diff --git "a/checkpoint-2442240/trainer_state.json" "b/checkpoint-2442240/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2442240/trainer_state.json" @@ -0,0 +1,28901 @@ +{ + "best_metric": 3.8445518016815186, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/det-adj-noun/transformer/4/checkpoints/checkpoint-839520", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2442240, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.9699, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8333, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1915, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9762, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8051, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7004, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6002, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5238, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4428, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3986, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3429, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3049, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.255, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2022, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1641, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1276, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.0973, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0754, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0379, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0079, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0009, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 4.9578, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9484, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9217, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9131, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.879, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8581, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.842, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8322, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8109, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.7959, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740117521192533e-05, + "loss": 4.7883, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731731573682013e-05, + "loss": 4.7654, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7593, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7441, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7329, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969820416244367e-05, + "loss": 4.7208, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.6899, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.697, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6698, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6776, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6614, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6617, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6444, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.6349, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6338, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6225, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6154, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5971, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.5826, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.5945, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5805, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5742, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5517, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.557, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.537, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.557, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5272, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 4.5382, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5228, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5036, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5106, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 4.5024, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 4.4829, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4822, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.4959, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.4733, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 4.4669, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4558, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4597, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 4.4732, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404794272397856e-05, + "loss": 4.4608, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4465, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4504, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.4515, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4347, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.426, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4296, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4162, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4179, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4154, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4131, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4163, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930422841748654e-05, + "loss": 4.4083, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.3882, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.3929, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.3895, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.3956, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3842, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.384, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3816, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3745, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3731, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.367, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921199937367455e-05, + "loss": 4.3586, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3663, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3533, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3511, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3507, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3546, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.352, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3407, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.3336, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3323, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3286, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3136, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3136, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3254, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.32, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3061, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.3027, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.3076, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3158, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3117, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3016, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3045, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.3067, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.2909, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.287, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.2923, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.2911, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.2732, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977291116202375e-05, + "loss": 4.2773, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.2753, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.2729, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2744, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2809, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.2651, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2666, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2569, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.2737, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2649, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.2554, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.2554, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.2631, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886829017736934e-05, + "loss": 4.2591, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.2531, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2493, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.2519, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.2511, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.2501, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.2313, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88096376812069e-05, + "loss": 4.2401, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880125173369638e-05, + "loss": 4.228, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.2187, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.2442, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.2314, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.2325, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.2327, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.2118, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.194186210632324, + "eval_runtime": 304.0468, + "eval_samples_per_second": 1255.04, + "eval_steps_per_second": 39.221, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.2128, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.2101, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.8725794584905426e-05, + "loss": 4.2298, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2109, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.2187, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.2003, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.2017, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.1957, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.2026, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.2008, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.2079, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.2057, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864198424621142e-05, + "loss": 4.1871, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.86335982987009e-05, + "loss": 4.1865, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862521235119038e-05, + "loss": 4.1825, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.1761, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.186, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.173, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.1726, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.1988, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857489666612726e-05, + "loss": 4.1736, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856651071861674e-05, + "loss": 4.1741, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558124771106226e-05, + "loss": 4.1762, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549755202399435e-05, + "loss": 4.1773, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541369254888915e-05, + "loss": 4.167, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532983307378395e-05, + "loss": 4.1635, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524597359867875e-05, + "loss": 4.1602, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851621141235735e-05, + "loss": 4.1681, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.1508, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.8499455896140044e-05, + "loss": 4.1593, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.8491069948629524e-05, + "loss": 4.1595, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.8482684001119e-05, + "loss": 4.1545, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847429805360848e-05, + "loss": 4.1581, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846592848490169e-05, + "loss": 4.1487, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845754253739117e-05, + "loss": 4.1504, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844915658988065e-05, + "loss": 4.1509, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844077064237013e-05, + "loss": 4.1319, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843238469485961e-05, + "loss": 4.141, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842401512615282e-05, + "loss": 4.1287, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.84156291786423e-05, + "loss": 4.1372, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840724323113178e-05, + "loss": 4.1403, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839885728362126e-05, + "loss": 4.1444, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839048771491447e-05, + "loss": 4.1355, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838210176740395e-05, + "loss": 4.1316, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837371581989343e-05, + "loss": 4.1395, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836532987238292e-05, + "loss": 4.1341, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.83569439248724e-05, + "loss": 4.1257, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.8348574356165606e-05, + "loss": 4.1223, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.8340188408655086e-05, + "loss": 4.1151, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331802461144566e-05, + "loss": 4.1301, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323416513634046e-05, + "loss": 4.1238, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315046944927255e-05, + "loss": 4.1216, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306660997416735e-05, + "loss": 4.1145, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298275049906215e-05, + "loss": 4.1207, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289889102395695e-05, + "loss": 4.1041, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281519533688904e-05, + "loss": 4.125, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273133586178384e-05, + "loss": 4.1065, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826474763866787e-05, + "loss": 4.1235, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825636169115735e-05, + "loss": 4.1131, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824799212245056e-05, + "loss": 4.0988, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823960617494004e-05, + "loss": 4.1037, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823122022742952e-05, + "loss": 4.1068, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222834279919e-05, + "loss": 4.0899, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821446471121221e-05, + "loss": 4.092, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820607876370169e-05, + "loss": 4.1081, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819769281619117e-05, + "loss": 4.0966, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818930686868065e-05, + "loss": 4.0902, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818093729997386e-05, + "loss": 4.0857, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817255135246334e-05, + "loss": 4.0904, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816416540495282e-05, + "loss": 4.1045, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155779457442305e-05, + "loss": 4.0998, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147393509931785e-05, + "loss": 4.0933, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8139023941224994e-05, + "loss": 4.0976, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.8130637993714474e-05, + "loss": 4.0958, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122252046203954e-05, + "loss": 4.0912, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811388247749716e-05, + "loss": 4.0784, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810549652998664e-05, + "loss": 4.0925, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809711058247612e-05, + "loss": 4.0834, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.80887246349656e-05, + "loss": 4.0827, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808035506625881e-05, + "loss": 4.0901, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807196911874829e-05, + "loss": 4.0832, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806358317123777e-05, + "loss": 4.0906, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805519722372726e-05, + "loss": 4.0864, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804681127621674e-05, + "loss": 4.062, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803842532870622e-05, + "loss": 4.0769, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.80300393811957e-05, + "loss": 4.0747, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802165343368518e-05, + "loss": 4.0817, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801328386497839e-05, + "loss": 4.0773, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004914296271596e-05, + "loss": 4.0765, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996528348761076e-05, + "loss": 4.0765, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988142401250556e-05, + "loss": 4.073, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979756453740036e-05, + "loss": 4.0754, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971370506229516e-05, + "loss": 4.0725, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7962984558718996e-05, + "loss": 4.0637, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795461499001221e-05, + "loss": 4.0744, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794622904250169e-05, + "loss": 4.0693, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793784309499117e-05, + "loss": 4.0615, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792945714748065e-05, + "loss": 4.0704, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792107119997013e-05, + "loss": 4.0694, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912685252459605e-05, + "loss": 4.0754, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.7904299304949085e-05, + "loss": 4.0638, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895913357438565e-05, + "loss": 4.0562, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887543788731774e-05, + "loss": 4.0605, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879157841221254e-05, + "loss": 4.0597, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870771893710734e-05, + "loss": 4.038, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786240232500395e-05, + "loss": 4.0547, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785401637749343e-05, + "loss": 4.0572, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784563042998291e-05, + "loss": 4.0564, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783724448247239e-05, + "loss": 4.0447, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782885853496187e-05, + "loss": 4.0406, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782047258745135e-05, + "loss": 4.0505, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781208663994083e-05, + "loss": 4.0614, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780370069243031e-05, + "loss": 4.0544, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779533112372352e-05, + "loss": 4.0534, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786945176213e-05, + "loss": 4.0519, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777855922870248e-05, + "loss": 4.0636, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777017328119196e-05, + "loss": 4.0402, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776180371248517e-05, + "loss": 4.0408, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775341776497465e-05, + "loss": 4.0476, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.7745031817464134e-05, + "loss": 4.0495, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.7736645869953614e-05, + "loss": 4.0318, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772827630124682e-05, + "loss": 4.0333, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.77198903537363e-05, + "loss": 4.0411, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771150440622578e-05, + "loss": 4.0379, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770311845871526e-05, + "loss": 4.0407, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769473251120474e-05, + "loss": 4.0469, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768634656369422e-05, + "loss": 4.0286, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.76779606161837e-05, + "loss": 4.0366, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766959104747691e-05, + "loss": 4.0273, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766120509996639e-05, + "loss": 4.0479, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765281915245587e-05, + "loss": 4.0445, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764443320494535e-05, + "loss": 4.0284, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763606363623857e-05, + "loss": 4.0327, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762767768872805e-05, + "loss": 4.0371, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761929174121753e-05, + "loss": 4.0398, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761090579370701e-05, + "loss": 4.0357, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760253622500022e-05, + "loss": 4.0314, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.75941502774897e-05, + "loss": 4.0312, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758576432997918e-05, + "loss": 4.0332, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757737838246866e-05, + "loss": 4.0343, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569008813761866e-05, + "loss": 4.021, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560622866251346e-05, + "loss": 4.0289, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552236918740826e-05, + "loss": 4.021, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543867350034035e-05, + "loss": 4.0077, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753548140252352e-05, + "loss": 4.0357, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527095455013e-05, + "loss": 4.0221, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751870950750248e-05, + "loss": 4.0262, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751032355999196e-05, + "loss": 4.027, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7501937612481435e-05, + "loss": 4.0104, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.0266523361206055, + "eval_runtime": 302.859, + "eval_samples_per_second": 1259.962, + "eval_steps_per_second": 39.375, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493551664970914e-05, + "loss": 4.0125, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.7485165717460394e-05, + "loss": 4.006, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.7476779769949874e-05, + "loss": 4.0322, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468393822439354e-05, + "loss": 4.0098, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460007874928834e-05, + "loss": 4.0254, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451621927418314e-05, + "loss": 4.0054, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443235979907794e-05, + "loss": 4.0059, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434850032397274e-05, + "loss": 3.9981, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426464084886754e-05, + "loss": 4.0129, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7418078137376234e-05, + "loss": 4.0086, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740969218986572e-05, + "loss": 4.015, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740132262115893e-05, + "loss": 4.0155, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739295305245214e-05, + "loss": 4.0013, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738456710494162e-05, + "loss": 4.0012, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.73761811574311e-05, + "loss": 3.9953, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736779520992058e-05, + "loss": 3.9924, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735940926241006e-05, + "loss": 4.0004, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735102331489954e-05, + "loss": 3.9936, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734263736738902e-05, + "loss": 3.9908, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.73342514198785e-05, + "loss": 4.0118, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732588185117171e-05, + "loss": 3.9954, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731749590366119e-05, + "loss": 3.9955, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309109956150674e-05, + "loss": 3.9983, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300740387443884e-05, + "loss": 4.0026, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292354439933364e-05, + "loss": 3.9906, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7283968492422844e-05, + "loss": 3.9912, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275582544912323e-05, + "loss": 3.9897, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726721297620553e-05, + "loss": 3.9903, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725882702869501e-05, + "loss": 3.9801, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725044108118449e-05, + "loss": 3.9893, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724205513367397e-05, + "loss": 3.9887, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723368556496718e-05, + "loss": 3.9866, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722529961745666e-05, + "loss": 3.9926, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721691366994614e-05, + "loss": 3.9824, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720852772243563e-05, + "loss": 3.983, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.72001417749251e-05, + "loss": 3.9838, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719175582741458e-05, + "loss": 3.9703, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718336987990406e-05, + "loss": 3.9737, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717500031119727e-05, + "loss": 3.967, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716661436368675e-05, + "loss": 3.9731, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715822841617623e-05, + "loss": 3.9806, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714984246866571e-05, + "loss": 3.9833, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714147289995892e-05, + "loss": 3.9756, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.71330869524484e-05, + "loss": 3.9727, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712470100493788e-05, + "loss": 3.9852, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116315057427366e-05, + "loss": 3.9724, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7107945488720575e-05, + "loss": 3.9701, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099559541210055e-05, + "loss": 3.9706, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091173593699535e-05, + "loss": 3.9565, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082804024992744e-05, + "loss": 3.9753, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074418077482224e-05, + "loss": 3.9675, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.7066032129971704e-05, + "loss": 3.9708, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.7057646182461184e-05, + "loss": 3.9632, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704927661375439e-05, + "loss": 3.9668, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704089066624387e-05, + "loss": 3.9514, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703250471873335e-05, + "loss": 3.9759, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702411877122283e-05, + "loss": 3.955, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701573282371232e-05, + "loss": 3.9745, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.70073468762018e-05, + "loss": 3.9625, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699896092869128e-05, + "loss": 3.9557, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699057498118076e-05, + "loss": 3.9532, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698220541247397e-05, + "loss": 3.964, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697381946496345e-05, + "loss": 3.9439, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696543351745293e-05, + "loss": 3.9511, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695704756994241e-05, + "loss": 3.9632, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694867800123562e-05, + "loss": 3.9567, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.69402920537251e-05, + "loss": 3.9466, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693190610621458e-05, + "loss": 3.9423, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692352015870406e-05, + "loss": 3.9465, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915150589997267e-05, + "loss": 3.9674, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690676464248675e-05, + "loss": 3.9561, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689837869497623e-05, + "loss": 3.952, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688999274746571e-05, + "loss": 3.9623, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688162317875892e-05, + "loss": 3.9562, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.68732372312484e-05, + "loss": 3.9538, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686485128373788e-05, + "loss": 3.9369, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685646533622736e-05, + "loss": 3.9566, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684809576752057e-05, + "loss": 3.9507, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683970982001005e-05, + "loss": 3.9434, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683134025130326e-05, + "loss": 3.9585, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682295430379274e-05, + "loss": 3.9476, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681456835628222e-05, + "loss": 3.9529, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680618240877171e-05, + "loss": 3.9512, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679779646126119e-05, + "loss": 3.9342, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789426892554396e-05, + "loss": 3.944, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.6781040945043876e-05, + "loss": 3.9424, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772654997533356e-05, + "loss": 3.9478, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764269050022836e-05, + "loss": 3.9471, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755883102512316e-05, + "loss": 3.943, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747513533805525e-05, + "loss": 3.9466, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739127586295005e-05, + "loss": 3.944, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730741638784485e-05, + "loss": 3.9425, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722355691273965e-05, + "loss": 3.9387, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6713986122567174e-05, + "loss": 3.9421, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670561655386039e-05, + "loss": 3.9485, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669723060634987e-05, + "loss": 3.9388, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668884465883935e-05, + "loss": 3.9341, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668045871132883e-05, + "loss": 3.9448, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667207276381831e-05, + "loss": 3.9445, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666368681630779e-05, + "loss": 3.9507, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665530086879727e-05, + "loss": 3.9374, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664691492128675e-05, + "loss": 3.9349, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663852897377623e-05, + "loss": 3.9358, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663015940506944e-05, + "loss": 3.9381, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662177345755892e-05, + "loss": 3.9145, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.66133875100484e-05, + "loss": 3.9322, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660500156253788e-05, + "loss": 3.9357, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596631993831094e-05, + "loss": 3.9299, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588246046320574e-05, + "loss": 3.9276, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579860098810054e-05, + "loss": 3.921, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657147415129953e-05, + "loss": 3.9271, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656308820378901e-05, + "loss": 3.9446, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655470225627849e-05, + "loss": 3.9305, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654631630876797e-05, + "loss": 3.9386, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6537946740061176e-05, + "loss": 3.931, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529560792550656e-05, + "loss": 3.9438, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521174845040136e-05, + "loss": 3.9264, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512788897529616e-05, + "loss": 3.9223, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.6504402950019096e-05, + "loss": 3.928, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649601700250858e-05, + "loss": 3.9308, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648764743380179e-05, + "loss": 3.9128, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647926148629127e-05, + "loss": 3.9169, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647087553878075e-05, + "loss": 3.9215, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646248959127023e-05, + "loss": 3.9277, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645410364375971e-05, + "loss": 3.9271, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644573407505292e-05, + "loss": 3.9316, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.64373481275424e-05, + "loss": 3.912, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642896218003188e-05, + "loss": 3.9198, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642057623252136e-05, + "loss": 3.9139, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641219028501084e-05, + "loss": 3.9347, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640380433750032e-05, + "loss": 3.9346, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.63954183899898e-05, + "loss": 3.9182, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638703244247928e-05, + "loss": 3.9152, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378662873772496e-05, + "loss": 3.924, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370276926261976e-05, + "loss": 3.9259, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361890978751456e-05, + "loss": 3.9278, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353521410044665e-05, + "loss": 3.9172, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345135462534145e-05, + "loss": 3.9222, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336749515023625e-05, + "loss": 3.9219, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328363567513105e-05, + "loss": 3.9279, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6319977620002585e-05, + "loss": 3.9132, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631159167249206e-05, + "loss": 3.9153, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303222103785274e-05, + "loss": 3.9143, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294836156274754e-05, + "loss": 3.8968, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286450208764234e-05, + "loss": 3.9277, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627808064005745e-05, + "loss": 3.9161, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626969469254693e-05, + "loss": 3.9183, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626130874503641e-05, + "loss": 3.9189, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625292279752589e-05, + "loss": 3.9029, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9524450302124023, + "eval_runtime": 304.3336, + "eval_samples_per_second": 1253.858, + "eval_steps_per_second": 39.184, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624453685001536e-05, + "loss": 3.9099, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623615090250484e-05, + "loss": 3.8997, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622778133379806e-05, + "loss": 3.924, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621939538628753e-05, + "loss": 3.9045, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621100943877701e-05, + "loss": 3.9291, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620262349126649e-05, + "loss": 3.8944, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619423754375597e-05, + "loss": 3.9053, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618585159624545e-05, + "loss": 3.8893, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617746564873494e-05, + "loss": 3.9116, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616907970122442e-05, + "loss": 3.9054, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616071013251763e-05, + "loss": 3.9069, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615234056381084e-05, + "loss": 3.9194, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614397099510405e-05, + "loss": 3.8956, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613558504759353e-05, + "loss": 3.9007, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127199100083006e-05, + "loss": 3.8919, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.6118813152572486e-05, + "loss": 3.893, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110427205061966e-05, + "loss": 3.8991, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.6102041257551446e-05, + "loss": 3.893, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.6093655310040926e-05, + "loss": 3.8934, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085269362530406e-05, + "loss": 3.9095, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607688341501989e-05, + "loss": 3.8981, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606849746750937e-05, + "loss": 3.8963, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606011151999885e-05, + "loss": 3.9031, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605174195129206e-05, + "loss": 3.9032, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604335600378154e-05, + "loss": 3.8902, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603497005627102e-05, + "loss": 3.8947, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.60265841087605e-05, + "loss": 3.894, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601819816124998e-05, + "loss": 3.8885, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600981221373946e-05, + "loss": 3.8859, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600142626622894e-05, + "loss": 3.8865, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599304031871842e-05, + "loss": 3.8993, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598467075001163e-05, + "loss": 3.8895, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597628480250111e-05, + "loss": 3.9004, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596789885499059e-05, + "loss": 3.8887, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595951290748008e-05, + "loss": 3.8868, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595112695996955e-05, + "loss": 3.8874, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.5942757391262766e-05, + "loss": 3.8803, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.5934371443752246e-05, + "loss": 3.8785, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5925985496241726e-05, + "loss": 3.8722, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.59175995487312e-05, + "loss": 3.8792, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.5909229980024415e-05, + "loss": 3.887, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.5900844032513895e-05, + "loss": 3.8882, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589245808500337e-05, + "loss": 3.8839, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588407213749285e-05, + "loss": 3.8836, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587568618998233e-05, + "loss": 3.8939, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.5867300242471815e-05, + "loss": 3.8796, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.5858914294961295e-05, + "loss": 3.8785, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.5850544726254504e-05, + "loss": 3.8769, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.5842158778743984e-05, + "loss": 3.8654, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.5833772831233464e-05, + "loss": 3.8872, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.5825386883722943e-05, + "loss": 3.8758, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.5817000936212423e-05, + "loss": 3.8786, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.58086149887019e-05, + "loss": 3.8711, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580024541999511e-05, + "loss": 3.8824, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579185947248459e-05, + "loss": 3.8585, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578347352497407e-05, + "loss": 3.885, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577508757746355e-05, + "loss": 3.8699, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576670162995303e-05, + "loss": 3.8812, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575831568244251e-05, + "loss": 3.8805, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.574992973493199e-05, + "loss": 3.864, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574156016622521e-05, + "loss": 3.864, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573317421871469e-05, + "loss": 3.8819, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572478827120417e-05, + "loss": 3.8581, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571640232369365e-05, + "loss": 3.8587, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570803275498686e-05, + "loss": 3.8773, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569964680747634e-05, + "loss": 3.8715, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569126085996582e-05, + "loss": 3.8571, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.56828749124553e-05, + "loss": 3.858, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567448896494478e-05, + "loss": 3.8597, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566610301743426e-05, + "loss": 3.878, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565771706992373e-05, + "loss": 3.8693, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564933112241322e-05, + "loss": 3.8664, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564096155370643e-05, + "loss": 3.8751, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563257560619591e-05, + "loss": 3.8752, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624189658685386e-05, + "loss": 3.8727, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.5615803711174866e-05, + "loss": 3.8543, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.5607417763664346e-05, + "loss": 3.8694, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.5599031816153826e-05, + "loss": 3.8641, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590645868643306e-05, + "loss": 3.8582, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.5582276299936515e-05, + "loss": 3.8776, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.5573890352425995e-05, + "loss": 3.8638, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.5565504404915475e-05, + "loss": 3.8699, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557118457404955e-05, + "loss": 3.8676, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.5548732509894434e-05, + "loss": 3.8537, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554036294118765e-05, + "loss": 3.8602, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553197699367713e-05, + "loss": 3.8587, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552359104616661e-05, + "loss": 3.8612, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551520509865609e-05, + "loss": 3.8656, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.55068355299493e-05, + "loss": 3.8584, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549844958243878e-05, + "loss": 3.866, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549006363492826e-05, + "loss": 3.8658, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548167768741774e-05, + "loss": 3.8576, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547330811871095e-05, + "loss": 3.8586, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546492217120043e-05, + "loss": 3.8607, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545655260249364e-05, + "loss": 3.8725, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.5448166654983124e-05, + "loss": 3.8589, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5439780707472604e-05, + "loss": 3.8544, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431394759962084e-05, + "loss": 3.8635, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.5423008812451564e-05, + "loss": 3.8586, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.5414622864941044e-05, + "loss": 3.8717, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406236917430524e-05, + "loss": 3.8579, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5397850969920004e-05, + "loss": 3.8573, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538948140121321e-05, + "loss": 3.8535, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538109545370269e-05, + "loss": 3.8609, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537270950619217e-05, + "loss": 3.8369, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536432355868165e-05, + "loss": 3.8498, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535595398997486e-05, + "loss": 3.8593, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534756804246434e-05, + "loss": 3.8528, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533919847375756e-05, + "loss": 3.8449, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533081252624704e-05, + "loss": 3.8462, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532242657873652e-05, + "loss": 3.8483, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314040631226e-05, + "loss": 3.8705, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530565468371548e-05, + "loss": 3.8482, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529726873620496e-05, + "loss": 3.8587, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528888278869444e-05, + "loss": 3.8548, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528049684118392e-05, + "loss": 3.8675, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.5272127272477126e-05, + "loss": 3.8522, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5263741324966606e-05, + "loss": 3.8431, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255355377456086e-05, + "loss": 3.8546, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5246969429945566e-05, + "loss": 3.8558, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238599861238775e-05, + "loss": 3.837, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.5230213913728255e-05, + "loss": 3.8407, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522182796621774e-05, + "loss": 3.8486, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521344201870722e-05, + "loss": 3.8514, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520507245000043e-05, + "loss": 3.8463, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519668650248991e-05, + "loss": 3.861, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518830055497939e-05, + "loss": 3.837, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.5179914607468864e-05, + "loss": 3.8448, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171528659958344e-05, + "loss": 3.837, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516315909125156e-05, + "loss": 3.8601, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515477314374104e-05, + "loss": 3.8592, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514638719623051e-05, + "loss": 3.8458, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513800124872e-05, + "loss": 3.8386, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512963168001321e-05, + "loss": 3.8521, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512124573250269e-05, + "loss": 3.8521, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511285978499217e-05, + "loss": 3.851, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510447383748165e-05, + "loss": 3.8464, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5096104268774865e-05, + "loss": 3.8464, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508771832126434e-05, + "loss": 3.8491, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507933237375382e-05, + "loss": 3.8586, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.50709464262433e-05, + "loss": 3.8382, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506256047873278e-05, + "loss": 3.8382, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505419091002599e-05, + "loss": 3.8413, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504580496251547e-05, + "loss": 3.8296, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503741901500495e-05, + "loss": 3.8518, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.5029033067494434e-05, + "loss": 3.844, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502066349878764e-05, + "loss": 3.8459, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501227755127712e-05, + "loss": 3.8425, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.50038916037666e-05, + "loss": 3.8382, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.910917043685913, + "eval_runtime": 305.7735, + "eval_samples_per_second": 1247.953, + "eval_steps_per_second": 38.999, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499550565625608e-05, + "loss": 3.8372, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498711970874556e-05, + "loss": 3.828, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497873376123504e-05, + "loss": 3.85, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497034781372452e-05, + "loss": 3.8367, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4961961866214e-05, + "loss": 3.8543, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495357591870348e-05, + "loss": 3.8327, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494518997119296e-05, + "loss": 3.8311, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493680402368244e-05, + "loss": 3.8211, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492841807617192e-05, + "loss": 3.8378, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.49200321286614e-05, + "loss": 3.8398, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491166255995462e-05, + "loss": 3.8379, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.49032766124441e-05, + "loss": 3.8456, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489490704373731e-05, + "loss": 3.8297, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488652109622679e-05, + "loss": 3.8315, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487813514871627e-05, + "loss": 3.8246, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486974920120575e-05, + "loss": 3.8215, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486136325369523e-05, + "loss": 3.8314, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.48529773061847e-05, + "loss": 3.8287, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484459135867418e-05, + "loss": 3.8227, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483620541116366e-05, + "loss": 3.84, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482781946365314e-05, + "loss": 3.8318, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481943351614262e-05, + "loss": 