loss": 3.3741, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3705586416861522e-05, + "loss": 3.3675, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3697216848154731e-05, + "loss": 3.37, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3688830900644211e-05, + "loss": 3.3795, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3680444953133693e-05, + "loss": 3.3746, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3672059005623172e-05, + "loss": 3.3923, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3663689436916383e-05, + "loss": 3.3873, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3655303489405863e-05, + "loss": 3.3602, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3646917541895343e-05, + "loss": 3.3687, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3638531594384823e-05, + "loss": 3.3634, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3630162025678034e-05, + "loss": 3.382, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3621776078167514e-05, + "loss": 3.3694, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3613390130656994e-05, + "loss": 3.3712, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3605004183146476e-05, + "loss": 3.372, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3596634614439685e-05, + "loss": 3.3818, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3588248666929165e-05, + "loss": 3.3736, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3579862719418646e-05, + "loss": 3.3746, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3571476771908126e-05, + "loss": 3.3748, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3563107203201337e-05, + "loss": 3.3838, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3554721255690817e-05, + "loss": 3.3762, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3546335308180297e-05, + "loss": 3.3656, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3537949360669777e-05, + "loss": 3.3815, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3529579791962988e-05, + "loss": 3.3641, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3521193844452468e-05, + "loss": 3.3674, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3512807896941948e-05, + "loss": 3.3781, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3504421949431426e-05, + "loss": 3.3705, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3496052380724638e-05, + "loss": 3.377, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3487666433214118e-05, + "loss": 3.379, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.34792804857036e-05, + "loss": 3.3708, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3470894538193076e-05, + "loss": 3.3739, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.346252496948629e-05, + "loss": 3.3738, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.345413902197577e-05, + "loss": 3.3612, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.344575307446525e-05, + "loss": 3.3727, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3437367126954729e-05, + "loss": 3.3596, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3428997558247941e-05, + "loss": 3.3712, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3420611610737421e-05, + "loss": 3.368, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.34122256632269e-05, + "loss": 3.3818, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.340383971571638e-05, + "loss": 3.3727, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3395470147009592e-05, + "loss": 3.3759, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3387084199499072e-05, + "loss": 3.3725, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.337869825198855e-05, + "loss": 3.3725, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.337031230447803e-05, + "loss": 3.3646, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3361942735771244e-05, + "loss": 3.3564, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3353556788260721e-05, + "loss": 3.3689, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.33451708407502e-05, + "loss": 3.3739, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3336801272043415e-05, + "loss": 3.3754, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3328415324532895e-05, + "loss": 3.3679, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3320029377022372e-05, + "loss": 3.3654, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3311643429511853e-05, + "loss": 3.3606, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3303273860805066e-05, + "loss": 3.3595, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3294887913294546e-05, + "loss": 3.3866, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3286501965784024e-05, + "loss": 3.3647, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3278116018273504e-05, + "loss": 3.3843, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3269746449566716e-05, + "loss": 3.3694, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3261360502056195e-05, + "loss": 3.3554, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3252974554545675e-05, + "loss": 3.3776, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3244588607035154e-05, + "loss": 3.3586, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3236219038328369e-05, + "loss": 3.3603, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3227833090817845e-05, + "loss": 3.3617, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3219447143307325e-05, + "loss": 3.3735, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3211061195796807e-05, + "loss": 3.3563, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.320269162709002e-05, + "loss": 3.37, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3194305679579496e-05, + "loss": 3.3534, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3185919732068978e-05, + "loss": 3.3671, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3177533784558457e-05, + "loss": 3.3741, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3169164215851668e-05, + "loss": 3.3687, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3160778268341148e-05, + "loss": 3.3732, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3152392320830628e-05, + "loss": 3.3654, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3144006373320108e-05, + "loss": 3.3809, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3135636804613319e-05, + "loss": 3.3602, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3127250857102799e-05, + "loss": 3.3748, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3118864909592279e-05, + "loss": 3.3691, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.311047896208176e-05, + "loss": 3.3627, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.310210939337497e-05, + "loss": 3.3751, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.309372344586445e-05, + "loss": 3.3677, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3085337498353931e-05, + "loss": 3.3774, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3076951550843411e-05, + "loss": 3.3794, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3068581982136622e-05, + "loss": 3.3672, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3060196034626102e-05, + "loss": 3.3593, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3051810087115582e-05, + "loss": 3.3611, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3043424139605062e-05, + "loss": 3.3694, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3035054570898273e-05, + "loss": 3.3715, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3026668623387753e-05, + "loss": 3.3652, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3018282675877233e-05, + "loss": 3.3758, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3009896728366714e-05, + "loss": 3.3679, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3001510780856194e-05, + "loss": 3.3643, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2993124833345674e-05, + "loss": 3.3695, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2984738885835152e-05, + "loss": 3.3743, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2976352938324632e-05, + "loss": 3.3712, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2967983369617845e-05, + "loss": 3.38, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2959597422107323e-05, + "loss": 3.3554, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2951211474596803e-05, + "loss": 3.3765, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2942825527086283e-05, + "loss": 3.3734, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2934455958379495e-05, + "loss": 3.3701, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2926070010868974e-05, + "loss": 3.3749, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2917684063358454e-05, + "loss": 3.3676, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2909314494651666e-05, + "loss": 3.3661, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2900928547141148e-05, + "loss": 3.3656, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2892542599630624e-05, + "loss": 3.3703, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2884156652120104e-05, + "loss": 3.3584, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2875787083413318e-05, + "loss": 3.3646, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2867401135902795e-05, + "loss": 3.3685, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2859015188392277e-05, + "loss": 3.3685, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2850629240881757e-05, + "loss": 3.3584, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2842259672174969e-05, + "loss": 3.362, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2833873724664447e-05, + "loss": 3.3715, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2825487777153927e-05, + "loss": 3.3744, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2817101829643407e-05, + "loss": 3.3656, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.280873226093662e-05, + "loss": 3.3795, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2800346313426098e-05, + "loss": 3.3766, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2791960365915578e-05, + "loss": 3.3739, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2783574418405058e-05, + "loss": 3.3615, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2775204849698269e-05, + "loss": 3.3679, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2766818902187749e-05, + "loss": 3.3693, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.275843295467723e-05, + "loss": 3.375, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.275004700716671e-05, + "loss": 3.3487, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.274167743845992e-05, + "loss": 3.367, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2733291490949401e-05, + "loss": 3.359, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2724905543438881e-05, + "loss": 3.3657, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2716519595928361e-05, + "loss": 3.3776, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2708150027221572e-05, + "loss": 3.3678, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2699764079711052e-05, + "loss": 3.36, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2691394511004264e-05, + "loss": 3.3609, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2683008563493742e-05, + "loss": 3.3805, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2674622615983222e-05, + "loss": 3.3684, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2666236668472702e-05, + "loss": 3.3808, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2657850720962184e-05, + "loss": 3.3574, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2649464773451664e-05, + "loss": 3.3749, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2641078825941144e-05, + "loss": 3.3728, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2632692878430624e-05, + "loss": 3.3721, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2624323309723835e-05, + "loss": 3.3661, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2615937362213315e-05, + "loss": 3.365, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2607551414702795e-05, + "loss": 3.3751, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2599165467192273e-05, + "loss": 3.3806, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2590795898485485e-05, + "loss": 3.3702, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2582409950974965e-05, + "loss": 3.3633, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2574024003464447e-05, + "loss": 3.3707, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2565638055953924e-05, + "loss": 3.3588, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2557268487247138e-05, + "loss": 3.358, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2548882539736618e-05, + "loss": 3.3808, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2540496592226098e-05, + "loss": 3.3649, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2532110644715576e-05, + "loss": 3.3749, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2523741076008788e-05, + "loss": 3.3645, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.86796236038208, + "eval_runtime": 304.9159, + "eval_samples_per_second": 1251.463, + "eval_steps_per_second": 39.109, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2515355128498268e-05, + "loss": 3.3609, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2506969180987747e-05, + "loss": 3.3623, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2498583233477228e-05, + "loss": 3.3651, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.249023004357417e-05, + "loss": 3.3772, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.248184409606365e-05, + "loss": 3.3782, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.247345814855313e-05, + "loss": 3.3696, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.246507220104261e-05, + "loss": 3.3612, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.245668625353209e-05, + "loss": 3.3571, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.244830030602157e-05, + "loss": 3.3607, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.243991435851105e-05, + "loss": 3.3672, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2431528411000528e-05, + "loss": 3.3713, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.242315884229374e-05, + "loss": 3.3797, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.241477289478322e-05, + "loss": 3.3794, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.24063869472727e-05, + "loss": 3.3508, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.239800099976218e-05, + "loss": 3.3594, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2389631431055391e-05, + "loss": 3.3548, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.2381245483544873e-05, + "loss": 3.3706, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2372859536034353e-05, + "loss": 3.3583, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2364473588523831e-05, + "loss": 3.3622, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2356104019817043e-05, + "loss": 3.3604, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2347718072306523e-05, + "loss": 3.3702, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2339332124796002e-05, + "loss": 3.3638, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2330946177285482e-05, + "loss": 3.3671, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.2322576608578694e-05, + "loss": 3.3648, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2314190661068174e-05, + "loss": 3.3751, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2305804713557654e-05, + "loss": 3.3615, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2297418766047134e-05, + "loss": 3.3576, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2289049197340345e-05, + "loss": 3.3684, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2280663249829826e-05, + "loss": 3.3546, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2272277302319305e-05, + "loss": 3.3579, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.2263891354808785e-05, + "loss": 3.3657, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.2255521786101997e-05, + "loss": 3.3669, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.2247135838591475e-05, + "loss": 3.365, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.2238749891080955e-05, + "loss": 3.3707, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.2230363943570435e-05, + "loss": 3.3619, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.2221994374863648e-05, + "loss": 3.363, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2213608427353126e-05, + "loss": 3.363, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2205238858646338e-05, + "loss": 