3.8304, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.4811063947435836e-05, + "loss": 3.8337, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.4802677999925316e-05, + "loss": 3.8353, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.4794292052414796e-05, + "loss": 3.8187, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.4785906104904276e-05, + "loss": 3.8341, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.4777536536197485e-05, + "loss": 3.8214, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.4769150588686965e-05, + "loss": 3.8232, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.4760764641176445e-05, + "loss": 3.8193, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.4752378693665925e-05, + "loss": 3.8233, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.4743992746155405e-05, + "loss": 3.8303, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.4735623177448614e-05, + "loss": 3.8276, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.4727237229938094e-05, + "loss": 3.8333, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4718851282427574e-05, + "loss": 3.8221, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710465334917054e-05, + "loss": 3.8202, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470209576621027e-05, + "loss": 3.8238, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469370981869975e-05, + "loss": 3.8179, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468532387118923e-05, + "loss": 3.8094, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467693792367871e-05, + "loss": 3.8098, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466856835497192e-05, + "loss": 3.8126, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.46601824074614e-05, + "loss": 3.8194, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465179645995088e-05, + "loss": 3.8245, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464341051244036e-05, + "loss": 3.8196, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463502456492984e-05, + "loss": 3.8154, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462663861741932e-05, + "loss": 3.8273, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461826904871253e-05, + "loss": 3.8184, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460988310120201e-05, + "loss": 3.8141, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460149715369149e-05, + "loss": 3.8119, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593111206180974e-05, + "loss": 3.8006, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584725258670454e-05, + "loss": 3.8255, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457635568996366e-05, + "loss": 3.8108, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456796974245314e-05, + "loss": 3.8169, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455958379494262e-05, + "loss": 3.8123, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.45511978474321e-05, + "loss": 3.8094, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454282827872531e-05, + "loss": 3.8005, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453444233121479e-05, + "loss": 3.8158, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452605638370427e-05, + "loss": 3.8096, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451767043619375e-05, + "loss": 3.8213, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450928448868323e-05, + "loss": 3.8164, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450091491997644e-05, + "loss": 3.8063, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449252897246593e-05, + "loss": 3.8005, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448414302495541e-05, + "loss": 3.8181, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447575707744489e-05, + "loss": 3.8001, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446737112993436e-05, + "loss": 3.7955, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4459001561227577e-05, + "loss": 3.8146, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450615613717056e-05, + "loss": 3.813, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442229666206536e-05, + "loss": 3.7968, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443384371869601e-05, + "loss": 3.7964, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425474149989225e-05, + "loss": 3.7957, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.4417088202478705e-05, + "loss": 3.8143, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440870225496818e-05, + "loss": 3.8086, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.4400316307457665e-05, + "loss": 3.8061, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.4391930359947145e-05, + "loss": 3.8126, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438356079124036e-05, + "loss": 3.8104, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.4375174843729834e-05, + "loss": 3.8149, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.4366788896219314e-05, + "loss": 3.7975, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.4358402948708794e-05, + "loss": 3.8058, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435003338000201e-05, + "loss": 3.806, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434164743249148e-05, + "loss": 3.7947, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433326148498096e-05, + "loss": 3.8207, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432487553747044e-05, + "loss": 3.8034, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431648958995992e-05, + "loss": 3.8091, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430812002125313e-05, + "loss": 3.8142, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429973407374262e-05, + "loss": 3.795, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.42913481262321e-05, + "loss": 3.7995, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428296217872158e-05, + "loss": 3.8001, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427459261001479e-05, + "loss": 3.802, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426620666250427e-05, + "loss": 3.8039, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425782071499375e-05, + "loss": 3.8021, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424943476748323e-05, + "loss": 3.8054, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424106519877644e-05, + "loss": 3.8069, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423269563006965e-05, + "loss": 3.796, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224309682559126e-05, + "loss": 3.801, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4215923735048606e-05, + "loss": 3.8026, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207537787538086e-05, + "loss": 3.8138, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419915184002757e-05, + "loss": 3.8018, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419076589251705e-05, + "loss": 3.7945, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418237994500653e-05, + "loss": 3.8058, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417399399749601e-05, + "loss": 3.8001, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416562442878922e-05, + "loss": 3.8171, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.41572384812787e-05, + "loss": 3.8022, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414885253376818e-05, + "loss": 3.7974, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414046658625766e-05, + "loss": 3.7932, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413209701755087e-05, + "loss": 3.8061, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412371107004035e-05, + "loss": 3.7788, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411532512252983e-05, + "loss": 3.7925, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410693917501931e-05, + "loss": 3.7999, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409855322750879e-05, + "loss": 3.7979, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4090200037605735e-05, + "loss": 3.7866, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4081814090095215e-05, + "loss": 3.7878, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073428142584695e-05, + "loss": 3.7928, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4065042195074175e-05, + "loss": 3.8102, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056656247563655e-05, + "loss": 3.7969, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.4048270300053135e-05, + "loss": 3.8006, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4039884352542615e-05, + "loss": 3.8012, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031498405032095e-05, + "loss": 3.806, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.4023128836325304e-05, + "loss": 3.7992, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.4014742888814784e-05, + "loss": 3.7859, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.4006356941304264e-05, + "loss": 3.7956, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.3997970993793744e-05, + "loss": 3.8003, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398960142508696e-05, + "loss": 3.7827, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398121547757644e-05, + "loss": 3.7858, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397282953006592e-05, + "loss": 3.7901, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.39644435825554e-05, + "loss": 3.7961, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395607401384861e-05, + "loss": 3.7929, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394768806633809e-05, + "loss": 3.8035, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393930211882757e-05, + "loss": 3.7791, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393091617131705e-05, + "loss": 3.7899, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392254660261026e-05, + "loss": 3.7826, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391416065509974e-05, + "loss": 3.8067, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390577470758922e-05, + "loss": 3.7968, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.38973887600787e-05, + "loss": 3.7974, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388900281256818e-05, + "loss": 3.7789, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880633243861394e-05, + "loss": 3.7989, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872247296350874e-05, + "loss": 3.8028, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3863861348840353e-05, + "loss": 3.7915, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855475401329833e-05, + "loss": 3.789, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384710583262304e-05, + "loss": 3.7976, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383871988511252e-05, + "loss": 3.7914, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830333937602e-05, + "loss": 3.8049, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382194799009148e-05, + "loss": 3.7811, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381357842138469e-05, + "loss": 3.7876, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380519247387417e-05, + "loss": 3.7858, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379680652636365e-05, + "loss": 3.7782, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378842057885313e-05, + "loss": 3.7937, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378005101014635e-05, + "loss": 3.7894, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377166506263583e-05, + "loss": 3.7931, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376327911512531e-05, + "loss": 3.7875, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375489316761479e-05, + "loss": 3.7878, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.885859251022339, + "eval_runtime": 310.1674, + "eval_samples_per_second": 1230.275, + "eval_steps_per_second": 38.447, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746523598907996e-05, + "loss": 3.783, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3738137651397476e-05, + "loss": 3.7718, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.3729751703886956e-05, + "loss": 3.7975, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.3721365756376436e-05, + "loss": 3.7858, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.3712996187669645e-05, + "loss": 3.8, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.3704610240159125e-05, + "loss": 3.7811, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.3696224292648605e-05, + "loss": 3.7745, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.3687838345138085e-05, + "loss": 3.7695, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.36794687764313e-05, + "loss": 3.7827, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367108282892078e-05, + "loss": 3.7887, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366269688141026e-05, + "loss": 3.7845, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.3654310933899734e-05, + "loss": 3.7949, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364594136519295e-05, + "loss": 3.7765, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363755541768243e-05, + "loss": 3.7824, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362916947017191e-05, + "loss": 3.7729, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362078352266138e-05, + "loss": 3.767, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361239757515086e-05, + "loss": 3.7779, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360401162764034e-05, + "loss": 3.7765, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359562568012982e-05, + "loss": 3.7715, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.35872397326193e-05, + "loss": 3.7859, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357887016391252e-05, + "loss": 3.7836, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.3570484216402e-05, + "loss": 3.78, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356209826889148e-05, + "loss": 3.7799, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355371232138096e-05, + "loss": 3.7823, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354534275267417e-05, + "loss": 3.7688, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353695680516365e-05, + "loss": 3.7831, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352857085765313e-05, + "loss": 3.7712, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352018491014261e-05, + "loss": 3.772, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3511815341435817e-05, + "loss": 3.7728, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503429393925297e-05, + "loss": 3.7687, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3495043446414777e-05, + "loss": 3.7787, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486657498904256e-05, + "loss": 3.7793, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347828793019747e-05, + "loss": 3.7805, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.346990198268695e-05, + "loss": 3.7705, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346151603517643e-05, + "loss": 3.7658, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345313008766591e-05, + "loss": 3.7795, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344476051895912e-05, + "loss": 3.7691, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.34363745714486e-05, + "loss": 3.7546, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342798862393808e-05, + "loss": 3.7646, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341960267642756e-05, + "loss": 3.7616, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341123310772077e-05, + "loss": 3.7687, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340284716021025e-05, + "loss": 3.7767, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339446121269973e-05, + "loss": 3.7689, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338607526518921e-05, + "loss": 3.771, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.3377705696482426e-05, + "loss": 3.7752, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.3369319748971906e-05, + "loss": 3.7667, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3360933801461386e-05, + "loss": 3.7689, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.3352547853950866e-05, + "loss": 3.7637, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3344178285244075e-05, + "loss": 3.7461, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.3335792337733555e-05, + "loss": 3.7772, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.3327406390223035e-05, + "loss": 3.763, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.3319020442712515e-05, + "loss": 3.771, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.3310650874005724e-05, + "loss": 3.7628, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.3302264926495204e-05, + "loss": 3.7602, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3293878978984684e-05, + "loss": 3.7551, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.3285493031474164e-05, + "loss": 3.7633, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327712346276738e-05, + "loss": 3.7645, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326873751525686e-05, + "loss": 3.77, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326035156774634e-05, + "loss": 3.7644, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325196562023582e-05, + "loss": 3.7625, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324359605152903e-05, + "loss": 3.7504, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323521010401851e-05, + "loss": 3.7729, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322682415650799e-05, + "loss": 3.7515, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321843820899747e-05, + "loss": 3.749, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321006864029068e-05, + "loss": 3.7666, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320168269278016e-05, + "loss": 3.7639, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319329674526964e-05, + "loss": 3.7459, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318491079775912e-05, + "loss": 3.7526, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317654122905233e-05, + "loss": 3.746, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316815528154181e-05, + "loss": 3.768, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315976933403129e-05, + "loss": 3.7604, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315138338652077e-05, + "loss": 3.7605, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314301381781398e-05, + "loss": 3.7619, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313462787030346e-05, + "loss": 3.762, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312624192279294e-05, + "loss": 3.7708, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311785597528242e-05, + "loss": 3.7468, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310948640657563e-05, + "loss": 3.7643, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310110045906511e-05, + "loss": 3.7556, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309271451155459e-05, + "loss": 3.7475, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308432856404407e-05, + "loss": 3.7661, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307595899533729e-05, + "loss": 3.762, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306757304782677e-05, + "loss": 3.7614, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305918710031625e-05, + "loss": 3.7681, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305080115280573e-05, + "loss": 3.7482, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042431584098936e-05, + "loss": 3.7525, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3034045636588416e-05, + "loss": 3.7515, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025659689077896e-05, + "loss": 3.7564, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3017273741567376e-05, + "loss": 3.7564, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3008904172860585e-05, + "loss": 3.758, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.3000518225350065e-05, + "loss": 3.7538, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.2992132277839545e-05, + "loss": 3.7647, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983746330329025e-05, + "loss": 3.752, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297537676162224e-05, + "loss": 3.7541, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296699081411172e-05, + "loss": 3.7587, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.29586048666012e-05, + "loss": 3.7653, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295021891909068e-05, + "loss": 3.7596, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294184935038389e-05, + "loss": 3.7457, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293346340287337e-05, + "loss": 3.7605, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292507745536285e-05, + "loss": 3.7567, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291669150785233e-05, + "loss": 3.7655, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290832193914554e-05, + "loss": 3.7567, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.289993599163502e-05, + "loss": 3.7535, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.28915500441245e-05, + "loss": 3.7446, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288316409661398e-05, + "loss": 3.7646, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.2874794527907194e-05, + "loss": 3.7345, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.2866408580396674e-05, + "loss": 3.75, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858022632886154e-05, + "loss": 3.7529, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.2849636685375634e-05, + "loss": 3.7505, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284128349547257e-05, + "loss": 3.7449, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283289754796205e-05, + "loss": 3.7435, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282451160045153e-05, + "loss": 3.7488, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281612565294101e-05, + "loss": 3.764, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280773970543049e-05, + "loss": 3.7542, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279935375791997e-05, + "loss": 3.7507, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279096781040945e-05, + "loss": 3.759, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278258186289893e-05, + "loss": 3.7623, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277421229419215e-05, + "loss": 3.7557, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276582634668163e-05, + "loss": 3.7426, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275744039917111e-05, + "loss": 3.7521, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274905445166059e-05, + "loss": 3.7545, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.27406848829538e-05, + "loss": 3.7375, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273229893544328e-05, + "loss": 3.7392, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272391298793276e-05, + "loss": 3.7493, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271552704042223e-05, + "loss": 3.7488, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.2707157471715446e-05, + "loss": 3.7489, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.2698771524204926e-05, + "loss": 3.7578, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.2690385576694406e-05, + "loss": 3.7401, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.2681999629183886e-05, + "loss": 3.7435, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.26736300604771e-05, + "loss": 3.7442, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266524411296658e-05, + "loss": 3.7572, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.2656858165456055e-05, + "loss": 3.7521, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.2648472217945535e-05, + "loss": 3.7529, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.264010264923875e-05, + "loss": 3.7403, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263171670172823e-05, + "loss": 3.7539, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623330754217704e-05, + "loss": 3.7573, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2614944806707184e-05, + "loss": 3.749, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.26065752380004e-05, + "loss": 3.7462, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259818929048988e-05, + "loss": 3.7533, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258980334297936e-05, + "loss": 3.7473, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258141739546884e-05, + "loss": 3.7654, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.2573047826762055e-05, + "loss": 3.7363, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256466187925153e-05, + "loss": 3.7466, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255627593174101e-05, + "loss": 3.7364, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254788998423049e-05, + "loss": 3.7376, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.2539520415523704e-05, + "loss": 3.7528, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253113446801318e-05, + "loss": 3.7424, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252274852050266e-05, + "loss": 3.7575, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251436257299214e-05, + "loss": 3.7369, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250599300428535e-05, + "loss": 3.7506, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.8703465461730957, + "eval_runtime": 308.3851, + "eval_samples_per_second": 1237.385, + "eval_steps_per_second": 38.669, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2497607056774826e-05, + "loss": 3.7521, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248922110926431e-05, + "loss": 3.7261, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248083516175379e-05, + "loss": 3.7522, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247244921424327e-05, + "loss": 3.7465, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246406326673275e-05, + "loss": 3.7556, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245567731922223e-05, + "loss": 3.7373, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244729137171171e-05, + "loss": 3.7306, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243890542420119e-05, + "loss": 3.7301, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.24305358554944e-05, + "loss": 3.7415, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242214990798388e-05, + "loss": 3.7442, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241376396047336e-05, + "loss": 3.7436, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240537801296284e-05, + "loss": 3.7521, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239702482305978e-05, + "loss": 3.739, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238863887554927e-05, + "loss": 3.7388, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238025292803875e-05, + "loss": 3.7304, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237186698052823e-05, + "loss": 3.7235, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236348103301771e-05, + "loss": 3.7389, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235509508550719e-05, + "loss": 3.7325, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234670913799667e-05, + "loss": 3.7314, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.2338323190486147e-05, + "loss": 3.7443, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2329953621779356e-05, + "loss": 3.7461, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.2321567674268836e-05, + "loss": 3.7373, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2313181726758316e-05, + "loss": 3.7375, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304795779247796e-05, + "loss": 3.7386, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296426210541005e-05, + "loss": 3.7323, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2288040263030485e-05, + "loss": 3.7382, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279654315519965e-05, + "loss": 3.7297, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227126836800945e-05, + "loss": 3.7336, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226289879930266e-05, + "loss": 3.7317, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225451285179214e-05, + "loss": 3.7307, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224612690428162e-05, + "loss": 3.7325, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.22377409567711e-05, + "loss": 3.7366, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222937138806431e-05, + "loss": 3.7397, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222098544055379e-05, + "loss": 3.7351, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221259949304327e-05, + "loss": 3.7238, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220421354553275e-05, + "loss": 3.7382, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219584397682596e-05, + "loss": 3.7322, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218745802931544e-05, + "loss": 3.7169, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217907208180492e-05, + "loss": 3.7227, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.21706861342944e-05, + "loss": 3.7219, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2162316565587614e-05, + "loss": 3.727, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2153930618077094e-05, + "loss": 3.735, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145544670566574e-05, + "loss": 3.7283, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137158723056054e-05, + "loss": 3.7349, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212878915434926e-05, + "loss": 3.7374, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212040320683874e-05, + "loss": 3.724, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211201725932822e-05, + "loss": 3.7278, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.21036313118177e-05, + "loss": 3.7282, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209526174311091e-05, + "loss": 3.7015, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208687579560039e-05, + "loss": 3.7421, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207848984808987e-05, + "loss": 3.7212, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207010390057935e-05, + "loss": 3.7364, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206173433187257e-05, + "loss": 3.7183, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205334838436205e-05, + "loss": 3.7246, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204496243685153e-05, + "loss": 3.7132, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203657648934101e-05, + "loss": 3.722, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202820692063422e-05, + "loss": 3.7255, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.20198209731237e-05, + "loss": 3.7342, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011435025613177e-05, + "loss": 3.7325, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.2003065456906386e-05, + "loss": 3.7165, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994679509395866e-05, + "loss": 3.711, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1986293561885346e-05, + "loss": 3.7386, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.1977907614374826e-05, + "loss": 3.7102, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196953804566804e-05, + "loss": 3.7067, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196115209815752e-05, + "loss": 3.726, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.1952766150647e-05, + "loss": 3.7304, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194438020313648e-05, + "loss": 3.7047, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193601063442969e-05, + "loss": 3.7139, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192762468691917e-05, + "loss": 3.7089, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191923873940865e-05, + "loss": 3.7262, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191085279189813e-05, + "loss": 3.724, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190248322319134e-05, + "loss": 3.7224, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189409727568082e-05, + "loss": 3.72, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.18857113281703e-05, + "loss": 3.7246, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187732538065978e-05, + "loss": 3.7353, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1868955811952995e-05, + "loss": 3.708, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860569864442475e-05, + "loss": 3.7253, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.1852183916931955e-05, + "loss": 3.7212, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1843797969421435e-05, + "loss": 3.7089, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835428400714644e-05, + "loss": 3.7259, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1827042453204124e-05, + "loss": 3.7255, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818656505693604e-05, + "loss": 3.7238, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181027055818308e-05, + "loss": 3.7299, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180190098947629e-05, + "loss": 3.7078, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179351504196577e-05, + "loss": 3.7164, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178512909445525e-05, + "loss": 3.7149, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177674314694473e-05, + "loss": 3.7186, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176837357823795e-05, + "loss": 3.7169, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175998763072743e-05, + "loss": 3.7247, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175160168321691e-05, + "loss": 3.7103, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174321573570638e-05, + "loss": 3.7289, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.17348461669996e-05, + "loss": 3.7175, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172646021948908e-05, + "loss": 3.7155, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171807427197855e-05, + "loss": 3.7224, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170970470327177e-05, + "loss": 3.7251, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170131875576125e-05, + "loss": 3.7264, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169293280825073e-05, + "loss": 3.7077, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684546860740207e-05, + "loss": 3.7208, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1676160913229687e-05, + "loss": 3.7192, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667774965719167e-05, + "loss": 3.7259, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1659389018208646e-05, + "loss": 3.7214, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1651003070698126e-05, + "loss": 3.7137, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642633501991336e-05, + "loss": 3.7123, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1634247554480815e-05, + "loss": 3.723, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625861606970295e-05, + "loss": 3.6985, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617475659459775e-05, + "loss": 3.7119, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609106090752984e-05, + "loss": 3.7152, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.1600720143242464e-05, + "loss": 3.7156, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1592350574535674e-05, + "loss": 3.7066, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158396462702516e-05, + "loss": 3.7103, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157557867951464e-05, + "loss": 3.7122, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156719273200412e-05, + "loss": 3.7252, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.15588067844936e-05, + "loss": 3.7201, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155042083698308e-05, + "loss": 3.7112, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154205126827629e-05, + "loss": 3.7223, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153366532076577e-05, + "loss": 3.7255, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152527937325525e-05, + "loss": 3.7213, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151689342574473e-05, + "loss": 3.7035, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150850747823421e-05, + "loss": 3.7145, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150012153072369e-05, + "loss": 3.7201, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149173558321317e-05, + "loss": 3.6999, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148334963570265e-05, + "loss": 3.7029, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147498006699586e-05, + "loss": 3.7132, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466594119485345e-05, + "loss": 3.7085, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458208171974825e-05, + "loss": 3.7148, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449822224464305e-05, + "loss": 3.7219, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441452655757514e-05, + "loss": 3.7073, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1433066708246994e-05, + "loss": 3.7062, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424680760736474e-05, + "loss": 3.7115, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1416294813225954e-05, + "loss": 3.7196, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140792524451916e-05, + "loss": 3.714, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139953929700864e-05, + "loss": 3.7194, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139115334949812e-05, + "loss": 3.7018, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.13827674019876e-05, + "loss": 3.7175, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137439783328081e-05, + "loss": 3.721, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136601188577029e-05, + "loss": 3.712, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135762593825978e-05, + "loss": 3.7144, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134923999074926e-05, + "loss": 3.7149, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134087042204247e-05, + "loss": 3.7097, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133248447453195e-05, + "loss": 3.7278, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132409852702143e-05, + "loss": 3.704, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131571257951091e-05, + "loss": 3.7103, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307343010804116e-05, + "loss": 3.703, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1298957063293596e-05, + "loss": 3.7026, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.1290571115783076e-05, + "loss": 3.713, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.1282185168272556e-05, + "loss": 3.7101, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273815599565765e-05, + "loss": 3.7192, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1265429652055245e-05, + "loss": 3.7031, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125704370454473e-05, + "loss": 3.7161, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.8606925010681152, + "eval_runtime": 312.732, + "eval_samples_per_second": 1220.185, + "eval_steps_per_second": 38.132, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124865775703421e-05, + "loss": 3.7031, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.124028818832742e-05, + "loss": 3.6931, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.12319022408169e-05, + "loss": 3.714, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122351629330638e-05, + "loss": 3.7099, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121513034579586e-05, + "loss": 3.7182, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120676077708907e-05, + "loss": 3.7051, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119837482957855e-05, + "loss": 3.6997, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.118998888206803e-05, + "loss": 3.6976, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118160293455751e-05, + "loss": 3.7067, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117323336585072e-05, + "loss": 3.7062, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.11648474183402e-05, + "loss": 3.7083, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1156461470829686e-05, + "loss": 3.7163, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1148091902122895e-05, + "loss": 3.7034, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139705954612375e-05, + "loss": 3.7046, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.1131320007101855e-05, + "loss": 3.6967, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.1122934059591335e-05, + "loss": 3.6886, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111454811208081e-05, + "loss": 3.7031, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110616216457029e-05, + "loss": 3.7016, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109777621705977e-05, + "loss": 3.6971, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108939026954925e-05, + "loss": 3.7009, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108102070084246e-05, + "loss": 3.7183, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107263475333194e-05, + "loss": 3.7025, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.1064248805821423e-05, + "loss": 3.7024, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1055862858310903e-05, + "loss": 3.7032, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104749328960411e-05, + "loss": 3.6998, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103910734209359e-05, + "loss": 3.7049, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103072139458307e-05, + "loss": 3.6982, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102233544707255e-05, + "loss": 3.7031, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101396587836576e-05, + "loss": 3.6942, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100557993085524e-05, + "loss": 3.6943, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099719398334472e-05, + "loss": 3.6981, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.09888080358342e-05, + "loss": 3.7067, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.098043846712741e-05, + "loss": 3.7065, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097205251961689e-05, + "loss": 3.7007, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096366657210638e-05, + "loss": 3.6932, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095528062459586e-05, + "loss": 3.6991, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0946911055889066e-05, + "loss": 3.7001, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0938525108378546e-05, + "loss": 3.6863, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930139160868026e-05, + "loss": 3.6868, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921753213357506e-05, + "loss": 3.6862, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913383644650715e-05, + "loss": 3.694, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0904997697140195e-05, + "loss": 3.698, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.0896611749629675e-05, + "loss": 3.6933, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0888225802119155e-05, + "loss": 3.7024, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.0879856233412364e-05, + "loss": 3.6993, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.0871470285901844e-05, + "loss": 3.6934, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086308433839133e-05, + "loss": 3.6965, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085471476968454e-05, + "loss": 3.6933, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084632882217402e-05, + "loss": 3.6702, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.08379428746635e-05, + "loss": 3.7061, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082955692715298e-05, + "loss": 3.6858, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082118735844619e-05, + "loss": 3.7027, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081280141093567e-05, + "loss": 3.6926, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080441546342515e-05, + "loss": 3.6895, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079602951591463e-05, + "loss": 3.6791, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078765994720784e-05, + "loss": 3.6869, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077927399969732e-05, + "loss": 3.6965, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.07708880521868e-05, + "loss": 3.6954, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0762502104676284e-05, + "loss": 3.6978, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0754132535969494e-05, + "loss": 3.6894, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745746588458974e-05, + "loss": 3.6775, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0737360640948453e-05, + "loss": 3.7041, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.0728974693437933e-05, + "loss": 3.6784, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072060512473114e-05, + "loss": 3.669, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071221917722062e-05, + "loss": 3.6921, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.07038332297101e-05, + "loss": 3.6974, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069544728219958e-05, + "loss": 3.6757, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068707771349279e-05, + "loss": 3.684, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067869176598227e-05, + "loss": 3.6748, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067030581847175e-05, + "loss": 3.6918, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066191987096124e-05, + "loss": 3.6939, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065355030225445e-05, + "loss": 3.6885, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064516435474393e-05, + "loss": 3.6887, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063677840723341e-05, + "loss": 3.6934, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062839245972289e-05, + "loss": 3.7014, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620022891016096e-05, + "loss": 3.6768, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611636943505576e-05, + "loss": 3.6941, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0603250995995056e-05, + "loss": 3.6819, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594865048484536e-05, + "loss": 3.6806, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0586495479777745e-05, + "loss": 3.6944, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578109532267225e-05, + "loss": 3.696, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569723584756705e-05, + "loss": 3.6886, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056133763724619e-05, + "loss": 3.701, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.05529680685394e-05, + "loss": 3.6733, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054458212102888e-05, + "loss": 3.6799, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053619617351836e-05, + "loss": 3.6838, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052781022600784e-05, + "loss": 3.6898, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051944065730105e-05, + "loss": 3.6842, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051105470979053e-05, + "loss": 3.6929, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050266876228001e-05, + "loss": 3.6792, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049428281476949e-05, + "loss": 3.6969, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.04859132460627e-05, + "loss": 3.6894, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047752729855218e-05, + "loss": 3.6808, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046914135104166e-05, + "loss": 3.6884, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.0460771782334875e-05, + "loss": 3.6941, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.0452385834824355e-05, + "loss": 3.6934, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.0443999887313835e-05, + "loss": 3.68, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.0435613939803314e-05, + "loss": 3.684, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.0427227992292794e-05, + "loss": 3.6864, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.0418842044782274e-05, + "loss": 3.6968, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.0410456097271754e-05, + "loss": 3.6913, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.0402070149761234e-05, + "loss": 3.682, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039370058105444e-05, + "loss": 3.6819, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038531463354392e-05, + "loss": 3.6932, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.03769286860334e-05, + "loss": 3.6632, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036854273852288e-05, + "loss": 3.6819, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036017316981609e-05, + "loss": 3.6817, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035178722230558e-05, + "loss": 3.6859, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034341765359879e-05, + "loss": 3.6731, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033503170608827e-05, + "loss": 3.6802, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032664575857775e-05, + "loss": 3.6852, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031825981106723e-05, + "loss": 3.6909, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030987386355671e-05, + "loss": 3.6863, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030148791604618e-05, + "loss": 3.6815, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.02931183473394e-05, + "loss": 3.691, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028473239982888e-05, + "loss": 3.6956, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027634645231836e-05, + "loss": 3.6884, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026796050480783e-05, + "loss": 3.6723, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025957455729732e-05, + "loss": 3.6851, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.02511886097868e-05, + "loss": 3.6887, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024280266227628e-05, + "loss": 3.6679, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023441671476576e-05, + "loss": 3.6739, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0226047146058966e-05, + "loss": 3.6819, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217661198548446e-05, + "loss": 3.6808, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0209275251037926e-05, + "loss": 3.6792, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200889303527406e-05, + "loss": 3.6903, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0192519734820615e-05, + "loss": 3.6815, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0184133787310095e-05, + "loss": 3.6732, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175747839799575e-05, + "loss": 3.6796, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0167361892289055e-05, + "loss": 3.6932, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015899232358227e-05, + "loss": 3.6804, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015060637607175e-05, + "loss": 3.6921, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014222042856123e-05, + "loss": 3.6698, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013383448105071e-05, + "loss": 3.6866, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012546491234392e-05, + "loss": 3.6892, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011709534363713e-05, + "loss": 3.6843, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010870939612661e-05, + "loss": 3.6815, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010032344861609e-05, + "loss": 3.6843, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009193750110557e-05, + "loss": 3.6796, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008355155359505e-05, + "loss": 3.6979, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007516560608453e-05, + "loss": 3.673, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006677965857401e-05, + "loss": 