3.3525, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.2196852911135818e-05, + "loss": 3.3628, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2188466963625298e-05, + "loss": 3.3526, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2180081016114778e-05, + "loss": 3.3569, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2171695068604258e-05, + "loss": 3.3587, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2163309121093738e-05, + "loss": 3.3744, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2154923173583216e-05, + "loss": 3.3625, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2146537226072698e-05, + "loss": 3.3654, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2138167657365909e-05, + "loss": 3.3633, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2129781709855389e-05, + "loss": 3.3625, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2121395762344869e-05, + "loss": 3.3534, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2113009814834349e-05, + "loss": 3.348, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2104640246127561e-05, + "loss": 3.3587, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.209625429861704e-05, + "loss": 3.364, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.208786835110652e-05, + "loss": 3.3642, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2079482403596e-05, + "loss": 3.3591, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2071112834889212e-05, + "loss": 3.3494, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.206272688737869e-05, + "loss": 3.3567, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.205434093986817e-05, + "loss": 3.3471, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2045954992357652e-05, + "loss": 3.377, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2037585423650861e-05, + "loss": 3.3538, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2029199476140343e-05, + "loss": 3.3747, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2020813528629822e-05, + "loss": 3.3586, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2012427581119302e-05, + "loss": 3.3481, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.2004058012412513e-05, + "loss": 3.361, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1995688443705724e-05, + "loss": 3.3562, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1987302496195204e-05, + "loss": 3.3524, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1978916548684686e-05, + "loss": 3.346, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1970530601174164e-05, + "loss": 3.3692, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1962144653663644e-05, + "loss": 3.3501, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1953758706153124e-05, + "loss": 3.3545, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1945372758642604e-05, + "loss": 3.3448, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.1936986811132084e-05, + "loss": 3.3586, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1928617242425296e-05, + "loss": 3.3632, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1920231294914776e-05, + "loss": 3.3598, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1911845347404254e-05, + "loss": 3.3603, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1903459399893734e-05, + "loss": 3.3604, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.1895089831186947e-05, + "loss": 3.3667, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.1886703883676425e-05, + "loss": 3.3571, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.1878317936165905e-05, + "loss": 3.3604, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1869931988655387e-05, + "loss": 3.3604, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1861562419948598e-05, + "loss": 3.3562, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1853176472438077e-05, + "loss": 3.3635, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1844790524927557e-05, + "loss": 3.3613, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1836404577417037e-05, + "loss": 3.3653, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1828035008710248e-05, + "loss": 3.3688, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1819665440003459e-05, + "loss": 3.3588, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1811279492492939e-05, + "loss": 3.346, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.180289354498242e-05, + "loss": 3.3512, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1794507597471899e-05, + "loss": 3.3633, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1786121649961379e-05, + "loss": 3.3599, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.1777735702450859e-05, + "loss": 3.3553, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.176934975494034e-05, + "loss": 3.3671, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.176098018623355e-05, + "loss": 3.3611, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1752594238723031e-05, + "loss": 3.3541, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1744208291212511e-05, + "loss": 3.3561, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.173582234370199e-05, + "loss": 3.3657, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.1727452774995202e-05, + "loss": 3.3616, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1719066827484682e-05, + "loss": 3.3699, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1710680879974162e-05, + "loss": 3.3442, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.170229493246364e-05, + "loss": 3.3644, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1693925363756852e-05, + "loss": 3.3645, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.1685539416246332e-05, + "loss": 3.3595, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1677153468735812e-05, + "loss": 3.3645, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1668767521225292e-05, + "loss": 3.361, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1660397952518503e-05, + "loss": 3.3556, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.1652012005007985e-05, + "loss": 3.3597, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.1643626057497463e-05, + "loss": 3.3566, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1635240109986943e-05, + "loss": 3.3548, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.1626870541280155e-05, + "loss": 3.3534, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1618484593769635e-05, + "loss": 3.3607, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1610098646259114e-05, + "loss": 3.3576, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.1601712698748594e-05, + "loss": 3.3458, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1593343130041806e-05, + "loss": 3.35, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.1584973561335017e-05, + "loss": 3.3624, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.1576587613824497e-05, + "loss": 3.3703, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1568201666313977e-05, + "loss": 3.3595, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1559815718803457e-05, + "loss": 3.3617, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1551429771292937e-05, + "loss": 3.368, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1543043823782417e-05, + "loss": 3.3623, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1534657876271897e-05, + "loss": 3.3554, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1526271928761377e-05, + "loss": 3.3572, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1517902360054587e-05, + "loss": 3.3602, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1509516412544067e-05, + "loss": 3.3667, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1501130465033547e-05, + "loss": 3.3375, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1492744517523027e-05, + "loss": 3.3597, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1484374948816238e-05, + "loss": 3.3472, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.147598900130572e-05, + "loss": 3.3557, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.14676030537952e-05, + "loss": 3.3648, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1459217106284678e-05, + "loss": 3.3628, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.145084753757789e-05, + "loss": 3.3478, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1442477968871101e-05, + "loss": 3.352, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1434092021360581e-05, + "loss": 3.3682, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1425706073850061e-05, + "loss": 3.36, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1417320126339541e-05, + "loss": 3.3701, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1408934178829021e-05, + "loss": 3.3526, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1400548231318501e-05, + "loss": 3.361, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1392162283807981e-05, + "loss": 3.3656, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1383776336297461e-05, + "loss": 3.361, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.1375423146394404e-05, + "loss": 3.3593, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.1367037198883882e-05, + "loss": 3.3572, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.1358651251373362e-05, + "loss": 3.3687, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.1350265303862844e-05, + "loss": 3.3702, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.1341879356352322e-05, + "loss": 3.3613, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.1333493408841802e-05, + "loss": 3.3513, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.1325107461331282e-05, + "loss": 3.3615, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.1316721513820764e-05, + "loss": 3.3518, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.1308351945113973e-05, + "loss": 3.3468, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.1299965997603455e-05, + "loss": 3.3703, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.1291580050092935e-05, + "loss": 3.3556, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.1283194102582413e-05, + "loss": 3.3664, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.1274808155071893e-05, + "loss": 3.3538, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.86948823928833, + "eval_runtime": 304.8648, + "eval_samples_per_second": 1251.673, + "eval_steps_per_second": 39.116, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.1266422207561374e-05, + "loss": 3.329, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1258036260050854e-05, + "loss": 3.3534, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.1249650312540333e-05, + "loss": 3.3566, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.1241264365029813e-05, + "loss": 3.3648, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1232894796323025e-05, + "loss": 3.3695, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1224508848812503e-05, + "loss": 3.3614, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.1216122901301983e-05, + "loss": 3.3518, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1207736953791465e-05, + "loss": 3.3485, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.1199367385084676e-05, + "loss": 3.3512, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1190981437574156e-05, + "loss": 3.3622, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1182595490063636e-05, + "loss": 3.355, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1174209542553116e-05, + "loss": 3.3756, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.1165839973846328e-05, + "loss": 3.3697, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1157454026335806e-05, + "loss": 3.3452, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1149068078825286e-05, + "loss": 3.3458, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1140682131314766e-05, + "loss": 3.3455, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1132312562607977e-05, + "loss": 3.3592, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1123926615097457e-05, + "loss": 3.3524, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1115540667586937e-05, + "loss": 3.3531, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1107154720076419e-05, + "loss": 3.3458, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1098785151369628e-05, + "loss": 3.3691, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.109039920385911e-05, + "loss": 3.3503, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.108201325634859e-05, + "loss": 3.358, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1073627308838068e-05, + "loss": 3.3568, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.106525774013128e-05, + "loss": 3.3672, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.105687179262076e-05, + "loss": 3.3493, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.104848584511024e-05, + "loss": 3.3505, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1040099897599718e-05, + "loss": 3.3536, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.103173032889293e-05, + "loss": 3.3551, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.102334438138241e-05, + "loss": 3.3463, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.101495843387189e-05, + "loss": 3.3543, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.100657248636137e-05, + "loss": 3.3554, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0998202917654581e-05, + "loss": 3.3554, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0989816970144063e-05, + "loss": 3.3593, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0981431022633541e-05, + "loss": 3.354, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0973045075123021e-05, + "loss": 3.3534, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0964675506416234e-05, + "loss": 3.352, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.0956305937709445e-05, + "loss": 3.3458, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0947919990198925e-05, + "loss": 3.3514, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0939534042688404e-05, + "loss": 3.3393, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0931148095177884e-05, + "loss": 3.3514, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0922762147667364e-05, + "loss": 3.3475, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.0914376200156844e-05, + "loss": 3.3638, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0905990252646324e-05, + "loss": 3.3527, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0897604305135804e-05, + "loss": 3.3519, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0889234736429015e-05, + "loss": 3.3593, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.0880848788918495e-05, + "loss": 3.3502, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0872462841407975e-05, + "loss": 3.3464, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0864076893897455e-05, + "loss": 3.3379, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0855707325190666e-05, + "loss": 3.3515, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0847321377680146e-05, + "loss": 3.3506, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0838935430169626e-05, + "loss": 3.3526, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0830565861462838e-05, + "loss": 3.354, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.0822179913952316e-05, + "loss": 3.3387, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0813793966441798e-05, + "loss": 3.3482, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.0805408018931278e-05, + "loss": 3.337, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0797022071420756e-05, + "loss": 3.3663, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0788636123910236e-05, + "loss": 3.3438, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.0780250176399718e-05, + "loss": 3.3692, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0771864228889196e-05, + "loss": 3.3483, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0763494660182407e-05, + "loss": 3.3369, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0755108712671889e-05, + "loss": 3.3508, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0746722765161369e-05, + "loss": 3.3494, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0738336817650847e-05, + "loss": 3.3405, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.072996724894406e-05, + "loss": 3.3373, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.072158130143354e-05, + "loss": 3.3591, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0713195353923017e-05, + "loss": 3.3428, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0704809406412499e-05, + "loss": 3.3422, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.069643983770571e-05, + "loss": 3.3351, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0688070268998922e-05, + "loss": 3.3483, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.06796843214884e-05, + "loss": 3.3557, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.067129837397788e-05, + "loss": 3.3485, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.066291242646736e-05, + "loss": 3.3466, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0654526478956842e-05, + "loss": 3.352, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.064614053144632e-05, + "loss": 3.3548, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.06377545839358e-05, + "loss": 3.3458, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.062936863642528e-05, + "loss": 3.3509, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0620999067718491e-05, + "loss": 3.3541, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.0612613120207971e-05, + "loss": 3.3459, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0604227172697453e-05, + "loss": 3.3519, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0595841225186933e-05, + "loss": 3.3506, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.0587471656480142e-05, + "loss": 3.3549, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0579085708969623e-05, + "loss": 3.3598, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0570716140262834e-05, + "loss": 3.3471, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.0562330192752314e-05, + "loss": 3.3385, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.0553944245241794e-05, + "loss": 3.3389, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0545558297731274e-05, + "loss": 3.3543, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0537188729024487e-05, + "loss": 3.3522, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.0528802781513965e-05, + "loss": 3.3438, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0520416834003445e-05, + "loss": 3.3554, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0512030886492925e-05, + "loss": 3.356, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0503644938982406e-05, + "loss": 3.343, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0495258991471885e-05, + "loss": 3.3459, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0486873043961365e-05, + "loss": 3.3583, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0478487096450845e-05, + "loss": 3.3473, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0470117527744055e-05, + "loss": 3.3589, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0461731580233535e-05, + "loss": 3.3406, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0453345632723015e-05, + "loss": 3.3562, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0444959685212497e-05, + "loss": 3.3554, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0436590116505706e-05, + "loss": 3.3503, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0428204168995188e-05, + "loss": 3.3579, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0419818221484668e-05, + "loss": 3.3497, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0411432273974146e-05, + "loss": 3.3448, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0403062705267358e-05, + "loss": 3.3476, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0394676757756838e-05, + "loss": 3.3502, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0386290810246318e-05, + "loss": 3.3418, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0377904862735798e-05, + "loss": 3.3448, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0369535294029009e-05, + "loss": 3.3558, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0361149346518489e-05, + "loss": 3.3471, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0352763399007969e-05, + "loss": 3.3348, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0344377451497449e-05, + "loss": 3.3397, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.033600788279066e-05, + "loss": 3.3497, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0327621935280141e-05, + "loss": 3.3616, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.031923598776962e-05, + "loss": 3.3489, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.031086641906283e-05, + "loss": 3.3517, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0302480471552312e-05, + "loss": 3.3551, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0294094524041792e-05, + "loss": 3.3605, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.028570857653127e-05, + "loss": 3.34, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0277339007824483e-05, + "loss": 3.3487, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0268953060313963e-05, + "loss": 3.3527, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.0260567112803443e-05, + "loss": 3.3508, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.0252181165292923e-05, + "loss": 3.3308, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0243811596586133e-05, + "loss": 3.3465, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0235425649075613e-05, + "loss": 3.3415, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0227039701565093e-05, + "loss": 3.3444, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0218653754054573e-05, + "loss": 3.3508, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0210284185347784e-05, + "loss": 3.3597, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.0201914616640997e-05, + "loss": 3.3386, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.0193528669130475e-05, + "loss": 3.3445, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.0185142721619957e-05, + "loss": 3.351, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0176756774109436e-05, + "loss": 3.3557, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.0168370826598916e-05, + "loss": 3.3589, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0159984879088395e-05, + "loss": 3.3453, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.0151598931577876e-05, + "loss": 3.35, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.0143212984067356e-05, + "loss": 3.3577, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.0134843415360565e-05, + "loss": 3.3554, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0126457467850047e-05, + "loss": 3.3487, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0118071520339527e-05, + "loss": 3.3478, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0109685572829005e-05, + "loss": 3.3593, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0101316004122218e-05, + "loss": 3.3558, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0092930056611698e-05, + "loss": 3.3549, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0084544109101178e-05, + "loss": 3.3431, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0076158161590658e-05, + "loss": 3.3484, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0067788592883868e-05, + "loss": 3.3379, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0059402645373348e-05, + "loss": 3.3389, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.005101669786283e-05, + "loss": 3.3612, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0042630750352308e-05, + "loss": 3.3467, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0034261181645519e-05, + "loss": 3.3543, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0025875234135e-05, + "loss": 3.3462, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0017489286624479e-05, + "loss": 3.3401, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.868882417678833, + "eval_runtime": 307.82, + "eval_samples_per_second": 1239.656, + "eval_steps_per_second": 38.74, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0009103339113959e-05, + "loss": 3.3443, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 1.0000733770407171e-05, + "loss": 3.3451, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.992347822896651e-06, + "loss": 3.3582, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.98396187538613e-06, + "loss": 3.3551, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.975575927875611e-06, + "loss": 3.3519, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.967206359168822e-06, + "loss": 3.343, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.958820411658302e-06, + "loss": 3.3403, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.950434464147782e-06, + "loss": 3.3391, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.942048516637262e-06, + "loss": 3.3549, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.933678947930473e-06, + "loss": 3.3464, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.925293000419953e-06, + "loss": 3.3611, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.916907052909433e-06, + "loss": 3.3565, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.908521105398913e-06, + "loss": 3.3402, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.900151536692125e-06, + "loss": 3.3386, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.891765589181603e-06, + "loss": 3.3387, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.883379641671083e-06, + "loss": 3.3434, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.875010072964296e-06, + "loss": 3.3444, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.866624125453776e-06, + "loss": 3.342, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.858238177943254e-06, + "loss": 3.3368, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.849852230432736e-06, + "loss": 3.3615, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.841482661725946e-06, + "loss": 3.3393, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.833096714215426e-06, + "loss": 3.3527, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.824710766704906e-06, + "loss": 3.3482, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.816341197998117e-06, + "loss": 3.3534, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.807955250487599e-06, + "loss": 3.3406, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.799569302977077e-06, + "loss": 3.3423, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.791183355466557e-06, + "loss": 3.3434, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.782797407956037e-06, + "loss": 3.3471, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.774411460445517e-06, + "loss": 3.3363, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.766025512934997e-06, + "loss": 3.344, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.757639565424477e-06, + "loss": 3.3488, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.74926999671769e-06, + "loss": 3.3451, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.740884049207168e-06, + "loss": 3.3497, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.732498101696648e-06, + "loss": 3.3447, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.724112154186127e-06, + "loss": 3.3424, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.71575896428307e-06, + "loss": 3.3416, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.70737301677255e-06, + "loss": 3.3338, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.69898706926203e-06, + "loss": 3.3449, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.69060112175151e-06, + "loss": 3.3301, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.682215174240989e-06, + "loss": 3.3392, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.67382922673047e-06, + "loss": 3.338, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.66544327921995e-06, + "loss": 3.3533, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.65705733170943e-06, + "loss": 3.3476, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.648687763002641e-06, + "loss": 3.3386, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.640301815492121e-06, + "loss": 3.3506, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.631915867981601e-06, + "loss": 3.3455, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.623529920471081e-06, + "loss": 3.3364, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.615160351764292e-06, + "loss": 3.3331, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.606774404253772e-06, + "loss": 3.3331, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.598388456743254e-06, + "loss": 3.3482, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.590002509232732e-06, + "loss": 3.3413, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.581649319329675e-06, + "loss": 3.3445, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.573263371819155e-06, + "loss": 3.3336, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.564877424308635e-06, + "loss": 3.3371, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.556491476798115e-06, + "loss": 3.3272, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.548105529287595e-06, + "loss": 3.3543, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.539719581777075e-06, + "loss": 3.3388, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.531333634266553e-06, + "loss": 3.3566, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.522947686756035e-06, + "loss": 3.3409, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.514578118049246e-06, + "loss": 3.3282, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.506192170538726e-06, + "loss": 3.3395, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.497822601831936e-06, + "loss": 3.3409, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.489436654321416e-06, + "loss": 3.3291, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.481050706810896e-06, + "loss": 3.3254, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.472664759300376e-06, + "loss": 3.3498, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.464278811789856e-06, + "loss": 3.3385, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.455892864279336e-06, + "loss": 3.3323, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.447506916768816e-06, + "loss": 3.3265, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.439137348062027e-06, + "loss": 3.3387, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.430751400551507e-06, + "loss": 3.3472, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.422365453040988e-06, + "loss": 3.3395, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.413979505530467e-06, + "loss": 3.3373, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.405593558019947e-06, + "loss": 3.3433, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.397207610509427e-06, + "loss": 3.3474, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.388821662998908e-06, + "loss": 3.3407, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.380435715488387e-06, + "loss": 3.3368, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.372066146781597e-06, + "loss": 3.3443, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.363680199271079e-06, + "loss": 3.3376, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.355294251760557e-06, + "loss": 3.3441, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.346908304250037e-06, + "loss": 3.3404, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.33853873554325e-06, + "loss": 3.347, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.33015278803273e-06, + "loss": 3.3494, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.32178321932594e-06, + "loss": 3.3359, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.31339727181542e-06, + "loss": 3.3312, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.3050113243049e-06, + "loss": 3.3304, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.29662537679438e-06, + "loss": 3.3418, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.288255808087591e-06, + "loss": 3.3446, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.279869860577071e-06, + "loss": 3.3388, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.271483913066551e-06, + "loss": 3.3428, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.263097965556031e-06, + "loss": 3.3429, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.254712018045511e-06, + "loss": 3.3382, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.246326070534991e-06, + "loss": 3.3375, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.23794012302447e-06, + "loss": 3.3451, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.22955417551395e-06, + "loss": 3.3405, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.221184606807162e-06, + "loss": 3.3481, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.212798659296643e-06, + "loss": 3.3358, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.204412711786122e-06, + "loss": 