3.6814, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005839371106349e-05, + "loss": 3.6761, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.0050024142356704e-05, + "loss": 3.6741, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.0041638194846184e-05, + "loss": 3.6767, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0033252247335664e-05, + "loss": 3.6792, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0024866299825144e-05, + "loss": 3.691, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001649673111835e-05, + "loss": 3.673, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000811078360783e-05, + "loss": 3.6852, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.8535947799682617, + "eval_runtime": 310.4307, + "eval_samples_per_second": 1229.231, + "eval_steps_per_second": 38.414, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999972483609731e-05, + "loss": 3.6847, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999133888858679e-05, + "loss": 3.664, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998295294107627e-05, + "loss": 3.6856, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997456699356575e-05, + "loss": 3.682, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996618104605523e-05, + "loss": 3.6878, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995779509854471e-05, + "loss": 3.6727, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994940915103419e-05, + "loss": 3.6746, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994102320352367e-05, + "loss": 3.665, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993265363481689e-05, + "loss": 3.6742, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992426768730637e-05, + "loss": 3.6797, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991588173979584e-05, + "loss": 3.6751, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990749579228532e-05, + "loss": 3.6839, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989914260238227e-05, + "loss": 3.6825, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989075665487175e-05, + "loss": 3.6673, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882370707361227e-05, + "loss": 3.665, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9873984759850707e-05, + "loss": 3.6637, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865598812340187e-05, + "loss": 3.6728, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857212864829666e-05, + "loss": 3.672, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848826917319146e-05, + "loss": 3.6648, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9840440969808626e-05, + "loss": 3.6752, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983207140110184e-05, + "loss": 3.6865, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823685453591315e-05, + "loss": 3.6739, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9815299506080795e-05, + "loss": 3.6762, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9806913558570275e-05, + "loss": 3.6707, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979854398986349e-05, + "loss": 3.6714, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9790158042352964e-05, + "loss": 3.6754, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781772094842444e-05, + "loss": 3.664, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9773386147331924e-05, + "loss": 3.678, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976501657862514e-05, + "loss": 3.6635, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975663063111461e-05, + "loss": 3.6623, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974824468360409e-05, + "loss": 3.6721, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973985873609358e-05, + "loss": 3.6702, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973148916738679e-05, + "loss": 3.6753, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972310321987627e-05, + "loss": 3.6747, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971471727236575e-05, + "loss": 3.6619, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970633132485523e-05, + "loss": 3.6686, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969796175614844e-05, + "loss": 3.6755, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968957580863792e-05, + "loss": 3.6538, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.96811898611274e-05, + "loss": 3.6612, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967280391361688e-05, + "loss": 3.6599, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966443434491009e-05, + "loss": 3.6633, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965604839739957e-05, + "loss": 3.6666, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964766244988905e-05, + "loss": 3.6665, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963929288118226e-05, + "loss": 3.6772, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963090693367174e-05, + "loss": 3.666, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962252098616122e-05, + "loss": 3.6691, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.96141350386507e-05, + "loss": 3.6653, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960576546994391e-05, + "loss": 3.6653, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959737952243339e-05, + "loss": 3.6419, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958899357492287e-05, + "loss": 3.6779, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958060762741235e-05, + "loss": 3.6602, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957223805870556e-05, + "loss": 3.6731, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956385211119504e-05, + "loss": 3.6629, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955546616368452e-05, + "loss": 3.6632, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9547080216174e-05, + "loss": 3.6477, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.9538710647467217e-05, + "loss": 3.6612, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.9530324699956696e-05, + "loss": 3.6714, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.9521938752446176e-05, + "loss": 3.6617, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.9513552804935656e-05, + "loss": 3.6702, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.9505183236228865e-05, + "loss": 3.6642, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.9496797288718345e-05, + "loss": 3.6425, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9488411341207825e-05, + "loss": 3.6744, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9480025393697305e-05, + "loss": 3.654, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471655824990514e-05, + "loss": 3.6437, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9463269877479994e-05, + "loss": 3.6682, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454883929969474e-05, + "loss": 3.6642, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446497982458954e-05, + "loss": 3.6479, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943812841375217e-05, + "loss": 3.6543, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942974246624165e-05, + "loss": 3.6507, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942135651873113e-05, + "loss": 3.6622, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941297057122061e-05, + "loss": 3.6645, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940460100251382e-05, + "loss": 3.6599, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.93962150550033e-05, + "loss": 3.664, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938782910749278e-05, + "loss": 3.6628, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937944315998226e-05, + "loss": 3.673, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937107359127547e-05, + "loss": 3.6493, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936268764376495e-05, + "loss": 3.6638, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935430169625443e-05, + "loss": 3.6548, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934591574874391e-05, + "loss": 3.6532, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9337546180037124e-05, + "loss": 3.6653, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329160232526604e-05, + "loss": 3.6652, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9320774285016084e-05, + "loss": 3.6621, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9312388337505564e-05, + "loss": 3.6736, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930401876879877e-05, + "loss": 3.6462, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929563282128825e-05, + "loss": 3.654, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928724687377773e-05, + "loss": 3.6544, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927886092626721e-05, + "loss": 3.6629, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927049135756042e-05, + "loss": 3.6547, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.92621054100499e-05, + "loss": 3.6641, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925371946253938e-05, + "loss": 3.6548, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924533351502886e-05, + "loss": 3.6639, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923698032512581e-05, + "loss": 3.6612, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922859437761529e-05, + "loss": 3.6538, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9220208430104767e-05, + "loss": 3.6626, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211822482594247e-05, + "loss": 3.6651, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9203436535083726e-05, + "loss": 3.6685, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9195050587573206e-05, + "loss": 3.6526, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.9186664640062686e-05, + "loss": 3.653, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178278692552166e-05, + "loss": 3.6621, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169909123845375e-05, + "loss": 3.669, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161523176334855e-05, + "loss": 3.6607, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9153137228824335e-05, + "loss": 3.6594, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144751281313815e-05, + "loss": 3.6547, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913638171260703e-05, + "loss": 3.6608, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912799576509651e-05, + "loss": 3.6399, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911960981758599e-05, + "loss": 3.6589, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911122387007547e-05, + "loss": 3.6447, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910285430136868e-05, + "loss": 3.6599, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909448473266189e-05, + "loss": 3.6486, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908609878515137e-05, + "loss": 3.6591, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907771283764085e-05, + "loss": 3.6545, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906932689013033e-05, + "loss": 3.664, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906094094261981e-05, + "loss": 3.6582, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905255499510929e-05, + "loss": 3.6561, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904416904759877e-05, + "loss": 3.6645, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035799478891985e-05, + "loss": 3.6656, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027413531381465e-05, + "loss": 3.6608, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9019027583870945e-05, + "loss": 3.6512, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010641636360425e-05, + "loss": 3.6528, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.9002255688849905e-05, + "loss": 3.6627, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993869741339385e-05, + "loss": 3.6467, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8985483793828865e-05, + "loss": 3.6429, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8977114225122074e-05, + "loss": 3.6546, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.8968728277611554e-05, + "loss": 3.653, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8960342330101034e-05, + "loss": 3.6524, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8951956382590514e-05, + "loss": 3.6637, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894358681388372e-05, + "loss": 3.6535, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.89352008663732e-05, + "loss": 3.6492, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892681491886269e-05, + "loss": 3.6495, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891842897135217e-05, + "loss": 3.6652, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891005940264538e-05, + "loss": 3.6571, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890167345513486e-05, + "loss": 3.6598, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889328750762434e-05, + "loss": 3.6445, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888490156011381e-05, + "loss": 3.6632, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887653199140703e-05, + "loss": 3.6625, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886814604389651e-05, + "loss": 3.6572, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885976009638599e-05, + "loss": 3.6555, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885137414887546e-05, + "loss": 3.6534, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884302095897241e-05, + "loss": 3.655, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883463501146189e-05, + "loss": 3.6721, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882624906395137e-05, + "loss": 3.6479, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881786311644085e-05, + "loss": 3.6547, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880949354773406e-05, + "loss": 3.6492, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880110760022354e-05, + "loss": 3.6489, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879272165271302e-05, + "loss": 3.6475, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.87843357052025e-05, + "loss": 3.6536, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877594975769198e-05, + "loss": 3.6634, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876756381018146e-05, + "loss": 3.6509, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8759177862670934e-05, + "loss": 3.6542, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.849144697189331, + "eval_runtime": 303.497, + "eval_samples_per_second": 1257.314, + "eval_steps_per_second": 39.292, + "step": 686880 + }, + { + "epoch": 0.0, + "learning_rate": 3.8750791915160414e-05, + "loss": 3.6581, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.8742405967649894e-05, + "loss": 3.6392, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.873402002013938e-05, + "loss": 3.6577, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.872563407262886e-05, + "loss": 3.654, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.871724812511834e-05, + "loss": 3.6654, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.870886217760782e-05, + "loss": 3.6454, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.87004762300973e-05, + "loss": 3.6479, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.869209028258678e-05, + "loss": 3.6389, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.868372071387999e-05, + "loss": 3.6498, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.867533476636947e-05, + "loss": 3.6535, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.866694881885895e-05, + "loss": 3.6471, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.865856287134843e-05, + "loss": 3.6576, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.865020968144537e-05, + "loss": 3.661, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.864182373393485e-05, + "loss": 3.6393, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.8633437786424334e-05, + "loss": 3.6412, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.8625051838913814e-05, + "loss": 3.6371, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.8616665891403294e-05, + "loss": 3.6497, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.8608279943892774e-05, + "loss": 3.6398, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.8599893996382254e-05, + "loss": 3.6426, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.8591508048871734e-05, + "loss": 3.6489, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.858313848016494e-05, + "loss": 3.6585, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.857475253265442e-05, + "loss": 3.65, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.856638296394763e-05, + "loss": 3.6483, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.855799701643711e-05, + "loss": 3.6458, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.854961106892659e-05, + "loss": 3.6472, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.854122512141607e-05, + "loss": 3.6508, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853283917390555e-05, + "loss": 3.6354, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.852445322639503e-05, + "loss": 3.6531, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.851608365768825e-05, + "loss": 3.6392, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.850769771017773e-05, + "loss": 3.6366, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.849931176266721e-05, + "loss": 3.6489, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.849092581515669e-05, + "loss": 3.6458, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.848253986764617e-05, + "loss": 3.6448, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.847415392013565e-05, + "loss": 3.6536, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.846576797262512e-05, + "loss": 3.6369, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.84573820251146e-05, + "loss": 3.6439, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.8449028835211546e-05, + "loss": 3.6497, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.8440642887701026e-05, + "loss": 3.6269, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.8432256940190506e-05, + "loss": 3.6382, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.8423870992679986e-05, + "loss": 3.635, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.84155014239732e-05, + "loss": 3.6369, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.840711547646268e-05, + "loss": 3.6423, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.839872952895216e-05, + "loss": 3.6378, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.839034358144164e-05, + "loss": 3.6528, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.838195763393112e-05, + "loss": 3.6409, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.8373571686420595e-05, + "loss": 3.645, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.8365185738910075e-05, + "loss": 3.6395, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.8356799791399555e-05, + "loss": 3.6404, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.834843022269277e-05, + "loss": 3.6205, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.8340044275182244e-05, + "loss": 3.6477, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.8331658327671724e-05, + "loss": 3.6332, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.832327238016121e-05, + "loss": 3.6481, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.831490281145442e-05, + "loss": 3.6357, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.83065168639439e-05, + "loss": 3.6367, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.829813091643338e-05, + "loss": 3.6266, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.828974496892286e-05, + "loss": 3.6371, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.828135902141234e-05, + "loss": 3.6451, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.827297307390182e-05, + "loss": 3.6345, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.826460350519503e-05, + "loss": 3.6508, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.825621755768451e-05, + "loss": 3.6395, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.824783161017399e-05, + "loss": 3.6154, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.823944566266347e-05, + "loss": 3.6511, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823105971515295e-05, + "loss": 3.6314, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.822267376764243e-05, + "loss": 3.6202, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821428782013191e-05, + "loss": 3.6399, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.820590187262139e-05, + "loss": 3.6426, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.8197532303914604e-05, + "loss": 3.6247, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.8189146356404084e-05, + "loss": 3.63, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.818077678769729e-05, + "loss": 3.624, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.817239084018677e-05, + "loss": 3.6388, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.816400489267625e-05, + "loss": 3.64, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.815561894516573e-05, + "loss": 3.6326, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.814723299765521e-05, + "loss": 3.6418, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.813884705014469e-05, + "loss": 3.6366, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.813046110263417e-05, + "loss": 3.6502, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.812207515512365e-05, + "loss": 3.6269, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.811370558641686e-05, + "loss": 3.6381, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810531963890634e-05, + "loss": 3.6303, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.809693369139583e-05, + "loss": 3.63, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.808854774388531e-05, + "loss": 3.6388, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.808017817517852e-05, + "loss": 3.6389, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.8071792227668e-05, + "loss": 3.6435, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.806340628015748e-05, + "loss": 3.6469, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.805502033264696e-05, + "loss": 3.6276, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.8046650763940166e-05, + "loss": 3.6269, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.8038281195233376e-05, + "loss": 3.6303, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.8029895247722855e-05, + "loss": 3.6391, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.8021509300212335e-05, + "loss": 3.6284, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.8013123352701815e-05, + "loss": 3.6346, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.8004737405191295e-05, + "loss": 3.6387, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.799635145768078e-05, + "loss": 3.6366, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.798798188897399e-05, + "loss": 3.6386, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.797959594146347e-05, + "loss": 3.6306, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.797120999395295e-05, + "loss": 3.6399, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.796282404644243e-05, + "loss": 3.6399, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.7954438098931904e-05, + "loss": 3.6446, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.7946052151421384e-05, + "loss": 3.625, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.7937666203910864e-05, + "loss": 3.634, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.792929663520407e-05, + "loss": 3.6375, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.792091068769355e-05, + "loss": 3.6453, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.791252474018303e-05, + "loss": 3.6375, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.790413879267252e-05, + "loss": 3.6359, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.7895752845162e-05, + "loss": 3.6314, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.788736689765148e-05, + "loss": 3.6345, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.787898095014096e-05, + "loss": 3.6188, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.787059500263044e-05, + "loss": 3.6279, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.786222543392365e-05, + "loss": 3.6224, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.785383948641313e-05, + "loss": 3.6402, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.784546991770634e-05, + "loss": 3.6249, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.783708397019582e-05, + "loss": 3.6296, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.78286980226853e-05, + "loss": 3.6333, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.782031207517478e-05, + "loss": 3.6365, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.781192612766426e-05, + "loss": 3.6389, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.780354018015374e-05, + "loss": 3.6315, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.779515423264322e-05, + "loss": 3.6401, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.7786784663936433e-05, + "loss": 3.6414, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.7778398716425913e-05, + "loss": 3.6336, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.777001276891539e-05, + "loss": 3.6326, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.776162682140487e-05, + "loss": 3.6268, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.775324087389435e-05, + "loss": 3.6358, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.774485492638383e-05, + "loss": 3.6293, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.773646897887331e-05, + "loss": 3.6146, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772809941016652e-05, + "loss": 3.63, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.7719713462656e-05, + "loss": 3.6267, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.771132751514548e-05, + "loss": 3.6322, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.770294156763496e-05, + "loss": 3.6366, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.769457199892817e-05, + "loss": 3.6337, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.768618605141765e-05, + "loss": 3.6229, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.767780010390714e-05, + "loss": 3.6269, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.766941415639662e-05, + "loss": 3.6424, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.766104458768983e-05, + "loss": 3.6311, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.765265864017931e-05, + "loss": 3.6388, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.764427269266879e-05, + "loss": 3.6172, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.763588674515827e-05, + "loss": 3.6434, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.7627517176451476e-05, + "loss": 3.6362, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.7619131228940956e-05, + "loss": 3.6351, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.7610761660234165e-05, + "loss": 3.6322, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.7602375712723645e-05, + "loss": 3.6294, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.7593989765213125e-05, + "loss": 3.6278, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.7585603817702605e-05, + "loss": 3.6539, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757721787019209e-05, + "loss": 3.6216, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.7568831922681565e-05, + "loss": 3.6327, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.756046235397478e-05, + "loss": 3.6285, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.755207640646426e-05, + "loss": 3.62, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.7543690458953734e-05, + "loss": 3.6287, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.7535304511443214e-05, + "loss": 3.63, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.7526918563932694e-05, + "loss": 3.6399, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.7518532616422174e-05, + "loss": 3.6291, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.751016304771538e-05, + "loss": 3.6276, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 3.846182107925415, + "eval_runtime": 302.64, + "eval_samples_per_second": 1260.874, + "eval_steps_per_second": 39.403, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750177710020486e-05, + "loss": 3.6327, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749339115269434e-05, + "loss": 3.6157, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748500520518383e-05, + "loss": 3.6342, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747661925767331e-05, + "loss": 3.6339, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746823331016279e-05, + "loss": 3.6403, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745984736265227e-05, + "loss": 3.6253, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745146141514175e-05, + "loss": 3.6236, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744307546763123e-05, + "loss": 3.6169, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743470589892444e-05, + "loss": 3.6219, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742631995141392e-05, + "loss": 3.6321, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.74179340039034e-05, + "loss": 3.6259, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740956443519661e-05, + "loss": 3.6364, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740117848768609e-05, + "loss": 3.6345, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739279254017557e-05, + "loss": 3.6181, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738440659266505e-05, + "loss": 3.6161, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737602064515453e-05, + "loss": 3.6134, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.7367634697644014e-05, + "loss": 3.6297, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7359248750133494e-05, + "loss": 3.6201, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.7350862802622974e-05, + "loss": 3.6165, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734249323391618e-05, + "loss": 3.6239, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733410728640566e-05, + "loss": 3.6366, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732572133889514e-05, + "loss": 3.625, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731733539138462e-05, + "loss": 3.6307, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7308949443874096e-05, + "loss": 3.6215, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.7300563496363576e-05, + "loss": 3.6272, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.7292177548853056e-05, + "loss": 3.626, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7283791601342536e-05, + "loss": 3.6113, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727542203263575e-05, + "loss": 3.6319, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726705246392897e-05, + "loss": 3.6132, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725866651641845e-05, + "loss": 3.6125, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725028056890793e-05, + "loss": 3.6315, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.72418946213974e-05, + "loss": 3.6225, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723350867388688e-05, + "loss": 3.6229, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722512272637636e-05, + "loss": 3.6303, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721673677886584e-05, + "loss": 3.6149, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720835083135532e-05, + "loss": 3.6216, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7199997641452265e-05, + "loss": 3.627, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191611693941745e-05, + "loss": 3.6014, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718322574643122e-05, + "loss": 3.6173, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174839798920705e-05, + "loss": 3.613, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7166453851410185e-05, + "loss": 3.6124, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.71580842827034e-05, + "loss": 3.6236, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7149698335192874e-05, + "loss": 3.6156, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.7141312387682354e-05, + "loss": 3.6292, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.7132926440171834e-05, + "loss": 3.6182, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.7124540492661314e-05, + "loss": 3.6226, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7116154545150794e-05, + "loss": 3.6157, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7107768597640274e-05, + "loss": 3.6174, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.7099382650129754e-05, + "loss": 3.5996, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709101308142296e-05, + "loss": 3.6246, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708262713391244e-05, + "loss": 3.613, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707424118640192e-05, + "loss": 3.6242, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706587161769514e-05, + "loss": 3.6162, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705748567018462e-05, + "loss": 3.6093, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.70490997226741e-05, + "loss": 3.6068, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704071377516358e-05, + "loss": 3.6132, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703232782765306e-05, + "loss": 3.6242, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702394188014254e-05, + "loss": 3.6131, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701557231143575e-05, + "loss": 3.6306, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700718636392523e-05, + "loss": 3.619, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699880041641471e-05, + "loss": 3.5896, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699041446890419e-05, + "loss": 3.6289, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698202852139367e-05, + "loss": 3.608, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697364257388315e-05, + "loss": 3.6007, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696525662637263e-05, + "loss": 3.6141, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695687067886211e-05, + "loss": 3.6224, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694850111015532e-05, + "loss": 3.6027, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.69401151626448e-05, + "loss": 3.6088, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693172921513428e-05, + "loss": 3.6038, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923343267623756e-05, + "loss": 3.6118, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691497369891697e-05, + "loss": 3.6203, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690658775140645e-05, + "loss": 3.6088, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689820180389593e-05, + "loss": 3.6193, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688983223518914e-05, + "loss": 3.6128, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688144628767862e-05, + "loss": 3.6258, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.68730603401681e-05, + "loss": 3.6054, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686467439265758e-05, + "loss": 3.621, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685628844514706e-05, + "loss": 3.6069, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684790249763654e-05, + "loss": 3.6067, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683953292892976e-05, + "loss": 3.6196, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683114698141923e-05, + "loss": 3.6142, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682276103390871e-05, + "loss": 3.6178, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681437508639819e-05, + "loss": 3.6282, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680598913888767e-05, + "loss": 3.61, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679761957018088e-05, + "loss": 3.6013, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678923362267036e-05, + "loss": 3.6079, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678084767515984e-05, + "loss": 3.6176, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677246172764932e-05, + "loss": 3.6051, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676409215894253e-05, + "loss": 3.6167, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6755706211432015e-05, + "loss": 3.6165, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6747320263921495e-05, + "loss": 3.6149, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6738934316410975e-05, + "loss": 3.6134, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6730548368900455e-05, + "loss": 3.6073, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6722162421389935e-05, + "loss": 3.6209, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6713792852683144e-05, + "loss": 3.6169, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.6705406905172624e-05, + "loss": 3.6213, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.6697020957662104e-05, + "loss": 3.6095, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.6688635010151584e-05, + "loss": 3.6096, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.6680249062641064e-05, + "loss": 3.6153, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667187949393427e-05, + "loss": 3.6229, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666349354642375e-05, + "loss": 3.615, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665510759891323e-05, + "loss": 3.613, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664672165140271e-05, + "loss": 3.6141, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.66383357038922e-05, + "loss": 3.6082, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.662996613518541e-05, + "loss": 3.6013, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662158018767489e-05, + "loss": 3.6066, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661319424016437e-05, + "loss": 3.6013, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660480829265385e-05, + "loss": 3.619, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659642234514333e-05, + "loss": 3.6054, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658805277643654e-05, + "loss": 3.6102, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657966682892602e-05, + "loss": 3.6068, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.65712808814155e-05, + "loss": 3.6186, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656289493390498e-05, + "loss": 3.6139, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655450898639446e-05, + "loss": 3.6119, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.6546139417687666e-05, + "loss": 3.6175, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653775347017715e-05, + "loss": 3.6209, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652936752266663e-05, + "loss": 3.614, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652098157515611e-05, + "loss": 3.6081, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651259562764559e-05, + "loss": 3.6057, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.6504209680135066e-05, + "loss": 3.6161, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.6495823732624546e-05, + "loss": 3.6123, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648745416391776e-05, + "loss": 3.5886, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647906821640724e-05, + "loss": 3.6126, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6470682268896715e-05, + "loss": 3.6086, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6462296321386195e-05, + "loss": 3.6101, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6453910373875675e-05, + "loss": 3.617, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6445524426365155e-05, + "loss": 3.61, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643715485765837e-05, + "loss": 3.604, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642876891014785e-05, + "loss": 3.6038, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642038296263733e-05, + "loss": 3.6232, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641199701512681e-05, + "loss": 3.609, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640361106761629e-05, + "loss": 3.6176, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.63952414989095e-05, + "loss": 3.5987, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638685555139898e-05, + "loss": 3.616, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637846960388846e-05, + "loss": 3.6152, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637008365637794e-05, + "loss": 3.6149, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636169770886742e-05, + "loss": 3.6133, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635332814016063e-05, + "loss": 3.6035, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634494219265011e-05, + "loss": 3.6116, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633655624513959e-05, + "loss": 3.6287, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632817029762907e-05, + "loss": 3.603, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6319784350118555e-05, + "loss": 3.6091, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6311398402608035e-05, + "loss": 3.6054, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.6303028833901244e-05, + "loss": 3.6046, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6294642886390724e-05, + "loss": 3.6049, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.6286256938880204e-05, + "loss": 3.6093, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6277870991369684e-05, + "loss": 3.6141, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626950142266289e-05, + "loss": 3.6162, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626111547515237e-05, + "loss": 3.6046, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8445518016815186, + "eval_runtime": 304.2826, + "eval_samples_per_second": 1254.068, + "eval_steps_per_second": 39.191, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625272952764185e-05, + "loss": 3.5982, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624434358013133e-05, + "loss": 3.5942, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623595763262081e-05, + "loss": 3.6131, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622758806391402e-05, + "loss": 3.6137, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621920211640351e-05, + "loss": 3.6181, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621081616889299e-05, + "loss": 3.6078, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620243022138247e-05, + "loss": 3.6042, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619404427387195e-05, + "loss": 3.5955, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618565832636143e-05, + "loss": 3.6019, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.61772723788509e-05, + "loss": 3.6031, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616890281014412e-05, + "loss": 3.6113, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.61605168626336e-05, + "loss": 3.6151, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615213091512308e-05, + "loss": 3.6199, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614374496761255e-05, + "loss": 3.5923, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613535902010203e-05, + "loss": 3.6001, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612697307259151e-05, + "loss": 3.5865, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611858712508099e-05, + "loss": 3.61, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611020117757048e-05, + "loss": 3.5997, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.6101831608863686e-05, + "loss": 3.5941, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.60934620401569e-05, + "loss": 3.6019, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.6085076092646375e-05, + "loss": 3.6195, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.6076690145135855e-05, + "loss": 3.6015, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6068304197625335e-05, + "loss": 3.6105, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.6059918250114815e-05, + "loss": 3.6006, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051548681408024e-05, + "loss": 3.6069, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.6043162733897504e-05, + "loss": 3.6034, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6034776786386984e-05, + "loss": 3.5939, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6026390838876464e-05, + "loss": 3.6075, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601802127016968e-05, + "loss": 3.5969, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600963532265916e-05, + "loss": 3.5933, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600124937514864e-05, + "loss": 3.6065, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599286342763812e-05, + "loss": 3.6033, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.59844774801276e-05, + "loss": 3.6044, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597609153261708e-05, + "loss": 3.6102, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596770558510656e-05, + "loss": 3.5944, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595931963759604e-05, + "loss": 3.6032, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595096644769298e-05, + "loss": 3.6041, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594258050018246e-05, + "loss": 3.5828, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593419455267194e-05, + "loss": 3.5978, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592580860516142e-05, + "loss": 3.5898, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.5917439036454634e-05, + "loss": 3.5907, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5909053088944114e-05, + "loss": 3.6032, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5900667141433594e-05, + "loss": 3.6045, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892281193923074e-05, + "loss": 3.6019, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588391162521628e-05, + "loss": 3.6028, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587552567770576e-05, + "loss": 3.6001, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586713973019524e-05, + "loss": 3.5965, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585875378268472e-05, + "loss": 3.5934, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.585038421397793e-05, + "loss": 3.5816, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584199826646741e-05, + "loss": 3.6012, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583361231895689e-05, + "loss": 3.5946, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582522637144637e-05, + "loss": 3.6036, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581684042393585e-05, + "loss": 3.5988, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580847085522907e-05, + "loss": 3.5909, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580008490771855e-05, + "loss": 3.5861, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579169896020803e-05, + "loss": 3.5899, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578331301269751e-05, + "loss": 3.6057, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577492706518699e-05, + "loss": 3.5874, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5766557496480196e-05, + "loss": 3.6116, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.5758171548969676e-05, + "loss": 3.5988, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.5749785601459156e-05, + "loss": 3.5746, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.5741399653948636e-05, + "loss": 3.6042, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5733013706438116e-05, + "loss": 3.5875, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.5724644137731325e-05, + "loss": 3.5803, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.5716258190220805e-05, + "loss": 3.5934, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.5707872242710285e-05, + "loss": 3.6011, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569948629519977e-05, + "loss": 3.5817, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569111672649298e-05, + "loss": 3.5935, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568273077898246e-05, + "loss": 3.5824, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567434483147194e-05, + "loss": 3.5916, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566595888396142e-05, + "loss": 3.6019, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565758931525463e-05, + "loss": 3.5914, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564920336774411e-05, + "loss": 3.5992, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564081742023359e-05, + "loss": 3.5945, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563243147272307e-05, + "loss": 3.6056, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562404552521255e-05, + "loss": 3.5878, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561565957770203e-05, + "loss": 3.5973, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560729000899524e-05, + "loss": 3.5868, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5598904061484726e-05, + "loss": 3.5892, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5590518113974206e-05, + "loss": 3.6005, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5582132166463686e-05, + "loss": 3.5904, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5573762597756895e-05, + "loss": 3.5997, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.5565376650246375e-05, + "loss": 3.6076, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5556990702735855e-05, + "loss": 3.5923, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554860475522533e-05, + "loss": 3.5768, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554021880771481e-05, + "loss": 3.5911, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.5531849239008024e-05, + "loss": 3.5949, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5523463291497504e-05, + "loss": 3.5911, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551507734398698e-05, + "loss": 3.5945, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.5506691396476463e-05, + "loss": 3.6, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549830544896594e-05, + "loss": 3.593, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.548993588025916e-05, + "loss": 3.5967, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548154993274863e-05, + "loss": 3.5885, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547316398523811e-05, + "loss": 3.5999, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546477803772759e-05, + "loss": 3.5963, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545639209021707e-05, + "loss": 3.6058, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544802252151028e-05, + "loss": 3.5839, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543963657399976e-05, + "loss": 3.595, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543125062648924e-05, + "loss": 3.5964, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542286467897872e-05, + "loss": 3.5971, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.54144787314682e-05, + "loss": 3.5971, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540610916276142e-05, + "loss": 3.591, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.53977232152509e-05, + "loss": 3.5933, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538933726774038e-05, + "loss": 3.5901, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538095132022986e-05, + "loss": 3.5867, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.5372581751523066e-05, + "loss": 3.5832, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.5364195804012546e-05, + "loss": 3.5861, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.5355809856502026e-05, + "loss": 3.5981, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.5347423908991506e-05, + "loss": 3.5898, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.5339054340284715e-05, + "loss": 