3.3436, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.196026764275601e-06, + "loss": 3.3465, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.187657195568814e-06, + "loss": 3.3438, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.179271248058294e-06, + "loss": 3.3432, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.170885300547772e-06, + "loss": 3.3436, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.162515731840985e-06, + "loss": 3.3334, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.154129784330465e-06, + "loss": 3.3395, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.145743836819945e-06, + "loss": 3.3433, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.137357889309425e-06, + "loss": 3.3301, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.128988320602635e-06, + "loss": 3.3304, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.120602373092115e-06, + "loss": 3.3498, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.112216425581595e-06, + "loss": 3.3398, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.103830478071075e-06, + "loss": 3.3233, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.095460909364286e-06, + "loss": 3.3357, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.087074961853768e-06, + "loss": 3.3387, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.078689014343246e-06, + "loss": 3.3529, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.070303066832726e-06, + "loss": 3.3434, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.061933498125938e-06, + "loss": 3.3381, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.053547550615418e-06, + "loss": 3.35, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.045161603104897e-06, + "loss": 3.3509, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.036775655594378e-06, + "loss": 3.3314, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.028406086887589e-06, + "loss": 3.337, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.020020139377067e-06, + "loss": 3.3465, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.011634191866549e-06, + "loss": 3.3405, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 9.003248244356029e-06, + "loss": 3.3282, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.99487867564924e-06, + "loss": 3.3335, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.98649272813872e-06, + "loss": 3.3334, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.9781067806282e-06, + "loss": 3.333, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.96972083311768e-06, + "loss": 3.3426, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.961351264410892e-06, + "loss": 3.3508, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.95296531690037e-06, + "loss": 3.3328, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.944595748193583e-06, + "loss": 3.3342, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.936209800683063e-06, + "loss": 3.3347, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.927823853172541e-06, + "loss": 3.3491, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.919437905662021e-06, + "loss": 3.3487, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.911051958151503e-06, + "loss": 3.3364, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.902666010640983e-06, + "loss": 3.3383, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.89428006313046e-06, + "loss": 3.3435, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.88589411561994e-06, + "loss": 3.3481, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.877524546913153e-06, + "loss": 3.3401, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.869138599402631e-06, + "loss": 3.3376, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.860752651892113e-06, + "loss": 3.3487, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.852383083185324e-06, + "loss": 3.3451, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.843997135674804e-06, + "loss": 3.3471, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.835611188164284e-06, + "loss": 3.3328, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.827225240653764e-06, + "loss": 3.3392, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.818839293143244e-06, + "loss": 3.3335, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.810469724436455e-06, + "loss": 3.3253, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.802083776925934e-06, + "loss": 3.3553, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.793697829415414e-06, + "loss": 3.338, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.785311881904894e-06, + "loss": 3.3456, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.776925934394374e-06, + "loss": 3.338, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.768539986883854e-06, + "loss": 3.3283, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.8690240383148193, + "eval_runtime": 306.0515, + "eval_samples_per_second": 1246.82, + "eval_steps_per_second": 38.964, + "step": 2518560 + }, + { + "epoch": 0.0, + "learning_rate": 8.760154039373334e-06, + "loss": 3.3359, + "step": 2519040 + }, + { + "epoch": 0.0, + "learning_rate": 8.751768091862814e-06, + "loss": 3.3389, + "step": 2519552 + }, + { + "epoch": 0.0, + "learning_rate": 8.743382144352294e-06, + "loss": 3.3513, + "step": 2520064 + }, + { + "epoch": 0.0, + "learning_rate": 8.735012575645505e-06, + "loss": 3.3404, + "step": 2520576 + }, + { + "epoch": 0.0, + "learning_rate": 8.726626628134987e-06, + "loss": 3.348, + "step": 2521088 + }, + { + "epoch": 0.0, + "learning_rate": 8.718240680624465e-06, + "loss": 3.3311, + "step": 2521600 + }, + { + "epoch": 0.0, + "learning_rate": 8.709854733113945e-06, + "loss": 3.3336, + "step": 2522112 + }, + { + "epoch": 0.0, + "learning_rate": 8.701485164407157e-06, + "loss": 3.3322, + "step": 2522624 + }, + { + "epoch": 0.0, + "learning_rate": 8.693099216896636e-06, + "loss": 3.3385, + "step": 2523136 + }, + { + "epoch": 0.0, + "learning_rate": 8.684713269386116e-06, + "loss": 3.3397, + "step": 2523648 + }, + { + "epoch": 0.0, + "learning_rate": 8.676327321875597e-06, + "loss": 3.3491, + "step": 2524160 + }, + { + "epoch": 0.0, + "learning_rate": 8.667957753168808e-06, + "loss": 3.3448, + "step": 2524672 + }, + { + "epoch": 0.0, + "learning_rate": 8.659571805658286e-06, + "loss": 3.3337, + "step": 2525184 + }, + { + "epoch": 0.0, + "learning_rate": 8.651185858147768e-06, + "loss": 3.3327, + "step": 2525696 + }, + { + "epoch": 0.0, + "learning_rate": 8.642799910637248e-06, + "loss": 3.3335, + "step": 2526208 + }, + { + "epoch": 0.0, + "learning_rate": 8.634430341930459e-06, + "loss": 3.3293, + "step": 2526720 + }, + { + "epoch": 0.0, + "learning_rate": 8.626044394419939e-06, + "loss": 3.336, + "step": 2527232 + }, + { + "epoch": 0.0, + "learning_rate": 8.617658446909419e-06, + "loss": 3.3318, + "step": 2527744 + }, + { + "epoch": 0.0, + "learning_rate": 8.609272499398898e-06, + "loss": 3.3288, + "step": 2528256 + }, + { + "epoch": 0.0, + "learning_rate": 8.60090293069211e-06, + "loss": 3.3558, + "step": 2528768 + }, + { + "epoch": 0.0, + "learning_rate": 8.59251698318159e-06, + "loss": 3.3339, + "step": 2529280 + }, + { + "epoch": 0.0, + "learning_rate": 8.58413103567107e-06, + "loss": 3.3377, + "step": 2529792 + }, + { + "epoch": 0.0, + "learning_rate": 8.57574508816055e-06, + "loss": 3.34, + "step": 2530304 + }, + { + "epoch": 0.0, + "learning_rate": 8.56737551945376e-06, + "loss": 3.3438, + "step": 2530816 + }, + { + "epoch": 0.0, + "learning_rate": 8.55898957194324e-06, + "loss": 3.3328, + "step": 2531328 + }, + { + "epoch": 0.0, + "learning_rate": 8.550620003236452e-06, + "loss": 3.3341, + "step": 2531840 + }, + { + "epoch": 0.0, + "learning_rate": 8.542234055725932e-06, + "loss": 3.3315, + "step": 2532352 + }, + { + "epoch": 0.0, + "learning_rate": 8.533848108215412e-06, + "loss": 3.3418, + "step": 2532864 + }, + { + "epoch": 0.0, + "learning_rate": 8.525462160704892e-06, + "loss": 3.3204, + "step": 2533376 + }, + { + "epoch": 0.01, + "learning_rate": 8.517076213194372e-06, + "loss": 3.3353, + "step": 2533888 + }, + { + "epoch": 0.01, + "learning_rate": 8.50869026568385e-06, + "loss": 3.3392, + "step": 2534400 + }, + { + "epoch": 0.01, + "learning_rate": 8.500304318173332e-06, + "loss": 3.3367, + "step": 2534912 + }, + { + "epoch": 0.01, + "learning_rate": 8.491918370662812e-06, + "loss": 3.3434, + "step": 2535424 + }, + { + "epoch": 0.01, + "learning_rate": 8.483548801956023e-06, + "loss": 3.3354, + "step": 2535936 + }, + { + "epoch": 0.01, + "learning_rate": 8.475162854445503e-06, + "loss": 3.3301, + "step": 2536448 + }, + { + "epoch": 0.01, + "learning_rate": 8.466793285738714e-06, + "loss": 3.3358, + "step": 2536960 + }, + { + "epoch": 0.01, + "learning_rate": 8.458407338228194e-06, + "loss": 3.3249, + "step": 2537472 + }, + { + "epoch": 0.01, + "learning_rate": 8.450021390717674e-06, + "loss": 3.3326, + "step": 2537984 + }, + { + "epoch": 0.01, + "learning_rate": 8.441635443207153e-06, + "loss": 3.3228, + "step": 2538496 + }, + { + "epoch": 0.01, + "learning_rate": 8.433249495696633e-06, + "loss": 3.3288, + "step": 2539008 + }, + { + "epoch": 0.01, + "learning_rate": 8.424863548186113e-06, + "loss": 3.3319, + "step": 2539520 + }, + { + "epoch": 0.01, + "learning_rate": 8.416477600675593e-06, + "loss": 3.3455, + "step": 2540032 + }, + { + "epoch": 0.01, + "learning_rate": 8.408091653165073e-06, + "loss": 3.3372, + "step": 2540544 + }, + { + "epoch": 0.01, + "learning_rate": 8.399722084458286e-06, + "loss": 3.3324, + "step": 2541056 + }, + { + "epoch": 0.01, + "learning_rate": 8.391336136947764e-06, + "loss": 3.3432, + "step": 2541568 + }, + { + "epoch": 0.01, + "learning_rate": 8.382950189437244e-06, + "loss": 3.3357, + "step": 2542080 + }, + { + "epoch": 0.01, + "learning_rate": 8.374564241926724e-06, + "loss": 3.3235, + "step": 2542592 + }, + { + "epoch": 0.01, + "learning_rate": 8.366194673219936e-06, + "loss": 3.3277, + "step": 2543104 + }, + { + "epoch": 0.01, + "learning_rate": 8.357808725709415e-06, + "loss": 3.3214, + "step": 2543616 + }, + { + "epoch": 0.01, + "learning_rate": 8.349422778198895e-06, + "loss": 3.3378, + "step": 2544128 + }, + { + "epoch": 0.01, + "learning_rate": 8.341036830688376e-06, + "loss": 3.3326, + "step": 2544640 + }, + { + "epoch": 0.01, + "learning_rate": 8.332683640785318e-06, + "loss": 3.3284, + "step": 2545152 + }, + { + "epoch": 0.01, + "learning_rate": 8.324297693274798e-06, + "loss": 3.329, + "step": 2545664 + }, + { + "epoch": 0.01, + "learning_rate": 8.315911745764278e-06, + "loss": 3.3311, + "step": 2546176 + }, + { + "epoch": 0.01, + "learning_rate": 8.307525798253758e-06, + "loss": 3.3191, + "step": 2546688 + }, + { + "epoch": 0.01, + "learning_rate": 8.299139850743238e-06, + "loss": 3.3402, + "step": 2547200 + }, + { + "epoch": 0.01, + "learning_rate": 8.290753903232718e-06, + "loss": 3.3294, + "step": 2547712 + }, + { + "epoch": 0.01, + "learning_rate": 8.282367955722198e-06, + "loss": 3.3468, + "step": 2548224 + }, + { + "epoch": 0.01, + "learning_rate": 8.273982008211678e-06, + "loss": 3.331, + "step": 2548736 + }, + { + "epoch": 0.01, + "learning_rate": 8.265612439504888e-06, + "loss": 3.3216, + "step": 2549248 + }, + { + "epoch": 0.01, + "learning_rate": 8.257226491994368e-06, + "loss": 3.3282, + "step": 2549760 + }, + { + "epoch": 0.01, + "learning_rate": 8.248840544483848e-06, + "loss": 3.3343, + "step": 2550272 + }, + { + "epoch": 0.01, + "learning_rate": 8.240454596973328e-06, + "loss": 3.3206, + "step": 2550784 + }, + { + "epoch": 0.01, + "learning_rate": 8.232085028266539e-06, + "loss": 3.3192, + "step": 2551296 + }, + { + "epoch": 0.01, + "learning_rate": 8.22369908075602e-06, + "loss": 3.3373, + "step": 2551808 + }, + { + "epoch": 0.01, + "learning_rate": 8.2153131332455e-06, + "loss": 3.3296, + "step": 2552320 + }, + { + "epoch": 0.01, + "learning_rate": 8.206927185734979e-06, + "loss": 3.3247, + "step": 2552832 + }, + { + "epoch": 0.01, + "learning_rate": 8.198557617028191e-06, + "loss": 3.3194, + "step": 2553344 + }, + { + "epoch": 0.01, + "learning_rate": 8.190171669517671e-06, + "loss": 3.3236, + "step": 2553856 + }, + { + "epoch": 0.01, + "learning_rate": 8.18178572200715e-06, + "loss": 3.3353, + "step": 2554368 + }, + { + "epoch": 0.01, + "learning_rate": 8.17339977449663e-06, + "loss": 3.3305, + "step": 2554880 + }, + { + "epoch": 0.01, + "learning_rate": 8.165030205789842e-06, + "loss": 3.3292, + "step": 2555392 + }, + { + "epoch": 0.01, + "learning_rate": 8.156644258279322e-06, + "loss": 3.3372, + "step": 2555904 + }, + { + "epoch": 0.01, + "learning_rate": 8.148258310768802e-06, + "loss": 3.3314, + "step": 2556416 + }, + { + "epoch": 0.01, + "learning_rate": 8.139872363258282e-06, + "loss": 3.3364, + "step": 2556928 + }, + { + "epoch": 0.01, + "learning_rate": 8.131502794551493e-06, + "loss": 3.3223, + "step": 2557440 + }, + { + "epoch": 0.01, + "learning_rate": 8.123116847040973e-06, + "loss": 3.3378, + "step": 2557952 + }, + { + "epoch": 0.01, + "learning_rate": 8.114730899530453e-06, + "loss": 3.3289, + "step": 2558464 + }, + { + "epoch": 0.01, + "learning_rate": 8.106344952019933e-06, + "loss": 3.3311, + "step": 2558976 + }, + { + "epoch": 0.01, + "learning_rate": 8.097975383313145e-06, + "loss": 3.3358, + "step": 2559488 + }, + { + "epoch": 0.01, + "learning_rate": 8.089589435802623e-06, + "loss": 3.3365, + "step": 2560000 + }, + { + "epoch": 0.01, + "learning_rate": 8.081203488292103e-06, + "loss": 3.3402, + "step": 2560512 + }, + { + "epoch": 0.01, + "learning_rate": 8.072833919585316e-06, + "loss": 3.3302, + "step": 2561024 + }, + { + "epoch": 0.01, + "learning_rate": 8.064447972074796e-06, + "loss": 3.3165, + "step": 2561536 + }, + { + "epoch": 0.01, + "learning_rate": 8.056062024564274e-06, + "loss": 3.3248, + "step": 2562048 + }, + { + "epoch": 0.01, + "learning_rate": 8.047676077053756e-06, + "loss": 3.3312, + "step": 2562560 + }, + { + "epoch": 0.01, + "learning_rate": 8.039306508346966e-06, + "loss": 3.335, + "step": 2563072 + }, + { + "epoch": 0.01, + "learning_rate": 8.030920560836446e-06, + "loss": 3.3285, + "step": 2563584 + }, + { + "epoch": 0.01, + "learning_rate": 8.022534613325926e-06, + "loss": 3.3342, + "step": 2564096 + }, + { + "epoch": 0.02, + "learning_rate": 8.014148665815406e-06, + "loss": 3.3334, + "step": 2564608 + }, + { + "epoch": 0.02, + "learning_rate": 8.005762718304886e-06, + "loss": 3.3284, + "step": 2565120 + }, + { + "epoch": 0.02, + "learning_rate": 7.997376770794365e-06, + "loss": 3.3307, + "step": 2565632 + }, + { + "epoch": 0.02, + "learning_rate": 7.988990823283846e-06, + "loss": 3.3329, + "step": 2566144 + }, + { + "epoch": 0.02, + "learning_rate": 7.980604875773326e-06, + "loss": 3.3276, + "step": 2566656 + }, + { + "epoch": 0.02, + "learning_rate": 7.972235307066537e-06, + "loss": 3.3398, + "step": 2567168 + }, + { + "epoch": 0.02, + "learning_rate": 7.963849359556017e-06, + "loss": 3.332, + "step": 2567680 + }, + { + "epoch": 0.02, + "learning_rate": 7.955463412045497e-06, + "loss": 3.3283, + "step": 2568192 + }, + { + "epoch": 0.02, + "learning_rate": 7.94709384333871e-06, + "loss": 3.3382, + "step": 2568704 + }, + { + "epoch": 0.02, + "learning_rate": 7.938707895828188e-06, + "loss": 3.3339, + "step": 2569216 + }, + { + "epoch": 0.02, + "learning_rate": 7.930321948317668e-06, + "loss": 3.339, + "step": 2569728 + }, + { + "epoch": 0.02, + "learning_rate": 7.921936000807147e-06, + "loss": 3.3334, + "step": 2570240 + }, + { + "epoch": 0.02, + "learning_rate": 7.913550053296629e-06, + "loss": 3.3236, + "step": 2570752 + }, + { + "epoch": 0.02, + "learning_rate": 7.905164105786107e-06, + "loss": 3.3326, + "step": 2571264 + }, + { + "epoch": 0.02, + "learning_rate": 7.896778158275587e-06, + "loss": 3.3328, + "step": 2571776 + }, + { + "epoch": 0.02, + "learning_rate": 7.888392210765067e-06, + "loss": 3.3144, + "step": 2572288 + }, + { + "epoch": 0.02, + "learning_rate": 7.880022642058278e-06, + "loss": 3.3279, + "step": 2572800 + }, + { + "epoch": 0.02, + "learning_rate": 7.871636694547758e-06, + "loss": 3.3366, + "step": 2573312 + }, + { + "epoch": 0.02, + "learning_rate": 7.863250747037238e-06, + "loss": 3.3329, + "step": 2573824 + }, + { + "epoch": 0.02, + "learning_rate": 7.85486479952672e-06, + "loss": 3.3151, + "step": 2574336 + }, + { + "epoch": 0.02, + "learning_rate": 7.846495230819929e-06, + "loss": 3.3204, + "step": 2574848 + }, + { + "epoch": 0.02, + "learning_rate": 7.83810928330941e-06, + "loss": 3.3312, + "step": 2575360 + }, + { + "epoch": 0.02, + "learning_rate": 7.82972333579889e-06, + "loss": 3.3407, + "step": 2575872 + }, + { + "epoch": 0.02, + "learning_rate": 7.821337388288369e-06, + "loss": 3.3313, + "step": 2576384 + }, + { + "epoch": 0.02, + "learning_rate": 7.812967819581581e-06, + "loss": 3.3334, + "step": 2576896 + }, + { + "epoch": 0.02, + "learning_rate": 7.804581872071061e-06, + "loss": 3.3359, + "step": 2577408 + }, + { + "epoch": 0.02, + "learning_rate": 7.796195924560541e-06, + "loss": 3.3454, + "step": 2577920 + }, + { + "epoch": 0.02, + "learning_rate": 7.78780997705002e-06, + "loss": 3.3212, + "step": 2578432 + }, + { + "epoch": 0.02, + "learning_rate": 7.779440408343232e-06, + "loss": 3.3282, + "step": 2578944 + }, + { + "epoch": 0.02, + "learning_rate": 7.771054460832712e-06, + "loss": 3.3352, + "step": 2579456 + }, + { + "epoch": 0.02, + "learning_rate": 7.762668513322192e-06, + "loss": 3.3308, + "step": 2579968 + }, + { + "epoch": 0.02, + "learning_rate": 7.754282565811672e-06, + "loss": 3.3173, + "step": 2580480 + }, + { + "epoch": 0.02, + "learning_rate": 7.745912997104882e-06, + "loss": 3.3206, + "step": 2580992 + }, + { + "epoch": 0.02, + "learning_rate": 7.737527049594364e-06, + "loss": 3.328, + "step": 2581504 + }, + { + "epoch": 0.02, + "learning_rate": 7.729141102083842e-06, + "loss": 3.3267, + "step": 2582016 + }, + { + "epoch": 0.02, + "learning_rate": 7.720755154573322e-06, + "loss": 3.3321, + "step": 2582528 + }, + { + "epoch": 0.02, + "learning_rate": 7.712385585866535e-06, + "loss": 3.3371, + "step": 2583040 + }, + { + "epoch": 0.02, + "learning_rate": 7.704016017159746e-06, + "loss": 3.3204, + "step": 2583552 + }, + { + "epoch": 0.02, + "learning_rate": 7.695630069649226e-06, + "loss": 3.3277, + "step": 2584064 + }, + { + "epoch": 0.02, + "learning_rate": 7.687244122138705e-06, + "loss": 3.3243, + "step": 2584576 + }, + { + "epoch": 0.02, + "learning_rate": 7.678858174628185e-06, + "loss": 3.3447, + "step": 2585088 + }, + { + "epoch": 0.02, + "learning_rate": 7.670472227117665e-06, + "loss": 3.3415, + "step": 2585600 + }, + { + "epoch": 0.02, + "learning_rate": 7.662086279607145e-06, + "loss": 3.3258, + "step": 2586112 + }, + { + "epoch": 0.02, + "learning_rate": 7.653700332096625e-06, + "loss": 3.3283, + "step": 2586624 + }, + { + "epoch": 0.02, + "learning_rate": 7.645330763389836e-06, + "loss": 3.3332, + "step": 2587136 + }, + { + "epoch": 0.02, + "learning_rate": 7.636944815879316e-06, + "loss": 3.3402, + "step": 2587648 + }, + { + "epoch": 0.02, + "learning_rate": 7.628558868368796e-06, + "loss": 3.3366, + "step": 2588160 + }, + { + "epoch": 0.02, + "learning_rate": 7.620172920858276e-06, + "loss": 3.3304, + "step": 2588672 + }, + { + "epoch": 0.02, + "learning_rate": 7.611786973347755e-06, + "loss": 3.3366, + "step": 2589184 + }, + { + "epoch": 0.02, + "learning_rate": 7.603401025837235e-06, + "loss": 3.3341, + "step": 2589696 + }, + { + "epoch": 0.02, + "learning_rate": 7.595015078326716e-06, + "loss": 3.3346, + "step": 2590208 + }, + { + "epoch": 0.02, + "learning_rate": 7.586629130816196e-06, + "loss": 3.3269, + "step": 2590720 + }, + { + "epoch": 0.02, + "learning_rate": 7.578259562109407e-06, + "loss": 3.3307, + "step": 2591232 + }, + { + "epoch": 0.02, + "learning_rate": 7.5698736145988865e-06, + "loss": 3.3264, + "step": 2591744 + }, + { + "epoch": 0.02, + "learning_rate": 7.561504045892098e-06, + "loss": 3.3158, + "step": 2592256 + }, + { + "epoch": 0.02, + "learning_rate": 7.553118098381579e-06, + "loss": 3.3459, + "step": 2592768 + }, + { + "epoch": 0.02, + "learning_rate": 7.544732150871057e-06, + "loss": 3.3303, + "step": 2593280 + }, + { + "epoch": 0.02, + "learning_rate": 7.536346203360538e-06, + "loss": 3.3352, + "step": 2593792 + }, + { + "epoch": 0.02, + "learning_rate": 7.527960255850018e-06, + "loss": 3.3296, + "step": 2594304 + }, + { + "epoch": 0.02, + "learning_rate": 7.519574308339497e-06, + "loss": 3.321, + "step": 2594816 + }, + { + "epoch": 0.03, + "eval_loss": 3.8694188594818115, + "eval_runtime": 303.152, + "eval_samples_per_second": 1258.745, + "eval_steps_per_second": 39.337, + "step": 2594880 + }, + { + "epoch": 0.0, + "learning_rate": 7.511188360828977e-06, + "loss": 3.3299, + "step": 2595328 + }, + { + "epoch": 0.0, + "learning_rate": 7.502802413318458e-06, + "loss": 3.3267, + "step": 2595840 + }, + { + "epoch": 0.0, + "learning_rate": 7.494416465807937e-06, + "loss": 3.3419, + "step": 2596352 + }, + { + "epoch": 0.0, + "learning_rate": 7.486030518297417e-06, + "loss": 3.3269, + "step": 2596864 + }, + { + "epoch": 0.0, + "learning_rate": 7.4776609495906286e-06, + "loss": 3.3423, + "step": 2597376 + }, + { + "epoch": 0.0, + "learning_rate": 7.4692750020801085e-06, + "loss": 3.3246, + "step": 2597888 + }, + { + "epoch": 0.0, + "learning_rate": 7.460889054569588e-06, + "loss": 3.3233, + "step": 2598400 + }, + { + "epoch": 0.0, + "learning_rate": 7.452519485862799e-06, + "loss": 3.3208, + "step": 2598912 + }, + { + "epoch": 0.0, + "learning_rate": 7.44413353835228e-06, + "loss": 3.3336, + "step": 2599424 + }, + { + "epoch": 0.0, + "learning_rate": 7.43574759084176e-06, + "loss": 3.3293, + "step": 2599936 + }, + { + "epoch": 0.0, + "learning_rate": 7.427361643331239e-06, + "loss": 3.3395, + "step": 2600448 + }, + { + "epoch": 0.0, + "learning_rate": 7.418992074624451e-06, + "loss": 3.3354, + "step": 2600960 + }, + { + "epoch": 0.0, + "learning_rate": 7.410606127113931e-06, + "loss": 3.3235, + "step": 2601472 + }, + { + "epoch": 0.0, + "learning_rate": 7.40222017960341e-06, + "loss": 3.3252, + "step": 2601984 + }, + { + "epoch": 0.0, + "learning_rate": 7.393834232092891e-06, + "loss": 3.3217, + "step": 2602496 + }, + { + "epoch": 0.0, + "learning_rate": 7.385464663386102e-06, + "loss": 3.3228, + "step": 2603008 + }, + { + "epoch": 0.0, + "learning_rate": 7.377078715875582e-06, + "loss": 3.3249, + "step": 2603520 + }, + { + "epoch": 0.0, + "learning_rate": 7.368692768365061e-06, + "loss": 3.324, + "step": 2604032 + }, + { + "epoch": 0.0, + "learning_rate": 7.360306820854541e-06, + "loss": 3.3224, + "step": 2604544 + }, + { + "epoch": 0.0, + "learning_rate": 7.351937252147753e-06, + "loss": 3.3389, + "step": 2605056 + }, + { + "epoch": 0.0, + "learning_rate": 7.343551304637234e-06, + "loss": 3.3253, + "step": 2605568 + }, + { + "epoch": 0.0, + "learning_rate": 7.335165357126712e-06, + "loss": 3.3274, + "step": 2606080 + }, + { + "epoch": 0.0, + "learning_rate": 7.326779409616193e-06, + "loss": 3.3278, + "step": 2606592 + }, + { + "epoch": 0.0, + "learning_rate": 7.3184098409094044e-06, + "loss": 3.3336, + "step": 2607104 + }, + { + "epoch": 0.0, + "learning_rate": 7.3100238933988835e-06, + "loss": 3.3256, + "step": 2607616 + }, + { + "epoch": 0.0, + "learning_rate": 7.3016379458883635e-06, + "loss": 3.3264, + "step": 2608128 + }, + { + "epoch": 0.0, + "learning_rate": 7.2932519983778435e-06, + "loss": 3.3265, + "step": 2608640 + }, + { + "epoch": 0.0, + "learning_rate": 7.284866050867324e-06, + "loss": 3.3252, + "step": 2609152 + }, + { + "epoch": 0.0, + "learning_rate": 7.276480103356803e-06, + "loss": 3.3156, + "step": 2609664 + }, + { + "epoch": 0.01, + "learning_rate": 7.268094155846283e-06, + "loss": 3.3275, + "step": 2610176 + }, + { + "epoch": 0.01, + "learning_rate": 7.259708208335764e-06, + "loss": 3.3289, + "step": 2610688 + }, + { + "epoch": 0.01, + "learning_rate": 7.251338639628974e-06, + "loss": 3.3282, + "step": 2611200 + }, + { + "epoch": 0.01, + "learning_rate": 7.242969070922186e-06, + "loss": 3.3351, + "step": 2611712 + }, + { + "epoch": 0.01, + "learning_rate": 7.234583123411666e-06, + "loss": 3.3245, + "step": 2612224 + }, + { + "epoch": 0.01, + "learning_rate": 7.2261971759011465e-06, + "loss": 3.3197, + "step": 2612736 + }, + { + "epoch": 0.01, + "learning_rate": 7.217827607194356e-06, + "loss": 3.3277, + "step": 2613248 + }, + { + "epoch": 0.01, + "learning_rate": 7.209441659683837e-06, + "loss": 3.3181, + "step": 2613760 + }, + { + "epoch": 0.01, + "learning_rate": 7.201055712173317e-06, + "loss": 3.3221, + "step": 2614272 + }, + { + "epoch": 0.01, + "learning_rate": 7.192669764662797e-06, + "loss": 3.3108, + "step": 2614784 + }, + { + "epoch": 0.01, + "learning_rate": 7.184283817152276e-06, + "loss": 3.3182, + "step": 2615296 + }, + { + "epoch": 0.01, + "learning_rate": 7.175897869641757e-06, + "loss": 3.3274, + "step": 2615808 + }, + { + "epoch": 0.01, + "learning_rate": 7.167511922131237e-06, + "loss": 3.3331, + "step": 2616320 + }, + { + "epoch": 0.01, + "learning_rate": 7.159125974620716e-06, + "loss": 3.3269, + "step": 2616832 + }, + { + "epoch": 0.01, + "learning_rate": 7.150756405913928e-06, + "loss": 3.321, + "step": 2617344 + }, + { + "epoch": 0.01, + "learning_rate": 7.142370458403408e-06, + "loss": 3.3353, + "step": 2617856 + }, + { + "epoch": 0.01, + "learning_rate": 7.1339845108928885e-06, + "loss": 3.3246, + "step": 2618368 + }, + { + "epoch": 0.01, + "learning_rate": 7.125598563382367e-06, + "loss": 3.3191, + "step": 2618880 + }, + { + "epoch": 0.01, + "learning_rate": 7.117228994675578e-06, + "loss": 3.324, + "step": 2619392 + }, + { + "epoch": 0.01, + "learning_rate": 7.10885942596879e-06, + "loss": 3.3102, + "step": 2619904 + }, + { + "epoch": 0.01, + "learning_rate": 7.100473478458271e-06, + "loss": 3.3277, + "step": 2620416 + }, + { + "epoch": 0.01, + "learning_rate": 7.09208753094775e-06, + "loss": 3.3221, + "step": 2620928 + }, + { + "epoch": 0.01, + "learning_rate": 7.08370158343723e-06, + "loss": 3.3206, + "step": 2621440 + }, + { + "epoch": 0.01, + "learning_rate": 7.075315635926711e-06, + "loss": 3.3205, + "step": 2621952 + }, + { + "epoch": 0.01, + "learning_rate": 7.066929688416189e-06, + "loss": 3.3208, + "step": 2622464 + }, + { + "epoch": 0.01, + "learning_rate": 7.05854374090567e-06, + "loss": 3.3087, + "step": 2622976 + }, + { + "epoch": 0.01, + "learning_rate": 7.05015779339515e-06, + "loss": 3.3322, + "step": 2623488 + }, + { + "epoch": 0.01, + "learning_rate": 7.041788224688361e-06, + "loss": 3.3179, + "step": 2624000 + }, + { + "epoch": 0.01, + "learning_rate": 7.0334022771778405e-06, + "loss": 3.3372, + "step": 2624512 + }, + { + "epoch": 0.01, + "learning_rate": 7.02501632966732e-06, + "loss": 3.3208, + "step": 2625024 + }, + { + "epoch": 0.01, + "learning_rate": 7.016630382156801e-06, + "loss": 3.3165, + "step": 2625536 + }, + { + "epoch": 0.01, + "learning_rate": 7.008260813450011e-06, + "loss": 3.3171, + "step": 2626048 + }, + { + "epoch": 0.01, + "learning_rate": 6.999874865939492e-06, + "loss": 3.3255, + "step": 2626560 + }, + { + "epoch": 0.01, + "learning_rate": 6.991488918428972e-06, + "loss": 3.3093, + "step": 2627072 + }, + { + "epoch": 0.01, + "learning_rate": 6.983102970918451e-06, + "loss": 3.3144, + "step": 2627584 + }, + { + "epoch": 0.01, + "learning_rate": 6.9747497810153935e-06, + "loss": 3.3228, + "step": 2628096 + }, + { + "epoch": 0.01, + "learning_rate": 6.966363833504874e-06, + "loss": 3.3207, + "step": 2628608 + }, + { + "epoch": 0.01, + "learning_rate": 6.957977885994354e-06, + "loss": 3.3141, + "step": 2629120 + }, + { + "epoch": 0.01, + "learning_rate": 6.949591938483833e-06, + "loss": 3.3093, + "step": 2629632 + }, + { + "epoch": 0.01, + "learning_rate": 6.941205990973313e-06, + "loss": 3.3129, + "step": 2630144 + }, + { + "epoch": 0.01, + "learning_rate": 6.932820043462794e-06, + "loss": 3.3318, + "step": 2630656 + }, + { + "epoch": 0.01, + "learning_rate": 6.924434095952274e-06, + "loss": 3.3192, + "step": 2631168 + }, + { + "epoch": 0.01, + "learning_rate": 6.916048148441753e-06, + "loss": 3.3193, + "step": 2631680 + }, + { + "epoch": 0.01, + "learning_rate": 6.907678579734965e-06, + "loss": 3.3298, + "step": 2632192 + }, + { + "epoch": 0.01, + "learning_rate": 6.899292632224446e-06, + "loss": 3.3225, + "step": 2632704 + }, + { + "epoch": 0.01, + "learning_rate": 6.890906684713924e-06, + "loss": 3.3286, + "step": 2633216 + }, + { + "epoch": 0.01, + "learning_rate": 6.8825371160071355e-06, + "loss": 3.3106, + "step": 2633728 + }, + { + "epoch": 0.01, + "learning_rate": 6.874151168496616e-06, + "loss": 3.3313, + "step": 2634240 + }, + { + "epoch": 0.01, + "learning_rate": 6.865765220986096e-06, + "loss": 3.3232, + "step": 2634752 + }, + { + "epoch": 0.01, + "learning_rate": 6.857379273475575e-06, + "loss": 3.3179, + "step": 2635264 + }, + { + "epoch": 0.01, + "learning_rate": 6.849009704768787e-06, + "loss": 3.3287, + "step": 2635776 + }, + { + "epoch": 0.01, + "learning_rate": 6.840623757258267e-06, + "loss": 3.3264, + "step": 2636288 + }, + { + "epoch": 0.01, + "learning_rate": 6.832237809747748e-06, + "loss": 3.3264, + "step": 2636800 + }, + { + "epoch": 0.01, + "learning_rate": 6.823868241040958e-06, + "loss": 3.323, + "step": 2637312 + }, + { + "epoch": 0.01, + "learning_rate": 6.8154822935304385e-06, + "loss": 3.3082, + "step": 2637824 + }, + { + "epoch": 0.01, + "learning_rate": 6.8070963460199185e-06, + "loss": 3.3153, + "step": 2638336 + }, + { + "epoch": 0.01, + "learning_rate": 6.798710398509398e-06, + "loss": 3.3179, + "step": 2638848 + }, + { + "epoch": 0.01, + "learning_rate": 6.790340829802609e-06, + "loss": 3.3258, + "step": 2639360 + }, + { + "epoch": 0.01, + "learning_rate": 6.781954882292089e-06, + "loss": 3.3234, + "step": 2639872 + }, + { + "epoch": 0.01, + "learning_rate": 6.77356893478157e-06, + "loss": 3.3225, + "step": 2640384 + }, + { + "epoch": 0.02, + "learning_rate": 6.765182987271049e-06, + "loss": 3.3237, + "step": 2640896 + }, + { + "epoch": 0.02, + "learning_rate": 6.756797039760529e-06, + "loss": 3.3203, + "step": 2641408 + }, + { + "epoch": 0.02, + "learning_rate": 6.748411092250009e-06, + "loss": 3.3209, + "step": 2641920 + }, + { + "epoch": 0.02, + "learning_rate": 6.740025144739488e-06, + "loss": 3.3207, + "step": 2642432 + }, + { + "epoch": 0.02, + "learning_rate": 6.731639197228969e-06, + "loss": 3.3237, + "step": 2642944 + }, + { + "epoch": 0.02, + "learning_rate": 6.7232696285221806e-06, + "loss": 3.3306, + "step": 2643456 + }, + { + "epoch": 0.02, + "learning_rate": 6.7148836810116605e-06, + "loss": 3.321, + "step": 2643968 + }, + { + "epoch": 0.02, + "learning_rate": 6.70649773350114e-06, + "loss": 3.3204, + "step": 2644480 + }, + { + "epoch": 0.02, + "learning_rate": 6.69811178599062e-06, + "loss": 3.3295, + "step": 2644992 + }, + { + "epoch": 0.02, + "learning_rate": 6.689742217283831e-06, + "loss": 3.3275, + "step": 2645504 + }, + { + "epoch": 0.02, + "learning_rate": 6.681356269773312e-06, + "loss": 3.3303, + "step": 2646016 + }, + { + "epoch": 0.02, + "learning_rate": 6.67297032226279e-06, + "loss": 3.3219, + "step": 2646528 + }, + { + "epoch": 0.02, + "learning_rate": 6.664584374752271e-06, + "loss": 3.3162, + "step": 2647040 + }, + { + "epoch": 0.02, + "learning_rate": 6.656214806045483e-06, + "loss": 3.3236, + "step": 2647552 + }, + { + "epoch": 0.02, + "learning_rate": 6.647828858534962e-06, + "loss": 3.326, + "step": 2648064 + }, + { + "epoch": 0.02, + "learning_rate": 6.639442911024442e-06, + "loss": 3.3033, + "step": 2648576 + }, + { + "epoch": 0.02, + "learning_rate": 6.631056963513923e-06, + "loss": 3.3191, + "step": 2649088 + }, + { + "epoch": 0.02, + "learning_rate": 6.622687394807134e-06, + "loss": 3.3292, + "step": 2649600 + }, + { + "epoch": 0.02, + "learning_rate": 6.6143014472966125e-06, + "loss": 3.3208, + "step": 2650112 + }, + { + "epoch": 0.02, + "learning_rate": 6.605915499786093e-06, + "loss": 3.3113, + "step": 2650624 + }, + { + "epoch": 0.02, + "learning_rate": 6.597545931079305e-06, + "loss": 3.3135, + "step": 2651136 + }, + { + "epoch": 0.02, + "learning_rate": 6.589159983568785e-06, + "loss": 3.3195, + "step": 2651648 + }, + { + "epoch": 0.02, + "learning_rate": 6.580774036058264e-06, + "loss": 3.3348, + "step": 2652160 + }, + { + "epoch": 0.02, + "learning_rate": 6.572388088547744e-06, + "loss": 3.3199, + "step": 2652672 + }, + { + "epoch": 0.02, + "learning_rate": 6.564018519840956e-06, + "loss": 3.3296, + "step": 2653184 + }, + { + "epoch": 0.02, + "learning_rate": 6.555632572330435e-06, + "loss": 3.3255, + "step": 2653696 + }, + { + "epoch": 0.02, + "learning_rate": 6.5472466248199155e-06, + "loss": 3.3356, + "step": 2654208 + }, + { + "epoch": 0.02, + "learning_rate": 6.5388606773093955e-06, + "loss": 3.316, + "step": 2654720 + }, + { + "epoch": 0.02, + "learning_rate": 6.530491108602607e-06, + "loss": 3.3197, + "step": 2655232 + }, + { + "epoch": 0.02, + "learning_rate": 6.522105161092086e-06, + "loss": 3.3238, + "step": 2655744 + }, + { + "epoch": 0.02, + "learning_rate": 6.513719213581566e-06, + "loss": 3.3213, + "step": 2656256 + }, + { + "epoch": 0.02, + "learning_rate": 6.505333266071047e-06, + "loss": 3.309, + "step": 2656768 + }, + { + "epoch": 0.02, + "learning_rate": 6.496963697364259e-06, + "loss": 3.3112, + "step": 2657280 + }, + { + "epoch": 0.02, + "learning_rate": 6.488577749853737e-06, + "loss": 3.3174, + "step": 2657792 + }, + { + "epoch": 0.02, + "learning_rate": 