3.5851, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5330668392774195e-05, + "loss": 3.5848, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.5322282445263675e-05, + "loss": 3.6001, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5313896497753155e-05, + "loss": 3.5961, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530552692904637e-05, + "loss": 3.5918, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529714098153585e-05, + "loss": 3.5993, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528875503402533e-05, + "loss": 3.601, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528036908651481e-05, + "loss": 3.592, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527198313900429e-05, + "loss": 3.5874, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.52636135702975e-05, + "loss": 3.5891, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525522762278698e-05, + "loss": 3.5914, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524684167527646e-05, + "loss": 3.5995, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523845572776594e-05, + "loss": 3.5671, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523008615905915e-05, + "loss": 3.5911, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522170021154863e-05, + "loss": 3.5886, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521331426403811e-05, + "loss": 3.5934, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520492831652759e-05, + "loss": 3.5954, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519654236901707e-05, + "loss": 3.5921, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.5188172800310284e-05, + "loss": 3.5863, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.5179786852799764e-05, + "loss": 3.5808, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.5171400905289244e-05, + "loss": 3.6033, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5163014957778724e-05, + "loss": 3.5897, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5154629010268204e-05, + "loss": 3.6011, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514625944156141e-05, + "loss": 3.5798, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513787349405089e-05, + "loss": 3.5948, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512948754654037e-05, + "loss": 3.6, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512110159902985e-05, + "loss": 3.5908, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511273203032306e-05, + "loss": 3.5948, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510434608281254e-05, + "loss": 3.586, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509596013530202e-05, + "loss": 3.5909, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.50875741877915e-05, + "loss": 3.6073, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507918824028099e-05, + "loss": 3.5878, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.50708186715742e-05, + "loss": 3.5876, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506243272406368e-05, + "loss": 3.5895, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505404677655316e-05, + "loss": 3.5835, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504566082904264e-05, + "loss": 3.5836, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503727488153211e-05, + "loss": 3.5937, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502888893402159e-05, + "loss": 3.5887, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502051936531481e-05, + "loss": 3.5958, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501213341780429e-05, + "loss": 3.587, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.8449225425720215, + "eval_runtime": 303.5879, + "eval_samples_per_second": 1256.937, + "eval_steps_per_second": 39.28, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500374747029376e-05, + "loss": 3.61, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499536152278324e-05, + "loss": 3.5724, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.4986975575272727e-05, + "loss": 3.59, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.4978589627762207e-05, + "loss": 3.6, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970220059055416e-05, + "loss": 3.5971, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.4961834111544896e-05, + "loss": 3.5902, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4953448164034376e-05, + "loss": 3.5843, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4945062216523856e-05, + "loss": 3.5787, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.4936692647817065e-05, + "loss": 3.5791, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.4928306700306545e-05, + "loss": 3.585, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4919920752796025e-05, + "loss": 3.5909, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4911534805285504e-05, + "loss": 3.5955, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4903165236578714e-05, + "loss": 3.6036, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4894779289068194e-05, + "loss": 3.5706, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488639334155768e-05, + "loss": 3.5794, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487800739404716e-05, + "loss": 3.567, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486962144653664e-05, + "loss": 3.5927, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486125187782985e-05, + "loss": 3.5831, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485286593031933e-05, + "loss": 3.5759, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484447998280881e-05, + "loss": 3.5806, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483609403529829e-05, + "loss": 3.5987, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482770808778777e-05, + "loss": 3.5839, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481933851908098e-05, + "loss": 3.5921, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481095257157046e-05, + "loss": 3.5833, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480256662405994e-05, + "loss": 3.5943, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479418067654942e-05, + "loss": 3.5809, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4785811107842634e-05, + "loss": 3.5753, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4777425160332114e-05, + "loss": 3.5915, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4769039212821594e-05, + "loss": 3.5705, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760653265311074e-05, + "loss": 3.5756, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4752267317800554e-05, + "loss": 3.5871, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4743881370290034e-05, + "loss": 3.5831, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473551180158324e-05, + "loss": 3.584, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472712585407272e-05, + "loss": 3.5917, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.47187399065622e-05, + "loss": 3.5754, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471035395905168e-05, + "loss": 3.5824, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470198439034489e-05, + "loss": 3.5868, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469359844283437e-05, + "loss": 3.5661, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468521249532385e-05, + "loss": 3.5805, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467682654781333e-05, + "loss": 3.5702, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466845697910655e-05, + "loss": 3.5735, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466007103159603e-05, + "loss": 3.5807, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465168508408551e-05, + "loss": 3.5866, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464329913657499e-05, + "loss": 3.5825, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.4634929567868196e-05, + "loss": 3.5842, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4626543620357676e-05, + "loss": 3.5827, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4618157672847156e-05, + "loss": 3.5795, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4609771725336636e-05, + "loss": 3.5775, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4601385777826116e-05, + "loss": 3.5614, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4593016209119325e-05, + "loss": 3.5814, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4584630261608805e-05, + "loss": 3.5783, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4576244314098285e-05, + "loss": 3.581, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.45678747453915e-05, + "loss": 3.5831, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455948879788098e-05, + "loss": 3.571, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455110285037046e-05, + "loss": 3.5676, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454271690285994e-05, + "loss": 3.5692, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453433095534942e-05, + "loss": 3.5876, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452596138664263e-05, + "loss": 3.5714, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451757543913211e-05, + "loss": 3.5925, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450918949162159e-05, + "loss": 3.5765, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450080354411106e-05, + "loss": 3.5627, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449243397540428e-05, + "loss": 3.5836, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448404802789376e-05, + "loss": 3.5692, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447566208038324e-05, + "loss": 3.5629, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446727613287272e-05, + "loss": 3.5732, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4458906564165935e-05, + "loss": 3.5839, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4450520616655415e-05, + "loss": 3.5628, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.4442134669144895e-05, + "loss": 3.5783, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443374872163437e-05, + "loss": 3.5599, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442536277412385e-05, + "loss": 3.5733, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4416993205417064e-05, + "loss": 3.5837, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440860725790654e-05, + "loss": 3.5747, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440022131039602e-05, + "loss": 3.5791, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.43918353628855e-05, + "loss": 3.5754, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438346579417871e-05, + "loss": 3.5873, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437507984666819e-05, + "loss": 3.5684, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436669389915767e-05, + "loss": 3.5804, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435830795164715e-05, + "loss": 3.5708, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.434992200413663e-05, + "loss": 3.5702, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434155243542984e-05, + "loss": 3.581, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433316648791932e-05, + "loss": 3.572, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.43247805404088e-05, + "loss": 3.5849, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431639459289828e-05, + "loss": 3.5867, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430800864538776e-05, + "loss": 3.5786, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429963907668097e-05, + "loss": 3.5608, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429125312917045e-05, + "loss": 3.5722, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428286718165993e-05, + "loss": 3.5764, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427448123414941e-05, + "loss": 3.5745, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4266111665442626e-05, + "loss": 3.5749, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4257725717932106e-05, + "loss": 3.5799, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.4249339770421586e-05, + "loss": 3.5762, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.4240953822911066e-05, + "loss": 3.5764, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.4232584254204275e-05, + "loss": 3.5707, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.4224198306693755e-05, + "loss": 3.5804, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.4215812359183235e-05, + "loss": 3.5806, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.4207426411672715e-05, + "loss": 3.587, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4199056842965924e-05, + "loss": 3.5633, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.4190670895455404e-05, + "loss": 3.5756, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.4182284947944884e-05, + "loss": 3.5794, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4173899000434364e-05, + "loss": 3.5791, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416551305292385e-05, + "loss": 3.5816, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415714348421706e-05, + "loss": 3.5722, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414875753670654e-05, + "loss": 3.5731, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414037158919602e-05, + "loss": 3.5706, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.41319856416855e-05, + "loss": 3.5705, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412361607297871e-05, + "loss": 3.5633, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411523012546819e-05, + "loss": 3.5689, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410684417795767e-05, + "loss": 3.5781, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409845823044715e-05, + "loss": 3.5738, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409008866174036e-05, + "loss": 3.567, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408170271422984e-05, + "loss": 3.5643, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407331676671932e-05, + "loss": 3.5815, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.4064930819208804e-05, + "loss": 3.5781, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4056561250502014e-05, + "loss": 3.572, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4048175302991494e-05, + "loss": 3.5822, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4039789355480973e-05, + "loss": 3.5859, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.4031403407970453e-05, + "loss": 3.5729, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402301746045993e-05, + "loss": 3.5706, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401464789175314e-05, + "loss": 3.5737, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400626194424262e-05, + "loss": 3.5758, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.39978759967321e-05, + "loss": 3.5798, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398949004922158e-05, + "loss": 3.5517, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398112048051479e-05, + "loss": 3.5764, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397273453300427e-05, + "loss": 3.5711, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396434858549376e-05, + "loss": 3.5721, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395596263798324e-05, + "loss": 3.5776, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394757669047272e-05, + "loss": 3.5734, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393920712176593e-05, + "loss": 3.5686, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.393082117425541e-05, + "loss": 3.564, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392243522674489e-05, + "loss": 3.5851, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391404927923437e-05, + "loss": 3.5706, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3905679710527576e-05, + "loss": 3.5837, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897293763017056e-05, + "loss": 3.5633, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3888907815506536e-05, + "loss": 3.5773, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3880521867996016e-05, + "loss": 3.5796, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3872152299289225e-05, + "loss": 3.5723, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386376635177871e-05, + "loss": 3.5759, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385538040426819e-05, + "loss": 3.5677, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384699445675767e-05, + "loss": 3.5763, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383862488805088e-05, + "loss": 3.592, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383023894054036e-05, + "loss": 3.5719, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382185299302984e-05, + "loss": 3.5681, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381346704551932e-05, + "loss": 3.5717, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380509747681253e-05, + "loss": 3.5681, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379671152930201e-05, + "loss": 3.5634, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378832558179149e-05, + "loss": 3.5815, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.377993963428097e-05, + "loss": 3.5673, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377157006557418e-05, + "loss": 3.5768, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3763184118063665e-05, + "loss": 3.5718, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.8450450897216797, + "eval_runtime": 313.352, + "eval_samples_per_second": 1217.771, + "eval_steps_per_second": 38.056, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.3754798170553145e-05, + "loss": 3.5947, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.374641222304262e-05, + "loss": 3.559, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.37380262755321e-05, + "loss": 3.5693, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.372964032802158e-05, + "loss": 3.5862, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.3721270759314794e-05, + "loss": 3.576, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.371288481180427e-05, + "loss": 3.5743, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.370449886429375e-05, + "loss": 3.564, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.369611291678323e-05, + "loss": 3.5616, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.368774334807644e-05, + "loss": 3.5613, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.3679357400565917e-05, + "loss": 3.5732, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.36709714530554e-05, + "loss": 3.5683, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.366258550554488e-05, + "loss": 3.5838, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.365421593683809e-05, + "loss": 3.5826, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364582998932757e-05, + "loss": 3.5534, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.363744404181705e-05, + "loss": 3.5614, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362905809430653e-05, + "loss": 3.5521, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.362067214679601e-05, + "loss": 3.5753, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361230257808922e-05, + "loss": 3.5618, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.36039166305787e-05, + "loss": 3.5599, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359553068306818e-05, + "loss": 3.5667, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358714473555766e-05, + "loss": 3.5778, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.357877516685087e-05, + "loss": 3.57, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.357038921934035e-05, + "loss": 3.5712, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.356200327182984e-05, + "loss": 3.5671, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.355361732431932e-05, + "loss": 3.5749, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.3545247755612526e-05, + "loss": 3.5685, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.3536861808102006e-05, + "loss": 3.5578, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.3528475860591486e-05, + "loss": 3.5734, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.3520089913080966e-05, + "loss": 3.5549, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.3511703965570446e-05, + "loss": 3.5608, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.3503334396863655e-05, + "loss": 3.5685, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.3494948449353135e-05, + "loss": 3.562, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.3486562501842615e-05, + "loss": 3.5669, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.3478176554332095e-05, + "loss": 3.5723, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.3469806985625304e-05, + "loss": 3.5619, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346142103811479e-05, + "loss": 3.5682, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.345303509060427e-05, + "loss": 3.5681, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344464914309375e-05, + "loss": 3.5496, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343627957438696e-05, + "loss": 3.5653, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.342789362687644e-05, + "loss": 3.551, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.341950767936592e-05, + "loss": 3.56, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.34111217318554e-05, + "loss": 3.5587, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.340275216314861e-05, + "loss": 3.5711, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.339436621563809e-05, + "loss": 3.5643, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.338598026812757e-05, + "loss": 3.5666, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.337759432061705e-05, + "loss": 3.5656, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.336922475191026e-05, + "loss": 3.5622, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.3360838804399744e-05, + "loss": 3.5601, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.3352452856889224e-05, + "loss": 3.5451, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.3344066909378704e-05, + "loss": 3.5625, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.3335680961868184e-05, + "loss": 3.566, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332731139316139e-05, + "loss": 3.5668, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331892544565087e-05, + "loss": 3.5604, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.331053949814035e-05, + "loss": 3.5531, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330215355062983e-05, + "loss": 3.5526, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329376760311931e-05, + "loss": 3.5513, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328539803441252e-05, + "loss": 3.5774, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.3277012086902e-05, + "loss": 3.5509, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326862613939148e-05, + "loss": 3.5722, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.326024019188096e-05, + "loss": 3.5614, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325187062317418e-05, + "loss": 3.5473, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.324348467566366e-05, + "loss": 3.568, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.323509872815314e-05, + "loss": 3.5491, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.322671278064262e-05, + "loss": 3.55, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.32183268331321e-05, + "loss": 3.5533, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.320995726442531e-05, + "loss": 3.5674, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.320157131691479e-05, + "loss": 3.5453, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319318536940427e-05, + "loss": 3.5604, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.318479942189375e-05, + "loss": 3.5441, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.3176429853186956e-05, + "loss": 3.5577, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.3168043905676436e-05, + "loss": 3.5653, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.3159657958165916e-05, + "loss": 3.561, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.3151272010655396e-05, + "loss": 3.563, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314290244194861e-05, + "loss": 3.5572, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.313451649443809e-05, + "loss": 3.5707, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312613054692757e-05, + "loss": 3.5522, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311774459941705e-05, + "loss": 3.5593, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310937503071026e-05, + "loss": 3.5578, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.310098908319974e-05, + "loss": 3.5511, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309260313568922e-05, + "loss": 3.5624, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.3084217188178694e-05, + "loss": 3.5571, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.3075831240668173e-05, + "loss": 3.5665, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.306746167196139e-05, + "loss": 3.5697, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.305907572445087e-05, + "loss": 3.5578, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.305068977694035e-05, + "loss": 3.5463, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.304230382942983e-05, + "loss": 3.5548, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.3033934260723045e-05, + "loss": 3.5602, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.3025548313212525e-05, + "loss": 3.5581, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.3017162365702e-05, + "loss": 3.5575, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.300877641819148e-05, + "loss": 3.5636, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.3000406849484694e-05, + "loss": 3.5579, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299202090197417e-05, + "loss": 3.5578, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.298363495446365e-05, + "loss": 3.5587, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.297524900695313e-05, + "loss": 3.5628, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.296687943824634e-05, + "loss": 3.5602, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295849349073582e-05, + "loss": 3.5717, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.29501075432253e-05, + "loss": 3.5458, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.294172159571478e-05, + "loss": 3.5641, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.2933352027008e-05, + "loss": 3.5659, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292496607949747e-05, + "loss": 3.5604, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291658013198695e-05, + "loss": 3.5639, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290819418447643e-05, + "loss": 3.5559, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289980823696591e-05, + "loss": 3.5568, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289143866825912e-05, + "loss": 3.5561, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.28830527207486e-05, + "loss": 3.5547, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287466677323808e-05, + "loss": 3.5463, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.286628082572756e-05, + "loss": 3.5552, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285791125702078e-05, + "loss": 3.5581, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.2849525309510257e-05, + "loss": 3.5586, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.2841139361999737e-05, + "loss": 3.5492, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.2832753414489216e-05, + "loss": 3.5505, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.2824383845782426e-05, + "loss": 3.5609, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.2815997898271906e-05, + "loss": 3.5625, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.2807611950761386e-05, + "loss": 3.556, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.2799226003250865e-05, + "loss": 3.5673, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.2790856434544075e-05, + "loss": 3.5677, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.2782470487033555e-05, + "loss": 3.5622, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.2774084539523034e-05, + "loss": 3.5529, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.2765698592012514e-05, + "loss": 3.558, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275732902330573e-05, + "loss": 3.5561, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.274894307579521e-05, + "loss": 3.5656, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.274055712828469e-05, + "loss": 3.539, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.273217118077417e-05, + "loss": 3.5579, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.272378523326365e-05, + "loss": 3.5506, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271541566455686e-05, + "loss": 3.5581, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270702971704634e-05, + "loss": 3.5639, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.269864376953582e-05, + "loss": 3.5566, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.26902578220253e-05, + "loss": 3.5487, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.268188825331851e-05, + "loss": 3.551, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.267350230580799e-05, + "loss": 3.5678, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.266511635829747e-05, + "loss": 3.5548, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.265673041078695e-05, + "loss": 3.5689, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.2648360842080164e-05, + "loss": 3.5442, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.2639974894569644e-05, + "loss": 3.5642, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.2631588947059124e-05, + "loss": 3.5623, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.2623202999548604e-05, + "loss": 3.5558, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261483343084181e-05, + "loss": 3.5543, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260644748333129e-05, + "loss": 3.5542, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.259806153582077e-05, + "loss": 3.5621, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.258967558831025e-05, + "loss": 3.5702, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258128964079973e-05, + "loss": 3.5607, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257292007209294e-05, + "loss": 3.5495, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.256453412458242e-05, + "loss": 3.5586, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.25561481770719e-05, + "loss": 3.5488, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254776222956138e-05, + "loss": 3.5466, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.25393926608546e-05, + "loss": 3.5653, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.253100671334408e-05, + "loss": 3.5506, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.252262076583356e-05, + "loss": 3.5642, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251423481832304e-05, + "loss": 3.5499, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.8458731174468994, + "eval_runtime": 302.137, + "eval_samples_per_second": 1262.973, + "eval_steps_per_second": 39.469, + "step": 1068480 + }, + { + "epoch": 1.0, + "learning_rate": 3.2505865249616247e-05, + "loss": 3.5454, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.2497479302105726e-05, + "loss": 3.5471, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.2489093354595206e-05, + "loss": 3.5522, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.2480707407084686e-05, + "loss": 3.5685, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.2472337838377895e-05, + "loss": 3.5641, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.2463951890867375e-05, + "loss": 3.5567, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.2455565943356855e-05, + "loss": 3.5458, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.2447179995846335e-05, + "loss": 3.5448, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.243879404833582e-05, + "loss": 3.5455, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.243042447962903e-05, + "loss": 3.5554, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.242203853211851e-05, + "loss": 3.5534, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.241365258460799e-05, + "loss": 3.565, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.24052830159012e-05, + "loss": 3.5676, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.239689706839068e-05, + "loss": 3.5406, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.238851112088016e-05, + "loss": 3.5453, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.238012517336964e-05, + "loss": 3.538, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.237173922585912e-05, + "loss": 3.5564, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.236336965715233e-05, + "loss": 3.5458, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.235498370964181e-05, + "loss": 3.5466, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.234659776213129e-05, + "loss": 3.5479, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.2338211814620776e-05, + "loss": 3.561, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.2329842245913985e-05, + "loss": 3.5509, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.2321456298403465e-05, + "loss": 3.5565, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.2313070350892945e-05, + "loss": 3.5522, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.2304684403382425e-05, + "loss": 3.5585, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.2296314834675634e-05, + "loss": 3.5484, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.2287928887165114e-05, + "loss": 3.5441, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.2279542939654594e-05, + "loss": 3.5543, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.2271156992144074e-05, + "loss": 3.5404, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.226278742343728e-05, + "loss": 3.5433, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.225440147592676e-05, + "loss": 3.5519, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.224601552841624e-05, + "loss": 3.5525, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.223762958090572e-05, + "loss": 3.5499, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.222926001219894e-05, + "loss": 3.5571, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.222087406468842e-05, + "loss": 3.5475, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.22124881171779e-05, + "loss": 3.5492, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.220410216966737e-05, + "loss": 3.5522, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.219573260096059e-05, + "loss": 3.5336, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.218734665345007e-05, + "loss": 3.5493, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.217896070593955e-05, + "loss": 3.5369, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.217057475842902e-05, + "loss": 3.5435, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.2162205189722236e-05, + "loss": 3.5429, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.2153819242211716e-05, + "loss": 3.5551, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.2145433294701196e-05, + "loss": 3.5476, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.2137047347190676e-05, + "loss": 3.5516, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.212867777848389e-05, + "loss": 3.551, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.212029183097337e-05, + "loss": 3.5477, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.2111905883462845e-05, + "loss": 3.5422, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.2103519935952325e-05, + "loss": 3.5314, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.209515036724554e-05, + "loss": 3.5442, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.208676441973502e-05, + "loss": 3.5487, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.2078378472224494e-05, + "loss": 3.5494, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.2069992524713974e-05, + "loss": 3.5467, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.2061606577203454e-05, + "loss": 3.5336, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.205323700849667e-05, + "loss": 3.5398, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.204485106098615e-05, + "loss": 3.5327, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.203646511347563e-05, + "loss": 3.5622, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.202807916596511e-05, + "loss": 3.5348, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.201970959725832e-05, + "loss": 3.5575, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.20113236497478e-05, + "loss": 3.5439, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.200293770223728e-05, + "loss": 3.5336, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.199455175472676e-05, + "loss": 3.5451, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.198618218601997e-05, + "loss": 3.5399, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.197779623850945e-05, + "loss": 3.5352, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.196941029099893e-05, + "loss": 3.5311, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.196102434348841e-05, + "loss": 3.558, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.1952654774781624e-05, + "loss": 3.536, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.1944268827271104e-05, + "loss": 3.5377, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.1935882879760584e-05, + "loss": 3.531, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.1927496932250064e-05, + "loss": 3.5426, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.1919110984739544e-05, + "loss": 3.5484, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.191074141603275e-05, + "loss": 3.5436, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.190235546852223e-05, + "loss": 3.5443, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189396952101171e-05, + "loss": 3.5473, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.188558357350119e-05, + "loss": 3.5521, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.18772140047944e-05, + "loss": 3.5398, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.186882805728388e-05, + "loss": 3.5433, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.186044210977336e-05, + "loss": 3.5401, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.185205616226284e-05, + "loss": 3.5401, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.184368659355606e-05, + "loss": 3.5446, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.183530064604554e-05, + "loss": 3.5438, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.182691469853502e-05, + "loss": 3.5473, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.18185287510245e-05, + "loss": 3.5532, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.1810159182317706e-05, + "loss": 3.5433, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.1801773234807186e-05, + "loss": 3.5303, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.1793387287296666e-05, + "loss": 3.5402, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.1785001339786146e-05, + "loss": 3.5471, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.1776615392275626e-05, + "loss": 3.5408, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.1768245823568835e-05, + "loss": 3.5423, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.1759859876058315e-05, + "loss": 3.549, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.1751473928547795e-05, + "loss": 3.544, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.1743087981037275e-05, + "loss": 3.5415, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.173471841233049e-05, + "loss": 3.5403, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.172633246481997e-05, + "loss": 3.5504, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.171794651730945e-05, + "loss": 3.5439, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.170956056979893e-05, + "loss": 3.5561, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.170119100109214e-05, + "loss": 3.5287, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.169280505358162e-05, + "loss": 3.5455, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.16844191060711e-05, + "loss": 3.55, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.167603315856058e-05, + "loss": 3.5463, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.166766358985379e-05, + "loss": 3.5468, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.165927764234327e-05, + "loss": 3.5444, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.165089169483275e-05, + "loss": 3.5399, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.164250574732223e-05, + "loss": 3.5428, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.1634136178615445e-05, + "loss": 3.5359, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.1625750231104925e-05, + "loss": 3.5375, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.1617364283594405e-05, + "loss": 3.5349, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.1608978336083884e-05, + "loss": 3.5429, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.1600608767377094e-05, + "loss": 3.5435, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.1592222819866574e-05, + "loss": 3.5323, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.1583836872356054e-05, + "loss": 3.533, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.1575450924845533e-05, + "loss": 3.5449, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.156708135613874e-05, + "loss": 3.5526, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.155869540862822e-05, + "loss": 3.5435, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.15503094611177e-05, + "loss": 3.5456, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.154192351360718e-05, + "loss": 3.5509, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.15335539449004e-05, + "loss": 3.5452, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.152516799738988e-05, + "loss": 3.5403, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.151678204987936e-05, + "loss": 3.5388, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.150839610236884e-05, + "loss": 3.5427, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.150001015485832e-05, + "loss": 3.5486, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.149164058615153e-05, + "loss": 3.52, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.148325463864101e-05, + "loss": 3.5436, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.147486869113049e-05, + "loss": 3.5347, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.146648274361997e-05, + "loss": 3.5431, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.1458113174913176e-05, + "loss": 3.5444, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.1449727227402656e-05, + "loss": 3.5425, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.1441341279892136e-05, + "loss": 3.5324, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.143295533238162e-05, + "loss": 3.5379, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.142458576367483e-05, + "loss": 3.5476, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.141619981616431e-05, + "loss": 3.5391, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.140781386865379e-05, + "loss": 3.552, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.139942792114327e-05, + "loss": 3.5361, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.139105835243648e-05, + "loss": 3.5441, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.138267240492596e-05, + "loss": 3.5476, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.137428645741544e-05, + "loss": 3.5419, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.136590050990492e-05, + "loss": 3.5403, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.1357514562394394e-05, + "loss": 3.5374, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.134914499368761e-05, + "loss": 3.5497, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.134075904617709e-05, + "loss": 3.5534, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.133237309866657e-05, + "loss": 3.5429, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.132398715115605e-05, + "loss": 3.5341, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.1315617582449266e-05, + "loss": 3.5434, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.1307231634938745e-05, + "loss": 3.5343, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.129884568742822e-05, + "loss": 3.5292, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.12904597399177e-05, + "loss": 3.5532, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.1282090171210915e-05, + "loss": 3.5366, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.1273704223700394e-05, + "loss": 3.5502, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.126531827618987e-05, + "loss": 3.5344, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 3.845832109451294, + "eval_runtime": 302.4402, + "eval_samples_per_second": 1261.707, + "eval_steps_per_second": 39.429, + "step": 1144800 + }, + { + "epoch": 0.0, + "learning_rate": 3.125693232867935e-05, + "loss": 3.5177, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.124854638116883e-05, + "loss": 3.5354, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.1240160433658314e-05, + "loss": 3.5376, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.1231774486147794e-05, + "loss": 3.5493, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.1223404917441e-05, + "loss": 3.5489, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.121501896993048e-05, + "loss": 3.5414, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.120663302241996e-05, + "loss": 3.5347, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.119824707490944e-05, + "loss": 3.5278, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.118987750620265e-05, + "loss": 3.5305, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.118149155869213e-05, + "loss": 3.5442, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.117310561118161e-05, + "loss": 3.5336, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.116471966367109e-05, + "loss": 3.5549, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.115633371616057e-05, + "loss": 3.5523, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.114796414745378e-05, + "loss": 3.5287, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.113957819994326e-05, + "loss": 3.5256, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.113119225243275e-05, + "loss": 3.524, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.112282268372596e-05, + "loss": 3.5408, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.111443673621544e-05, + "loss": 3.5351, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.110605078870492e-05, + "loss": 3.5313, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.10976648411944e-05, + "loss": 3.5281, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.1089295272487606e-05, + "loss": 3.5507, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.1080909324977086e-05, + "loss": 3.5328, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.1072523377466566e-05, + "loss": 3.5415, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.1064137429956046e-05, + "loss": 3.5387, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.1055767861249255e-05, + "loss": 3.5471, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.1047381913738735e-05, + "loss": 3.5303, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.1038995966228215e-05, + "loss": 3.5332, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.10306100187177e-05, + "loss": 3.5343, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.102224045001091e-05, + "loss": 3.5348, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.101385450250039e-05, + "loss": 3.528, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.100546855498987e-05, + "loss": 3.5314, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.099708260747935e-05, + "loss": 3.5357, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.098869665996883e-05, + "loss": 3.5355, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.098032709126204e-05, + "loss": 3.542, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.097194114375152e-05, + "loss": 3.5326, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.0963555196241e-05, + "loss": 3.5355, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.095516924873048e-05, + "loss": 3.5341, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.094679968002369e-05, + "loss": 3.5227, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.093841373251317e-05, + "loss": 3.5319, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.0930027785002655e-05, + "loss": 3.5207, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.0921641837492135e-05, + "loss": 3.5318, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.0913272268785344e-05, + "loss": 3.5279, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.0904886321274824e-05, + "loss": 3.5403, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.0896500373764304e-05, + "loss": 3.5323, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.0888114426253784e-05, + "loss": 3.535, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.087974485754699e-05, + "loss": 3.5404, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.087135891003647e-05, + "loss": 3.5307, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.086297296252595e-05, + "loss": 3.5282, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.085458701501543e-05, + "loss": 3.5173, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.084621744630864e-05, + "loss": 3.5317, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.083783149879812e-05, + "loss": 3.532, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.082944555128761e-05, + "loss": 3.5321, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.082105960377709e-05, + "loss": 3.5352, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.08126900350703e-05, + "loss": 3.5174, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.080430408755978e-05, + "loss": 3.5268, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.079591814004926e-05, + "loss": 3.5182, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.078753219253874e-05, + "loss": 3.5471, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.077916262383195e-05, + "loss": 3.5197, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.077077667632143e-05, + "loss": 3.5453, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.076239072881091e-05, + "loss": 3.531, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.075400478130039e-05, + "loss": 3.5143, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.0745635212593596e-05, + "loss": 3.5317, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.0737249265083076e-05, + "loss": 3.5274, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.072886331757256e-05, + "loss": 3.519, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.072047737006204e-05, + "loss": 3.5174, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.071210780135525e-05, + "loss": 3.5403, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.070372185384473e-05, + "loss": 3.5253, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.069533590633421e-05, + "loss": 3.5207, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.068694995882369e-05, + "loss": 3.515, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.06785803901169e-05, + "loss": 3.5296, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.067019444260638e-05, + "loss": 3.5346, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.066180849509586e-05, + "loss": 3.5292, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.065342254758534e-05, + "loss": 3.526, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.064505297887855e-05, + "loss": 3.5314, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063666703136803e-05, + "loss": 3.5359, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.0628281083857516e-05, + "loss": 3.5266, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.0619895136346996e-05, + "loss": 