6.480191802343218e-06, + "loss": 3.3182, + "step": 2658304 + }, + { + "epoch": 0.02, + "learning_rate": 6.471805854832698e-06, + "loss": 3.3252, + "step": 2658816 + }, + { + "epoch": 0.02, + "learning_rate": 6.463436286125908e-06, + "loss": 3.3299, + "step": 2659328 + }, + { + "epoch": 0.02, + "learning_rate": 6.45506671741912e-06, + "loss": 3.3099, + "step": 2659840 + }, + { + "epoch": 0.02, + "learning_rate": 6.4466807699086e-06, + "loss": 3.315, + "step": 2660352 + }, + { + "epoch": 0.02, + "learning_rate": 6.438294822398081e-06, + "loss": 3.3162, + "step": 2660864 + }, + { + "epoch": 0.02, + "learning_rate": 6.429908874887559e-06, + "loss": 3.3315, + "step": 2661376 + }, + { + "epoch": 0.02, + "learning_rate": 6.421539306180771e-06, + "loss": 3.3377, + "step": 2661888 + }, + { + "epoch": 0.02, + "learning_rate": 6.4131533586702515e-06, + "loss": 3.3207, + "step": 2662400 + }, + { + "epoch": 0.02, + "learning_rate": 6.4047674111597315e-06, + "loss": 3.3145, + "step": 2662912 + }, + { + "epoch": 0.02, + "learning_rate": 6.396381463649211e-06, + "loss": 3.3236, + "step": 2663424 + }, + { + "epoch": 0.02, + "learning_rate": 6.3879955161386905e-06, + "loss": 3.3282, + "step": 2663936 + }, + { + "epoch": 0.02, + "learning_rate": 6.379609568628171e-06, + "loss": 3.3265, + "step": 2664448 + }, + { + "epoch": 0.02, + "learning_rate": 6.3712236211176505e-06, + "loss": 3.3195, + "step": 2664960 + }, + { + "epoch": 0.02, + "learning_rate": 6.36283767360713e-06, + "loss": 3.3267, + "step": 2665472 + }, + { + "epoch": 0.02, + "learning_rate": 6.354468104900342e-06, + "loss": 3.3248, + "step": 2665984 + }, + { + "epoch": 0.02, + "learning_rate": 6.346082157389821e-06, + "loss": 3.3312, + "step": 2666496 + }, + { + "epoch": 0.02, + "learning_rate": 6.337696209879301e-06, + "loss": 3.3189, + "step": 2667008 + }, + { + "epoch": 0.02, + "learning_rate": 6.329310262368782e-06, + "loss": 3.3183, + "step": 2667520 + }, + { + "epoch": 0.02, + "learning_rate": 6.320924314858262e-06, + "loss": 3.3199, + "step": 2668032 + }, + { + "epoch": 0.02, + "learning_rate": 6.312554746151473e-06, + "loss": 3.3029, + "step": 2668544 + }, + { + "epoch": 0.02, + "learning_rate": 6.304168798640953e-06, + "loss": 3.3358, + "step": 2669056 + }, + { + "epoch": 0.02, + "learning_rate": 6.2957828511304326e-06, + "loss": 3.322, + "step": 2669568 + }, + { + "epoch": 0.02, + "learning_rate": 6.287396903619912e-06, + "loss": 3.3255, + "step": 2670080 + }, + { + "epoch": 0.02, + "learning_rate": 6.2790109561093925e-06, + "loss": 3.3229, + "step": 2670592 + }, + { + "epoch": 0.02, + "learning_rate": 6.2706250085988724e-06, + "loss": 3.3106, + "step": 2671104 + }, + { + "epoch": 0.03, + "eval_loss": 3.870218515396118, + "eval_runtime": 303.2028, + "eval_samples_per_second": 1258.534, + "eval_steps_per_second": 39.33, + "step": 2671200 + }, + { + "epoch": 1.0, + "learning_rate": 6.262239061088352e-06, + "loss": 3.3204, + "step": 2671616 + }, + { + "epoch": 1.0, + "learning_rate": 6.2538531135778315e-06, + "loss": 3.3155, + "step": 2672128 + }, + { + "epoch": 1.0, + "learning_rate": 6.245483544871043e-06, + "loss": 3.3304, + "step": 2672640 + }, + { + "epoch": 1.0, + "learning_rate": 6.237097597360524e-06, + "loss": 3.319, + "step": 2673152 + }, + { + "epoch": 1.0, + "learning_rate": 6.228711649850003e-06, + "loss": 3.3412, + "step": 2673664 + }, + { + "epoch": 1.0, + "learning_rate": 6.220325702339483e-06, + "loss": 3.3103, + "step": 2674176 + }, + { + "epoch": 1.0, + "learning_rate": 6.211956133632695e-06, + "loss": 3.3205, + "step": 2674688 + }, + { + "epoch": 1.0, + "learning_rate": 6.203570186122174e-06, + "loss": 3.3058, + "step": 2675200 + }, + { + "epoch": 1.0, + "learning_rate": 6.1951842386116546e-06, + "loss": 3.3254, + "step": 2675712 + }, + { + "epoch": 1.0, + "learning_rate": 6.186798291101134e-06, + "loss": 3.3218, + "step": 2676224 + }, + { + "epoch": 1.0, + "learning_rate": 6.178428722394346e-06, + "loss": 3.3244, + "step": 2676736 + }, + { + "epoch": 1.0, + "learning_rate": 6.170042774883825e-06, + "loss": 3.3345, + "step": 2677248 + }, + { + "epoch": 1.0, + "learning_rate": 6.161656827373306e-06, + "loss": 3.3118, + "step": 2677760 + }, + { + "epoch": 1.0, + "learning_rate": 6.153270879862785e-06, + "loss": 3.3172, + "step": 2678272 + }, + { + "epoch": 1.0, + "learning_rate": 6.144901311155997e-06, + "loss": 3.3128, + "step": 2678784 + }, + { + "epoch": 1.0, + "learning_rate": 6.136515363645477e-06, + "loss": 3.3152, + "step": 2679296 + }, + { + "epoch": 1.0, + "learning_rate": 6.128129416134956e-06, + "loss": 3.3143, + "step": 2679808 + }, + { + "epoch": 1.0, + "learning_rate": 6.119743468624437e-06, + "loss": 3.3131, + "step": 2680320 + }, + { + "epoch": 1.0, + "learning_rate": 6.1113738999176475e-06, + "loss": 3.3164, + "step": 2680832 + }, + { + "epoch": 1.0, + "learning_rate": 6.102987952407127e-06, + "loss": 3.3289, + "step": 2681344 + }, + { + "epoch": 1.0, + "learning_rate": 6.094602004896607e-06, + "loss": 3.3176, + "step": 2681856 + }, + { + "epoch": 1.0, + "learning_rate": 6.086216057386087e-06, + "loss": 3.3177, + "step": 2682368 + }, + { + "epoch": 1.0, + "learning_rate": 6.077846488679299e-06, + "loss": 3.3228, + "step": 2682880 + }, + { + "epoch": 1.0, + "learning_rate": 6.069460541168779e-06, + "loss": 3.3253, + "step": 2683392 + }, + { + "epoch": 1.0, + "learning_rate": 6.061074593658259e-06, + "loss": 3.3152, + "step": 2683904 + }, + { + "epoch": 1.0, + "learning_rate": 6.052688646147738e-06, + "loss": 3.3186, + "step": 2684416 + }, + { + "epoch": 1.0, + "learning_rate": 6.044302698637219e-06, + "loss": 3.3162, + "step": 2684928 + }, + { + "epoch": 1.0, + "learning_rate": 6.035916751126698e-06, + "loss": 3.3139, + "step": 2685440 + }, + { + "epoch": 1.0, + "learning_rate": 6.027530803616178e-06, + "loss": 3.3092, + "step": 2685952 + }, + { + "epoch": 1.01, + "learning_rate": 6.0191612349093895e-06, + "loss": 3.3127, + "step": 2686464 + }, + { + "epoch": 1.01, + "learning_rate": 6.0107752873988694e-06, + "loss": 3.3248, + "step": 2686976 + }, + { + "epoch": 1.01, + "learning_rate": 6.002389339888349e-06, + "loss": 3.3167, + "step": 2687488 + }, + { + "epoch": 1.01, + "learning_rate": 5.994003392377829e-06, + "loss": 3.3282, + "step": 2688000 + }, + { + "epoch": 1.01, + "learning_rate": 5.985633823671041e-06, + "loss": 3.3167, + "step": 2688512 + }, + { + "epoch": 1.01, + "learning_rate": 5.97724787616052e-06, + "loss": 3.3118, + "step": 2689024 + }, + { + "epoch": 1.01, + "learning_rate": 5.968861928650001e-06, + "loss": 3.3156, + "step": 2689536 + }, + { + "epoch": 1.01, + "learning_rate": 5.960492359943212e-06, + "loss": 3.3126, + "step": 2690048 + }, + { + "epoch": 1.01, + "learning_rate": 5.952106412432692e-06, + "loss": 3.3107, + "step": 2690560 + }, + { + "epoch": 1.01, + "learning_rate": 5.943720464922172e-06, + "loss": 3.3047, + "step": 2691072 + }, + { + "epoch": 1.01, + "learning_rate": 5.935334517411651e-06, + "loss": 3.3076, + "step": 2691584 + }, + { + "epoch": 1.01, + "learning_rate": 5.9269485699011315e-06, + "loss": 3.3199, + "step": 2692096 + }, + { + "epoch": 1.01, + "learning_rate": 5.918562622390611e-06, + "loss": 3.3224, + "step": 2692608 + }, + { + "epoch": 1.01, + "learning_rate": 5.9101766748800914e-06, + "loss": 3.3174, + "step": 2693120 + }, + { + "epoch": 1.01, + "learning_rate": 5.901807106173302e-06, + "loss": 3.3157, + "step": 2693632 + }, + { + "epoch": 1.01, + "learning_rate": 5.893421158662782e-06, + "loss": 3.3299, + "step": 2694144 + }, + { + "epoch": 1.01, + "learning_rate": 5.885035211152262e-06, + "loss": 3.3157, + "step": 2694656 + }, + { + "epoch": 1.01, + "learning_rate": 5.876649263641742e-06, + "loss": 3.3119, + "step": 2695168 + }, + { + "epoch": 1.01, + "learning_rate": 5.868279694934954e-06, + "loss": 3.3104, + "step": 2695680 + }, + { + "epoch": 1.01, + "learning_rate": 5.859893747424433e-06, + "loss": 3.3001, + "step": 2696192 + }, + { + "epoch": 1.01, + "learning_rate": 5.851507799913914e-06, + "loss": 3.3228, + "step": 2696704 + }, + { + "epoch": 1.01, + "learning_rate": 5.843121852403393e-06, + "loss": 3.31, + "step": 2697216 + }, + { + "epoch": 1.01, + "learning_rate": 5.834752283696604e-06, + "loss": 3.3143, + "step": 2697728 + }, + { + "epoch": 1.01, + "learning_rate": 5.826366336186084e-06, + "loss": 3.3088, + "step": 2698240 + }, + { + "epoch": 1.01, + "learning_rate": 5.817980388675564e-06, + "loss": 3.3174, + "step": 2698752 + }, + { + "epoch": 1.01, + "learning_rate": 5.809594441165044e-06, + "loss": 3.2976, + "step": 2699264 + }, + { + "epoch": 1.01, + "learning_rate": 5.801224872458256e-06, + "loss": 3.3211, + "step": 2699776 + }, + { + "epoch": 1.01, + "learning_rate": 5.792838924947736e-06, + "loss": 3.3113, + "step": 2700288 + }, + { + "epoch": 1.01, + "learning_rate": 5.784452977437215e-06, + "loss": 3.3235, + "step": 2700800 + }, + { + "epoch": 1.01, + "learning_rate": 5.776067029926696e-06, + "loss": 3.3166, + "step": 2701312 + }, + { + "epoch": 1.01, + "learning_rate": 5.7676974612199065e-06, + "loss": 3.305, + "step": 2701824 + }, + { + "epoch": 1.01, + "learning_rate": 5.759327892513118e-06, + "loss": 3.3053, + "step": 2702336 + }, + { + "epoch": 1.01, + "learning_rate": 5.750941945002597e-06, + "loss": 3.3219, + "step": 2702848 + }, + { + "epoch": 1.01, + "learning_rate": 5.742555997492078e-06, + "loss": 3.301, + "step": 2703360 + }, + { + "epoch": 1.01, + "learning_rate": 5.734170049981557e-06, + "loss": 3.3025, + "step": 2703872 + }, + { + "epoch": 1.01, + "learning_rate": 5.725784102471038e-06, + "loss": 3.3166, + "step": 2704384 + }, + { + "epoch": 1.01, + "learning_rate": 5.717398154960517e-06, + "loss": 3.3163, + "step": 2704896 + }, + { + "epoch": 1.01, + "learning_rate": 5.709012207449997e-06, + "loss": 3.3036, + "step": 2705408 + }, + { + "epoch": 1.01, + "learning_rate": 5.700626259939478e-06, + "loss": 3.3048, + "step": 2705920 + }, + { + "epoch": 1.01, + "learning_rate": 5.692256691232689e-06, + "loss": 3.3007, + "step": 2706432 + }, + { + "epoch": 1.01, + "learning_rate": 5.683870743722169e-06, + "loss": 3.3206, + "step": 2706944 + }, + { + "epoch": 1.01, + "learning_rate": 5.6754847962116486e-06, + "loss": 3.3096, + "step": 2707456 + }, + { + "epoch": 1.01, + "learning_rate": 5.6670988487011285e-06, + "loss": 3.3087, + "step": 2707968 + }, + { + "epoch": 1.01, + "learning_rate": 5.658729279994339e-06, + "loss": 3.3201, + "step": 2708480 + }, + { + "epoch": 1.01, + "learning_rate": 5.65034333248382e-06, + "loss": 3.3159, + "step": 2708992 + }, + { + "epoch": 1.01, + "learning_rate": 5.641957384973299e-06, + "loss": 3.3228, + "step": 2709504 + }, + { + "epoch": 1.01, + "learning_rate": 5.633587816266511e-06, + "loss": 3.3036, + "step": 2710016 + }, + { + "epoch": 1.01, + "learning_rate": 5.625201868755991e-06, + "loss": 3.3178, + "step": 2710528 + }, + { + "epoch": 1.01, + "learning_rate": 5.616815921245471e-06, + "loss": 3.3134, + "step": 2711040 + }, + { + "epoch": 1.01, + "learning_rate": 5.608429973734951e-06, + "loss": 3.3083, + "step": 2711552 + }, + { + "epoch": 1.01, + "learning_rate": 5.6000604050281615e-06, + "loss": 3.3249, + "step": 2712064 + }, + { + "epoch": 1.01, + "learning_rate": 5.591674457517642e-06, + "loss": 3.3157, + "step": 2712576 + }, + { + "epoch": 1.01, + "learning_rate": 5.5832885100071214e-06, + "loss": 3.3186, + "step": 2713088 + }, + { + "epoch": 1.01, + "learning_rate": 5.574918941300333e-06, + "loss": 3.3142, + "step": 2713600 + }, + { + "epoch": 1.01, + "learning_rate": 5.566532993789813e-06, + "loss": 3.3026, + "step": 2714112 + }, + { + "epoch": 1.01, + "learning_rate": 5.558147046279293e-06, + "loss": 3.3068, + "step": 2714624 + }, + { + "epoch": 1.01, + "learning_rate": 5.549761098768773e-06, + "loss": 3.3077, + "step": 2715136 + }, + { + "epoch": 1.01, + "learning_rate": 5.541391530061985e-06, + "loss": 3.3116, + "step": 2715648 + }, + { + "epoch": 1.01, + "learning_rate": 5.5330055825514645e-06, + "loss": 3.3165, + "step": 2716160 + }, + { + "epoch": 1.01, + "learning_rate": 5.524619635040944e-06, + "loss": 3.3105, + "step": 2716672 + }, + { + "epoch": 1.02, + "learning_rate": 5.5162336875304244e-06, + "loss": 3.3163, + "step": 2717184 + }, + { + "epoch": 1.02, + "learning_rate": 5.5078477400199036e-06, + "loss": 3.3163, + "step": 2717696 + }, + { + "epoch": 1.02, + "learning_rate": 5.499461792509384e-06, + "loss": 3.3082, + "step": 2718208 + }, + { + "epoch": 1.02, + "learning_rate": 5.4910758449988635e-06, + "loss": 3.3117, + "step": 2718720 + }, + { + "epoch": 1.02, + "learning_rate": 5.4826898974883434e-06, + "loss": 3.3145, + "step": 2719232 + }, + { + "epoch": 1.02, + "learning_rate": 5.474320328781555e-06, + "loss": 3.3252, + "step": 2719744 + }, + { + "epoch": 1.02, + "learning_rate": 5.465934381271034e-06, + "loss": 3.3133, + "step": 2720256 + }, + { + "epoch": 1.02, + "learning_rate": 5.457548433760515e-06, + "loss": 3.3124, + "step": 2720768 + }, + { + "epoch": 1.02, + "learning_rate": 5.449162486249994e-06, + "loss": 3.3177, + "step": 2721280 + }, + { + "epoch": 1.02, + "learning_rate": 5.440792917543206e-06, + "loss": 3.3152, + "step": 2721792 + }, + { + "epoch": 1.02, + "learning_rate": 5.432406970032686e-06, + "loss": 3.3216, + "step": 2722304 + }, + { + "epoch": 1.02, + "learning_rate": 5.424021022522166e-06, + "loss": 3.3125, + "step": 2722816 + }, + { + "epoch": 1.02, + "learning_rate": 5.415635075011646e-06, + "loss": 3.3117, + "step": 2723328 + }, + { + "epoch": 1.02, + "learning_rate": 5.407265506304856e-06, + "loss": 3.3133, + "step": 2723840 + }, + { + "epoch": 1.02, + "learning_rate": 5.398879558794337e-06, + "loss": 3.3172, + "step": 2724352 + }, + { + "epoch": 1.02, + "learning_rate": 5.390493611283816e-06, + "loss": 3.2963, + "step": 2724864 + }, + { + "epoch": 1.02, + "learning_rate": 5.382107663773297e-06, + "loss": 3.308, + "step": 2725376 + }, + { + "epoch": 1.02, + "learning_rate": 5.373738095066508e-06, + "loss": 3.32, + "step": 2725888 + }, + { + "epoch": 1.02, + "learning_rate": 5.365352147555988e-06, + "loss": 3.3094, + "step": 2726400 + }, + { + "epoch": 1.02, + "learning_rate": 5.356966200045468e-06, + "loss": 3.3002, + "step": 2726912 + }, + { + "epoch": 1.02, + "learning_rate": 5.3485966313386794e-06, + "loss": 3.3078, + "step": 2727424 + }, + { + "epoch": 1.02, + "learning_rate": 5.340210683828159e-06, + "loss": 3.3098, + "step": 2727936 + }, + { + "epoch": 1.02, + "learning_rate": 5.3318247363176385e-06, + "loss": 3.3286, + "step": 2728448 + }, + { + "epoch": 1.02, + "learning_rate": 5.323438788807119e-06, + "loss": 3.3056, + "step": 2728960 + }, + { + "epoch": 1.02, + "learning_rate": 5.31506922010033e-06, + "loss": 3.3197, + "step": 2729472 + }, + { + "epoch": 1.02, + "learning_rate": 5.30668327258981e-06, + "loss": 3.3165, + "step": 2729984 + }, + { + "epoch": 1.02, + "learning_rate": 5.29829732507929e-06, + "loss": 3.3292, + "step": 2730496 + }, + { + "epoch": 1.02, + "learning_rate": 5.28991137756877e-06, + "loss": 3.3101, + "step": 2731008 + }, + { + "epoch": 1.02, + "learning_rate": 5.28152543005825e-06, + "loss": 3.3064, + "step": 2731520 + }, + { + "epoch": 1.02, + "learning_rate": 5.273139482547729e-06, + "loss": 3.3188, + "step": 2732032 + }, + { + "epoch": 1.02, + "learning_rate": 5.26475353503721e-06, + "loss": 3.314, + "step": 2732544 + }, + { + "epoch": 1.02, + "learning_rate": 5.256367587526689e-06, + "loss": 3.2998, + "step": 2733056 + }, + { + "epoch": 1.02, + "learning_rate": 5.247998018819901e-06, + "loss": 3.3022, + "step": 2733568 + }, + { + "epoch": 1.02, + "learning_rate": 5.2396120713093805e-06, + "loss": 3.3105, + "step": 2734080 + }, + { + "epoch": 1.02, + "learning_rate": 5.231226123798861e-06, + "loss": 3.3116, + "step": 2734592 + }, + { + "epoch": 1.02, + "learning_rate": 5.2228401762883404e-06, + "loss": 3.3116, + "step": 2735104 + }, + { + "epoch": 1.02, + "learning_rate": 5.214470607581552e-06, + "loss": 3.325, + "step": 2735616 + }, + { + "epoch": 1.02, + "learning_rate": 5.206084660071032e-06, + "loss": 3.3016, + "step": 2736128 + }, + { + "epoch": 1.02, + "learning_rate": 5.197715091364244e-06, + "loss": 3.3065, + "step": 2736640 + }, + { + "epoch": 1.02, + "learning_rate": 5.189329143853723e-06, + "loss": 3.305, + "step": 2737152 + }, + { + "epoch": 1.02, + "learning_rate": 5.180943196343203e-06, + "loss": 3.3249, + "step": 2737664 + }, + { + "epoch": 1.02, + "learning_rate": 5.172557248832683e-06, + "loss": 3.3274, + "step": 2738176 + }, + { + "epoch": 1.02, + "learning_rate": 5.164171301322163e-06, + "loss": 3.3124, + "step": 2738688 + }, + { + "epoch": 1.02, + "learning_rate": 5.155785353811643e-06, + "loss": 3.3054, + "step": 2739200 + }, + { + "epoch": 1.02, + "learning_rate": 5.147415785104854e-06, + "loss": 3.3175, + "step": 2739712 + }, + { + "epoch": 1.02, + "learning_rate": 5.139029837594334e-06, + "loss": 3.3179, + "step": 2740224 + }, + { + "epoch": 1.02, + "learning_rate": 5.130643890083814e-06, + "loss": 3.3158, + "step": 2740736 + }, + { + "epoch": 1.02, + "learning_rate": 5.122257942573293e-06, + "loss": 3.3135, + "step": 2741248 + }, + { + "epoch": 1.02, + "learning_rate": 5.113871995062774e-06, + "loss": 3.314, + "step": 2741760 + }, + { + "epoch": 1.02, + "learning_rate": 5.105502426355985e-06, + "loss": 3.3179, + "step": 2742272 + }, + { + "epoch": 1.02, + "learning_rate": 5.097116478845465e-06, + "loss": 3.3246, + "step": 2742784 + }, + { + "epoch": 1.02, + "learning_rate": 5.088730531334945e-06, + "loss": 3.31, + "step": 2743296 + }, + { + "epoch": 1.02, + "learning_rate": 5.080344583824425e-06, + "loss": 3.3058, + "step": 2743808 + }, + { + "epoch": 1.02, + "learning_rate": 5.071958636313905e-06, + "loss": 3.3117, + "step": 2744320 + }, + { + "epoch": 1.02, + "learning_rate": 5.063589067607116e-06, + "loss": 3.2999, + "step": 2744832 + }, + { + "epoch": 1.02, + "learning_rate": 5.055203120096596e-06, + "loss": 3.3221, + "step": 2745344 + }, + { + "epoch": 1.02, + "learning_rate": 5.046817172586075e-06, + "loss": 3.3149, + "step": 2745856 + }, + { + "epoch": 1.02, + "learning_rate": 5.038431225075556e-06, + "loss": 3.3178, + "step": 2746368 + }, + { + "epoch": 1.02, + "learning_rate": 5.030045277565035e-06, + "loss": 3.3101, + "step": 2746880 + }, + { + "epoch": 1.02, + "learning_rate": 5.021659330054516e-06, + "loss": 3.3082, + "step": 2747392 + }, + { + "epoch": 1.03, + "eval_loss": 3.8699307441711426, + "eval_runtime": 302.9524, + "eval_samples_per_second": 1259.574, + "eval_steps_per_second": 39.363, + "step": 2747520 + }, + { + "epoch": 0.0, + "learning_rate": 5.013273382543995e-06, + "loss": 3.3134, + "step": 2747904 + }, + { + "epoch": 0.0, + "learning_rate": 5.004887435033475e-06, + "loss": 3.3052, + "step": 2748416 + }, + { + "epoch": 0.0, + "learning_rate": 4.996501487522955e-06, + "loss": 3.3199, + "step": 2748928 + }, + { + "epoch": 0.0, + "learning_rate": 4.988131918816166e-06, + "loss": 3.3124, + "step": 2749440 + }, + { + "epoch": 0.0, + "learning_rate": 4.979745971305647e-06, + "loss": 3.3251, + "step": 2749952 + }, + { + "epoch": 0.0, + "learning_rate": 4.971360023795126e-06, + "loss": 3.3094, + "step": 2750464 + }, + { + "epoch": 0.0, + "learning_rate": 4.962974076284607e-06, + "loss": 3.3061, + "step": 2750976 + }, + { + "epoch": 0.0, + "learning_rate": 4.954588128774086e-06, + "loss": 3.2983, + "step": 2751488 + }, + { + "epoch": 0.0, + "learning_rate": 4.946202181263566e-06, + "loss": 3.3125, + "step": 2752000 + }, + { + "epoch": 0.0, + "learning_rate": 4.9378162337530465e-06, + "loss": 3.3173, + "step": 2752512 + }, + { + "epoch": 0.0, + "learning_rate": 4.929446665046257e-06, + "loss": 3.3154, + "step": 2753024 + }, + { + "epoch": 0.0, + "learning_rate": 4.921060717535737e-06, + "loss": 3.3194, + "step": 2753536 + }, + { + "epoch": 0.0, + "learning_rate": 4.912674770025217e-06, + "loss": 3.3072, + "step": 2754048 + }, + { + "epoch": 0.0, + "learning_rate": 4.904288822514697e-06, + "loss": 3.3086, + "step": 2754560 + }, + { + "epoch": 0.0, + "learning_rate": 4.895919253807908e-06, + "loss": 3.3046, + "step": 2755072 + }, + { + "epoch": 0.0, + "learning_rate": 4.887533306297389e-06, + "loss": 3.3059, + "step": 2755584 + }, + { + "epoch": 0.0, + "learning_rate": 4.879147358786868e-06, + "loss": 3.3078, + "step": 2756096 + }, + { + "epoch": 0.0, + "learning_rate": 4.870761411276348e-06, + "loss": 3.3089, + "step": 2756608 + }, + { + "epoch": 0.0, + "learning_rate": 4.8623918425695594e-06, + "loss": 3.3064, + "step": 2757120 + }, + { + "epoch": 0.0, + "learning_rate": 4.854005895059039e-06, + "loss": 3.3174, + "step": 2757632 + }, + { + "epoch": 0.0, + "learning_rate": 4.845619947548519e-06, + "loss": 3.3119, + "step": 2758144 + }, + { + "epoch": 0.0, + "learning_rate": 4.837234000037999e-06, + "loss": 3.31, + "step": 2758656 + }, + { + "epoch": 0.0, + "learning_rate": 4.828864431331211e-06, + "loss": 3.3115, + "step": 2759168 + }, + { + "epoch": 0.0, + "learning_rate": 4.82047848382069e-06, + "loss": 3.3174, + "step": 2759680 + }, + { + "epoch": 0.0, + "learning_rate": 4.812092536310171e-06, + "loss": 3.3026, + "step": 2760192 + }, + { + "epoch": 0.0, + "learning_rate": 4.80370658879965e-06, + "loss": 3.3175, + "step": 2760704 + }, + { + "epoch": 0.0, + "learning_rate": 4.795337020092861e-06, + "loss": 3.3004, + "step": 2761216 + }, + { + "epoch": 0.0, + "learning_rate": 4.7869510725823415e-06, + "loss": 3.3079, + "step": 2761728 + }, + { + "epoch": 0.0, + "learning_rate": 4.7785651250718215e-06, + "loss": 3.3006, + "step": 2762240 + }, + { + "epoch": 0.0, + "learning_rate": 4.7701791775613015e-06, + "loss": 3.3063, + "step": 2762752 + }, + { + "epoch": 0.01, + "learning_rate": 4.761793230050781e-06, + "loss": 3.3143, + "step": 2763264 + }, + { + "epoch": 0.01, + "learning_rate": 4.7534072825402605e-06, + "loss": 3.3108, + "step": 2763776 + }, + { + "epoch": 0.01, + "learning_rate": 4.745037713833472e-06, + "loss": 3.3171, + "step": 2764288 + }, + { + "epoch": 0.01, + "learning_rate": 4.736651766322952e-06, + "loss": 3.3091, + "step": 2764800 + }, + { + "epoch": 0.01, + "learning_rate": 4.728265818812432e-06, + "loss": 3.2998, + "step": 2765312 + }, + { + "epoch": 0.01, + "learning_rate": 4.719879871301912e-06, + "loss": 3.309, + "step": 2765824 + }, + { + "epoch": 0.01, + "learning_rate": 4.711510302595124e-06, + "loss": 3.3076, + "step": 2766336 + }, + { + "epoch": 0.01, + "learning_rate": 4.703124355084603e-06, + "loss": 3.2994, + "step": 2766848 + }, + { + "epoch": 0.01, + "learning_rate": 4.694738407574084e-06, + "loss": 3.2958, + "step": 2767360 + }, + { + "epoch": 0.01, + "learning_rate": 4.686352460063563e-06, + "loss": 3.3001, + "step": 2767872 + }, + { + "epoch": 0.01, + "learning_rate": 4.677966512553043e-06, + "loss": 3.3081, + "step": 2768384 + }, + { + "epoch": 0.01, + "learning_rate": 4.669580565042523e-06, + "loss": 3.3145, + "step": 2768896 + }, + { + "epoch": 0.01, + "learning_rate": 4.6611946175320026e-06, + "loss": 3.3096, + "step": 2769408 + }, + { + "epoch": 0.01, + "learning_rate": 4.652825048825214e-06, + "loss": 3.2998, + "step": 2769920 + }, + { + "epoch": 0.01, + "learning_rate": 4.644439101314694e-06, + "loss": 3.3218, + "step": 2770432 + }, + { + "epoch": 0.01, + "learning_rate": 4.636053153804174e-06, + "loss": 3.3085, + "step": 2770944 + }, + { + "epoch": 0.01, + "learning_rate": 4.627667206293654e-06, + "loss": 3.3024, + "step": 2771456 + }, + { + "epoch": 0.01, + "learning_rate": 4.619297637586866e-06, + "loss": 3.3009, + "step": 2771968 + }, + { + "epoch": 0.01, + "learning_rate": 4.610911690076345e-06, + "loss": 3.2894, + "step": 2772480 + }, + { + "epoch": 0.01, + "learning_rate": 4.602525742565825e-06, + "loss": 3.3161, + "step": 2772992 + }, + { + "epoch": 0.01, + "learning_rate": 4.594139795055305e-06, + "loss": 3.303, + "step": 2773504 + }, + { + "epoch": 0.01, + "learning_rate": 4.585770226348516e-06, + "loss": 3.3065, + "step": 2774016 + }, + { + "epoch": 0.01, + "learning_rate": 4.577400657641728e-06, + "loss": 3.3044, + "step": 2774528 + }, + { + "epoch": 0.01, + "learning_rate": 4.569014710131207e-06, + "loss": 3.3009, + "step": 2775040 + }, + { + "epoch": 0.01, + "learning_rate": 4.560628762620688e-06, + "loss": 3.2933, + "step": 2775552 + }, + { + "epoch": 0.01, + "learning_rate": 4.552242815110167e-06, + "loss": 3.3088, + "step": 2776064 + }, + { + "epoch": 0.01, + "learning_rate": 4.543856867599648e-06, + "loss": 3.3055, + "step": 2776576 + }, + { + "epoch": 0.01, + "learning_rate": 4.535470920089127e-06, + "loss": 3.316, + "step": 2777088 + }, + { + "epoch": 0.01, + "learning_rate": 4.527084972578607e-06, + "loss": 3.3068, + "step": 2777600 + }, + { + "epoch": 0.01, + "learning_rate": 4.5187154038718185e-06, + "loss": 3.3009, + "step": 2778112 + }, + { + "epoch": 0.01, + "learning_rate": 4.510329456361298e-06, + "loss": 3.2968, + "step": 2778624 + }, + { + "epoch": 0.01, + "learning_rate": 4.5019435088507784e-06, + "loss": 3.3131, + "step": 2779136 + }, + { + "epoch": 0.01, + "learning_rate": 4.493573940143989e-06, + "loss": 3.2936, + "step": 2779648 + }, + { + "epoch": 0.01, + "learning_rate": 4.485187992633469e-06, + "loss": 3.2917, + "step": 2780160 + }, + { + "epoch": 0.01, + "learning_rate": 4.476802045122949e-06, + "loss": 3.3058, + "step": 2780672 + }, + { + "epoch": 0.01, + "learning_rate": 4.46841609761243e-06, + "loss": 3.307, + "step": 2781184 + }, + { + "epoch": 0.01, + "learning_rate": 4.460030150101909e-06, + "loss": 3.2967, + "step": 2781696 + }, + { + "epoch": 0.01, + "learning_rate": 4.451644202591389e-06, + "loss": 3.2952, + "step": 2782208 + }, + { + "epoch": 0.01, + "learning_rate": 4.443258255080869e-06, + "loss": 3.2925, + "step": 2782720 + }, + { + "epoch": 0.01, + "learning_rate": 4.43488868637408e-06, + "loss": 3.3079, + "step": 2783232 + }, + { + "epoch": 0.01, + "learning_rate": 4.4265027388635605e-06, + "loss": 3.3044, + "step": 2783744 + }, + { + "epoch": 0.01, + "learning_rate": 4.41811679135304e-06, + "loss": 3.3028, + "step": 2784256 + }, + { + "epoch": 0.01, + "learning_rate": 4.4097308438425205e-06, + "loss": 3.3109, + "step": 2784768 + }, + { + "epoch": 0.01, + "learning_rate": 4.401361275135731e-06, + "loss": 3.303, + "step": 2785280 + }, + { + "epoch": 0.01, + "learning_rate": 4.392975327625211e-06, + "loss": 3.3158, + "step": 2785792 + }, + { + "epoch": 0.01, + "learning_rate": 4.384589380114691e-06, + "loss": 3.2961, + "step": 2786304 + }, + { + "epoch": 0.01, + "learning_rate": 4.376203432604171e-06, + "loss": 3.307, + "step": 2786816 + }, + { + "epoch": 0.01, + "learning_rate": 4.367833863897383e-06, + "loss": 3.3044, + "step": 2787328 + }, + { + "epoch": 0.01, + "learning_rate": 4.359447916386862e-06, + "loss": 3.2967, + "step": 2787840 + }, + { + "epoch": 0.01, + "learning_rate": 4.351061968876343e-06, + "loss": 3.3196, + "step": 2788352 + }, + { + "epoch": 0.01, + "learning_rate": 4.342676021365822e-06, + "loss": 3.3084, + "step": 2788864 + }, + { + "epoch": 0.01, + "learning_rate": 4.334306452659033e-06, + "loss": 3.31, + "step": 2789376 + }, + { + "epoch": 0.01, + "learning_rate": 4.325936883952244e-06, + "loss": 3.3108, + "step": 2789888 + }, + { + "epoch": 0.01, + "learning_rate": 4.317550936441725e-06, + "loss": 3.2942, + "step": 2790400 + }, + { + "epoch": 0.01, + "learning_rate": 4.309164988931205e-06, + "loss": 3.297, + "step": 2790912 + }, + { + "epoch": 0.01, + "learning_rate": 4.300779041420685e-06, + "loss": 3.299, + "step": 2791424 + }, + { + "epoch": 0.01, + "learning_rate": 4.292409472713896e-06, + "loss": 3.3032, + "step": 2791936 + }, + { + "epoch": 0.01, + "learning_rate": 4.2840235252033765e-06, + "loss": 3.306, + "step": 2792448 + }, + { + "epoch": 0.01, + "learning_rate": 4.275637577692856e-06, + "loss": 3.3053, + "step": 2792960 + }, + { + "epoch": 0.02, + "learning_rate": 4.2672516301823356e-06, + "loss": 3.3064, + "step": 2793472 + }, + { + "epoch": 0.02, + "learning_rate": 4.2588656826718155e-06, + "loss": 3.3091, + "step": 2793984 + }, + { + "epoch": 0.02, + "learning_rate": 4.2504797351612955e-06, + "loss": 3.2972, + "step": 2794496 + }, + { + "epoch": 0.02, + "learning_rate": 4.2420937876507754e-06, + "loss": 3.3041, + "step": 2795008 + }, + { + "epoch": 0.02, + "learning_rate": 4.233707840140255e-06, + "loss": 3.3052, + "step": 2795520 + }, + { + "epoch": 0.02, + "learning_rate": 4.225338271433467e-06, + "loss": 3.3168, + "step": 2796032 + }, + { + "epoch": 0.02, + "learning_rate": 4.216952323922946e-06, + "loss": 3.3065, + "step": 2796544 + }, + { + "epoch": 0.02, + "learning_rate": 4.208566376412426e-06, + "loss": 3.3016, + "step": 2797056 + }, + { + "epoch": 0.02, + "learning_rate": 4.200196807705638e-06, + "loss": 3.3114, + "step": 2797568 + }, + { + "epoch": 0.02, + "learning_rate": 4.191810860195118e-06, + "loss": 3.3047, + "step": 2798080 + }, + { + "epoch": 0.02, + "learning_rate": 4.183424912684598e-06, + "loss": 3.3155, + "step": 2798592 + }, + { + "epoch": 0.02, + "learning_rate": 4.175038965174078e-06, + "loss": 3.3076, + "step": 2799104 + }, + { + "epoch": 0.02, + "learning_rate": 4.166653017663557e-06, + "loss": 3.3006, + "step": 2799616 + }, + { + "epoch": 0.02, + "learning_rate": 4.1582670701530375e-06, + "loss": 3.302, + "step": 2800128 + }, + { + "epoch": 0.02, + "learning_rate": 4.149881122642517e-06, + "loss": 3.3118, + "step": 2800640 + }, + { + "epoch": 0.02, + "learning_rate": 4.141495175131997e-06, + "loss": 3.2865, + "step": 2801152 + }, + { + "epoch": 0.02, + "learning_rate": 4.133125606425208e-06, + "loss": 3.3014, + "step": 2801664 + }, + { + "epoch": 0.02, + "learning_rate": 4.12475603771842e-06, + "loss": 3.3072, + "step": 2802176 + }, + { + "epoch": 0.02, + "learning_rate": 4.1163700902079e-06, + "loss": 3.3079, + "step": 2802688 + }, + { + "epoch": 0.02, + "learning_rate": 4.10798414269738e-06, + "loss": 3.2899, + "step": 2803200 + }, + { + "epoch": 0.02, + "learning_rate": 4.09959819518686e-06, + "loss": 3.2983, + "step": 2803712 + }, + { + "epoch": 0.02, + "learning_rate": 4.091212247676339e-06, + "loss": 3.3012, + "step": 2804224 + }, + { + "epoch": 0.02, + "learning_rate": 4.08282630016582e-06, + "loss": 3.3164, + "step": 2804736 + }, + { + "epoch": 0.02, + "learning_rate": 4.074440352655299e-06, + "loss": 3.3012, + "step": 2805248 + }, + { + "epoch": 0.02, + "learning_rate": 4.0660544051447795e-06, + "loss": 3.3093, + "step": 2805760 + }, + { + "epoch": 0.02, + "learning_rate": 4.05768483643799e-06, + "loss": 3.3083, + "step": 2806272 + }, + { + "epoch": 0.02, + "learning_rate": 4.04929888892747e-06, + "loss": 3.3156, + "step": 2806784 + }, + { + "epoch": 0.02, + "learning_rate": 4.04091294141695e-06, + "loss": 3.3041, + "step": 2807296 + }, + { + "epoch": 0.02, + "learning_rate": 4.032526993906429e-06, + "loss": 3.2978, + "step": 2807808 + }, + { + "epoch": 0.02, + "learning_rate": 4.024157425199641e-06, + "loss": 3.3082, + "step": 2808320 + }, + { + "epoch": 0.02, + "learning_rate": 4.015771477689121e-06, + "loss": 3.3085, + "step": 2808832 + }, + { + "epoch": 0.02, + "learning_rate": 4.007385530178602e-06, + "loss": 3.2918, + "step": 2809344 + }, + { + "epoch": 0.02, + "learning_rate": 3.998999582668081e-06, + "loss": 3.2977, + "step": 2809856 + }, + { + "epoch": 0.02, + "learning_rate": 3.9906300139612925e-06, + "loss": 3.2998, + "step": 2810368 + }, + { + "epoch": 0.02, + "learning_rate": 3.9822440664507724e-06, + "loss": 3.3019, + "step": 2810880 + }, + { + "epoch": 0.02, + "learning_rate": 3.973858118940252e-06, + "loss": 3.3045, + "step": 2811392 + }, + { + "epoch": 0.02, + "learning_rate": 3.965488550233463e-06, + "loss": 3.3148, + "step": 2811904 + }, + { + "epoch": 0.02, + "learning_rate": 3.957102602722944e-06, + "loss": 3.2902, + "step": 2812416 + }, + { + "epoch": 0.02, + "learning_rate": 3.948716655212423e-06, + "loss": 3.3, + "step": 2812928 + }, + { + "epoch": 0.02, + "learning_rate": 3.940330707701903e-06, + "loss": 3.2952, + "step": 2813440 + }, + { + "epoch": 0.02, + "learning_rate": 3.931944760191383e-06, + "loss": 3.3195, + "step": 2813952 + }, + { + "epoch": 0.02, + "learning_rate": 3.923575191484595e-06, + "loss": 3.3122, + "step": 2814464 + }, + { + "epoch": 0.02, + "learning_rate": 3.915189243974075e-06, + "loss": 3.309, + "step": 2814976 + }, + { + "epoch": 0.02, + "learning_rate": 3.9068032964635546e-06, + "loss": 3.2937, + "step": 2815488 + }, + { + "epoch": 0.02, + "learning_rate": 3.8984173489530345e-06, + "loss": 3.3102, + "step": 2816000 + }, + { + "epoch": 0.02, + "learning_rate": 3.8900314014425145e-06, + "loss": 3.3147, + "step": 2816512 + }, + { + "epoch": 0.02, + "learning_rate": 3.881645453931994e-06, + "loss": 3.306, + "step": 2817024 + }, + { + "epoch": 0.02, + "learning_rate": 3.873259506421474e-06, + "loss": 3.3024, + "step": 2817536 + }, + { + "epoch": 0.02, + "learning_rate": 3.8648735589109535e-06, + "loss": 3.3107, + "step": 2818048 + }, + { + "epoch": 0.02, + "learning_rate": 3.856520369007897e-06, + "loss": 3.3051, + "step": 2818560 + }, + { + "epoch": 0.02, + "learning_rate": 3.848134421497377e-06, + "loss": 3.3199, + "step": 2819072 + }, + { + "epoch": 0.02, + "learning_rate": 3.839748473986857e-06, + "loss": 3.2969, + "step": 2819584 + }, + { + "epoch": 0.02, + "learning_rate": 3.831362526476337e-06, + "loss": 3.3024, + "step": 2820096 + }, + { + "epoch": 0.02, + "learning_rate": 3.822976578965817e-06, + "loss": 3.3008, + "step": 2820608 + }, + { + "epoch": 