3.5273, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.0611525567640205e-05, + "loss": 3.5286, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.0603139620129685e-05, + "loss": 3.5257, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.0594753672619165e-05, + "loss": 3.529, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.0586367725108645e-05, + "loss": 3.5294, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.0577998156401854e-05, + "loss": 3.5332, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.0569612208891334e-05, + "loss": 3.5408, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.0561226261380814e-05, + "loss": 3.5286, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.0552840313870294e-05, + "loss": 3.5167, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.05444707451635e-05, + "loss": 3.5237, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.053608479765298e-05, + "loss": 3.5328, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.052769885014247e-05, + "loss": 3.5314, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.051931290263195e-05, + "loss": 3.5247, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.0510943333925156e-05, + "loss": 3.5323, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.050255738641464e-05, + "loss": 3.5335, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.049417143890412e-05, + "loss": 3.524, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.0485785491393592e-05, + "loss": 3.5233, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0477415922686808e-05, + "loss": 3.537, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.0469029975176288e-05, + "loss": 3.5248, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.0460644027665768e-05, + "loss": 3.5417, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.0452258080155244e-05, + "loss": 3.5214, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.044388851144846e-05, + "loss": 3.5311, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.043550256393794e-05, + "loss": 3.5368, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.042711661642742e-05, + "loss": 3.5295, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.0418730668916893e-05, + "loss": 3.5358, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.0410344721406377e-05, + "loss": 3.5277, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.0401975152699593e-05, + "loss": 3.5236, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.0393589205189066e-05, + "loss": 3.5257, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.0385203257678546e-05, + "loss": 3.5242, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.0376817310168026e-05, + "loss": 3.5187, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.036844774146124e-05, + "loss": 3.5224, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.0360061793950718e-05, + "loss": 3.534, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.0351675846440198e-05, + "loss": 3.5276, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.0343289898929678e-05, + "loss": 3.5174, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.0334920330222894e-05, + "loss": 3.5182, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.0326534382712367e-05, + "loss": 3.5252, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.0318148435201847e-05, + "loss": 3.5396, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.030976248769133e-05, + "loss": 3.5296, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.030139291898454e-05, + "loss": 3.5294, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.029300697147402e-05, + "loss": 3.5339, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.02846210239635e-05, + "loss": 3.5392, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.027623507645298e-05, + "loss": 3.5213, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0267865507746192e-05, + "loss": 3.5249, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0259479560235672e-05, + "loss": 3.5294, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0251093612725152e-05, + "loss": 3.5328, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.024270766521463e-05, + "loss": 3.5112, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.023433809650784e-05, + "loss": 3.524, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.022595214899732e-05, + "loss": 3.5221, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.02175662014868e-05, + "loss": 3.5248, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0209180253976284e-05, + "loss": 3.5264, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0200810685269493e-05, + "loss": 3.5376, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.0192424737758973e-05, + "loss": 3.5173, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0184038790248453e-05, + "loss": 3.5234, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.0175652842737933e-05, + "loss": 3.5267, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.0167283274031145e-05, + "loss": 3.5324, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.0158897326520625e-05, + "loss": 3.5354, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.0150511379010105e-05, + "loss": 3.5203, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.0142125431499585e-05, + "loss": 3.5282, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0133755862792794e-05, + "loss": 3.5355, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.0125369915282274e-05, + "loss": 3.5286, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.0116983967771754e-05, + "loss": 3.5234, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.0108598020261238e-05, + "loss": 3.5264, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.0100228451554447e-05, + "loss": 3.5374, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.0091842504043927e-05, + "loss": 3.5341, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.0083456556533407e-05, + "loss": 3.5334, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.0075070609022887e-05, + "loss": 3.52, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.00667010403161e-05, + "loss": 3.5255, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.005831509280558e-05, + "loss": 3.5146, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.004992914529506e-05, + "loss": 3.5161, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.004154319778454e-05, + "loss": 3.5373, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.0033173629077748e-05, + "loss": 3.524, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.0024787681567228e-05, + "loss": 3.5343, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.0016401734056708e-05, + "loss": 3.5235, + "step": 1220608 + }, + { + "epoch": 0.03, + "learning_rate": 3.000801578654619e-05, + "loss": 3.5158, + "step": 1221120 + }, + { + "epoch": 0.03, + "eval_loss": 3.8467841148376465, + "eval_runtime": 304.5526, + "eval_samples_per_second": 1252.956, + "eval_steps_per_second": 39.156, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 2.99996462178394e-05, + "loss": 3.5212, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.999126027032888e-05, + "loss": 3.521, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.998287432281836e-05, + "loss": 3.535, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.997448837530784e-05, + "loss": 3.5311, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.9966118806601053e-05, + "loss": 3.5298, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9957732859090533e-05, + "loss": 3.5175, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.9949346911580013e-05, + "loss": 3.5174, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.9940960964069493e-05, + "loss": 3.5132, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.9932591395362702e-05, + "loss": 3.5314, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.9924205447852182e-05, + "loss": 3.521, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.9915819500341662e-05, + "loss": 3.5369, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.990743355283114e-05, + "loss": 3.5348, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.9899063984124354e-05, + "loss": 3.5198, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.9890678036613834e-05, + "loss": 3.5143, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.9882292089103314e-05, + "loss": 3.5143, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.9873906141592794e-05, + "loss": 3.5159, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.9865536572886006e-05, + "loss": 3.5209, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.9857150625375486e-05, + "loss": 3.515, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.9848764677864966e-05, + "loss": 3.513, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.9840378730354446e-05, + "loss": 3.54, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.9832009161647655e-05, + "loss": 3.5157, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9823623214137135e-05, + "loss": 3.5321, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.9815237266626615e-05, + "loss": 3.5245, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.9806851319116095e-05, + "loss": 3.5305, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.9798481750409308e-05, + "loss": 3.5154, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9790095802898788e-05, + "loss": 3.5182, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.9781709855388268e-05, + "loss": 3.5172, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.9773323907877748e-05, + "loss": 3.522, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.9764954339170957e-05, + "loss": 3.5136, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.975656839166044e-05, + "loss": 3.5187, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.974818244414992e-05, + "loss": 3.5259, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.97397964966394e-05, + "loss": 3.5182, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.973142692793261e-05, + "loss": 3.525, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.972304098042209e-05, + "loss": 3.5209, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.971465503291157e-05, + "loss": 3.519, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.970626908540105e-05, + "loss": 3.5191, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9697883137890532e-05, + "loss": 3.5069, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.968951356918374e-05, + "loss": 3.5213, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.968112762167322e-05, + "loss": 3.5064, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.96727416741627e-05, + "loss": 3.5169, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.966435572665218e-05, + "loss": 3.5136, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.9655986157945394e-05, + "loss": 3.524, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.9647600210434874e-05, + "loss": 3.521, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.9639214262924354e-05, + "loss": 3.5173, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.9630828315413834e-05, + "loss": 3.5265, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.9622458746707043e-05, + "loss": 3.5208, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.9614072799196523e-05, + "loss": 3.5137, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.9605686851686003e-05, + "loss": 3.5053, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.9597300904175486e-05, + "loss": 3.5098, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.9588931335468695e-05, + "loss": 3.5222, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.9580545387958175e-05, + "loss": 3.5174, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.9572159440447655e-05, + "loss": 3.518, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.9563773492937135e-05, + "loss": 3.5079, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.9555403924230347e-05, + "loss": 3.5127, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.9547017976719827e-05, + "loss": 3.503, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.9538632029209307e-05, + "loss": 3.5291, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.9530246081698787e-05, + "loss": 3.5085, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.9521876512991996e-05, + "loss": 3.5282, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.9513490565481476e-05, + "loss": 3.5154, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9505104617970956e-05, + "loss": 3.5021, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.949671867046044e-05, + "loss": 3.5183, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.948834910175365e-05, + "loss": 3.514, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.947996315424313e-05, + "loss": 3.5055, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.947157720673261e-05, + "loss": 3.5014, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.946319125922209e-05, + "loss": 3.5266, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.94548216905153e-05, + "loss": 3.5133, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.944643574300478e-05, + "loss": 3.5044, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.943804979549426e-05, + "loss": 3.5019, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.942966384798374e-05, + "loss": 3.515, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.942129427927695e-05, + "loss": 3.5211, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.941290833176643e-05, + "loss": 3.517, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.940452238425591e-05, + "loss": 3.5131, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.9396136436745387e-05, + "loss": 3.517, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.9387750489234867e-05, + "loss": 3.5222, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.9379380920528082e-05, + "loss": 3.5128, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.9370994973017562e-05, + "loss": 3.5105, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.936260902550704e-05, + "loss": 3.5149, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.935422307799652e-05, + "loss": 3.5122, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.9345853509289735e-05, + "loss": 3.5168, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9337467561779215e-05, + "loss": 3.5164, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.9329081614268688e-05, + "loss": 3.5205, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.9320712045561904e-05, + "loss": 3.5249, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.9312326098051384e-05, + "loss": 3.5157, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.930394015054086e-05, + "loss": 3.5054, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.929555420303034e-05, + "loss": 3.5089, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.928716825551982e-05, + "loss": 3.5165, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.92787823080093e-05, + "loss": 3.5189, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.927039636049878e-05, + "loss": 3.5144, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.926201041298826e-05, + "loss": 3.5166, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9253640844281473e-05, + "loss": 3.5198, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9245254896770952e-05, + "loss": 3.5139, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9236868949260432e-05, + "loss": 3.5127, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.9228483001749912e-05, + "loss": 3.5164, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.922011343304312e-05, + "loss": 3.5156, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.92117274855326e-05, + "loss": 3.5215, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.9203341538022085e-05, + "loss": 3.5118, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9194955590511565e-05, + "loss": 3.5154, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.9186586021804774e-05, + "loss": 3.5227, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.9178200074294254e-05, + "loss": 3.5187, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.9169814126783734e-05, + "loss": 3.5175, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.9161428179273214e-05, + "loss": 3.5194, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.9153058610566426e-05, + "loss": 3.5106, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.9144672663055906e-05, + "loss": 3.5126, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.9136286715545386e-05, + "loss": 3.5148, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.9127900768034866e-05, + "loss": 3.5024, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.9119531199328075e-05, + "loss": 3.5066, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.9111145251817555e-05, + "loss": 3.5226, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.910275930430704e-05, + "loss": 3.5131, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.909437335679652e-05, + "loss": 3.5009, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.9086003788089728e-05, + "loss": 3.5069, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.9077617840579207e-05, + "loss": 3.5121, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.9069231893068687e-05, + "loss": 3.524, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.9060845945558167e-05, + "loss": 3.5186, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.905247637685138e-05, + "loss": 3.512, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.904409042934086e-05, + "loss": 3.5224, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.903570448183034e-05, + "loss": 3.5241, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.902731853431982e-05, + "loss": 3.5076, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.901894896561303e-05, + "loss": 3.5087, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.901056301810251e-05, + "loss": 3.518, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.900217707059199e-05, + "loss": 3.5151, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.8993791123081472e-05, + "loss": 3.5005, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.898542155437468e-05, + "loss": 3.5046, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.897703560686416e-05, + "loss": 3.5103, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.896864965935364e-05, + "loss": 3.511, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.896026371184312e-05, + "loss": 3.5128, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.8951894143136334e-05, + "loss": 3.5237, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.8943508195625813e-05, + "loss": 3.5073, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8935122248115293e-05, + "loss": 3.5109, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.8926736300604773e-05, + "loss": 3.5063, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.8918366731897982e-05, + "loss": 3.5218, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.8909980784387462e-05, + "loss": 3.5221, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.8901594836876942e-05, + "loss": 3.5081, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.8893208889366426e-05, + "loss": 3.5117, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.8884839320659635e-05, + "loss": 3.5194, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.8876453373149115e-05, + "loss": 3.518, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.8868067425638595e-05, + "loss": 3.5122, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.8859681478128075e-05, + "loss": 3.512, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.8851311909421287e-05, + "loss": 3.5235, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.8842925961910767e-05, + "loss": 3.5181, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.8834540014400247e-05, + "loss": 3.5204, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.8826154066889727e-05, + "loss": 3.5063, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.8817784498182936e-05, + "loss": 3.5126, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.8809398550672416e-05, + "loss": 3.5054, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.8801012603161896e-05, + "loss": 3.4983, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.879262665565138e-05, + "loss": 3.527, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.878425708694459e-05, + "loss": 3.5139, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.877587113943407e-05, + "loss": 3.5194, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.876748519192355e-05, + "loss": 3.5099, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.875909924441303e-05, + "loss": 3.4972, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 3.8480420112609863, + "eval_runtime": 304.8935, + "eval_samples_per_second": 1251.555, + "eval_steps_per_second": 39.112, + "step": 1297440 + }, + { + "epoch": 0.0, + "learning_rate": 2.875071329690251e-05, + "loss": 3.5071, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8742327349391988e-05, + "loss": 3.5082, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8733941401881465e-05, + "loss": 3.5244, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8725555454370945e-05, + "loss": 3.5121, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.871718588566416e-05, + "loss": 3.5214, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.870879993815364e-05, + "loss": 3.5018, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8700413990643117e-05, + "loss": 3.5042, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8692044421936333e-05, + "loss": 3.502, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.8683658474425813e-05, + "loss": 3.513, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.8675272526915293e-05, + "loss": 3.5106, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.8666886579404766e-05, + "loss": 3.5206, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.8658500631894246e-05, + "loss": 3.5216, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650131063187462e-05, + "loss": 3.505, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.864174511567694e-05, + "loss": 3.5052, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.863335916816642e-05, + "loss": 3.5028, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.86249732206559e-05, + "loss": 3.5018, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8616603651949114e-05, + "loss": 3.5094, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.8608217704438588e-05, + "loss": 3.5008, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.859983175692807e-05, + "loss": 3.4999, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.859144580941755e-05, + "loss": 3.53, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8583076240710767e-05, + "loss": 3.5059, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.857469029320024e-05, + "loss": 3.5129, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.856630434568972e-05, + "loss": 3.5132, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8557934776982936e-05, + "loss": 3.5139, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.8549548829472412e-05, + "loss": 3.5046, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.8541162881961892e-05, + "loss": 3.5082, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8532776934451372e-05, + "loss": 3.5033, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8524407365744588e-05, + "loss": 3.5126, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.851602141823406e-05, + "loss": 3.4917, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.850763547072354e-05, + "loss": 3.508, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8499249523213025e-05, + "loss": 3.5105, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.849087995450624e-05, + "loss": 3.5077, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8482494006995714e-05, + "loss": 3.5158, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8474108059485194e-05, + "loss": 3.5056, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8465722111974674e-05, + "loss": 3.5033, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.8457352543267886e-05, + "loss": 3.5059, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8448966595757366e-05, + "loss": 3.4951, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8440580648246846e-05, + "loss": 3.504, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.8432194700736326e-05, + "loss": 3.4947, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.8423825132029535e-05, + "loss": 3.501, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.8415439184519015e-05, + "loss": 3.5025, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.8407053237008495e-05, + "loss": 3.5133, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.8398667289497978e-05, + "loss": 3.5055, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.8390297720791187e-05, + "loss": 3.5043, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8381911773280667e-05, + "loss": 3.5145, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.8373525825770147e-05, + "loss": 3.5079, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.8365139878259627e-05, + "loss": 3.4989, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.835677030955284e-05, + "loss": 3.4959, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.834838436204232e-05, + "loss": 3.494, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.83399984145318e-05, + "loss": 3.507, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.833161246702128e-05, + "loss": 3.5034, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.832322651951076e-05, + "loss": 3.5025, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.831485695080397e-05, + "loss": 3.4978, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.830647100329345e-05, + "loss": 3.501, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.8298085055782932e-05, + "loss": 3.4914, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.8289699108272412e-05, + "loss": 3.5113, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.828132953956562e-05, + "loss": 3.4967, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.82729435920551e-05, + "loss": 3.5142, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.826455764454458e-05, + "loss": 3.5026, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.825617169703406e-05, + "loss": 3.4928, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.8247802128327273e-05, + "loss": 3.5018, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8239416180816753e-05, + "loss": 3.5038, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8231030233306233e-05, + "loss": 3.4908, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8222644285795713e-05, + "loss": 3.4903, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8214274717088922e-05, + "loss": 3.5111, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8205888769578402e-05, + "loss": 3.5022, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8197502822067882e-05, + "loss": 3.4913, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8189116874557366e-05, + "loss": 3.4918, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8180747305850575e-05, + "loss": 3.4971, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8172361358340055e-05, + "loss": 3.5061, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.8163975410829535e-05, + "loss": 3.5042, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.8155589463319014e-05, + "loss": 3.502, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.8147219894612227e-05, + "loss": 3.5065, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.8138833947101707e-05, + "loss": 3.5048, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8130447999591187e-05, + "loss": 3.5064, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.8122062052080667e-05, + "loss": 3.4921, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.8113692483373876e-05, + "loss": 3.5052, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.8105306535863356e-05, + "loss": 3.5, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.8096920588352836e-05, + "loss": 3.4999, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.808853464084232e-05, + "loss": 3.5073, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.80801486933318e-05, + "loss": 3.5037, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.8071795503428737e-05, + "loss": 3.51, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.8063409555918217e-05, + "loss": 3.5037, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8055023608407697e-05, + "loss": 3.4875, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.804663766089718e-05, + "loss": 3.4981, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.803825171338666e-05, + "loss": 3.5006, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.802986576587614e-05, + "loss": 3.5054, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.802147981836562e-05, + "loss": 3.5025, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.80130938708551e-05, + "loss": 3.5032, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.800472430214831e-05, + "loss": 3.5024, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.799633835463779e-05, + "loss": 3.5023, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.7987952407127273e-05, + "loss": 3.5008, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7979566459616753e-05, + "loss": 3.5029, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7971196890909962e-05, + "loss": 3.4978, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7962810943399442e-05, + "loss": 3.509, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7954424995888922e-05, + "loss": 3.5052, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7946039048378402e-05, + "loss": 3.4968, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7937669479671614e-05, + "loss": 3.5119, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7929283532161094e-05, + "loss": 3.5055, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7920897584650574e-05, + "loss": 3.5074, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7912511637140054e-05, + "loss": 3.5038, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.7904142068433263e-05, + "loss": 3.4949, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.7895756120922743e-05, + "loss": 3.5006, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7887370173412227e-05, + "loss": 3.5009, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.7878984225901706e-05, + "loss": 3.4847, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.7870614657194916e-05, + "loss": 3.5004, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7862228709684396e-05, + "loss": 3.5045, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.7853842762173875e-05, + "loss": 3.502, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.7845456814663355e-05, + "loss": 3.4902, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.7837087245956568e-05, + "loss": 3.4911, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7828701298446048e-05, + "loss": 3.4995, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.7820315350935528e-05, + "loss": 3.5108, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.7811929403425008e-05, + "loss": 3.5033, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7803559834718217e-05, + "loss": 3.5033, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7795173887207697e-05, + "loss": 3.5056, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.778678793969718e-05, + "loss": 3.5167, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.777840199218666e-05, + "loss": 3.4926, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.777003242347987e-05, + "loss": 3.4957, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.776164647596935e-05, + "loss": 3.5058, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.775326052845883e-05, + "loss": 3.5039, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.774487458094831e-05, + "loss": 3.4887, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.773650501224152e-05, + "loss": 3.4878, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.7728119064731e-05, + "loss": 3.5008, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.771973311722048e-05, + "loss": 3.4993, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.771134716970996e-05, + "loss": 3.5007, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.770297760100317e-05, + "loss": 3.5069, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.769459165349265e-05, + "loss": 3.492, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7686205705982134e-05, + "loss": 3.4986, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.7677819758471614e-05, + "loss": 3.4923, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.7669450189764823e-05, + "loss": 3.5111, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.7661064242254303e-05, + "loss": 3.511, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.7652678294743783e-05, + "loss": 3.4947, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.7644292347233263e-05, + "loss": 3.4965, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7635922778526475e-05, + "loss": 3.5049, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.7627536831015955e-05, + "loss": 3.5065, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7619150883505435e-05, + "loss": 3.5019, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.761076493599491e-05, + "loss": 3.4992, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.7602395367288124e-05, + "loss": 3.5061, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.7594009419777604e-05, + "loss": 3.5034, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.7585623472267088e-05, + "loss": 3.5058, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.757723752475656e-05, + "loss": 3.4953, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.7568867956049777e-05, + "loss": 3.5016, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7560482008539257e-05, + "loss": 3.4949, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.7552096061028736e-05, + "loss": 3.4856, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7543710113518213e-05, + "loss": 3.5118, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.753534054481143e-05, + "loss": 3.4989, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.752695459730091e-05, + "loss": 3.5056, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7518568649790382e-05, + "loss": 3.4983, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.7510182702279862e-05, + "loss": 3.4863, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.848675012588501, + "eval_runtime": 303.8319, + "eval_samples_per_second": 1255.928, + "eval_steps_per_second": 39.249, + "step": 1373760 + }, + { + "epoch": 1.0, + "learning_rate": 2.7501813133573078e-05, + "loss": 3.499, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.7493427186062558e-05, + "loss": 3.4919, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.7485041238552034e-05, + "loss": 3.5123, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.7476655291041514e-05, + "loss": 3.4981, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.746828572233473e-05, + "loss": 3.5113, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.745989977482421e-05, + "loss": 3.49, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.7451513827313687e-05, + "loss": 3.4917, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.7443127879803167e-05, + "loss": 3.4851, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.7434758311096383e-05, + "loss": 3.5045, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.7426372363585856e-05, + "loss": 3.4961, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.7417986416075336e-05, + "loss": 3.5048, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.7409600468564816e-05, + "loss": 3.5065, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.740123089985803e-05, + "loss": 3.4924, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7392844952347508e-05, + "loss": 3.4952, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.7384459004836988e-05, + "loss": 3.4874, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.7376073057326468e-05, + "loss": 3.4885, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.7367703488619677e-05, + "loss": 3.4934, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.7359317541109157e-05, + "loss": 3.4908, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.735093159359864e-05, + "loss": 3.4892, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.734254564608812e-05, + "loss": 3.5092, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.733417607738133e-05, + "loss": 3.4965, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.732579012987081e-05, + "loss": 3.4981, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.731740418236029e-05, + "loss": 3.5008, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.730901823484977e-05, + "loss": 3.5017, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.7300648666142982e-05, + "loss": 3.4923, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.7292262718632462e-05, + "loss": 3.4955, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7283876771121942e-05, + "loss": 3.4932, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.727549082361142e-05, + "loss": 3.494, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.726712125490463e-05, + "loss": 3.4828, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.725873530739411e-05, + "loss": 3.4958, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.7250349359883594e-05, + "loss": 3.4986, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.7241963412373074e-05, + "loss": 3.4943, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7233593843666283e-05, + "loss": 3.5027, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.7225207896155763e-05, + "loss": 3.4942, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.7216821948645243e-05, + "loss": 3.4893, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.7208436001134723e-05, + "loss": 3.4934, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.7200066432427935e-05, + "loss": 3.4858, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.7191680484917415e-05, + "loss": 3.4873, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.7183294537406895e-05, + "loss": 3.4799, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.7174908589896375e-05, + "loss": 3.487, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.7166539021189584e-05, + "loss": 3.4927, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.7158153073679064e-05, + "loss": 3.4977, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.7149767126168544e-05, + "loss": 3.4937, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.7141381178658028e-05, + "loss": 3.4907, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.7133011609951237e-05, + "loss": 3.5042, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.7124625662440717e-05, + "loss": 3.4892, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.7116239714930197e-05, + "loss": 3.4891, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.7107853767419677e-05, + "loss": 3.489, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.709948419871289e-05, + "loss": 3.4773, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.709109825120237e-05, + "loss": 3.4944, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.708271230369185e-05, + "loss": 3.4883, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.707432635618133e-05, + "loss": 3.4906, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.7065956787474538e-05, + "loss": 3.4864, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.7057570839964018e-05, + "loss": 3.4872, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.7049184892453498e-05, + "loss": 3.4789, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.704079894494298e-05, + "loss": 3.4994, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.703242937623619e-05, + "loss": 3.4837, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.702404342872567e-05, + "loss": 3.5016, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.701565748121515e-05, + "loss": 3.4881, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.700727153370463e-05, + "loss": 3.487, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.6998901964997843e-05, + "loss": 3.4866, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.6990516017487323e-05, + "loss": 3.4902, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.6982130069976803e-05, + "loss": 3.478, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.6973744122466283e-05, + "loss": 3.4826, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.6965374553759492e-05, + "loss": 3.4955, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.6956988606248972e-05, + "loss": 3.4916, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.694860265873845e-05, + "loss": 3.4803, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.6940216711227935e-05, + "loss": 3.4779, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.6931847142521144e-05, + "loss": 3.4815, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.6923461195010624e-05, + "loss": 3.5002, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.6915075247500104e-05, + "loss": 3.4889, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6906689299989584e-05, + "loss": 3.4874, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.6898319731282796e-05, + "loss": 3.4952, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.6889933783772276e-05, + "loss": 3.4925, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.6881547836261756e-05, + "loss": 3.4941, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.6873161888751236e-05, + "loss": 3.4753, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.6864792320044445e-05, + "loss": 3.4942, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.6856406372533925e-05, + "loss": 3.4902, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.6848020425023405e-05, + "loss": 3.4854, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.683963447751289e-05, + "loss": 3.4985, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.6831264908806098e-05, + "loss": 3.4915, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.6822895340099307e-05, + "loss": 3.4947, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.6814509392588787e-05, + "loss": 3.4923, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.6806123445078267e-05, + "loss": 3.4754, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.679773749756775e-05, + "loss": 3.4864, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.678935155005723e-05, + "loss": 3.4873, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.678096560254671e-05, + "loss": 3.493, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.677257965503619e-05, + "loss": 3.4906, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.676419370752567e-05, + "loss": 3.4878, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.675582413881888e-05, + "loss": 3.4915, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.674743819130836e-05, + "loss": 3.4887, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.6739052243797842e-05, + "loss": 3.4869, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.6730666296287322e-05, + "loss": 3.4879, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.672229672758053e-05, + "loss": 3.4917, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.671391078007001e-05, + "loss": 3.497, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.670552483255949e-05, + "loss": 3.4893, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.669713888504897e-05, + "loss": 3.4856, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.6688769316342184e-05, + "loss": 3.4984, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.6680383368831664e-05, + "loss": 3.4907, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.6671997421321144e-05, + "loss": 3.4965, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.6663611473810624e-05, + "loss": 3.4894, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.6655241905103833e-05, + "loss": 3.4844, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.6646855957593313e-05, + "loss": 3.4896, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.6638470010082796e-05, + "loss": 3.4892, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.6630084062572276e-05, + "loss": 3.4693, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.6621714493865485e-05, + "loss": 3.4865, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.6613328546354965e-05, + "loss": 3.4946, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.6604942598844445e-05, + "loss": 3.4856, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.6596556651333925e-05, + "loss": 3.4811, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.6588187082627137e-05, + "loss": 3.4789, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.6579801135116617e-05, + "loss": 3.4829, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.6571415187606097e-05, + "loss": 3.5017, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.6563029240095577e-05, + "loss": 3.4853, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.6554659671388786e-05, + "loss": 3.4947, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.6546273723878266e-05, + "loss": 3.4918, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.653788777636775e-05, + "loss": 3.5022, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.652950182885723e-05, + "loss": 3.485, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.652113226015044e-05, + "loss": 3.484, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.651274631263992e-05, + "loss": 3.4907, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.65043603651294e-05, + "loss": 3.4919, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.649597441761888e-05, + "loss": 3.4759, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.648760484891209e-05, + "loss": 3.4765, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.647921890140157e-05, + "loss": 3.4851, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.647083295389105e-05, + "loss": 3.4903, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.646244700638053e-05, + "loss": 3.4887, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.645407743767374e-05, + "loss": 3.494, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.644569149016322e-05, + "loss": 3.4775, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.64373055426527e-05, + "loss": 3.4854, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.6428919595142177e-05, + "loss": 3.4811, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.6420550026435392e-05, + "loss": 3.4973, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.6412164078924872e-05, + "loss": 3.501, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6403778131414352e-05, + "loss": 3.486, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.639539218390383e-05, + "loss": 3.4806, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6387022615197045e-05, + "loss": 3.4916, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.6378636667686525e-05, + "loss": 3.4922, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.6370250720176005e-05, + "loss": 3.4915, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.6361864772665478e-05, + "loss": 3.4857, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.6353495203958694e-05, + "loss": 3.4938, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.6345109256448174e-05, + "loss": 3.4893, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.633672330893765e-05, + "loss": 3.4973, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.632833736142713e-05, + "loss": 3.4838, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.6319967792720346e-05, + "loss": 3.4877, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.6311581845209826e-05, + "loss": 3.4862, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.6303195897699303e-05, + "loss": 3.4678, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.6294809950188783e-05, + "loss": 3.4981, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.6286440381482e-05, + "loss": 3.4891, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.627805443397148e-05, + "loss": 3.4931, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.626966848646095e-05, + "loss": 3.4896, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.626128253895043e-05, + "loss": 3.4704, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.850994348526001, + "eval_runtime": 304.8106, + "eval_samples_per_second": 1251.896, + "eval_steps_per_second": 39.123, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.625289659143991e-05, + "loss": 3.4864, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.624451064392939e-05, + "loss": 3.4787, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6236124696418875e-05, + "loss": 3.499, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.6227738748908355e-05, + "loss": 3.4838, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6219369180201564e-05, + "loss": 3.5069, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6210983232691044e-05, + "loss": 3.4742, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6202597285180524e-05, + "loss": 3.4822, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6194211337670004e-05, + "loss": 3.4691, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6185841768963216e-05, + "loss": 3.4906, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6177455821452696e-05, + "loss": 3.485, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6169069873942176e-05, + "loss": 3.4873, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6160683926431656e-05, + "loss": 3.5031, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152314357724865e-05, + "loss": 3.4772, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6143928410214345e-05, + "loss": 3.4842, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.613554246270383e-05, + "loss": 3.4749, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6127172893997038e-05, + "loss": 3.4792, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6118786946486518e-05, + "loss": 3.4816, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.6110400998975997e-05, + "loss": 3.4773, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6102015051465477e-05, + "loss": 3.4774, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.6093629103954957e-05, + "loss": 3.4952, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.608525953524817e-05, + "loss": 3.4854, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.607687358773765e-05, + "loss": 3.4853, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.606848764022713e-05, + "loss": 3.4912, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.606010169271661e-05, + "loss": 3.4903, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.605173212400982e-05, + "loss": 3.4777, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.60433461764993e-05, + "loss": 3.4848, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6034960228988782e-05, + "loss": 3.4803, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6026574281478262e-05, + "loss": 3.4781, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.601820471277147e-05, + "loss": 3.4733, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.600981876526095e-05, + "loss": 3.4776, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.600143281775043e-05, + "loss": 3.49, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5993063249043644e-05, + "loss": 3.4806, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5984677301533124e-05, + "loss": 3.4931, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.5976291354022603e-05, + "loss": 3.4828, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.5967905406512083e-05, + "loss": 3.4776, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5959535837805293e-05, + "loss": 3.479, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5951149890294772e-05, + "loss": 3.4786, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.5942763942784252e-05, + "loss": 