0.02, + "learning_rate": 3.8146070102590274e-06, + "loss": 3.2945, + "step": 2821120 + }, + { + "epoch": 0.02, + "learning_rate": 3.806221062748508e-06, + "loss": 3.3105, + "step": 2821632 + }, + { + "epoch": 0.02, + "learning_rate": 3.7978351152379873e-06, + "loss": 3.3075, + "step": 2822144 + }, + { + "epoch": 0.02, + "learning_rate": 3.7894491677274673e-06, + "loss": 3.3079, + "step": 2822656 + }, + { + "epoch": 0.02, + "learning_rate": 3.7810632202169473e-06, + "loss": 3.3002, + "step": 2823168 + }, + { + "epoch": 0.02, + "learning_rate": 3.772677272706427e-06, + "loss": 3.303, + "step": 2823680 + }, + { + "epoch": 0.03, + "eval_loss": 3.8704311847686768, + "eval_runtime": 303.0795, + "eval_samples_per_second": 1259.046, + "eval_steps_per_second": 39.346, + "step": 2823840 + }, + { + "epoch": 1.0, + "learning_rate": 3.764291325195907e-06, + "loss": 3.3004, + "step": 2824192 + }, + { + "epoch": 1.0, + "learning_rate": 3.755905377685387e-06, + "loss": 3.2934, + "step": 2824704 + }, + { + "epoch": 1.0, + "learning_rate": 3.7475358089785988e-06, + "loss": 3.314, + "step": 2825216 + }, + { + "epoch": 1.0, + "learning_rate": 3.7391498614680783e-06, + "loss": 3.3068, + "step": 2825728 + }, + { + "epoch": 1.0, + "learning_rate": 3.730763913957558e-06, + "loss": 3.3168, + "step": 2826240 + }, + { + "epoch": 1.0, + "learning_rate": 3.722377966447038e-06, + "loss": 3.3021, + "step": 2826752 + }, + { + "epoch": 1.0, + "learning_rate": 3.714008397740249e-06, + "loss": 3.2956, + "step": 2827264 + }, + { + "epoch": 1.0, + "learning_rate": 3.7056224502297294e-06, + "loss": 3.2924, + "step": 2827776 + }, + { + "epoch": 1.0, + "learning_rate": 3.697236502719209e-06, + "loss": 3.3035, + "step": 2828288 + }, + { + "epoch": 1.0, + "learning_rate": 3.6888505552086893e-06, + "loss": 3.3086, + "step": 2828800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6804809865019005e-06, + "loss": 3.3062, + "step": 2829312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6720950389913805e-06, + "loss": 3.3136, + "step": 2829824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6637090914808604e-06, + "loss": 3.2977, + "step": 2830336 + }, + { + "epoch": 1.0, + "learning_rate": 3.65532314397034e-06, + "loss": 3.3027, + "step": 2830848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6469535752635516e-06, + "loss": 3.2978, + "step": 2831360 + }, + { + "epoch": 1.0, + "learning_rate": 3.638567627753031e-06, + "loss": 3.2931, + "step": 2831872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6301816802425115e-06, + "loss": 3.2977, + "step": 2832384 + }, + { + "epoch": 1.0, + "learning_rate": 3.621795732731991e-06, + "loss": 3.3, + "step": 2832896 + }, + { + "epoch": 1.0, + "learning_rate": 3.6134261640252027e-06, + "loss": 3.2957, + "step": 2833408 + }, + { + "epoch": 1.0, + "learning_rate": 3.605040216514682e-06, + "loss": 3.3083, + "step": 2833920 + }, + { + "epoch": 1.0, + "learning_rate": 3.5966542690041626e-06, + "loss": 3.305, + "step": 2834432 + }, + { + "epoch": 1.0, + "learning_rate": 3.588268321493642e-06, + "loss": 3.3024, + "step": 2834944 + }, + { + "epoch": 1.0, + "learning_rate": 3.579898752786854e-06, + "loss": 3.3032, + "step": 2835456 + }, + { + "epoch": 1.0, + "learning_rate": 3.5715128052763337e-06, + "loss": 3.3066, + "step": 2835968 + }, + { + "epoch": 1.0, + "learning_rate": 3.5631268577658132e-06, + "loss": 3.2954, + "step": 2836480 + }, + { + "epoch": 1.0, + "learning_rate": 3.5547409102552936e-06, + "loss": 3.3097, + "step": 2836992 + }, + { + "epoch": 1.0, + "learning_rate": 3.5463713415485044e-06, + "loss": 3.2922, + "step": 2837504 + }, + { + "epoch": 1.0, + "learning_rate": 3.5379853940379848e-06, + "loss": 3.2995, + "step": 2838016 + }, + { + "epoch": 1.0, + "learning_rate": 3.5295994465274643e-06, + "loss": 3.2958, + "step": 2838528 + }, + { + "epoch": 1.0, + "learning_rate": 3.521213499016944e-06, + "loss": 3.2958, + "step": 2839040 + }, + { + "epoch": 1.01, + "learning_rate": 3.5128275515064242e-06, + "loss": 3.3048, + "step": 2839552 + }, + { + "epoch": 1.01, + "learning_rate": 3.5044416039959037e-06, + "loss": 3.3058, + "step": 2840064 + }, + { + "epoch": 1.01, + "learning_rate": 3.496055656485384e-06, + "loss": 3.3057, + "step": 2840576 + }, + { + "epoch": 1.01, + "learning_rate": 3.4876860877785953e-06, + "loss": 3.2984, + "step": 2841088 + }, + { + "epoch": 1.01, + "learning_rate": 3.4793001402680757e-06, + "loss": 3.2925, + "step": 2841600 + }, + { + "epoch": 1.01, + "learning_rate": 3.4709141927575553e-06, + "loss": 3.3058, + "step": 2842112 + }, + { + "epoch": 1.01, + "learning_rate": 3.462544624050767e-06, + "loss": 3.2991, + "step": 2842624 + }, + { + "epoch": 1.01, + "learning_rate": 3.4541586765402464e-06, + "loss": 3.2872, + "step": 2843136 + }, + { + "epoch": 1.01, + "learning_rate": 3.445772729029726e-06, + "loss": 3.2901, + "step": 2843648 + }, + { + "epoch": 1.01, + "learning_rate": 3.4373867815192063e-06, + "loss": 3.2894, + "step": 2844160 + }, + { + "epoch": 1.01, + "learning_rate": 3.429000834008686e-06, + "loss": 3.2978, + "step": 2844672 + }, + { + "epoch": 1.01, + "learning_rate": 3.4206148864981662e-06, + "loss": 3.3067, + "step": 2845184 + }, + { + "epoch": 1.01, + "learning_rate": 3.4122289389876458e-06, + "loss": 3.3019, + "step": 2845696 + }, + { + "epoch": 1.01, + "learning_rate": 3.4038429914771257e-06, + "loss": 3.298, + "step": 2846208 + }, + { + "epoch": 1.01, + "learning_rate": 3.3954734227703374e-06, + "loss": 3.3096, + "step": 2846720 + }, + { + "epoch": 1.01, + "learning_rate": 3.387087475259817e-06, + "loss": 3.2993, + "step": 2847232 + }, + { + "epoch": 1.01, + "learning_rate": 3.3787015277492973e-06, + "loss": 3.2991, + "step": 2847744 + }, + { + "epoch": 1.01, + "learning_rate": 3.370331959042508e-06, + "loss": 3.2943, + "step": 2848256 + }, + { + "epoch": 1.01, + "learning_rate": 3.3619460115319885e-06, + "loss": 3.2767, + "step": 2848768 + }, + { + "epoch": 1.01, + "learning_rate": 3.353560064021468e-06, + "loss": 3.3092, + "step": 2849280 + }, + { + "epoch": 1.01, + "learning_rate": 3.3451741165109484e-06, + "loss": 3.2943, + "step": 2849792 + }, + { + "epoch": 1.01, + "learning_rate": 3.336804547804159e-06, + "loss": 3.3009, + "step": 2850304 + }, + { + "epoch": 1.01, + "learning_rate": 3.328434979097371e-06, + "loss": 3.2959, + "step": 2850816 + }, + { + "epoch": 1.01, + "learning_rate": 3.3200490315868507e-06, + "loss": 3.2916, + "step": 2851328 + }, + { + "epoch": 1.01, + "learning_rate": 3.3116630840763307e-06, + "loss": 3.2887, + "step": 2851840 + }, + { + "epoch": 1.01, + "learning_rate": 3.3032771365658107e-06, + "loss": 3.2961, + "step": 2852352 + }, + { + "epoch": 1.01, + "learning_rate": 3.29489118905529e-06, + "loss": 3.3, + "step": 2852864 + }, + { + "epoch": 1.01, + "learning_rate": 3.2865052415447706e-06, + "loss": 3.3066, + "step": 2853376 + }, + { + "epoch": 1.01, + "learning_rate": 3.27811929403425e-06, + "loss": 3.2981, + "step": 2853888 + }, + { + "epoch": 1.01, + "learning_rate": 3.2697497253274617e-06, + "loss": 3.2955, + "step": 2854400 + }, + { + "epoch": 1.01, + "learning_rate": 3.2613637778169413e-06, + "loss": 3.284, + "step": 2854912 + }, + { + "epoch": 1.01, + "learning_rate": 3.2529778303064217e-06, + "loss": 3.3065, + "step": 2855424 + }, + { + "epoch": 1.01, + "learning_rate": 3.2446082615996324e-06, + "loss": 3.2874, + "step": 2855936 + }, + { + "epoch": 1.01, + "learning_rate": 3.236222314089113e-06, + "loss": 3.2835, + "step": 2856448 + }, + { + "epoch": 1.01, + "learning_rate": 3.2278363665785924e-06, + "loss": 3.2999, + "step": 2856960 + }, + { + "epoch": 1.01, + "learning_rate": 3.2194504190680723e-06, + "loss": 3.2999, + "step": 2857472 + }, + { + "epoch": 1.01, + "learning_rate": 3.2110644715575523e-06, + "loss": 3.2854, + "step": 2857984 + }, + { + "epoch": 1.01, + "learning_rate": 3.2026785240470322e-06, + "loss": 3.2902, + "step": 2858496 + }, + { + "epoch": 1.01, + "learning_rate": 3.1942925765365126e-06, + "loss": 3.2798, + "step": 2859008 + }, + { + "epoch": 1.01, + "learning_rate": 3.185906629025992e-06, + "loss": 3.3043, + "step": 2859520 + }, + { + "epoch": 1.01, + "learning_rate": 3.1775370603192038e-06, + "loss": 3.2949, + "step": 2860032 + }, + { + "epoch": 1.01, + "learning_rate": 3.1691511128086833e-06, + "loss": 3.293, + "step": 2860544 + }, + { + "epoch": 1.01, + "learning_rate": 3.160765165298163e-06, + "loss": 3.3023, + "step": 2861056 + }, + { + "epoch": 1.01, + "learning_rate": 3.1523955965913745e-06, + "loss": 3.2945, + "step": 2861568 + }, + { + "epoch": 1.01, + "learning_rate": 3.144009649080854e-06, + "loss": 3.3111, + "step": 2862080 + }, + { + "epoch": 1.01, + "learning_rate": 3.1356237015703344e-06, + "loss": 3.2855, + "step": 2862592 + }, + { + "epoch": 1.01, + "learning_rate": 3.127237754059814e-06, + "loss": 3.3033, + "step": 2863104 + }, + { + "epoch": 1.01, + "learning_rate": 3.118868185353026e-06, + "loss": 3.2949, + "step": 2863616 + }, + { + "epoch": 1.01, + "learning_rate": 3.1104822378425055e-06, + "loss": 3.2888, + "step": 2864128 + }, + { + "epoch": 1.01, + "learning_rate": 3.1020962903319855e-06, + "loss": 3.3049, + "step": 2864640 + }, + { + "epoch": 1.01, + "learning_rate": 3.0937103428214654e-06, + "loss": 3.3031, + "step": 2865152 + }, + { + "epoch": 1.01, + "learning_rate": 3.0853407741146766e-06, + "loss": 3.3011, + "step": 2865664 + }, + { + "epoch": 1.01, + "learning_rate": 3.076971205407888e-06, + "loss": 3.3046, + "step": 2866176 + }, + { + "epoch": 1.01, + "learning_rate": 3.068585257897368e-06, + "loss": 3.2881, + "step": 2866688 + }, + { + "epoch": 1.01, + "learning_rate": 3.0601993103868478e-06, + "loss": 3.2888, + "step": 2867200 + }, + { + "epoch": 1.01, + "learning_rate": 3.0518133628763277e-06, + "loss": 3.2885, + "step": 2867712 + }, + { + "epoch": 1.01, + "learning_rate": 3.0434437941695394e-06, + "loss": 3.2963, + "step": 2868224 + }, + { + "epoch": 1.01, + "learning_rate": 3.0350578466590193e-06, + "loss": 3.2986, + "step": 2868736 + }, + { + "epoch": 1.01, + "learning_rate": 3.026671899148499e-06, + "loss": 3.2973, + "step": 2869248 + }, + { + "epoch": 1.02, + "learning_rate": 3.018285951637979e-06, + "loss": 3.2938, + "step": 2869760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0099000041274588e-06, + "loss": 3.3066, + "step": 2870272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0015140566169387e-06, + "loss": 3.2897, + "step": 2870784 + }, + { + "epoch": 1.02, + "learning_rate": 2.9931281091064187e-06, + "loss": 3.2939, + "step": 2871296 + }, + { + "epoch": 1.02, + "learning_rate": 2.984742161595898e-06, + "loss": 3.2995, + "step": 2871808 + }, + { + "epoch": 1.02, + "learning_rate": 2.97637259288911e-06, + "loss": 3.3059, + "step": 2872320 + }, + { + "epoch": 1.02, + "learning_rate": 2.9679866453785894e-06, + "loss": 3.2991, + "step": 2872832 + }, + { + "epoch": 1.02, + "learning_rate": 2.9596006978680693e-06, + "loss": 3.289, + "step": 2873344 + }, + { + "epoch": 1.02, + "learning_rate": 2.9512147503575493e-06, + "loss": 3.3041, + "step": 2873856 + }, + { + "epoch": 1.02, + "learning_rate": 2.942845181650761e-06, + "loss": 3.2985, + "step": 2874368 + }, + { + "epoch": 1.02, + "learning_rate": 2.934459234140241e-06, + "loss": 3.3025, + "step": 2874880 + }, + { + "epoch": 1.02, + "learning_rate": 2.926073286629721e-06, + "loss": 3.2992, + "step": 2875392 + }, + { + "epoch": 1.02, + "learning_rate": 2.9176873391192008e-06, + "loss": 3.2946, + "step": 2875904 + }, + { + "epoch": 1.02, + "learning_rate": 2.909317770412412e-06, + "loss": 3.2887, + "step": 2876416 + }, + { + "epoch": 1.02, + "learning_rate": 2.900931822901892e-06, + "loss": 3.3067, + "step": 2876928 + }, + { + "epoch": 1.02, + "learning_rate": 2.8925458753913715e-06, + "loss": 3.277, + "step": 2877440 + }, + { + "epoch": 1.02, + "learning_rate": 2.8841599278808514e-06, + "loss": 3.296, + "step": 2877952 + }, + { + "epoch": 1.02, + "learning_rate": 2.8757903591740627e-06, + "loss": 3.2973, + "step": 2878464 + }, + { + "epoch": 1.02, + "learning_rate": 2.8674044116635426e-06, + "loss": 3.2969, + "step": 2878976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8590184641530226e-06, + "loss": 3.2869, + "step": 2879488 + }, + { + "epoch": 1.02, + "learning_rate": 2.8506325166425025e-06, + "loss": 3.2882, + "step": 2880000 + }, + { + "epoch": 1.02, + "learning_rate": 2.842262947935714e-06, + "loss": 3.2951, + "step": 2880512 + }, + { + "epoch": 1.02, + "learning_rate": 2.833877000425194e-06, + "loss": 3.3079, + "step": 2881024 + }, + { + "epoch": 1.02, + "learning_rate": 2.825491052914674e-06, + "loss": 3.2961, + "step": 2881536 + }, + { + "epoch": 1.02, + "learning_rate": 2.8171051054041536e-06, + "loss": 3.2962, + "step": 2882048 + }, + { + "epoch": 1.02, + "learning_rate": 2.8087355366973652e-06, + "loss": 3.3021, + "step": 2882560 + }, + { + "epoch": 1.02, + "learning_rate": 2.8003495891868448e-06, + "loss": 3.3111, + "step": 2883072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7919636416763247e-06, + "loss": 3.2977, + "step": 2883584 + }, + { + "epoch": 1.02, + "learning_rate": 2.783594072969536e-06, + "loss": 3.2859, + "step": 2884096 + }, + { + "epoch": 1.02, + "learning_rate": 2.775208125459016e-06, + "loss": 3.3006, + "step": 2884608 + }, + { + "epoch": 1.02, + "learning_rate": 2.766822177948496e-06, + "loss": 3.2981, + "step": 2885120 + }, + { + "epoch": 1.02, + "learning_rate": 2.758436230437976e-06, + "loss": 3.2831, + "step": 2885632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7500666617311874e-06, + "loss": 3.287, + "step": 2886144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7416807142206674e-06, + "loss": 3.2943, + "step": 2886656 + }, + { + "epoch": 1.02, + "learning_rate": 2.733294766710147e-06, + "loss": 3.2915, + "step": 2887168 + }, + { + "epoch": 1.02, + "learning_rate": 2.724908819199627e-06, + "loss": 3.297, + "step": 2887680 + }, + { + "epoch": 1.02, + "learning_rate": 2.716539250492838e-06, + "loss": 3.3075, + "step": 2888192 + }, + { + "epoch": 1.02, + "learning_rate": 2.708153302982318e-06, + "loss": 3.286, + "step": 2888704 + }, + { + "epoch": 1.02, + "learning_rate": 2.6997837342755293e-06, + "loss": 3.2895, + "step": 2889216 + }, + { + "epoch": 1.02, + "learning_rate": 2.6913977867650092e-06, + "loss": 3.2908, + "step": 2889728 + }, + { + "epoch": 1.02, + "learning_rate": 2.683011839254489e-06, + "loss": 3.308, + "step": 2890240 + }, + { + "epoch": 1.02, + "learning_rate": 2.674625891743969e-06, + "loss": 3.3035, + "step": 2890752 + }, + { + "epoch": 1.02, + "learning_rate": 2.666239944233449e-06, + "loss": 3.304, + "step": 2891264 + }, + { + "epoch": 1.02, + "learning_rate": 2.657853996722929e-06, + "loss": 3.2895, + "step": 2891776 + }, + { + "epoch": 1.02, + "learning_rate": 2.649468049212409e-06, + "loss": 3.3021, + "step": 2892288 + }, + { + "epoch": 1.02, + "learning_rate": 2.6410984805056202e-06, + "loss": 3.3045, + "step": 2892800 + }, + { + "epoch": 1.02, + "learning_rate": 2.6327125329951e-06, + "loss": 3.2991, + "step": 2893312 + }, + { + "epoch": 1.02, + "learning_rate": 2.62432658548458e-06, + "loss": 3.2943, + "step": 2893824 + }, + { + "epoch": 1.02, + "learning_rate": 2.61594063797406e-06, + "loss": 3.3016, + "step": 2894336 + }, + { + "epoch": 1.02, + "learning_rate": 2.6075710692672713e-06, + "loss": 3.2971, + "step": 2894848 + }, + { + "epoch": 1.02, + "learning_rate": 2.5991851217567513e-06, + "loss": 3.3124, + "step": 2895360 + }, + { + "epoch": 1.02, + "learning_rate": 2.5907991742462312e-06, + "loss": 3.2885, + "step": 2895872 + }, + { + "epoch": 1.02, + "learning_rate": 2.5824132267357107e-06, + "loss": 3.2967, + "step": 2896384 + }, + { + "epoch": 1.02, + "learning_rate": 2.574027279225191e-06, + "loss": 3.2867, + "step": 2896896 + }, + { + "epoch": 1.02, + "learning_rate": 2.565641331714671e-06, + "loss": 3.2914, + "step": 2897408 + }, + { + "epoch": 1.02, + "learning_rate": 2.5572717630078823e-06, + "loss": 3.3059, + "step": 2897920 + }, + { + "epoch": 1.02, + "learning_rate": 2.5488858154973623e-06, + "loss": 3.2952, + "step": 2898432 + }, + { + "epoch": 1.02, + "learning_rate": 2.540499867986842e-06, + "loss": 3.3077, + "step": 2898944 + }, + { + "epoch": 1.02, + "learning_rate": 2.532113920476322e-06, + "loss": 3.2864, + "step": 2899456 + }, + { + "epoch": 1.02, + "learning_rate": 2.5237279729658017e-06, + "loss": 3.2996, + "step": 2899968 + }, + { + "epoch": 1.03, + "eval_loss": 3.869267702102661, + "eval_runtime": 308.001, + "eval_samples_per_second": 1238.928, + "eval_steps_per_second": 38.717, + "step": 2900160 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 2.0077569839934996e+18, + "trial_name": null, + "trial_params": null +}