3.4729, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5934377995273736e-05, + "loss": 3.4691, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5926008426566945e-05, + "loss": 3.4749, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5917622479056425e-05, + "loss": 3.4817, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5909236531545905e-05, + "loss": 3.484, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5900850584035385e-05, + "loss": 3.4811, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.5892481015328597e-05, + "loss": 3.48, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5884095067818077e-05, + "loss": 3.4938, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5875709120307557e-05, + "loss": 3.4772, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5867323172797037e-05, + "loss": 3.4762, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5858953604090246e-05, + "loss": 3.4735, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5850567656579726e-05, + "loss": 3.4627, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5842181709069206e-05, + "loss": 3.4869, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.583379576155869e-05, + "loss": 3.4746, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.58254261928519e-05, + "loss": 3.4804, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.581704024534138e-05, + "loss": 3.472, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.580865429783086e-05, + "loss": 3.4802, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.580026835032034e-05, + "loss": 3.4627, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.579189878161355e-05, + "loss": 3.4867, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.578351283410303e-05, + "loss": 3.4745, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.577512688659251e-05, + "loss": 3.4859, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.576674093908199e-05, + "loss": 3.4809, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.57583713703752e-05, + "loss": 3.4715, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.574998542286468e-05, + "loss": 3.4706, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.574159947535416e-05, + "loss": 3.4847, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5733213527843643e-05, + "loss": 3.4657, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5724843959136852e-05, + "loss": 3.4644, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5716458011626332e-05, + "loss": 3.4854, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.5708072064115812e-05, + "loss": 3.4805, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.5699686116605292e-05, + "loss": 3.4652, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.5691316547898505e-05, + "loss": 3.4682, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.5682930600387985e-05, + "loss": 3.4684, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.5674544652877464e-05, + "loss": 3.4831, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.5666158705366944e-05, + "loss": 3.4753, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.5657789136660154e-05, + "loss": 3.4739, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.5649403189149633e-05, + "loss": 3.483, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.5641017241639113e-05, + "loss": 3.4831, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5632631294128597e-05, + "loss": 3.4839, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5624261725421806e-05, + "loss": 3.4661, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.5615875777911286e-05, + "loss": 3.4793, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5607489830400766e-05, + "loss": 3.4759, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.5599103882890246e-05, + "loss": 3.4693, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5590734314183458e-05, + "loss": 3.4897, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5582348366672938e-05, + "loss": 3.4789, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5573978797966147e-05, + "loss": 3.4837, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5565592850455627e-05, + "loss": 3.4809, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5557206902945107e-05, + "loss": 3.4666, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5548820955434587e-05, + "loss": 3.4734, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5540435007924067e-05, + "loss": 3.4721, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5532049060413547e-05, + "loss": 3.4775, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.552366311290303e-05, + "loss": 3.4777, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5515277165392504e-05, + "loss": 3.4742, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.550690759668572e-05, + "loss": 3.4808, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.54985216491752e-05, + "loss": 3.4796, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5490135701664676e-05, + "loss": 3.4731, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5481749754154156e-05, + "loss": 3.4745, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5473380185447372e-05, + "loss": 3.4786, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5464994237936852e-05, + "loss": 3.489, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5456608290426325e-05, + "loss": 3.4778, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5448222342915805e-05, + "loss": 3.4735, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.543985277420902e-05, + "loss": 3.4843, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5431466826698497e-05, + "loss": 3.4751, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.5423080879187977e-05, + "loss": 3.4875, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.5414694931677457e-05, + "loss": 3.4746, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.5406325362970673e-05, + "loss": 3.4765, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.5397939415460146e-05, + "loss": 3.4737, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.538955346794963e-05, + "loss": 3.4785, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.538116752043911e-05, + "loss": 3.4595, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.5372797951732325e-05, + "loss": 3.4736, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.53644120042218e-05, + "loss": 3.4831, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.535602605671128e-05, + "loss": 3.4755, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.534764010920076e-05, + "loss": 3.4659, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.533927054049397e-05, + "loss": 3.4702, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.533088459298345e-05, + "loss": 3.4709, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.532249864547293e-05, + "loss": 3.491, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.531411269796241e-05, + "loss": 3.4713, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.530574312925562e-05, + "loss": 3.4819, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.52973571817451e-05, + "loss": 3.4791, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5288971234234583e-05, + "loss": 3.4918, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5280585286724063e-05, + "loss": 3.4743, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5272215718017272e-05, + "loss": 3.4663, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5263829770506752e-05, + "loss": 3.4805, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.5255443822996232e-05, + "loss": 3.4789, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5247057875485712e-05, + "loss": 3.4653, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5238688306778925e-05, + "loss": 3.4643, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5230302359268405e-05, + "loss": 3.4762, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5221916411757885e-05, + "loss": 3.4775, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5213530464247365e-05, + "loss": 3.4738, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5205160895540574e-05, + "loss": 3.4873, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5196774948030054e-05, + "loss": 3.4639, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5188389000519537e-05, + "loss": 3.472, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.5180003053009017e-05, + "loss": 3.4662, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.5171633484302226e-05, + "loss": 3.4856, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.5163247536791706e-05, + "loss": 3.4894, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.5154861589281186e-05, + "loss": 3.4745, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5146475641770666e-05, + "loss": 3.4687, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.513810607306388e-05, + "loss": 3.482, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.512972012555336e-05, + "loss": 3.4792, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.5121334178042838e-05, + "loss": 3.4772, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.5112964609336047e-05, + "loss": 3.4763, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.5104578661825527e-05, + "loss": 3.4774, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5096192714315007e-05, + "loss": 3.4787, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.508780676680449e-05, + "loss": 3.487, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.50794371980977e-05, + "loss": 3.4712, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.507105125058718e-05, + "loss": 3.4708, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.506266530307666e-05, + "loss": 3.4739, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.505427935556614e-05, + "loss": 3.4626, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5045909786859352e-05, + "loss": 3.4821, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5037523839348832e-05, + "loss": 3.4772, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5029137891838312e-05, + "loss": 3.481, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5020751944327792e-05, + "loss": 3.4721, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5012382375621e-05, + "loss": 3.4663, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.8527395725250244, + "eval_runtime": 305.7986, + "eval_samples_per_second": 1247.851, + "eval_steps_per_second": 38.996, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500399642811048e-05, + "loss": 3.4749, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499561048059996e-05, + "loss": 3.4668, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4987224533089444e-05, + "loss": 3.4852, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4978838585578924e-05, + "loss": 3.4754, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970469016872133e-05, + "loss": 3.4911, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962083069361613e-05, + "loss": 3.47, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4953697121851093e-05, + "loss": 3.4685, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4945311174340573e-05, + "loss": 3.4593, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4936941605633786e-05, + "loss": 3.4764, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928555658123266e-05, + "loss": 3.4776, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920169710612746e-05, + "loss": 3.4745, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911783763102226e-05, + "loss": 3.4851, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903414194395435e-05, + "loss": 3.4702, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895028246884915e-05, + "loss": 3.4703, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886642299374398e-05, + "loss": 3.4626, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878256351863878e-05, + "loss": 3.4645, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4869886783157087e-05, + "loss": 3.4685, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861500835646567e-05, + "loss": 3.4688, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853114888136047e-05, + "loss": 3.4664, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844728940625527e-05, + "loss": 3.48, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.483635937191874e-05, + "loss": 3.4736, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482797342440822e-05, + "loss": 3.4745, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.48195874768977e-05, + "loss": 3.4757, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.481120152938718e-05, + "loss": 3.4786, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.480283196068039e-05, + "loss": 3.4639, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.479444601316987e-05, + "loss": 3.4788, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.478606006565935e-05, + "loss": 3.4644, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.477767411814883e-05, + "loss": 3.4682, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.476930454944204e-05, + "loss": 3.4617, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.476091860193152e-05, + "loss": 3.4679, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752532654421e-05, + "loss": 3.4744, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.474414670691048e-05, + "loss": 3.4726, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4735777138203693e-05, + "loss": 3.4789, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727391190693173e-05, + "loss": 3.4699, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719005243182653e-05, + "loss": 3.4617, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4710619295672133e-05, + "loss": 3.4694, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702249726965342e-05, + "loss": 3.4691, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4693863779454822e-05, + "loss": 3.4595, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685477831944305e-05, + "loss": 3.4586, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677091884433785e-05, + "loss": 3.4615, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668722315726994e-05, + "loss": 3.4685, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660336368216474e-05, + "loss": 3.4734, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4651950420705954e-05, + "loss": 3.4697, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464356447319543e-05, + "loss": 3.4662, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4635194904488647e-05, + "loss": 3.4825, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4626808956978127e-05, + "loss": 3.4696, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618423009467607e-05, + "loss": 3.4647, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610037061957083e-05, + "loss": 3.4606, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601667493250296e-05, + "loss": 3.451, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593281545739776e-05, + "loss": 3.4778, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4584895598229256e-05, + "loss": 3.462, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576509650718736e-05, + "loss": 3.4684, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568140082011948e-05, + "loss": 3.4651, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559754134501428e-05, + "loss": 3.4627, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551368186990905e-05, + "loss": 3.4557, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4542982239480385e-05, + "loss": 3.4679, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.45346126707736e-05, + "loss": 3.4628, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.452622672326308e-05, + "loss": 3.4745, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517840775752557e-05, + "loss": 3.4664, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509454828242037e-05, + "loss": 3.4609, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.450108525953525e-05, + "loss": 3.4589, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.449269931202473e-05, + "loss": 3.4717, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.448431336451421e-05, + "loss": 3.4581, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.447592741700369e-05, + "loss": 3.4536, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467557848296902e-05, + "loss": 3.4726, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459171900786378e-05, + "loss": 3.4707, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450785953275858e-05, + "loss": 3.4559, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442400005765338e-05, + "loss": 3.456, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434030437058554e-05, + "loss": 3.4538, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.442564448954803e-05, + "loss": 3.4708, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.441725854203751e-05, + "loss": 3.4654, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440887259452699e-05, + "loss": 3.4642, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4400503025820203e-05, + "loss": 3.4718, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4392117078309683e-05, + "loss": 3.4684, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4383731130799163e-05, + "loss": 3.4757, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375345183288643e-05, + "loss": 3.456, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4366975614581852e-05, + "loss": 3.4639, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358589667071332e-05, + "loss": 3.465, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4350203719560812e-05, + "loss": 3.4561, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4341817772050292e-05, + "loss": 3.4808, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333448203343504e-05, + "loss": 3.4671, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325078634636717e-05, + "loss": 3.4714, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316692687126197e-05, + "loss": 3.4738, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308306739615677e-05, + "loss": 3.4563, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4299920792105153e-05, + "loss": 3.458, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291534844594637e-05, + "loss": 3.4611, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4283148897084117e-05, + "loss": 3.4666, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4274762949573597e-05, + "loss": 3.4665, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266377002063077e-05, + "loss": 3.4652, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258007433356286e-05, + "loss": 3.4666, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249621485845766e-05, + "loss": 3.4698, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241235538335246e-05, + "loss": 3.4592, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4232849590824725e-05, + "loss": 3.4639, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4224480022117938e-05, + "loss": 3.4662, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4216094074607418e-05, + "loss": 3.4769, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207708127096898e-05, + "loss": 3.4666, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199322179586378e-05, + "loss": 3.4612, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.419095261087959e-05, + "loss": 3.4715, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.418256666336907e-05, + "loss": 3.4635, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.417418071585855e-05, + "loss": 3.4783, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.416579476834803e-05, + "loss": 3.4643, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.415742519964124e-05, + "loss": 3.4631, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.414903925213072e-05, + "loss": 3.4583, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.41406533046202e-05, + "loss": 3.4697, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.413226735710968e-05, + "loss": 3.4459, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.412389778840289e-05, + "loss": 3.4628, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.411551184089237e-05, + "loss": 3.4694, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.410712589338185e-05, + "loss": 3.468, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4098739945871328e-05, + "loss": 3.453, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.409037037716454e-05, + "loss": 3.4575, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4081984429654024e-05, + "loss": 3.4599, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073598482143504e-05, + "loss": 3.4749, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.406521253463298e-05, + "loss": 3.4638, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4056842965926193e-05, + "loss": 3.4693, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4048457018415673e-05, + "loss": 3.4695, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4040071070905153e-05, + "loss": 3.4744, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031685123394633e-05, + "loss": 3.4646, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023315554687845e-05, + "loss": 3.4536, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4014929607177325e-05, + "loss": 3.4658, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006543659666802e-05, + "loss": 3.4682, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998157712156282e-05, + "loss": 3.4542, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3989788143449494e-05, + "loss": 3.4559, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3981402195938978e-05, + "loss": 3.463, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3973016248428454e-05, + "loss": 3.4639, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964630300917934e-05, + "loss": 3.4609, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956260732211147e-05, + "loss": 3.4747, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3947874784700627e-05, + "loss": 3.451, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939488837190107e-05, + "loss": 3.4605, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3931102889679586e-05, + "loss": 3.4566, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.39227333209728e-05, + "loss": 3.4755, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914347373462276e-05, + "loss": 3.4691, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3905961425951755e-05, + "loss": 3.4671, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897575478441235e-05, + "loss": 3.4531, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889205909734448e-05, + "loss": 3.4716, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3880819962223928e-05, + "loss": 3.4717, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872434014713408e-05, + "loss": 3.4625, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3864048067202888e-05, + "loss": 3.4611, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.38556784984961e-05, + "loss": 3.4719, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847292550985577e-05, + "loss": 3.4646, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.383890660347506e-05, + "loss": 3.4784, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830537034768273e-05, + "loss": 3.4568, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.382215108725775e-05, + "loss": 3.4625, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381376513974723e-05, + "loss": 3.4597, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380537919223671e-05, + "loss": 3.4521, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.379700962352992e-05, + "loss": 3.4692, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.37886236760194e-05, + "loss": 3.4643, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.378023772850888e-05, + "loss": 3.4699, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.377185178099836e-05, + "loss": 3.4584, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763482212291574e-05, + "loss": 3.4605, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8529205322265625, + "eval_runtime": 305.6463, + "eval_samples_per_second": 1248.473, + "eval_steps_per_second": 39.016, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.375509626478105e-05, + "loss": 3.4589, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.374671031727053e-05, + "loss": 3.4537, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3738324369760014e-05, + "loss": 3.4719, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3729938422249494e-05, + "loss": 3.4647, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3721552474738974e-05, + "loss": 3.4783, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713166527228454e-05, + "loss": 3.4595, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.370478057971793e-05, + "loss": 3.4515, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.3696411011011143e-05, + "loss": 3.4502, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.3688025063500623e-05, + "loss": 3.461, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.3679639115990103e-05, + "loss": 3.4658, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3671253168479583e-05, + "loss": 3.4604, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3662883599772795e-05, + "loss": 3.476, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3654497652262275e-05, + "loss": 3.4576, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3646111704751755e-05, + "loss": 3.4619, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.363772575724123e-05, + "loss": 3.4537, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3629356188534447e-05, + "loss": 3.45, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3620970241023927e-05, + "loss": 3.4578, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3612584293513404e-05, + "loss": 3.4575, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604198346002884e-05, + "loss": 3.4538, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3595828777296096e-05, + "loss": 3.4683, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3587442829785576e-05, + "loss": 3.4653, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.3579056882275056e-05, + "loss": 3.463, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.357068731356827e-05, + "loss": 3.4623, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.356230136605775e-05, + "loss": 3.4643, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.355391541854723e-05, + "loss": 3.4518, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545529471036705e-05, + "loss": 3.4671, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537159902329918e-05, + "loss": 3.4533, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.35287739548194e-05, + "loss": 3.4576, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3520388007308878e-05, + "loss": 3.4561, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3512002059798358e-05, + "loss": 3.4538, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.350363249109157e-05, + "loss": 3.4629, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.349524654358105e-05, + "loss": 3.4636, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.348686059607053e-05, + "loss": 3.4647, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.347847464856001e-05, + "loss": 3.4581, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3470105079853223e-05, + "loss": 3.4485, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.34617191323427e-05, + "loss": 3.4634, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345333318483218e-05, + "loss": 3.4585, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.344494723732166e-05, + "loss": 3.4434, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.343657766861487e-05, + "loss": 3.451, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.342819172110435e-05, + "loss": 3.4484, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.341980577359383e-05, + "loss": 3.4542, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.341141982608331e-05, + "loss": 3.4633, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.3403050257376524e-05, + "loss": 3.4564, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.3394664309866e-05, + "loss": 3.4605, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.3386278362355484e-05, + "loss": 3.4669, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3377892414844964e-05, + "loss": 3.4547, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3369522846138173e-05, + "loss": 3.457, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3361136898627653e-05, + "loss": 3.4505, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3352750951117133e-05, + "loss": 3.436, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.3344365003606613e-05, + "loss": 3.4677, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.3335995434899825e-05, + "loss": 3.4522, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.3327609487389305e-05, + "loss": 3.4603, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.3319223539878785e-05, + "loss": 3.4535, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3310837592368265e-05, + "loss": 3.4494, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3302468023661474e-05, + "loss": 3.4488, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.3294082076150954e-05, + "loss": 3.452, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3285696128640434e-05, + "loss": 3.4556, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.3277310181129917e-05, + "loss": 3.4633, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3268940612423126e-05, + "loss": 3.4532, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3260554664912606e-05, + "loss": 3.4558, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252168717402086e-05, + "loss": 3.4425, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3243782769891566e-05, + "loss": 3.4622, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.323541320118478e-05, + "loss": 3.445, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.322702725367426e-05, + "loss": 3.441, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.321864130616374e-05, + "loss": 3.4611, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.321025535865322e-05, + "loss": 3.459, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3201885789946428e-05, + "loss": 3.4415, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193499842435908e-05, + "loss": 3.4481, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3185113894925388e-05, + "loss": 3.4389, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.317672794741487e-05, + "loss": 3.4605, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.316835837870808e-05, + "loss": 3.4533, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.315997243119756e-05, + "loss": 3.4547, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.315158648368704e-05, + "loss": 3.4581, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.314320053617652e-05, + "loss": 3.4567, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3134830967469732e-05, + "loss": 3.4669, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126445019959212e-05, + "loss": 3.4427, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.3118059072448692e-05, + "loss": 3.4577, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.3109673124938172e-05, + "loss": 3.4512, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.310130355623138e-05, + "loss": 3.4445, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.309291760872086e-05, + "loss": 3.4636, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.308453166121034e-05, + "loss": 3.4601, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076145713699825e-05, + "loss": 3.4576, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3067776144993034e-05, + "loss": 3.4659, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.3059390197482514e-05, + "loss": 3.4441, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.3051004249971994e-05, + "loss": 3.4482, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.3042634681265203e-05, + "loss": 3.4481, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.3034248733754686e-05, + "loss": 3.4529, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3025862786244166e-05, + "loss": 3.4553, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3017476838733646e-05, + "loss": 3.456, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3009090891223126e-05, + "loss": 3.4523, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3000704943712603e-05, + "loss": 3.4615, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.2992318996202083e-05, + "loss": 3.4498, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.2983949427495295e-05, + "loss": 3.4527, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.2975563479984775e-05, + "loss": 3.4568, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.2967177532474255e-05, + "loss": 3.4622, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2958791584963735e-05, + "loss": 3.4571, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2950422016256947e-05, + "loss": 3.4464, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2942036068746424e-05, + "loss": 3.4619, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2933650121235907e-05, + "loss": 3.4557, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2925264173725387e-05, + "loss": 3.4609, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.29168946050186e-05, + "loss": 3.4537, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908508657508076e-05, + "loss": 3.4546, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900122709997556e-05, + "loss": 3.4437, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891736762487036e-05, + "loss": 3.4618, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.288336719378025e-05, + "loss": 3.4358, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.287498124626973e-05, + "loss": 3.4535, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.286659529875921e-05, + "loss": 3.4568, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.285820935124869e-05, + "loss": 3.4518, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2849839782541898e-05, + "loss": 3.4453, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2841453835031378e-05, + "loss": 3.4472, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2833067887520858e-05, + "loss": 3.4505, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.282468194001034e-05, + "loss": 3.4634, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.281631237130355e-05, + "loss": 3.4552, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.280792642379303e-05, + "loss": 3.4537, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.279954047628251e-05, + "loss": 3.4596, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.279115452877199e-05, + "loss": 3.4657, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2782784960065202e-05, + "loss": 3.4561, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2774399012554682e-05, + "loss": 3.4444, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.2766013065044162e-05, + "loss": 3.4549, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.2757627117533642e-05, + "loss": 3.458, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.274925754882685e-05, + "loss": 3.4427, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.274087160131633e-05, + "loss": 3.4429, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.273248565380581e-05, + "loss": 3.4546, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2724099706295295e-05, + "loss": 3.453, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2715730137588504e-05, + "loss": 3.4516, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707344190077984e-05, + "loss": 3.4601, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2698958242567464e-05, + "loss": 3.4428, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2690572295056944e-05, + "loss": 3.4481, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.2682202726350156e-05, + "loss": 3.4496, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2673816778839636e-05, + "loss": 3.4601, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665430831329116e-05, + "loss": 3.458, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2657044883818596e-05, + "loss": 3.4577, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2648675315111805e-05, + "loss": 3.4442, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2640289367601285e-05, + "loss": 3.4605, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2631903420090765e-05, + "loss": 3.459, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.2623517472580248e-05, + "loss": 3.4516, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2615147903873457e-05, + "loss": 3.4521, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2606761956362937e-05, + "loss": 3.458, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598376008852417e-05, + "loss": 3.4514, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2589990061341897e-05, + "loss": 3.4681, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.258162049263511e-05, + "loss": 3.4466, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.257323454512459e-05, + "loss": 3.453, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.256484859761407e-05, + "loss": 3.4422, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.255646265010355e-05, + "loss": 3.4455, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.254809308139676e-05, + "loss": 3.462, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.253970713388624e-05, + "loss": 3.4512, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.253132118637572e-05, + "loss": 3.4649, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.25229352388652e-05, + "loss": 3.4429, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.251456567015841e-05, + "loss": 3.4528, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.8553547859191895, + "eval_runtime": 304.1611, + "eval_samples_per_second": 1254.569, + "eval_steps_per_second": 39.206, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.250617972264789e-05, + "loss": 3.4594, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.249779377513737e-05, + "loss": 3.4382, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2489407827626847e-05, + "loss": 3.4591, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.248102188011633e-05, + "loss": 3.4565, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472652311409543e-05, + "loss": 3.4656, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464266363899023e-05, + "loss": 3.4488, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.24558804163885e-05, + "loss": 3.4391, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244749446887798e-05, + "loss": 3.4411, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.2439124900171192e-05, + "loss": 3.4488, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2430738952660672e-05, + "loss": 3.4529, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2422353005150152e-05, + "loss": 3.4525, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2413967057639632e-05, + "loss": 3.4618, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2405597488932845e-05, + "loss": 3.4506, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.239721154142232e-05, + "loss": 3.4496, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.23888255939118e-05, + "loss": 3.4406, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.238043964640128e-05, + "loss": 3.4368, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2372070077694497e-05, + "loss": 3.4501, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2363684130183974e-05, + "loss": 3.4434, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355298182673453e-05, + "loss": 3.4443, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2346912235162933e-05, + "loss": 3.4556, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338542666456143e-05, + "loss": 3.4583, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2330156718945626e-05, + "loss": 3.4517, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2321770771435106e-05, + "loss": 3.4505, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313384823924586e-05, + "loss": 3.4517, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2305015255217795e-05, + "loss": 3.4465, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2296629307707275e-05, + "loss": 3.4536, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2288243360196755e-05, + "loss": 3.4403, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.227987379148997e-05, + "loss": 3.4483, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2271487843979447e-05, + "loss": 3.4444, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2263101896468927e-05, + "loss": 3.4446, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2254715948958407e-05, + "loss": 3.4485, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246346380251616e-05, + "loss": 3.4516, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2237960432741096e-05, + "loss": 3.4526, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.222957448523058e-05, + "loss": 3.4518, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.222118853772006e-05, + "loss": 3.4371, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.221281896901327e-05, + "loss": 3.4504, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.220443302150275e-05, + "loss": 3.4473, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.219604707399223e-05, + "loss": 3.434, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.218766112648171e-05, + "loss": 3.4379, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.217929155777492e-05, + "loss": 3.4391, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.21709056102644e-05, + "loss": 3.4405, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.216251966275388e-05, + "loss": 3.4501, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.215413371524336e-05, + "loss": 3.4455, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.214576414653657e-05, + "loss": 3.4506, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.213737819902605e-05, + "loss": 3.4565, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2128992251515533e-05, + "loss": 3.4419, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120606304005013e-05, + "loss": 3.4434, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2112236735298222e-05, + "loss": 3.4433, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2103850787787702e-05, + "loss": 3.4187, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2095464840277182e-05, + "loss": 3.46, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2087078892766662e-05, + "loss": 3.4377, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2078709324059875e-05, + "loss": 3.4537, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2070323376549355e-05, + "loss": 3.4366, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2061937429038835e-05, + "loss": 3.4405, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2053551481528314e-05, + "loss": 3.4335, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2045181912821524e-05, + "loss": 3.4397, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2036795965311004e-05, + "loss": 3.4446, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028410017800487e-05, + "loss": 3.4514, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2020024070289967e-05, + "loss": 3.4497, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011654501583176e-05, + "loss": 3.4363, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003268554072656e-05, + "loss": 3.4317, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1994882606562136e-05, + "loss": 3.456, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986496659051616e-05, + "loss": 3.4297, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1978127090344828e-05, + "loss": 3.4255, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1969741142834308e-05, + "loss": 3.4496, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961355195323788e-05, + "loss": 3.4521, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1952969247813268e-05, + "loss": 3.4292, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944599679106477e-05, + "loss": 3.4349, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936213731595957e-05, + "loss": 3.4318, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.192782778408544e-05, + "loss": 3.4467, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.191944183657492e-05, + "loss": 3.4463, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.191107226786813e-05, + "loss": 3.4414, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.190268632035761e-05, + "loss": 3.4428, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.189430037284709e-05, + "loss": 3.4444, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1885914425336566e-05, + "loss": 3.4595, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877544856629782e-05, + "loss": 3.4313, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1869158909119262e-05, + "loss": 3.4472, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1860772961608742e-05, + "loss": 3.4412, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.185238701409822e-05, + "loss": 3.4317, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.184401744539143e-05, + "loss": 3.4511, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.183563149788091e-05, + "loss": 3.4508, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827245550370394e-05, + "loss": 3.4478, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.181885960285987e-05, + "loss": 3.4555, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1810490034153083e-05, + "loss": 3.4316, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.1802104086642563e-05, + "loss": 3.4376, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.1793734517935772e-05, + "loss": 3.4373, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1785348570425256e-05, + "loss": 3.4448, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1776962622914736e-05, + "loss": 3.4426, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768576675404216e-05, + "loss": 3.4499, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1760190727893692e-05, + "loss": 3.4344, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.1751804780383172e-05, + "loss": 3.452, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.1743418832872652e-05, + "loss": 3.4413, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.1735032885362132e-05, + "loss": 3.4377, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.1726663316655345e-05, + "loss": 3.4484, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1718277369144824e-05, + "loss": 3.4455, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1709891421634304e-05, + "loss": 3.4519, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701521852927514e-05, + "loss": 3.435, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693135905416993e-05, + "loss": 3.4511, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1684749957906473e-05, + "loss": 3.4443, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1676364010395957e-05, + "loss": 3.4482, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1667994441689166e-05, + "loss": 3.4462, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.165962487298238e-05, + "loss": 3.4415, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651238925471858e-05, + "loss": 3.4379, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1642852977961338e-05, + "loss": 3.4466, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634467030450818e-05, + "loss": 3.4257, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1626081082940298e-05, + "loss": 3.4402, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1617695135429778e-05, + "loss": 3.442, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1609309187919258e-05, + "loss": 3.4435, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1600923240408738e-05, + "loss": 3.4339, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592553671701947e-05, + "loss": 3.4383, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584167724191427e-05, + "loss": 3.4371, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.157578177668091e-05, + "loss": 3.4518, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.156741220797412e-05, + "loss": 3.4462, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.15590262604636e-05, + "loss": 3.4399, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.155064031295308e-05, + "loss": 3.4479, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.154225436544256e-05, + "loss": 3.4559, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1533884796735772e-05, + "loss": 3.4452, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525498849225252e-05, + "loss": 3.4322, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517112901714732e-05, + "loss": 3.4438, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1508726954204212e-05, + "loss": 3.4472, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.150035738549742e-05, + "loss": 3.4319, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.14919714379869e-05, + "loss": 3.4324, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.148358549047638e-05, + "loss": 3.441, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1475199542965864e-05, + "loss": 3.4394, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1466829974259073e-05, + "loss": 3.4425, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.1458444026748553e-05, + "loss": 3.4512, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1450058079238033e-05, + "loss": 3.4345, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.1441672131727513e-05, + "loss": 3.4342, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1433302563020726e-05, + "loss": 3.4415, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1424916615510206e-05, + "loss": 3.4462, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1416530667999685e-05, + "loss": 3.4477, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1408144720489165e-05, + "loss": 3.4494, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1399775151782375e-05, + "loss": 3.4333, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1391389204271854e-05, + "loss": 3.4485, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1383003256761334e-05, + "loss": 3.4472, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1374617309250818e-05, + "loss": 3.4408, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1366247740544027e-05, + "loss": 3.4436, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1357861793033507e-05, + "loss": 3.4437, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349475845522987e-05, + "loss": 3.4402, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1341089898012463e-05, + "loss": 3.457, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.133272032930568e-05, + "loss": 3.4355, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.132433438179516e-05, + "loss": 3.4408, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1315964813088368e-05, + "loss": 3.4337, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307578865577848e-05, + "loss": 3.4343, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299192918067328e-05, + "loss": 3.4449, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1290806970556808e-05, + "loss": 3.4431, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282421023046288e-05, + "loss": 3.4502, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1274035075535768e-05, + "loss": 3.4336, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1265649128025248e-05, + "loss": 3.4454, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.856490135192871, + "eval_runtime": 303.9551, + "eval_samples_per_second": 1255.419, + "eval_steps_per_second": 39.233, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.1257263180514728e-05, + "loss": 3.4341, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1248893611807937e-05, + "loss": 3.43, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1240507664297417e-05, + "loss": 3.4447, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.1232121716786897e-05, + "loss": 3.443, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.122373576927638e-05, + "loss": 3.4513, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.121536620056959e-05, + "loss": 3.439, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.120698025305907e-05, + "loss": 3.4305, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.119859430554855e-05, + "loss": 3.434, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.119020835803803e-05, + "loss": 3.4382, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.1181838789331242e-05, + "loss": 3.4406, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.1173452841820722e-05, + "loss": 3.4405, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.11650668943102e-05, + "loss": 3.4511, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.115668094679968e-05, + "loss": 3.4372, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.114831137809289e-05, + "loss": 3.437, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.113992543058237e-05, + "loss": 3.4335, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.113153948307185e-05, + "loss": 3.4252, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.1123153535561334e-05, + "loss": 3.4366, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.1114783966854543e-05, + "loss": 3.4359, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.1106398019344023e-05, + "loss": 3.4324, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.1098012071833503e-05, + "loss": 3.4378, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.1089626124322983e-05, + "loss": 3.4534, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.1081256555616195e-05, + "loss": 3.4389, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.1072870608105675e-05, + "loss": 3.4401, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.1064484660595155e-05, + "loss": 3.439, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1056098713084635e-05, + "loss": 3.4346, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1047729144377844e-05, + "loss": 3.4408, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1039343196867324e-05, + "loss": 3.4309, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.1030957249356804e-05, + "loss": 3.4404, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.1022571301846288e-05, + "loss": 3.4314, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.1014201733139497e-05, + "loss": 3.432, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1005815785628977e-05, + "loss": 3.4353, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0997429838118457e-05, + "loss": 3.4419, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0989043890607937e-05, + "loss": 3.4428, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.098067432190115e-05, + "loss": 3.4424, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.097228837439063e-05, + "loss": 3.4276, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.096390242688011e-05, + "loss": 3.435, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.095551647936959e-05, + "loss": 3.4391, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0947146910662798e-05, + "loss": 3.4252, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0938760963152278e-05, + "loss": 3.4266, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0930375015641758e-05, + "loss": 3.4251, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.092200544693497e-05, + "loss": 3.4319, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.091361949942445e-05, + "loss": 3.4358, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.090523355191393e-05, + "loss": 3.4342, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.089684760440341e-05, + "loss": 3.4429, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.088847803569662e-05, + "loss": 3.4423, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0880092088186103e-05, + "loss": 3.4318, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.0871706140675583e-05, + "loss": 3.4347, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.0863320193165063e-05, + "loss": 3.4313, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.0854950624458272e-05, + "loss": 3.4112, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.0846564676947752e-05, + "loss": 3.4457, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.083817872943723e-05, + "loss": 3.4257, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.082979278192671e-05, + "loss": 3.4422, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.0821423213219924e-05, + "loss": 3.4296, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.0813037265709404e-05, + "loss": 3.4276, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.0804651318198884e-05, + "loss": 3.4217, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.079626537068836e-05, + "loss": 3.429, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.0787895801981573e-05, + "loss": 3.4372, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.0779509854471056e-05, + "loss": 3.4372, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.0771123906960536e-05, + "loss": 3.4397, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.0762737959450013e-05, + "loss": 3.4287, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.0754368390743225e-05, + "loss": 3.4227, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.0745982443232705e-05, + "loss": 3.4461, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.0737596495722185e-05, + "loss": 3.4217, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.0729210548211665e-05, + "loss": 3.4119, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.0720840979504878e-05, + "loss": 3.4383, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.0712455031994358e-05, + "loss": 3.441, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0704069084483834e-05, + "loss": 3.4207, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0695683136973314e-05, + "loss": 3.4267, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0687313568266527e-05, + "loss": 3.4196, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.067892762075601e-05, + "loss": 3.4329, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.0670541673245487e-05, + "loss": 3.4367, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0662155725734967e-05, + "loss": 3.4277, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.065378615702818e-05, + "loss": 3.4329, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0645416588321388e-05, + "loss": 3.4367, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.063703064081087e-05, + "loss": 3.4466, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.062864469330035e-05, + "loss": 3.4204, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.062025874578983e-05, + "loss": 3.4369, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.0611872798279308e-05, + "loss": 3.4258, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0603486850768788e-05, + "loss": 3.4253, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0595100903258268e-05, + "loss": 3.4385, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0586714955747748e-05, + "loss": 3.4412, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.057834538704096e-05, + "loss": 3.4341, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.056995943953044e-05, + "loss": 3.4468, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.056157349201992e-05, + "loss": 3.4201, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.05531875445094e-05, + "loss": 3.4241, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.0544834354606342e-05, + "loss": 3.4268, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.0536448407095825e-05, + "loss": 3.4345, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0528062459585305e-05, + "loss": 3.4288, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0519676512074782e-05, + "loss": 3.4381, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.051129056456426e-05, + "loss": 3.4249, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.050290461705374e-05, + "loss": 3.4394, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.049451866954322e-05, + "loss": 3.4343, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.04861327220327e-05, + "loss": 3.4261, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0477763153325914e-05, + "loss": 3.4359, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0469377205815394e-05, + "loss": 3.4387, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0460991258304874e-05, + "loss": 3.443, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0452605310794354e-05, + "loss": 3.4243, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.0444235742087563e-05, + "loss": 3.4353, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.0435849794577043e-05, + "loss": 3.4341, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.0427463847066526e-05, + "loss": 3.4405, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.0419077899556006e-05, + "loss": 3.4339, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0410708330849215e-05, + "loss": 3.43, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.0402322383338695e-05, + "loss": 3.4264, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.0393936435828175e-05, + "loss": 3.4372, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.0385550488317655e-05, + "loss": 3.4119, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.0377180919610868e-05, + "loss": 3.4302, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.0368794972100348e-05, + "loss": 3.4276, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.0360409024589828e-05, + "loss": 3.4352, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0352039455883037e-05, + "loss": 3.4213, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.0343653508372517e-05, + "loss": 3.4292, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0335267560861997e-05, + "loss": 3.4323, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.032688161335148e-05, + "loss": 3.436, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.031851204464469e-05, + "loss": 3.4334, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.031012609713417e-05, + "loss": 3.4305, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.030174014962365e-05, + "loss": 3.4392, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.029335420211313e-05, + "loss": 3.4467, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.028498463340634e-05, + "loss": 3.4339, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.027659868589582e-05, + "loss": 3.4218, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.02682127383853e-05, + "loss": 3.4343, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.025982679087478e-05, + "loss": 3.436, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.025145722216799e-05, + "loss": 3.4178, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.024307127465747e-05, + "loss": 3.4226, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.023468532714695e-05, + "loss": 3.4305, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.0226299379636434e-05, + "loss": 3.4292, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.0217929810929643e-05, + "loss": 3.4277, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.0209543863419123e-05, + "loss": 3.4388, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.0201157915908603e-05, + "loss": 3.4269, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.0192771968398083e-05, + "loss": 3.4231, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0184402399691295e-05, + "loss": 3.4278, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0176016452180775e-05, + "loss": 3.4411, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0167630504670255e-05, + "loss": 3.4316, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.015924455715973e-05, + "loss": 3.4409, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.0150874988452944e-05, + "loss": 3.4194, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.0142489040942424e-05, + "loss": 3.438, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.0134103093431904e-05, + "loss": 3.4342, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0125717145921384e-05, + "loss": 3.4306, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0117347577214596e-05, + "loss": 3.4299, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0108961629704076e-05, + "loss": 3.4356, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0100575682193556e-05, + "loss": 3.4297, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0092189734683033e-05, + "loss": 3.4459, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0083820165976245e-05, + "loss": 3.4247, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.007543421846573e-05, + "loss": 3.4315, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0067064649758938e-05, + "loss": 3.4253, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.0058678702248418e-05, + "loss": 3.4242, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0050292754737898e-05, + "loss": 3.427, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0041906807227378e-05, + "loss": 3.4323, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.0033520859716858e-05, + "loss": 3.4428, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.0025134912206338e-05, + "loss": 3.4237, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.001676534349955e-05, + "loss": 3.4331, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.857814311981201, + "eval_runtime": 305.3659, + "eval_samples_per_second": 1249.619, + "eval_steps_per_second": 39.052, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.000837939598903e-05, + "loss": 3.4347, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9999993448478507e-05, + "loss": 3.421, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.999162387977172e-05, + "loss": 3.4359, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.99832379322612e-05, + "loss": 3.4356, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.997485198475068e-05, + "loss": 3.4407, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.996646603724016e-05, + "loss": 3.4269, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.995808008972964e-05, + "loss": 3.4259, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.994969414221912e-05, + "loss": 3.4196, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.99413081947086e-05, + "loss": 3.4261, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.993292224719808e-05, + "loss": 3.4348, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.992455267849129e-05, + "loss": 3.4285, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.991616673098077e-05, + "loss": 3.4382, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.990778078347025e-05, + "loss": 3.4336, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.989939483595973e-05, + "loss": 3.4234, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.989102526725294e-05, + "loss": 3.4205, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.988263931974242e-05, + "loss": 3.4197, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9874253372231904e-05, + "loss": 3.4266, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9865867424721383e-05, + "loss": 3.4266, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.9857497856014593e-05, + "loss": 3.4186, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.9849111908504073e-05, + "loss": 3.4299, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9840725960993552e-05, + "loss": 3.4395, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9832340013483032e-05, + "loss": 3.4291, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9823970444776245e-05, + "loss": 3.4313, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9815584497265725e-05, + "loss": 3.4279, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9807198549755205e-05, + "loss": 3.4258, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9798812602244685e-05, + "loss": 3.4311, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.9790443033537894e-05, + "loss": 3.4206, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9782057086027374e-05, + "loss": 3.4351, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9773671138516857e-05, + "loss": 3.4195, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9765285191006334e-05, + "loss": 3.4181, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9756915622299546e-05, + "loss": 3.4287, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9748529674789026e-05, + "loss": 3.427, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.9740143727278506e-05, + "loss": 3.4307, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.9731757779767983e-05, + "loss": 3.4325, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.97233882110612e-05, + "loss": 3.4189, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.971500226355068e-05, + "loss": 3.4245, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.970661631604016e-05, + "loss": 3.4319, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.9698230368529635e-05, + "loss": 3.4129, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9689860799822848e-05, + "loss": 3.4177, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.9681474852312328e-05, + "loss": 3.4155, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.9673088904801807e-05, + "loss": 3.4195, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.9664702957291287e-05, + "loss": 3.4244, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.96563333885845e-05, + "loss": 3.4228, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.964794744107398e-05, + "loss": 3.4356, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9639561493563456e-05, + "loss": 3.4256, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9631175546052936e-05, + "loss": 3.4261, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.9622805977346152e-05, + "loss": 3.423, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.961442002983563e-05, + "loss": 3.4206, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.960603408232511e-05, + "loss": 3.4, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.959764813481459e-05, + "loss": 3.4354, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.95892785661078e-05, + "loss": 3.4157, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.958089261859728e-05, + "loss": 3.4304, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.957250667108676e-05, + "loss": 3.419, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.956412072357624e-05, + "loss": 3.4227, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.9555751154869454e-05, + "loss": 3.4057, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.954736520735893e-05, + "loss": 3.4197, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.953897925984841e-05, + "loss": 3.4295, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.953059331233789e-05, + "loss": 3.4213, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9522223743631103e-05, + "loss": 3.43, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9513837796120582e-05, + "loss": 3.4242, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.9505451848610062e-05, + "loss": 3.4053, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.9497065901099542e-05, + "loss": 3.4344, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.948869633239275e-05, + "loss": 3.4143, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9480310384882235e-05, + "loss": 3.4042, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9471924437371715e-05, + "loss": 3.429, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9463538489861195e-05, + "loss": 3.4247, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9455168921154404e-05, + "loss": 3.4094, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9446782973643884e-05, + "loss": 3.4156, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9438397026133364e-05, + "loss": 3.4131, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.9430027457426576e-05, + "loss": 3.4186, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9421641509916056e-05, + "loss": 3.4252, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9413255562405536e-05, + "loss": 3.4203, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9404869614895016e-05, + "loss": 3.4237, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9396500046188225e-05, + "loss": 3.4231, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9388114098677705e-05, + "loss": 3.4353, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.937972815116719e-05, + "loss": 3.41, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.937134220365667e-05, + "loss": 3.4266, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9362972634949878e-05, + "loss": 3.4154, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9354586687439358e-05, + "loss": 3.4153, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9346200739928837e-05, + "loss": 3.4289, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9337814792418317e-05, + "loss": 3.4274, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.932944522371153e-05, + "loss": 3.4251, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.932105927620101e-05, + "loss": 3.435, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.931267332869049e-05, + "loss": 3.4076, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.930428738117997e-05, + "loss": 3.4137, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.929591781247318e-05, + "loss": 3.4169, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.928753186496266e-05, + "loss": 3.4244, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9279145917452142e-05, + "loss": 3.416, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9270759969941622e-05, + "loss": 3.4249, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.9262374022431102e-05, + "loss": 3.4177, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.9253988074920582e-05, + "loss": 3.4259, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.924560212741006e-05, + "loss": 3.4222, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.923721617989954e-05, + "loss": 3.4152, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.922884661119275e-05, + "loss": 3.4266, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.922046066368223e-05, + "loss": 3.424, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.921207471617171e-05, + "loss": 3.4329, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.920368876866119e-05, + "loss": 3.4159, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.9195319199954403e-05, + "loss": 3.4201, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.918693325244388e-05, + "loss": 3.4247, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.917854730493336e-05, + "loss": 3.4303, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9170161357422843e-05, + "loss": 3.4189, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9161791788716056e-05, + "loss": 3.4236, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9153405841205532e-05, + "loss": 3.4173, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9145019893695012e-05, + "loss": 3.4242, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.9136633946184492e-05, + "loss": 3.4046, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.9128264377477705e-05, + "loss": 3.4237, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9119878429967185e-05, + "loss": 3.4095, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.9111492482456665e-05, + "loss": 3.4243, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9103106534946145e-05, + "loss": 3.4126, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.9094736966239354e-05, + "loss": 3.4224, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.9086351018728834e-05, + "loss": 3.4198, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9077965071218314e-05, + "loss": 3.4267, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9069579123707797e-05, + "loss": 3.4217, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9061209555001006e-05, + "loss": 3.4211, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9052823607490486e-05, + "loss": 3.4277, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9044437659979966e-05, + "loss": 3.4312, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9036068091273175e-05, + "loss": 3.4215, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.902768214376266e-05, + "loss": 3.4139, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.901929619625214e-05, + "loss": 3.4191, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9010910248741618e-05, + "loss": 3.427, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.9002540680034827e-05, + "loss": 3.4129, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8994154732524307e-05, + "loss": 3.4092, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8985768785013787e-05, + "loss": 3.4205, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8977382837503267e-05, + "loss": 3.4175, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.896901326879648e-05, + "loss": 3.4149, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.896062732128596e-05, + "loss": 3.4284, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.895224137377544e-05, + "loss": 3.4189, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.894385542626492e-05, + "loss": 3.4141, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.893548585755813e-05, + "loss": 3.4127, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8927099910047612e-05, + "loss": 3.4276, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8918713962537092e-05, + "loss": 3.4259, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.8910328015026572e-05, + "loss": 3.4265, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.890195844631978e-05, + "loss": 3.4106, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.889357249880926e-05, + "loss": 3.4297, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.888518655129874e-05, + "loss": 3.4247, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.887680060378822e-05, + "loss": 3.423, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8868431035081433e-05, + "loss": 3.42, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8860045087570913e-05, + "loss": 3.4187, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8851659140060393e-05, + "loss": 3.4203, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.8843273192549873e-05, + "loss": 3.4376, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.8834903623843082e-05, + "loss": 3.415, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8826517676332566e-05, + "loss": 3.4194, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8818148107625775e-05, + "loss": 3.4163, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8809762160115255e-05, + "loss": 3.4137, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8801376212604735e-05, + "loss": 3.4164, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8792990265094215e-05, + "loss": 3.4216, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8784604317583695e-05, + "loss": 3.4288, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8776218370073175e-05, + "loss": 3.4182, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8767848801366387e-05, + "loss": 3.4187, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.857804298400879, + "eval_runtime": 310.3867, + "eval_samples_per_second": 1229.405, + "eval_steps_per_second": 38.42, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8759462853855867e-05, + "loss": 3.412, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.8751076906345347e-05, + "loss": 3.4096, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.8742690958834827e-05, + "loss": 3.4255, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.8734305011324304e-05, + "loss": 3.4223, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.8725919063813783e-05, + "loss": 3.4342, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.8717533116303267e-05, + "loss": 3.4139, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.8709147168792747e-05, + "loss": 3.4165, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.8700777600085956e-05, + "loss": 3.4081, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.8692391652575436e-05, + "loss": 3.4163, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.8684005705064916e-05, + "loss": 3.4245, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.8675619757554396e-05, + "loss": 3.4152, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.8667250188847608e-05, + "loss": 3.4262, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.8658864241337088e-05, + "loss": 3.4289, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.8650478293826568e-05, + "loss": 3.408, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.8642092346316048e-05, + "loss": 3.4098, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.8633722777609257e-05, + "loss": 3.4069, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.8625336830098737e-05, + "loss": 3.418, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.861695088258822e-05, + "loss": 3.4107, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.86085649350777e-05, + "loss": 3.4125, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.860019536637091e-05, + "loss": 3.4185, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.859180941886039e-05, + "loss": 3.426, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.858342347134987e-05, + "loss": 3.42, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.857503752383935e-05, + "loss": 3.419, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.8566667955132562e-05, + "loss": 3.4155, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8558282007622042e-05, + "loss": 3.4177, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.8549896060111522e-05, + "loss": 3.4207, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.8541510112601002e-05, + "loss": 3.4039, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.853314054389421e-05, + "loss": 3.4259, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.852475459638369e-05, + "loss": 3.4096, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8516368648873174e-05, + "loss": 3.4066, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.8507982701362654e-05, + "loss": 3.4208, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.8499613132655863e-05, + "loss": 3.416, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.8491227185145343e-05, + "loss": 3.4164, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.8482841237634823e-05, + "loss": 3.4253, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.8474471668928036e-05, + "loss": 3.4079, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.8466085721417516e-05, + "loss": 3.413, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8457699773906996e-05, + "loss": 3.4211, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.8449313826396475e-05, + "loss": 3.3978, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8440944257689685e-05, + "loss": 3.4102, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.8432558310179165e-05, + "loss": 3.406, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.8424172362668644e-05, + "loss": 3.4092, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.8415786415158124e-05, + "loss": 3.4166, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.8407416846451337e-05, + "loss": 3.4087, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.8399030898940817e-05, + "loss": 3.4246, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.8390644951430297e-05, + "loss": 3.4141, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.8382259003919777e-05, + "loss": 3.4176, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.8373889435212986e-05, + "loss": 3.4125, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.836550348770247e-05, + "loss": 3.4119, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.835711754019195e-05, + "loss": 3.393, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.834873159268143e-05, + "loss": 3.4208, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.8340362023974638e-05, + "loss": 3.4065, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8331976076464118e-05, + "loss": 3.4216, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.8323590128953598e-05, + "loss": 3.4087, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.8315204181443078e-05, + "loss": 3.4085, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.830683461273629e-05, + "loss": 3.3987, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.829844866522577e-05, + "loss": 3.4097, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.829006271771525e-05, + "loss": 3.4191, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8281676770204727e-05, + "loss": 3.4091, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.827330720149794e-05, + "loss": 3.4226, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.8264921253987423e-05, + "loss": 3.4125, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.8256535306476903e-05, + "loss": 3.3914, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.824814935896638e-05, + "loss": 3.4241, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8239779790259592e-05, + "loss": 3.4034, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.8231393842749072e-05, + "loss": 3.3959, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.8223007895238552e-05, + "loss": 3.4153, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.8214621947728032e-05, + "loss": 3.4188, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.8206252379021244e-05, + "loss": 3.403, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.8197866431510724e-05, + "loss": 3.4026, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.81894804840002e-05, + "loss": 3.4015, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.818109453648968e-05, + "loss": 3.4108, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.8172724967782893e-05, + "loss": 3.4154, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.8164339020272377e-05, + "loss": 3.4059, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.8155953072761853e-05, + "loss": 3.4144, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.8147583504055066e-05, + "loss": 3.4128, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.8139197556544546e-05, + "loss": 3.4263, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.8130811609034022e-05, + "loss": 3.4028, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.8122425661523505e-05, + "loss": 3.4124, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.8114039714012985e-05, + "loss": 3.4044, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.8105653766502465e-05, + "loss": 3.4067, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.8097267818991945e-05, + "loss": 3.4139, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.8088881871481425e-05, + "loss": 3.4146, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.8080512302774634e-05, + "loss": 3.4195, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.8072126355264114e-05, + "loss": 3.4215, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.8063740407753598e-05, + "loss": 3.4046, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.8055354460243078e-05, + "loss": 3.4001, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.804700127034002e-05, + "loss": 3.406, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.8038615322829496e-05, + "loss": 3.416, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.8030229375318976e-05, + "loss": 3.4037, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.802184342780846e-05, + "loss": 3.4113, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.801345748029794e-05, + "loss": 3.4143, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.800507153278742e-05, + "loss": 3.4122, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.79966855852769e-05, + "loss": 3.4121, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.798829963776638e-05, + "loss": 3.409, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7979930069059588e-05, + "loss": 3.4159, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.7971544121549068e-05, + "loss": 3.4155, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.7963158174038548e-05, + "loss": 3.4212, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.795477222652803e-05, + "loss": 3.4011, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.794640265782124e-05, + "loss": 3.412, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.793801671031072e-05, + "loss": 3.4155, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.79296307628002e-05, + "loss": 3.419, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7921244815289677e-05, + "loss": 3.4102, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.7912875246582893e-05, + "loss": 3.4145, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.7904489299072373e-05, + "loss": 3.4079, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.7896103351561853e-05, + "loss": 3.4082, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.788771740405133e-05, + "loss": 3.3981, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.7879347835344542e-05, + "loss": 3.4082, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.787096188783402e-05, + "loss": 3.4017, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.78625759403235e-05, + "loss": 3.4161, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.785418999281298e-05, + "loss": 3.4037, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.7845820424106194e-05, + "loss": 3.4095, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.7837434476595674e-05, + "loss": 3.4113, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.782904852908515e-05, + "loss": 3.4127, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.782066258157463e-05, + "loss": 3.4163, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7812293012867846e-05, + "loss": 3.4111, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7803907065357326e-05, + "loss": 3.4178, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.7795521117846803e-05, + "loss": 3.4194, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.7787151549140015e-05, + "loss": 3.4099, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.7778765601629495e-05, + "loss": 3.4082, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.7770379654118975e-05, + "loss": 3.4065, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.7761993706608455e-05, + "loss": 3.4143, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.7753624137901668e-05, + "loss": 3.4094, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.7745238190391148e-05, + "loss": 3.3943, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.7736852242880624e-05, + "loss": 3.4095, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.7728466295370104e-05, + "loss": 3.4068, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.7720096726663317e-05, + "loss": 3.4089, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.77117107791528e-05, + "loss": 3.4153, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.7703324831642277e-05, + "loss": 3.41, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.7694938884131757e-05, + "loss": 3.4019, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.768656931542497e-05, + "loss": 3.4056, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.767818336791445e-05, + "loss": 3.4205, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.766979742040393e-05, + "loss": 3.4124, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.766141147289341e-05, + "loss": 3.4179, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.765304190418662e-05, + "loss": 3.3989, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.7644655956676098e-05, + "loss": 3.4247, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.7636270009165578e-05, + "loss": 3.4136, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.7627884061655058e-05, + "loss": 3.4122, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.761951449294827e-05, + "loss": 3.4109, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.761112854543775e-05, + "loss": 3.4077, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.760274259792723e-05, + "loss": 3.4089, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.759435665041671e-05, + "loss": 3.4296, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.758598708170992e-05, + "loss": 3.4029, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.75776011341994e-05, + "loss": 3.412, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7569215186688883e-05, + "loss": 3.4086, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7560845617982095e-05, + "loss": 3.399, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.7552459670471572e-05, + "loss": 3.4096, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.754407372296105e-05, + "loss": 3.4115, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.753568777545053e-05, + "loss": 3.419, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.752730182794001e-05, + "loss": 3.4087, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.7518932259233224e-05, + "loss": 3.4054, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.860870122909546, + "eval_runtime": 310.9116, + "eval_samples_per_second": 1227.33, + "eval_steps_per_second": 38.355, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.7510546311722704e-05, + "loss": 3.4107, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7502160364212184e-05, + "loss": 3.399, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.7493774416701664e-05, + "loss": 3.4134, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7485404847994873e-05, + "loss": 3.4143, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7477018900484353e-05, + "loss": 3.4212, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7468632952973833e-05, + "loss": 3.4078, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7460247005463316e-05, + "loss": 3.4033, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7451861057952796e-05, + "loss": 3.3992, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.7443475110442276e-05, + "loss": 3.4011, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.7435089162931753e-05, + "loss": 3.4131, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.7426719594224965e-05, + "loss": 3.4069, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.7418333646714445e-05, + "loss": 3.4196, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.7409947699203925e-05, + "loss": 3.4157, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.7401561751693405e-05, + "loss": 3.3994, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.7393192182986618e-05, + "loss": 3.3992, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.7384806235476098e-05, + "loss": 3.3963, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.7376420287965574e-05, + "loss": 3.4115, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.7368034340455054e-05, + "loss": 3.4033, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.735966477174827e-05, + "loss": 3.3995, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.735127882423775e-05, + "loss": 3.4051, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.7342892876727226e-05, + "loss": 3.4168, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.7334506929216706e-05, + "loss": 3.409, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.732613736050992e-05, + "loss": 3.4126, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.73177514129994e-05, + "loss": 3.4038, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.730936546548888e-05, + "loss": 3.4097, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.730097951797836e-05, + "loss": 3.409, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.729260994927157e-05, + "loss": 3.3935, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.7284224001761048e-05, + "loss": 3.4152, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7275838054250528e-05, + "loss": 3.396, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.7267452106740008e-05, + "loss": 3.3964, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.7259082538033224e-05, + "loss": 3.4137, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.72506965905227e-05, + "loss": 3.4043, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.724231064301218e-05, + "loss": 3.4062, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.723392469550166e-05, + "loss": 3.4118, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.7225555126794873e-05, + "loss": 3.3981, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.7217169179284353e-05, + "loss": 3.4046, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.7208783231773833e-05, + "loss": 3.409, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.7200397284263312e-05, + "loss": 3.385, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.719202771555652e-05, + "loss": 3.4007, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.7183641768046e-05, + "loss": 3.3944, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.717525582053548e-05, + "loss": 3.397, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.7166886251828694e-05, + "loss": 3.4059, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.7158500304318174e-05, + "loss": 3.4019, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7150114356807654e-05, + "loss": 3.4138, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.7141728409297134e-05, + "loss": 3.4044, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.7133342461786614e-05, + "loss": 3.4068, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.7124956514276094e-05, + "loss": 3.4008, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.7116570566765574e-05, + "loss": 3.4003, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.7108184619255054e-05, + "loss": 3.3822, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.7099815050548266e-05, + "loss": 3.4098, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.7091429103037746e-05, + "loss": 3.3985, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.7083043155527226e-05, + "loss": 3.4069, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.7074657208016703e-05, + "loss": 3.4007, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.7066287639309915e-05, + "loss": 3.3933, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7057901691799395e-05, + "loss": 3.3927, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.704951574428888e-05, + "loss": 3.3971, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.7041129796778355e-05, + "loss": 3.4104, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.7032760228071567e-05, + "loss": 3.3968, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.7024374280561047e-05, + "loss": 3.4145, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.7015988333050524e-05, + "loss": 3.4045, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.7007602385540007e-05, + "loss": 3.3794, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.699923281683322e-05, + "loss": 3.4146, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.69908468693227e-05, + "loss": 3.3947, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.6982460921812176e-05, + "loss": 3.3858, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.6974074974301656e-05, + "loss": 3.4007, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.696570540559487e-05, + "loss": 3.409, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.695731945808435e-05, + "loss": 3.3918, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.694893351057383e-05, + "loss": 3.3961, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.694054756306331e-05, + "loss": 3.3918, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.693217799435652e-05, + "loss": 3.3955, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6923792046845998e-05, + "loss": 3.4076, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.6915406099335478e-05, + "loss": 3.3953, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6907036530628694e-05, + "loss": 3.405, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.6898666961921903e-05, + "loss": 3.3996, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.6890281014411383e-05, + "loss": 3.4144, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.6881895066900863e-05, + "loss": 3.3938, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6873509119390342e-05, + "loss": 3.4074, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6865123171879822e-05, + "loss": 3.3932, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.6856737224369302e-05, + "loss": 3.3946, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.6848351276858782e-05, + "loss": 3.4079, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.6839965329348262e-05, + "loss": 3.401, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.683159576064147e-05, + "loss": 3.4061, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.682320981313095e-05, + "loss": 3.4158, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.681482386562043e-05, + "loss": 3.3991, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.6806437918109915e-05, + "loss": 3.3894, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.6798068349403124e-05, + "loss": 3.3954, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789682401892604e-05, + "loss": 3.4072, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.6781296454382084e-05, + "loss": 3.3916, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.6772910506871564e-05, + "loss": 3.4042, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6764524559361044e-05, + "loss": 3.4051, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.6756138611850524e-05, + "loss": 3.4011, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.6747752664340003e-05, + "loss": 3.4021, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.6739366716829483e-05, + "loss": 3.3951, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.6730997148122696e-05, + "loss": 3.4077, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.6722611200612176e-05, + "loss": 3.4008, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.6714225253101652e-05, + "loss": 3.4092, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.6705839305591132e-05, + "loss": 3.3969, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.6697469736884348e-05, + "loss": 3.3994, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.6689083789373828e-05, + "loss": 3.4058, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.6680697841863305e-05, + "loss": 3.4075, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.6672311894352785e-05, + "loss": 3.3975, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.6663942325645997e-05, + "loss": 3.4029, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.6655556378135477e-05, + "loss": 3.403, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.6647170430624957e-05, + "loss": 3.3962, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.6638784483114437e-05, + "loss": 3.3909, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.663041491440765e-05, + "loss": 3.3964, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6622028966897126e-05, + "loss": 3.3921, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.6613643019386606e-05, + "loss": 3.4068, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.6605257071876086e-05, + "loss": 3.396, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.6596887503169302e-05, + "loss": 3.3981, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.658850155565878e-05, + "loss": 3.3977, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.658011560814826e-05, + "loss": 3.4067, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.657172966063774e-05, + "loss": 3.4012, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.656336009193095e-05, + "loss": 3.4008, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.655497414442043e-05, + "loss": 3.4067, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.654658819690991e-05, + "loss": 3.4087, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.653820224939939e-05, + "loss": 3.4014, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.65298326806926e-05, + "loss": 3.3971, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.652144673318208e-05, + "loss": 3.3962, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.651306078567156e-05, + "loss": 3.4049, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.6504691216964772e-05, + "loss": 3.4008, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.6496305269454252e-05, + "loss": 3.3797, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.6487919321943732e-05, + "loss": 3.4022, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.6479533374433212e-05, + "loss": 3.3987, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.6471163805726425e-05, + "loss": 3.3983, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.64627778582159e-05, + "loss": 3.4069, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.6454391910705385e-05, + "loss": 3.3996, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.6446005963194864e-05, + "loss": 3.3919, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.6437636394488074e-05, + "loss": 3.3929, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.6429250446977554e-05, + "loss": 3.4124, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.6420880878270766e-05, + "loss": 3.4034, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.6412494930760246e-05, + "loss": 3.4073, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.6404108983249726e-05, + "loss": 3.3908, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.6395723035739206e-05, + "loss": 3.4095, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.6387337088228686e-05, + "loss": 3.4021, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.6378951140718166e-05, + "loss": 3.4024, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.6370565193207646e-05, + "loss": 3.4017, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.6362179245697126e-05, + "loss": 3.3952, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.6353809676990338e-05, + "loss": 3.4039, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6345423729479818e-05, + "loss": 3.419, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.6337037781969298e-05, + "loss": 3.3943, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.6328651834458778e-05, + "loss": 3.3977, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.6320282265751987e-05, + "loss": 3.3945, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.63119126970452e-05, + "loss": 3.3934, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.630352674953468e-05, + "loss": 3.395, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.629514080202416e-05, + "loss": 3.4026, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.628675485451364e-05, + "loss": 3.4065, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.627836890700312e-05, + "loss": 3.4064, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.626999933829633e-05, + "loss": 3.3958, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.8602986335754395, + "eval_runtime": 308.3862, + "eval_samples_per_second": 1237.38, + "eval_steps_per_second": 38.669, + "step": 2060640 + }, + { + "epoch": 1.0, + "learning_rate": 1.626161339078581e-05, + "loss": 3.3887, + "step": 2060800 + }, + { + "epoch": 1.0, + "learning_rate": 1.625322744327529e-05, + "loss": 3.3887, + "step": 2061312 + }, + { + "epoch": 1.0, + "learning_rate": 1.6244841495764772e-05, + "loss": 3.4029, + "step": 2061824 + }, + { + "epoch": 1.0, + "learning_rate": 1.6236455548254252e-05, + "loss": 3.4043, + "step": 2062336 + }, + { + "epoch": 1.0, + "learning_rate": 1.622806960074373e-05, + "loss": 3.4088, + "step": 2062848 + }, + { + "epoch": 1.0, + "learning_rate": 1.6219683653233208e-05, + "loss": 3.3988, + "step": 2063360 + }, + { + "epoch": 1.0, + "learning_rate": 1.6211297705722688e-05, + "loss": 3.3941, + "step": 2063872 + }, + { + "epoch": 1.0, + "learning_rate": 1.62029281370159e-05, + "loss": 3.3904, + "step": 2064384 + }, + { + "epoch": 1.0, + "learning_rate": 1.619454218950538e-05, + "loss": 3.3909, + "step": 2064896 + }, + { + "epoch": 1.0, + "learning_rate": 1.618615624199486e-05, + "loss": 3.3944, + "step": 2065408 + }, + { + "epoch": 1.0, + "learning_rate": 1.617777029448434e-05, + "loss": 3.4025, + "step": 2065920 + }, + { + "epoch": 1.0, + "learning_rate": 1.616940072577755e-05, + "loss": 3.409, + "step": 2066432 + }, + { + "epoch": 1.0, + "learning_rate": 1.616101477826703e-05, + "loss": 3.4073, + "step": 2066944 + }, + { + "epoch": 1.0, + "learning_rate": 1.615262883075651e-05, + "loss": 3.3846, + "step": 2067456 + }, + { + "epoch": 1.0, + "learning_rate": 1.6144242883245993e-05, + "loss": 3.3928, + "step": 2067968 + }, + { + "epoch": 1.0, + "learning_rate": 1.6135873314539202e-05, + "loss": 3.3784, + "step": 2068480 + }, + { + "epoch": 1.0, + "learning_rate": 1.6127487367028682e-05, + "loss": 3.4017, + "step": 2068992 + }, + { + "epoch": 1.0, + "learning_rate": 1.6119101419518162e-05, + "loss": 3.3923, + "step": 2069504 + }, + { + "epoch": 1.0, + "learning_rate": 1.6110715472007642e-05, + "loss": 3.3873, + "step": 2070016 + }, + { + "epoch": 1.0, + "learning_rate": 1.6102345903300854e-05, + "loss": 3.3941, + "step": 2070528 + }, + { + "epoch": 1.0, + "learning_rate": 1.6093959955790334e-05, + "loss": 3.4098, + "step": 2071040 + }, + { + "epoch": 1.0, + "learning_rate": 1.6085574008279814e-05, + "loss": 3.3949, + "step": 2071552 + }, + { + "epoch": 1.0, + "learning_rate": 1.6077188060769294e-05, + "loss": 3.4047, + "step": 2072064 + }, + { + "epoch": 1.0, + "learning_rate": 1.6068818492062503e-05, + "loss": 3.3956, + "step": 2072576 + }, + { + "epoch": 1.0, + "learning_rate": 1.6060432544551983e-05, + "loss": 3.4007, + "step": 2073088 + }, + { + "epoch": 1.0, + "learning_rate": 1.6052046597041463e-05, + "loss": 3.3963, + "step": 2073600 + }, + { + "epoch": 1.0, + "learning_rate": 1.6043660649530947e-05, + "loss": 3.387, + "step": 2074112 + }, + { + "epoch": 1.0, + "learning_rate": 1.6035291080824156e-05, + "loss": 3.4022, + "step": 2074624 + }, + { + "epoch": 1.0, + "learning_rate": 1.6026905133313636e-05, + "loss": 3.3895, + "step": 2075136 + }, + { + "epoch": 1.0, + "learning_rate": 1.6018519185803116e-05, + "loss": 3.3865, + "step": 2075648 + }, + { + "epoch": 1.01, + "learning_rate": 1.6010133238292596e-05, + "loss": 3.402, + "step": 2076160 + }, + { + "epoch": 1.01, + "learning_rate": 1.6001763669585808e-05, + "loss": 3.395, + "step": 2076672 + }, + { + "epoch": 1.01, + "learning_rate": 1.5993377722075288e-05, + "loss": 3.3978, + "step": 2077184 + }, + { + "epoch": 1.01, + "learning_rate": 1.5984991774564768e-05, + "loss": 3.4028, + "step": 2077696 + }, + { + "epoch": 1.01, + "learning_rate": 1.5976622205857977e-05, + "loss": 3.3879, + "step": 2078208 + }, + { + "epoch": 1.01, + "learning_rate": 1.5968236258347457e-05, + "loss": 3.397, + "step": 2078720 + }, + { + "epoch": 1.01, + "learning_rate": 1.5959850310836937e-05, + "loss": 3.3976, + "step": 2079232 + }, + { + "epoch": 1.01, + "learning_rate": 1.5951464363326417e-05, + "loss": 3.3776, + "step": 2079744 + }, + { + "epoch": 1.01, + "learning_rate": 1.594309479461963e-05, + "loss": 3.3934, + "step": 2080256 + }, + { + "epoch": 1.01, + "learning_rate": 1.593470884710911e-05, + "loss": 3.382, + "step": 2080768 + }, + { + "epoch": 1.01, + "learning_rate": 1.592632289959859e-05, + "loss": 3.3837, + "step": 2081280 + }, + { + "epoch": 1.01, + "learning_rate": 1.59179533308918e-05, + "loss": 3.3979, + "step": 2081792 + }, + { + "epoch": 1.01, + "learning_rate": 1.590956738338128e-05, + "loss": 3.3987, + "step": 2082304 + }, + { + "epoch": 1.01, + "learning_rate": 1.5901181435870762e-05, + "loss": 3.396, + "step": 2082816 + }, + { + "epoch": 1.01, + "learning_rate": 1.589279548836024e-05, + "loss": 3.3988, + "step": 2083328 + }, + { + "epoch": 1.01, + "learning_rate": 1.588440954084972e-05, + "loss": 3.394, + "step": 2083840 + }, + { + "epoch": 1.01, + "learning_rate": 1.58760235933392e-05, + "loss": 3.3917, + "step": 2084352 + }, + { + "epoch": 1.01, + "learning_rate": 1.5867637645828678e-05, + "loss": 3.3864, + "step": 2084864 + }, + { + "epoch": 1.01, + "learning_rate": 1.5859251698318158e-05, + "loss": 3.3757, + "step": 2085376 + }, + { + "epoch": 1.01, + "learning_rate": 1.585088212961137e-05, + "loss": 3.3962, + "step": 2085888 + }, + { + "epoch": 1.01, + "learning_rate": 1.584249618210085e-05, + "loss": 3.3892, + "step": 2086400 + }, + { + "epoch": 1.01, + "learning_rate": 1.583411023459033e-05, + "loss": 3.3963, + "step": 2086912 + }, + { + "epoch": 1.01, + "learning_rate": 1.582572428707981e-05, + "loss": 3.3927, + "step": 2087424 + }, + { + "epoch": 1.01, + "learning_rate": 1.5817354718373023e-05, + "loss": 3.3847, + "step": 2087936 + }, + { + "epoch": 1.01, + "learning_rate": 1.5808968770862503e-05, + "loss": 3.3828, + "step": 2088448 + }, + { + "epoch": 1.01, + "learning_rate": 1.580058282335198e-05, + "loss": 3.3858, + "step": 2088960 + }, + { + "epoch": 1.01, + "learning_rate": 1.5792196875841463e-05, + "loss": 3.4006, + "step": 2089472 + }, + { + "epoch": 1.01, + "learning_rate": 1.5783827307134675e-05, + "loss": 3.3836, + "step": 2089984 + }, + { + "epoch": 1.01, + "learning_rate": 1.5775441359624152e-05, + "loss": 3.4095, + "step": 2090496 + }, + { + "epoch": 1.01, + "learning_rate": 1.5767055412113632e-05, + "loss": 3.3925, + "step": 2091008 + }, + { + "epoch": 1.01, + "learning_rate": 1.5758669464603112e-05, + "loss": 3.3711, + "step": 2091520 + }, + { + "epoch": 1.01, + "learning_rate": 1.5750299895896324e-05, + "loss": 3.4005, + "step": 2092032 + }, + { + "epoch": 1.01, + "learning_rate": 1.5741913948385804e-05, + "loss": 3.3846, + "step": 2092544 + }, + { + "epoch": 1.01, + "learning_rate": 1.5733528000875284e-05, + "loss": 3.376, + "step": 2093056 + }, + { + "epoch": 1.01, + "learning_rate": 1.5725142053364764e-05, + "loss": 3.3906, + "step": 2093568 + }, + { + "epoch": 1.01, + "learning_rate": 1.5716772484657973e-05, + "loss": 3.3993, + "step": 2094080 + }, + { + "epoch": 1.01, + "learning_rate": 1.5708386537147453e-05, + "loss": 3.3803, + "step": 2094592 + }, + { + "epoch": 1.01, + "learning_rate": 1.5700000589636933e-05, + "loss": 3.3901, + "step": 2095104 + }, + { + "epoch": 1.01, + "learning_rate": 1.5691614642126416e-05, + "loss": 3.3798, + "step": 2095616 + }, + { + "epoch": 1.01, + "learning_rate": 1.5683245073419626e-05, + "loss": 3.3876, + "step": 2096128 + }, + { + "epoch": 1.01, + "learning_rate": 1.5674859125909106e-05, + "loss": 3.3973, + "step": 2096640 + }, + { + "epoch": 1.01, + "learning_rate": 1.5666473178398585e-05, + "loss": 3.3866, + "step": 2097152 + }, + { + "epoch": 1.01, + "learning_rate": 1.5658087230888065e-05, + "loss": 3.3942, + "step": 2097664 + }, + { + "epoch": 1.01, + "learning_rate": 1.564973404098501e-05, + "loss": 3.3906, + "step": 2098176 + }, + { + "epoch": 1.01, + "learning_rate": 1.564134809347449e-05, + "loss": 3.4015, + "step": 2098688 + }, + { + "epoch": 1.01, + "learning_rate": 1.563296214596397e-05, + "loss": 3.3858, + "step": 2099200 + }, + { + "epoch": 1.01, + "learning_rate": 1.5624576198453447e-05, + "loss": 3.3923, + "step": 2099712 + }, + { + "epoch": 1.01, + "learning_rate": 1.5616190250942927e-05, + "loss": 3.383, + "step": 2100224 + }, + { + "epoch": 1.01, + "learning_rate": 1.5607804303432407e-05, + "loss": 3.3856, + "step": 2100736 + }, + { + "epoch": 1.01, + "learning_rate": 1.5599418355921887e-05, + "loss": 3.3987, + "step": 2101248 + }, + { + "epoch": 1.01, + "learning_rate": 1.559103240841137e-05, + "loss": 3.3877, + "step": 2101760 + }, + { + "epoch": 1.01, + "learning_rate": 1.558266283970458e-05, + "loss": 3.3981, + "step": 2102272 + }, + { + "epoch": 1.01, + "learning_rate": 1.557427689219406e-05, + "loss": 3.4012, + "step": 2102784 + }, + { + "epoch": 1.01, + "learning_rate": 1.556589094468354e-05, + "loss": 3.3914, + "step": 2103296 + }, + { + "epoch": 1.01, + "learning_rate": 1.555750499717302e-05, + "loss": 3.3736, + "step": 2103808 + }, + { + "epoch": 1.01, + "learning_rate": 1.5549151807269964e-05, + "loss": 3.3881, + "step": 2104320 + }, + { + "epoch": 1.01, + "learning_rate": 1.5540765859759444e-05, + "loss": 3.3949, + "step": 2104832 + }, + { + "epoch": 1.01, + "learning_rate": 1.553237991224892e-05, + "loss": 3.3856, + "step": 2105344 + }, + { + "epoch": 1.01, + "learning_rate": 1.55239939647384e-05, + "loss": 3.3923, + "step": 2105856 + }, + { + "epoch": 1.01, + "learning_rate": 1.551560801722788e-05, + "loss": 3.3974, + "step": 2106368 + }, + { + "epoch": 1.02, + "learning_rate": 1.550722206971736e-05, + "loss": 3.39, + "step": 2106880 + }, + { + "epoch": 1.02, + "learning_rate": 1.549883612220684e-05, + "loss": 3.3922, + "step": 2107392 + }, + { + "epoch": 1.02, + "learning_rate": 1.549045017469632e-05, + "loss": 3.3871, + "step": 2107904 + }, + { + "epoch": 1.02, + "learning_rate": 1.5482080605989533e-05, + "loss": 3.3958, + "step": 2108416 + }, + { + "epoch": 1.02, + "learning_rate": 1.5473694658479013e-05, + "loss": 3.3944, + "step": 2108928 + }, + { + "epoch": 1.02, + "learning_rate": 1.5465308710968493e-05, + "loss": 3.4038, + "step": 2109440 + }, + { + "epoch": 1.02, + "learning_rate": 1.5456922763457973e-05, + "loss": 3.3803, + "step": 2109952 + }, + { + "epoch": 1.02, + "learning_rate": 1.5448553194751182e-05, + "loss": 3.3952, + "step": 2110464 + }, + { + "epoch": 1.02, + "learning_rate": 1.5440167247240665e-05, + "loss": 3.3951, + "step": 2110976 + }, + { + "epoch": 1.02, + "learning_rate": 1.5431781299730145e-05, + "loss": 3.393, + "step": 2111488 + }, + { + "epoch": 1.02, + "learning_rate": 1.5423395352219625e-05, + "loss": 3.3908, + "step": 2112000 + }, + { + "epoch": 1.02, + "learning_rate": 1.5415025783512834e-05, + "loss": 3.3898, + "step": 2112512 + }, + { + "epoch": 1.02, + "learning_rate": 1.5406639836002314e-05, + "loss": 3.3924, + "step": 2113024 + }, + { + "epoch": 1.02, + "learning_rate": 1.5398253888491794e-05, + "loss": 3.3852, + "step": 2113536 + }, + { + "epoch": 1.02, + "learning_rate": 1.5389867940981274e-05, + "loss": 3.3872, + "step": 2114048 + }, + { + "epoch": 1.02, + "learning_rate": 1.5381498372274487e-05, + "loss": 3.3806, + "step": 2114560 + }, + { + "epoch": 1.02, + "learning_rate": 1.5373112424763967e-05, + "loss": 3.3848, + "step": 2115072 + }, + { + "epoch": 1.02, + "learning_rate": 1.5364726477253446e-05, + "loss": 3.395, + "step": 2115584 + }, + { + "epoch": 1.02, + "learning_rate": 1.5356356908546656e-05, + "loss": 3.3878, + "step": 2116096 + }, + { + "epoch": 1.02, + "learning_rate": 1.5347970961036136e-05, + "loss": 3.3838, + "step": 2116608 + }, + { + "epoch": 1.02, + "learning_rate": 1.533958501352562e-05, + "loss": 3.3845, + "step": 2117120 + }, + { + "epoch": 1.02, + "learning_rate": 1.53311990660151e-05, + "loss": 3.3983, + "step": 2117632 + }, + { + "epoch": 1.02, + "learning_rate": 1.5322813118504575e-05, + "loss": 3.3955, + "step": 2118144 + }, + { + "epoch": 1.02, + "learning_rate": 1.5314427170994055e-05, + "loss": 3.3909, + "step": 2118656 + }, + { + "epoch": 1.02, + "learning_rate": 1.5306041223483535e-05, + "loss": 3.3976, + "step": 2119168 + }, + { + "epoch": 1.02, + "learning_rate": 1.5297671654776748e-05, + "loss": 3.4012, + "step": 2119680 + }, + { + "epoch": 1.02, + "learning_rate": 1.5289285707266228e-05, + "loss": 3.3883, + "step": 2120192 + }, + { + "epoch": 1.02, + "learning_rate": 1.5280899759755708e-05, + "loss": 3.3843, + "step": 2120704 + }, + { + "epoch": 1.02, + "learning_rate": 1.5272513812245188e-05, + "loss": 3.3875, + "step": 2121216 + }, + { + "epoch": 1.02, + "learning_rate": 1.5264127864734668e-05, + "loss": 3.3903, + "step": 2121728 + }, + { + "epoch": 1.02, + "learning_rate": 1.5255741917224148e-05, + "loss": 3.3978, + "step": 2122240 + }, + { + "epoch": 1.02, + "learning_rate": 1.5247355969713628e-05, + "loss": 3.368, + "step": 2122752 + }, + { + "epoch": 1.02, + "learning_rate": 1.5238986401006838e-05, + "loss": 3.3914, + "step": 2123264 + }, + { + "epoch": 1.02, + "learning_rate": 1.5230600453496318e-05, + "loss": 3.3892, + "step": 2123776 + }, + { + "epoch": 1.02, + "learning_rate": 1.5222214505985798e-05, + "loss": 3.3916, + "step": 2124288 + }, + { + "epoch": 1.02, + "learning_rate": 1.521382855847528e-05, + "loss": 3.3929, + "step": 2124800 + }, + { + "epoch": 1.02, + "learning_rate": 1.5205458989768489e-05, + "loss": 3.392, + "step": 2125312 + }, + { + "epoch": 1.02, + "learning_rate": 1.519707304225797e-05, + "loss": 3.3844, + "step": 2125824 + }, + { + "epoch": 1.02, + "learning_rate": 1.518868709474745e-05, + "loss": 3.381, + "step": 2126336 + }, + { + "epoch": 1.02, + "learning_rate": 1.518030114723693e-05, + "loss": 3.3994, + "step": 2126848 + }, + { + "epoch": 1.02, + "learning_rate": 1.5171931578530141e-05, + "loss": 3.3908, + "step": 2127360 + }, + { + "epoch": 1.02, + "learning_rate": 1.5163545631019621e-05, + "loss": 3.4003, + "step": 2127872 + }, + { + "epoch": 1.02, + "learning_rate": 1.5155159683509101e-05, + "loss": 3.3786, + "step": 2128384 + }, + { + "epoch": 1.02, + "learning_rate": 1.5146773735998581e-05, + "loss": 3.3942, + "step": 2128896 + }, + { + "epoch": 1.02, + "learning_rate": 1.513838778848806e-05, + "loss": 3.3973, + "step": 2129408 + }, + { + "epoch": 1.02, + "learning_rate": 1.513000184097754e-05, + "loss": 3.3867, + "step": 2129920 + }, + { + "epoch": 1.02, + "learning_rate": 1.512161589346702e-05, + "loss": 3.3917, + "step": 2130432 + }, + { + "epoch": 1.02, + "learning_rate": 1.5113229945956501e-05, + "loss": 3.384, + "step": 2130944 + }, + { + "epoch": 1.02, + "learning_rate": 1.510486037724971e-05, + "loss": 3.3937, + "step": 2131456 + }, + { + "epoch": 1.02, + "learning_rate": 1.509647442973919e-05, + "loss": 3.4064, + "step": 2131968 + }, + { + "epoch": 1.02, + "learning_rate": 1.5088088482228672e-05, + "loss": 3.3878, + "step": 2132480 + }, + { + "epoch": 1.02, + "learning_rate": 1.5079702534718152e-05, + "loss": 3.3876, + "step": 2132992 + }, + { + "epoch": 1.02, + "learning_rate": 1.5071332966011362e-05, + "loss": 3.3872, + "step": 2133504 + }, + { + "epoch": 1.02, + "learning_rate": 1.5062963397304575e-05, + "loss": 3.3849, + "step": 2134016 + }, + { + "epoch": 1.02, + "learning_rate": 1.5054577449794052e-05, + "loss": 3.3853, + "step": 2134528 + }, + { + "epoch": 1.02, + "learning_rate": 1.5046191502283533e-05, + "loss": 3.3953, + "step": 2135040 + }, + { + "epoch": 1.02, + "learning_rate": 1.5037805554773013e-05, + "loss": 3.3883, + "step": 2135552 + }, + { + "epoch": 1.02, + "learning_rate": 1.5029419607262493e-05, + "loss": 3.3948, + "step": 2136064 + }, + { + "epoch": 1.02, + "learning_rate": 1.5021050038555704e-05, + "loss": 3.3855, + "step": 2136576 + }, + { + "epoch": 1.03, + "eval_loss": 3.8620526790618896, + "eval_runtime": 308.8498, + "eval_samples_per_second": 1235.523, + "eval_steps_per_second": 38.611, + "step": 2136960 + }, + { + "epoch": 0.0, + "learning_rate": 1.5012664091045184e-05, + "loss": 3.4139, + "step": 2137088 + }, + { + "epoch": 0.0, + "learning_rate": 1.5004278143534664e-05, + "loss": 3.3754, + "step": 2137600 + }, + { + "epoch": 0.0, + "learning_rate": 1.4995892196024144e-05, + "loss": 3.3884, + "step": 2138112 + }, + { + "epoch": 0.0, + "learning_rate": 1.4987522627317355e-05, + "loss": 3.3989, + "step": 2138624 + }, + { + "epoch": 0.0, + "learning_rate": 1.4979136679806835e-05, + "loss": 3.3975, + "step": 2139136 + }, + { + "epoch": 0.0, + "learning_rate": 1.4970750732296316e-05, + "loss": 3.3893, + "step": 2139648 + }, + { + "epoch": 0.0, + "learning_rate": 1.4962364784785796e-05, + "loss": 3.3863, + "step": 2140160 + }, + { + "epoch": 0.0, + "learning_rate": 1.4953978837275276e-05, + "loss": 3.3817, + "step": 2140672 + }, + { + "epoch": 0.0, + "learning_rate": 1.4945592889764756e-05, + "loss": 3.3813, + "step": 2141184 + }, + { + "epoch": 0.0, + "learning_rate": 1.4937206942254234e-05, + "loss": 3.3876, + "step": 2141696 + }, + { + "epoch": 0.0, + "learning_rate": 1.4928820994743714e-05, + "loss": 3.3933, + "step": 2142208 + }, + { + "epoch": 0.0, + "learning_rate": 1.4920451426036927e-05, + "loss": 3.3989, + "step": 2142720 + }, + { + "epoch": 0.0, + "learning_rate": 1.4912065478526407e-05, + "loss": 3.4045, + "step": 2143232 + }, + { + "epoch": 0.0, + "learning_rate": 1.4903679531015885e-05, + "loss": 3.3721, + "step": 2143744 + }, + { + "epoch": 0.0, + "learning_rate": 1.4895309962309097e-05, + "loss": 3.3809, + "step": 2144256 + }, + { + "epoch": 0.0, + "learning_rate": 1.4886924014798579e-05, + "loss": 3.3719, + "step": 2144768 + }, + { + "epoch": 0.0, + "learning_rate": 1.4878538067288059e-05, + "loss": 3.3933, + "step": 2145280 + }, + { + "epoch": 0.0, + "learning_rate": 1.4870152119777536e-05, + "loss": 3.383, + "step": 2145792 + }, + { + "epoch": 0.0, + "learning_rate": 1.486178255107075e-05, + "loss": 3.3785, + "step": 2146304 + }, + { + "epoch": 0.0, + "learning_rate": 1.485339660356023e-05, + "loss": 3.3832, + "step": 2146816 + }, + { + "epoch": 0.0, + "learning_rate": 1.4845010656049706e-05, + "loss": 3.3979, + "step": 2147328 + }, + { + "epoch": 0.0, + "learning_rate": 1.4836624708539188e-05, + "loss": 3.3866, + "step": 2147840 + }, + { + "epoch": 0.0, + "learning_rate": 1.48282551398324e-05, + "loss": 3.3931, + "step": 2148352 + }, + { + "epoch": 0.0, + "learning_rate": 1.481986919232188e-05, + "loss": 3.384, + "step": 2148864 + }, + { + "epoch": 0.0, + "learning_rate": 1.4811483244811359e-05, + "loss": 3.3962, + "step": 2149376 + }, + { + "epoch": 0.0, + "learning_rate": 1.4803097297300839e-05, + "loss": 3.3843, + "step": 2149888 + }, + { + "epoch": 0.0, + "learning_rate": 1.4794727728594051e-05, + "loss": 3.3782, + "step": 2150400 + }, + { + "epoch": 0.0, + "learning_rate": 1.4786341781083533e-05, + "loss": 3.3944, + "step": 2150912 + }, + { + "epoch": 0.0, + "learning_rate": 1.477795583357301e-05, + "loss": 3.3739, + "step": 2151424 + }, + { + "epoch": 0.0, + "learning_rate": 1.476956988606249e-05, + "loss": 3.3784, + "step": 2151936 + }, + { + "epoch": 0.01, + "learning_rate": 1.4761200317355703e-05, + "loss": 3.392, + "step": 2152448 + }, + { + "epoch": 0.01, + "learning_rate": 1.475281436984518e-05, + "loss": 3.3846, + "step": 2152960 + }, + { + "epoch": 0.01, + "learning_rate": 1.474442842233466e-05, + "loss": 3.3856, + "step": 2153472 + }, + { + "epoch": 0.01, + "learning_rate": 1.4736042474824142e-05, + "loss": 3.3933, + "step": 2153984 + }, + { + "epoch": 0.01, + "learning_rate": 1.4727672906117354e-05, + "loss": 3.3776, + "step": 2154496 + }, + { + "epoch": 0.01, + "learning_rate": 1.4719286958606832e-05, + "loss": 3.3862, + "step": 2155008 + }, + { + "epoch": 0.01, + "learning_rate": 1.4710901011096312e-05, + "loss": 3.3869, + "step": 2155520 + }, + { + "epoch": 0.01, + "learning_rate": 1.4702515063585792e-05, + "loss": 3.3696, + "step": 2156032 + }, + { + "epoch": 0.01, + "learning_rate": 1.4694145494879005e-05, + "loss": 3.3828, + "step": 2156544 + }, + { + "epoch": 0.01, + "learning_rate": 1.4685759547368483e-05, + "loss": 3.3736, + "step": 2157056 + }, + { + "epoch": 0.01, + "learning_rate": 1.4677373599857963e-05, + "loss": 3.3771, + "step": 2157568 + }, + { + "epoch": 0.01, + "learning_rate": 1.4669004031151175e-05, + "loss": 3.3822, + "step": 2158080 + }, + { + "epoch": 0.01, + "learning_rate": 1.4660618083640654e-05, + "loss": 3.3889, + "step": 2158592 + }, + { + "epoch": 0.01, + "learning_rate": 1.4652232136130134e-05, + "loss": 3.3867, + "step": 2159104 + }, + { + "epoch": 0.01, + "learning_rate": 1.4643846188619614e-05, + "loss": 3.3872, + "step": 2159616 + }, + { + "epoch": 0.01, + "learning_rate": 1.4635460241109095e-05, + "loss": 3.3862, + "step": 2160128 + }, + { + "epoch": 0.01, + "learning_rate": 1.4627074293598575e-05, + "loss": 3.3808, + "step": 2160640 + }, + { + "epoch": 0.01, + "learning_rate": 1.4618688346088055e-05, + "loss": 3.3794, + "step": 2161152 + }, + { + "epoch": 0.01, + "learning_rate": 1.4610302398577535e-05, + "loss": 3.3639, + "step": 2161664 + }, + { + "epoch": 0.01, + "learning_rate": 1.4601932829870746e-05, + "loss": 3.3841, + "step": 2162176 + }, + { + "epoch": 0.01, + "learning_rate": 1.4593546882360226e-05, + "loss": 3.3821, + "step": 2162688 + }, + { + "epoch": 0.01, + "learning_rate": 1.4585160934849706e-05, + "loss": 3.3847, + "step": 2163200 + }, + { + "epoch": 0.01, + "learning_rate": 1.4576774987339187e-05, + "loss": 3.3837, + "step": 2163712 + }, + { + "epoch": 0.01, + "learning_rate": 1.4568405418632397e-05, + "loss": 3.3738, + "step": 2164224 + }, + { + "epoch": 0.01, + "learning_rate": 1.4560019471121877e-05, + "loss": 3.3724, + "step": 2164736 + }, + { + "epoch": 0.01, + "learning_rate": 1.4551633523611358e-05, + "loss": 3.3755, + "step": 2165248 + }, + { + "epoch": 0.01, + "learning_rate": 1.4543247576100835e-05, + "loss": 3.3912, + "step": 2165760 + }, + { + "epoch": 0.01, + "learning_rate": 1.4534878007394049e-05, + "loss": 3.3757, + "step": 2166272 + }, + { + "epoch": 0.01, + "learning_rate": 1.4526492059883529e-05, + "loss": 3.3976, + "step": 2166784 + }, + { + "epoch": 0.01, + "learning_rate": 1.4518106112373009e-05, + "loss": 3.3792, + "step": 2167296 + }, + { + "epoch": 0.01, + "learning_rate": 1.4509720164862487e-05, + "loss": 3.368, + "step": 2167808 + }, + { + "epoch": 0.01, + "learning_rate": 1.45013505961557e-05, + "loss": 3.3893, + "step": 2168320 + }, + { + "epoch": 0.01, + "learning_rate": 1.449296464864518e-05, + "loss": 3.3736, + "step": 2168832 + }, + { + "epoch": 0.01, + "learning_rate": 1.4484578701134658e-05, + "loss": 3.3681, + "step": 2169344 + }, + { + "epoch": 0.01, + "learning_rate": 1.4476192753624138e-05, + "loss": 3.3783, + "step": 2169856 + }, + { + "epoch": 0.01, + "learning_rate": 1.446782318491735e-05, + "loss": 3.3877, + "step": 2170368 + }, + { + "epoch": 0.01, + "learning_rate": 1.445943723740683e-05, + "loss": 3.3706, + "step": 2170880 + }, + { + "epoch": 0.01, + "learning_rate": 1.4451051289896308e-05, + "loss": 3.3825, + "step": 2171392 + }, + { + "epoch": 0.01, + "learning_rate": 1.4442665342385788e-05, + "loss": 3.3673, + "step": 2171904 + }, + { + "epoch": 0.01, + "learning_rate": 1.4434295773679003e-05, + "loss": 3.378, + "step": 2172416 + }, + { + "epoch": 0.01, + "learning_rate": 1.4425909826168483e-05, + "loss": 3.3876, + "step": 2172928 + }, + { + "epoch": 0.01, + "learning_rate": 1.4417540257461692e-05, + "loss": 3.38, + "step": 2173440 + }, + { + "epoch": 0.01, + "learning_rate": 1.4409154309951173e-05, + "loss": 3.3818, + "step": 2173952 + }, + { + "epoch": 0.01, + "learning_rate": 1.4400768362440653e-05, + "loss": 3.3809, + "step": 2174464 + }, + { + "epoch": 0.01, + "learning_rate": 1.439238241493013e-05, + "loss": 3.3906, + "step": 2174976 + }, + { + "epoch": 0.01, + "learning_rate": 1.4383996467419611e-05, + "loss": 3.3769, + "step": 2175488 + }, + { + "epoch": 0.01, + "learning_rate": 1.4375610519909091e-05, + "loss": 3.3852, + "step": 2176000 + }, + { + "epoch": 0.01, + "learning_rate": 1.4367224572398571e-05, + "loss": 3.3755, + "step": 2176512 + }, + { + "epoch": 0.01, + "learning_rate": 1.4358838624888051e-05, + "loss": 3.3727, + "step": 2177024 + }, + { + "epoch": 0.01, + "learning_rate": 1.4350469056181262e-05, + "loss": 3.3881, + "step": 2177536 + }, + { + "epoch": 0.01, + "learning_rate": 1.4342083108670742e-05, + "loss": 3.3764, + "step": 2178048 + }, + { + "epoch": 0.01, + "learning_rate": 1.4333697161160222e-05, + "loss": 3.3912, + "step": 2178560 + }, + { + "epoch": 0.01, + "learning_rate": 1.4325311213649704e-05, + "loss": 3.3893, + "step": 2179072 + }, + { + "epoch": 0.01, + "learning_rate": 1.4316941644942913e-05, + "loss": 3.3837, + "step": 2179584 + }, + { + "epoch": 0.01, + "learning_rate": 1.4308555697432394e-05, + "loss": 3.3656, + "step": 2180096 + }, + { + "epoch": 0.01, + "learning_rate": 1.4300186128725604e-05, + "loss": 3.3778, + "step": 2180608 + }, + { + "epoch": 0.01, + "learning_rate": 1.4291800181215084e-05, + "loss": 3.3826, + "step": 2181120 + }, + { + "epoch": 0.01, + "learning_rate": 1.4283414233704565e-05, + "loss": 3.3776, + "step": 2181632 + }, + { + "epoch": 0.01, + "learning_rate": 1.4275028286194045e-05, + "loss": 3.3804, + "step": 2182144 + }, + { + "epoch": 0.01, + "learning_rate": 1.4266642338683525e-05, + "loss": 3.3847, + "step": 2182656 + }, + { + "epoch": 0.02, + "learning_rate": 1.4258256391173005e-05, + "loss": 3.3807, + "step": 2183168 + }, + { + "epoch": 0.02, + "learning_rate": 1.4249870443662485e-05, + "loss": 3.381, + "step": 2183680 + }, + { + "epoch": 0.02, + "learning_rate": 1.4241484496151963e-05, + "loss": 3.3779, + "step": 2184192 + }, + { + "epoch": 0.02, + "learning_rate": 1.4233114927445176e-05, + "loss": 3.3864, + "step": 2184704 + }, + { + "epoch": 0.02, + "learning_rate": 1.4224745358738387e-05, + "loss": 3.3843, + "step": 2185216 + }, + { + "epoch": 0.02, + "learning_rate": 1.4216359411227866e-05, + "loss": 3.3927, + "step": 2185728 + }, + { + "epoch": 0.02, + "learning_rate": 1.4207973463717348e-05, + "loss": 3.3706, + "step": 2186240 + }, + { + "epoch": 0.02, + "learning_rate": 1.4199587516206828e-05, + "loss": 3.3835, + "step": 2186752 + }, + { + "epoch": 0.02, + "learning_rate": 1.4191201568696308e-05, + "loss": 3.3873, + "step": 2187264 + }, + { + "epoch": 0.02, + "learning_rate": 1.4182815621185785e-05, + "loss": 3.3841, + "step": 2187776 + }, + { + "epoch": 0.02, + "learning_rate": 1.4174429673675266e-05, + "loss": 3.3846, + "step": 2188288 + }, + { + "epoch": 0.02, + "learning_rate": 1.4166043726164746e-05, + "loss": 3.379, + "step": 2188800 + }, + { + "epoch": 0.02, + "learning_rate": 1.4157674157457959e-05, + "loss": 3.38, + "step": 2189312 + }, + { + "epoch": 0.02, + "learning_rate": 1.4149288209947437e-05, + "loss": 3.3766, + "step": 2189824 + }, + { + "epoch": 0.02, + "learning_rate": 1.4140902262436917e-05, + "loss": 3.377, + "step": 2190336 + }, + { + "epoch": 0.02, + "learning_rate": 1.4132516314926397e-05, + "loss": 3.3701, + "step": 2190848 + }, + { + "epoch": 0.02, + "learning_rate": 1.4124146746219611e-05, + "loss": 3.3764, + "step": 2191360 + }, + { + "epoch": 0.02, + "learning_rate": 1.4115760798709088e-05, + "loss": 3.3857, + "step": 2191872 + }, + { + "epoch": 0.02, + "learning_rate": 1.41073912300023e-05, + "loss": 3.3809, + "step": 2192384 + }, + { + "epoch": 0.02, + "learning_rate": 1.4099005282491782e-05, + "loss": 3.3738, + "step": 2192896 + }, + { + "epoch": 0.02, + "learning_rate": 1.4090619334981258e-05, + "loss": 3.3718, + "step": 2193408 + }, + { + "epoch": 0.02, + "learning_rate": 1.4082233387470738e-05, + "loss": 3.3878, + "step": 2193920 + }, + { + "epoch": 0.02, + "learning_rate": 1.407384743996022e-05, + "loss": 3.3851, + "step": 2194432 + }, + { + "epoch": 0.02, + "learning_rate": 1.40654614924497e-05, + "loss": 3.3813, + "step": 2194944 + }, + { + "epoch": 0.02, + "learning_rate": 1.405707554493918e-05, + "loss": 3.3878, + "step": 2195456 + }, + { + "epoch": 0.02, + "learning_rate": 1.404870597623239e-05, + "loss": 3.3906, + "step": 2195968 + }, + { + "epoch": 0.02, + "learning_rate": 1.404032002872187e-05, + "loss": 3.38, + "step": 2196480 + }, + { + "epoch": 0.02, + "learning_rate": 1.403193408121135e-05, + "loss": 3.3761, + "step": 2196992 + }, + { + "epoch": 0.02, + "learning_rate": 1.402354813370083e-05, + "loss": 3.3799, + "step": 2197504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4015162186190312e-05, + "loss": 3.3838, + "step": 2198016 + }, + { + "epoch": 0.02, + "learning_rate": 1.4006776238679792e-05, + "loss": 3.387, + "step": 2198528 + }, + { + "epoch": 0.02, + "learning_rate": 1.3998390291169269e-05, + "loss": 3.3587, + "step": 2199040 + }, + { + "epoch": 0.02, + "learning_rate": 1.3990020722462483e-05, + "loss": 3.3802, + "step": 2199552 + }, + { + "epoch": 0.02, + "learning_rate": 1.3981634774951963e-05, + "loss": 3.3782, + "step": 2200064 + }, + { + "epoch": 0.02, + "learning_rate": 1.3973248827441441e-05, + "loss": 3.3792, + "step": 2200576 + }, + { + "epoch": 0.02, + "learning_rate": 1.3964862879930921e-05, + "loss": 3.3838, + "step": 2201088 + }, + { + "epoch": 0.02, + "learning_rate": 1.3956493311224133e-05, + "loss": 3.3827, + "step": 2201600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3948107363713613e-05, + "loss": 3.3742, + "step": 2202112 + }, + { + "epoch": 0.02, + "learning_rate": 1.3939721416203092e-05, + "loss": 3.3725, + "step": 2202624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3931335468692572e-05, + "loss": 3.3914, + "step": 2203136 + }, + { + "epoch": 0.02, + "learning_rate": 1.3922965899985784e-05, + "loss": 3.3808, + "step": 2203648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3914579952475266e-05, + "loss": 3.3918, + "step": 2204160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3906194004964742e-05, + "loss": 3.3705, + "step": 2204672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3897808057454222e-05, + "loss": 3.386, + "step": 2205184 + }, + { + "epoch": 0.02, + "learning_rate": 1.3889438488747437e-05, + "loss": 3.3868, + "step": 2205696 + }, + { + "epoch": 0.02, + "learning_rate": 1.3881052541236913e-05, + "loss": 3.3786, + "step": 2206208 + }, + { + "epoch": 0.02, + "learning_rate": 1.3872666593726395e-05, + "loss": 3.3787, + "step": 2206720 + }, + { + "epoch": 0.02, + "learning_rate": 1.3864280646215875e-05, + "loss": 3.3761, + "step": 2207232 + }, + { + "epoch": 0.02, + "learning_rate": 1.3855911077509087e-05, + "loss": 3.3841, + "step": 2207744 + }, + { + "epoch": 0.02, + "learning_rate": 1.3847525129998565e-05, + "loss": 3.3987, + "step": 2208256 + }, + { + "epoch": 0.02, + "learning_rate": 1.3839139182488045e-05, + "loss": 3.3783, + "step": 2208768 + }, + { + "epoch": 0.02, + "learning_rate": 1.3830753234977525e-05, + "loss": 3.3766, + "step": 2209280 + }, + { + "epoch": 0.02, + "learning_rate": 1.3822383666270736e-05, + "loss": 3.3786, + "step": 2209792 + }, + { + "epoch": 0.02, + "learning_rate": 1.3814014097563949e-05, + "loss": 3.3755, + "step": 2210304 + }, + { + "epoch": 0.02, + "learning_rate": 1.3805628150053429e-05, + "loss": 3.3715, + "step": 2210816 + }, + { + "epoch": 0.02, + "learning_rate": 1.3797242202542909e-05, + "loss": 3.3904, + "step": 2211328 + }, + { + "epoch": 0.02, + "learning_rate": 1.3788856255032387e-05, + "loss": 3.3738, + "step": 2211840 + }, + { + "epoch": 0.02, + "learning_rate": 1.3780470307521867e-05, + "loss": 3.3864, + "step": 2212352 + }, + { + "epoch": 0.02, + "learning_rate": 1.3772100738815081e-05, + "loss": 3.3777, + "step": 2212864 + }, + { + "epoch": 0.03, + "eval_loss": 3.863626003265381, + "eval_runtime": 302.1107, + "eval_samples_per_second": 1263.083, + "eval_steps_per_second": 39.472, + "step": 2213280 + }, + { + "epoch": 1.0, + "learning_rate": 1.3763714791304561e-05, + "loss": 3.3701, + "step": 2213376 + }, + { + "epoch": 1.0, + "learning_rate": 1.3755328843794037e-05, + "loss": 3.3681, + "step": 2213888 + }, + { + "epoch": 1.0, + "learning_rate": 1.3746942896283519e-05, + "loss": 3.3784, + "step": 2214400 + }, + { + "epoch": 1.0, + "learning_rate": 1.3738556948772999e-05, + "loss": 3.3932, + "step": 2214912 + }, + { + "epoch": 1.0, + "learning_rate": 1.3730171001262479e-05, + "loss": 3.3858, + "step": 2215424 + }, + { + "epoch": 1.0, + "learning_rate": 1.3721785053751959e-05, + "loss": 3.3818, + "step": 2215936 + }, + { + "epoch": 1.0, + "learning_rate": 1.3713399106241439e-05, + "loss": 3.3702, + "step": 2216448 + }, + { + "epoch": 1.0, + "learning_rate": 1.370502953753465e-05, + "loss": 3.3723, + "step": 2216960 + }, + { + "epoch": 1.0, + "learning_rate": 1.369664359002413e-05, + "loss": 3.3693, + "step": 2217472 + }, + { + "epoch": 1.0, + "learning_rate": 1.3688257642513611e-05, + "loss": 3.3823, + "step": 2217984 + }, + { + "epoch": 1.0, + "learning_rate": 1.367988807380682e-05, + "loss": 3.3745, + "step": 2218496 + }, + { + "epoch": 1.0, + "learning_rate": 1.36715021262963e-05, + "loss": 3.3949, + "step": 2219008 + }, + { + "epoch": 1.0, + "learning_rate": 1.3663116178785782e-05, + "loss": 3.3909, + "step": 2219520 + }, + { + "epoch": 1.0, + "learning_rate": 1.3654730231275262e-05, + "loss": 3.3644, + "step": 2220032 + }, + { + "epoch": 1.0, + "learning_rate": 1.3646344283764742e-05, + "loss": 3.3714, + "step": 2220544 + }, + { + "epoch": 1.0, + "learning_rate": 1.363795833625422e-05, + "loss": 3.3637, + "step": 2221056 + }, + { + "epoch": 1.0, + "learning_rate": 1.36295723887437e-05, + "loss": 3.3821, + "step": 2221568 + }, + { + "epoch": 1.0, + "learning_rate": 1.362118644123318e-05, + "loss": 3.3706, + "step": 2222080 + }, + { + "epoch": 1.0, + "learning_rate": 1.3612816872526391e-05, + "loss": 3.3708, + "step": 2222592 + }, + { + "epoch": 1.0, + "learning_rate": 1.360443092501587e-05, + "loss": 3.3748, + "step": 2223104 + }, + { + "epoch": 1.0, + "learning_rate": 1.359604497750535e-05, + "loss": 3.3848, + "step": 2223616 + }, + { + "epoch": 1.0, + "learning_rate": 1.358765902999483e-05, + "loss": 3.3786, + "step": 2224128 + }, + { + "epoch": 1.0, + "learning_rate": 1.3579289461288042e-05, + "loss": 3.38, + "step": 2224640 + }, + { + "epoch": 1.0, + "learning_rate": 1.3570903513777521e-05, + "loss": 3.377, + "step": 2225152 + }, + { + "epoch": 1.0, + "learning_rate": 1.3562517566267003e-05, + "loss": 3.3847, + "step": 2225664 + }, + { + "epoch": 1.0, + "learning_rate": 1.3554131618756483e-05, + "loss": 3.3772, + "step": 2226176 + }, + { + "epoch": 1.0, + "learning_rate": 1.3545762050049692e-05, + "loss": 3.3672, + "step": 2226688 + }, + { + "epoch": 1.0, + "learning_rate": 1.3537376102539174e-05, + "loss": 3.384, + "step": 2227200 + }, + { + "epoch": 1.0, + "learning_rate": 1.3528990155028654e-05, + "loss": 3.3663, + "step": 2227712 + }, + { + "epoch": 1.0, + "learning_rate": 1.3520604207518134e-05, + "loss": 3.3706, + "step": 2228224 + }, + { + "epoch": 1.01, + "learning_rate": 1.3512234638811345e-05, + "loss": 3.3795, + "step": 2228736 + }, + { + "epoch": 1.01, + "learning_rate": 1.3503848691300825e-05, + "loss": 3.373, + "step": 2229248 + }, + { + "epoch": 1.01, + "learning_rate": 1.3495462743790304e-05, + "loss": 3.3762, + "step": 2229760 + }, + { + "epoch": 1.01, + "learning_rate": 1.3487093175083515e-05, + "loss": 3.3826, + "step": 2230272 + }, + { + "epoch": 1.01, + "learning_rate": 1.3478707227572995e-05, + "loss": 3.3723, + "step": 2230784 + }, + { + "epoch": 1.01, + "learning_rate": 1.3470321280062475e-05, + "loss": 3.3754, + "step": 2231296 + }, + { + "epoch": 1.01, + "learning_rate": 1.3461935332551955e-05, + "loss": 3.3768, + "step": 2231808 + }, + { + "epoch": 1.01, + "learning_rate": 1.3453565763845166e-05, + "loss": 3.361, + "step": 2232320 + }, + { + "epoch": 1.01, + "learning_rate": 1.344519619513838e-05, + "loss": 3.3756, + "step": 2232832 + }, + { + "epoch": 1.01, + "learning_rate": 1.343681024762786e-05, + "loss": 3.3607, + "step": 2233344 + }, + { + "epoch": 1.01, + "learning_rate": 1.3428424300117337e-05, + "loss": 3.3718, + "step": 2233856 + }, + { + "epoch": 1.01, + "learning_rate": 1.3420038352606817e-05, + "loss": 3.3689, + "step": 2234368 + }, + { + "epoch": 1.01, + "learning_rate": 1.3411652405096298e-05, + "loss": 3.3829, + "step": 2234880 + }, + { + "epoch": 1.01, + "learning_rate": 1.3403266457585778e-05, + "loss": 3.3733, + "step": 2235392 + }, + { + "epoch": 1.01, + "learning_rate": 1.3394880510075258e-05, + "loss": 3.3798, + "step": 2235904 + }, + { + "epoch": 1.01, + "learning_rate": 1.3386494562564738e-05, + "loss": 3.3764, + "step": 2236416 + }, + { + "epoch": 1.01, + "learning_rate": 1.3378124993857949e-05, + "loss": 3.3715, + "step": 2236928 + }, + { + "epoch": 1.01, + "learning_rate": 1.3369739046347429e-05, + "loss": 3.3687, + "step": 2237440 + }, + { + "epoch": 1.01, + "learning_rate": 1.3361353098836909e-05, + "loss": 3.3537, + "step": 2237952 + }, + { + "epoch": 1.01, + "learning_rate": 1.335296715132639e-05, + "loss": 3.3734, + "step": 2238464 + }, + { + "epoch": 1.01, + "learning_rate": 1.33445975826196e-05, + "loss": 3.3762, + "step": 2238976 + }, + { + "epoch": 1.01, + "learning_rate": 1.3336211635109081e-05, + "loss": 3.3768, + "step": 2239488 + }, + { + "epoch": 1.01, + "learning_rate": 1.3327825687598561e-05, + "loss": 3.371, + "step": 2240000 + }, + { + "epoch": 1.01, + "learning_rate": 1.3319439740088041e-05, + "loss": 3.365, + "step": 2240512 + }, + { + "epoch": 1.01, + "learning_rate": 1.3311070171381252e-05, + "loss": 3.3629, + "step": 2241024 + }, + { + "epoch": 1.01, + "learning_rate": 1.3302684223870732e-05, + "loss": 3.362, + "step": 2241536 + }, + { + "epoch": 1.01, + "learning_rate": 1.3294298276360212e-05, + "loss": 3.3886, + "step": 2242048 + }, + { + "epoch": 1.01, + "learning_rate": 1.3285912328849692e-05, + "loss": 3.364, + "step": 2242560 + }, + { + "epoch": 1.01, + "learning_rate": 1.3277542760142903e-05, + "loss": 3.3838, + "step": 2243072 + }, + { + "epoch": 1.01, + "learning_rate": 1.3269156812632382e-05, + "loss": 3.3708, + "step": 2243584 + }, + { + "epoch": 1.01, + "learning_rate": 1.3260770865121862e-05, + "loss": 3.3596, + "step": 2244096 + }, + { + "epoch": 1.01, + "learning_rate": 1.3252384917611344e-05, + "loss": 3.3781, + "step": 2244608 + }, + { + "epoch": 1.01, + "learning_rate": 1.3244015348904553e-05, + "loss": 3.3627, + "step": 2245120 + }, + { + "epoch": 1.01, + "learning_rate": 1.3235629401394035e-05, + "loss": 3.3617, + "step": 2245632 + }, + { + "epoch": 1.01, + "learning_rate": 1.3227243453883515e-05, + "loss": 3.363, + "step": 2246144 + }, + { + "epoch": 1.01, + "learning_rate": 1.3218857506372991e-05, + "loss": 3.3785, + "step": 2246656 + }, + { + "epoch": 1.01, + "learning_rate": 1.3210487937666206e-05, + "loss": 3.3608, + "step": 2247168 + }, + { + "epoch": 1.01, + "learning_rate": 1.3202101990155686e-05, + "loss": 3.371, + "step": 2247680 + }, + { + "epoch": 1.01, + "learning_rate": 1.3193716042645165e-05, + "loss": 3.3577, + "step": 2248192 + }, + { + "epoch": 1.01, + "learning_rate": 1.3185346473938376e-05, + "loss": 3.3709, + "step": 2248704 + }, + { + "epoch": 1.01, + "learning_rate": 1.3176960526427856e-05, + "loss": 3.3754, + "step": 2249216 + }, + { + "epoch": 1.01, + "learning_rate": 1.3168574578917336e-05, + "loss": 3.373, + "step": 2249728 + }, + { + "epoch": 1.01, + "learning_rate": 1.3160188631406814e-05, + "loss": 3.3722, + "step": 2250240 + }, + { + "epoch": 1.01, + "learning_rate": 1.3151819062700027e-05, + "loss": 3.3699, + "step": 2250752 + }, + { + "epoch": 1.01, + "learning_rate": 1.3143433115189507e-05, + "loss": 3.3824, + "step": 2251264 + }, + { + "epoch": 1.01, + "learning_rate": 1.3135047167678989e-05, + "loss": 3.3671, + "step": 2251776 + }, + { + "epoch": 1.01, + "learning_rate": 1.3126661220168465e-05, + "loss": 3.3716, + "step": 2252288 + }, + { + "epoch": 1.01, + "learning_rate": 1.3118275272657945e-05, + "loss": 3.3695, + "step": 2252800 + }, + { + "epoch": 1.01, + "learning_rate": 1.3109889325147427e-05, + "loss": 3.3638, + "step": 2253312 + }, + { + "epoch": 1.01, + "learning_rate": 1.3101503377636907e-05, + "loss": 3.3758, + "step": 2253824 + }, + { + "epoch": 1.01, + "learning_rate": 1.3093117430126387e-05, + "loss": 3.3689, + "step": 2254336 + }, + { + "epoch": 1.01, + "learning_rate": 1.3084747861419597e-05, + "loss": 3.3805, + "step": 2254848 + }, + { + "epoch": 1.01, + "learning_rate": 1.3076361913909077e-05, + "loss": 3.38, + "step": 2255360 + }, + { + "epoch": 1.01, + "learning_rate": 1.3067975966398557e-05, + "loss": 3.3703, + "step": 2255872 + }, + { + "epoch": 1.01, + "learning_rate": 1.3059590018888037e-05, + "loss": 3.3583, + "step": 2256384 + }, + { + "epoch": 1.01, + "learning_rate": 1.305123682898498e-05, + "loss": 3.3672, + "step": 2256896 + }, + { + "epoch": 1.01, + "learning_rate": 1.304285088147446e-05, + "loss": 3.3731, + "step": 2257408 + }, + { + "epoch": 1.01, + "learning_rate": 1.3034464933963939e-05, + "loss": 3.3694, + "step": 2257920 + }, + { + "epoch": 1.01, + "learning_rate": 1.3026078986453419e-05, + "loss": 3.3691, + "step": 2258432 + }, + { + "epoch": 1.01, + "learning_rate": 1.3017693038942899e-05, + "loss": 3.3786, + "step": 2258944 + }, + { + "epoch": 1.02, + "learning_rate": 1.3009307091432379e-05, + "loss": 3.3708, + "step": 2259456 + }, + { + "epoch": 1.02, + "learning_rate": 1.300092114392186e-05, + "loss": 3.3692, + "step": 2259968 + }, + { + "epoch": 1.02, + "learning_rate": 1.299253519641134e-05, + "loss": 3.3703, + "step": 2260480 + }, + { + "epoch": 1.02, + "learning_rate": 1.2984165627704551e-05, + "loss": 3.3754, + "step": 2260992 + }, + { + "epoch": 1.02, + "learning_rate": 1.2975779680194031e-05, + "loss": 3.3711, + "step": 2261504 + }, + { + "epoch": 1.02, + "learning_rate": 1.2967393732683511e-05, + "loss": 3.3853, + "step": 2262016 + }, + { + "epoch": 1.02, + "learning_rate": 1.2959007785172991e-05, + "loss": 3.3576, + "step": 2262528 + }, + { + "epoch": 1.02, + "learning_rate": 1.2950638216466202e-05, + "loss": 3.3788, + "step": 2263040 + }, + { + "epoch": 1.02, + "learning_rate": 1.2942252268955682e-05, + "loss": 3.379, + "step": 2263552 + }, + { + "epoch": 1.02, + "learning_rate": 1.2933866321445162e-05, + "loss": 3.3708, + "step": 2264064 + }, + { + "epoch": 1.02, + "learning_rate": 1.2925480373934643e-05, + "loss": 3.3733, + "step": 2264576 + }, + { + "epoch": 1.02, + "learning_rate": 1.2917110805227852e-05, + "loss": 3.3702, + "step": 2265088 + }, + { + "epoch": 1.02, + "learning_rate": 1.2908724857717332e-05, + "loss": 3.3698, + "step": 2265600 + }, + { + "epoch": 1.02, + "learning_rate": 1.2900338910206814e-05, + "loss": 3.3667, + "step": 2266112 + }, + { + "epoch": 1.02, + "learning_rate": 1.2891952962696294e-05, + "loss": 3.3694, + "step": 2266624 + }, + { + "epoch": 1.02, + "learning_rate": 1.2883583393989505e-05, + "loss": 3.3589, + "step": 2267136 + }, + { + "epoch": 1.02, + "learning_rate": 1.2875197446478985e-05, + "loss": 3.3697, + "step": 2267648 + }, + { + "epoch": 1.02, + "learning_rate": 1.2866811498968465e-05, + "loss": 3.3711, + "step": 2268160 + }, + { + "epoch": 1.02, + "learning_rate": 1.2858441930261675e-05, + "loss": 3.3718, + "step": 2268672 + }, + { + "epoch": 1.02, + "learning_rate": 1.2850055982751155e-05, + "loss": 3.3616, + "step": 2269184 + }, + { + "epoch": 1.02, + "learning_rate": 1.2841670035240635e-05, + "loss": 3.3647, + "step": 2269696 + }, + { + "epoch": 1.02, + "learning_rate": 1.2833284087730115e-05, + "loss": 3.3746, + "step": 2270208 + }, + { + "epoch": 1.02, + "learning_rate": 1.2824898140219594e-05, + "loss": 3.3759, + "step": 2270720 + }, + { + "epoch": 1.02, + "learning_rate": 1.2816512192709074e-05, + "loss": 3.37, + "step": 2271232 + }, + { + "epoch": 1.02, + "learning_rate": 1.2808126245198553e-05, + "loss": 3.3793, + "step": 2271744 + }, + { + "epoch": 1.02, + "learning_rate": 1.2799756676491768e-05, + "loss": 3.3801, + "step": 2272256 + }, + { + "epoch": 1.02, + "learning_rate": 1.2791370728981244e-05, + "loss": 3.3754, + "step": 2272768 + }, + { + "epoch": 1.02, + "learning_rate": 1.2782984781470724e-05, + "loss": 3.3626, + "step": 2273280 + }, + { + "epoch": 1.02, + "learning_rate": 1.2774598833960206e-05, + "loss": 3.3693, + "step": 2273792 + }, + { + "epoch": 1.02, + "learning_rate": 1.2766212886449686e-05, + "loss": 3.3696, + "step": 2274304 + }, + { + "epoch": 1.02, + "learning_rate": 1.2757826938939166e-05, + "loss": 3.3797, + "step": 2274816 + }, + { + "epoch": 1.02, + "learning_rate": 1.2749440991428646e-05, + "loss": 3.3529, + "step": 2275328 + }, + { + "epoch": 1.02, + "learning_rate": 1.2741055043918124e-05, + "loss": 3.3698, + "step": 2275840 + }, + { + "epoch": 1.02, + "learning_rate": 1.2732685475211336e-05, + "loss": 3.3645, + "step": 2276352 + }, + { + "epoch": 1.02, + "learning_rate": 1.2724299527700816e-05, + "loss": 3.3696, + "step": 2276864 + }, + { + "epoch": 1.02, + "learning_rate": 1.2715913580190298e-05, + "loss": 3.3758, + "step": 2277376 + }, + { + "epoch": 1.02, + "learning_rate": 1.2707544011483507e-05, + "loss": 3.3687, + "step": 2277888 + }, + { + "epoch": 1.02, + "learning_rate": 1.2699158063972987e-05, + "loss": 3.3607, + "step": 2278400 + }, + { + "epoch": 1.02, + "learning_rate": 1.2690772116462469e-05, + "loss": 3.3628, + "step": 2278912 + }, + { + "epoch": 1.02, + "learning_rate": 1.2682386168951949e-05, + "loss": 3.3817, + "step": 2279424 + }, + { + "epoch": 1.02, + "learning_rate": 1.267401660024516e-05, + "loss": 3.3714, + "step": 2279936 + }, + { + "epoch": 1.02, + "learning_rate": 1.266563065273464e-05, + "loss": 3.3835, + "step": 2280448 + }, + { + "epoch": 1.02, + "learning_rate": 1.265724470522412e-05, + "loss": 3.3605, + "step": 2280960 + }, + { + "epoch": 1.02, + "learning_rate": 1.2648858757713598e-05, + "loss": 3.378, + "step": 2281472 + }, + { + "epoch": 1.02, + "learning_rate": 1.2640472810203078e-05, + "loss": 3.3751, + "step": 2281984 + }, + { + "epoch": 1.02, + "learning_rate": 1.2632086862692558e-05, + "loss": 3.3703, + "step": 2282496 + }, + { + "epoch": 1.02, + "learning_rate": 1.2623700915182038e-05, + "loss": 3.3671, + "step": 2283008 + }, + { + "epoch": 1.02, + "learning_rate": 1.2615314967671517e-05, + "loss": 3.3689, + "step": 2283520 + }, + { + "epoch": 1.02, + "learning_rate": 1.2606945398964728e-05, + "loss": 3.3773, + "step": 2284032 + }, + { + "epoch": 1.02, + "learning_rate": 1.2598559451454208e-05, + "loss": 3.3827, + "step": 2284544 + }, + { + "epoch": 1.02, + "learning_rate": 1.259017350394369e-05, + "loss": 3.3738, + "step": 2285056 + }, + { + "epoch": 1.02, + "learning_rate": 1.258178755643317e-05, + "loss": 3.365, + "step": 2285568 + }, + { + "epoch": 1.02, + "learning_rate": 1.2573417987726379e-05, + "loss": 3.3718, + "step": 2286080 + }, + { + "epoch": 1.02, + "learning_rate": 1.2565048419019593e-05, + "loss": 3.3636, + "step": 2286592 + }, + { + "epoch": 1.02, + "learning_rate": 1.255666247150907e-05, + "loss": 3.3622, + "step": 2287104 + }, + { + "epoch": 1.02, + "learning_rate": 1.2548276523998551e-05, + "loss": 3.3791, + "step": 2287616 + }, + { + "epoch": 1.02, + "learning_rate": 1.2539890576488031e-05, + "loss": 3.3644, + "step": 2288128 + }, + { + "epoch": 1.02, + "learning_rate": 1.2531504628977511e-05, + "loss": 3.3794, + "step": 2288640 + }, + { + "epoch": 1.02, + "learning_rate": 1.2523135060270722e-05, + "loss": 3.3661, + "step": 2289152 + }, + { + "epoch": 1.03, + "eval_loss": 3.8649725914001465, + "eval_runtime": 303.5455, + "eval_samples_per_second": 1257.113, + "eval_steps_per_second": 39.286, + "step": 2289600 + }, + { + "epoch": 0.0, + "learning_rate": 1.2514749112760202e-05, + "loss": 3.3756, + "step": 2289664 + }, + { + "epoch": 0.0, + "learning_rate": 1.2506363165249682e-05, + "loss": 3.3634, + "step": 2290176 + }, + { + "epoch": 0.0, + "learning_rate": 1.2497977217739162e-05, + "loss": 3.3664, + "step": 2290688 + }, + { + "epoch": 0.0, + "learning_rate": 1.2489607649032374e-05, + "loss": 3.3831, + "step": 2291200 + }, + { + "epoch": 0.0, + "learning_rate": 1.2481221701521853e-05, + "loss": 3.379, + "step": 2291712 + }, + { + "epoch": 0.0, + "learning_rate": 1.2472835754011333e-05, + "loss": 3.3714, + "step": 2292224 + }, + { + "epoch": 0.0, + "learning_rate": 1.2464449806500814e-05, + "loss": 3.3626, + "step": 2292736 + }, + { + "epoch": 0.0, + "learning_rate": 1.2456063858990293e-05, + "loss": 3.3622, + "step": 2293248 + }, + { + "epoch": 0.0, + "learning_rate": 1.2447677911479772e-05, + "loss": 3.3584, + "step": 2293760 + }, + { + "epoch": 0.0, + "learning_rate": 1.2439291963969252e-05, + "loss": 3.3708, + "step": 2294272 + }, + { + "epoch": 0.0, + "learning_rate": 1.2430906016458734e-05, + "loss": 3.368, + "step": 2294784 + }, + { + "epoch": 0.0, + "learning_rate": 1.2422536447751943e-05, + "loss": 3.3837, + "step": 2295296 + }, + { + "epoch": 0.0, + "learning_rate": 1.2414150500241425e-05, + "loss": 3.3824, + "step": 2295808 + }, + { + "epoch": 0.0, + "learning_rate": 1.2405764552730905e-05, + "loss": 3.3552, + "step": 2296320 + }, + { + "epoch": 0.0, + "learning_rate": 1.2397378605220383e-05, + "loss": 3.3605, + "step": 2296832 + }, + { + "epoch": 0.0, + "learning_rate": 1.2389009036513596e-05, + "loss": 3.3556, + "step": 2297344 + }, + { + "epoch": 0.0, + "learning_rate": 1.2380623089003075e-05, + "loss": 3.3713, + "step": 2297856 + }, + { + "epoch": 0.0, + "learning_rate": 1.2372237141492555e-05, + "loss": 3.3611, + "step": 2298368 + }, + { + "epoch": 0.0, + "learning_rate": 1.2363867572785766e-05, + "loss": 3.3635, + "step": 2298880 + }, + { + "epoch": 0.0, + "learning_rate": 1.2355481625275246e-05, + "loss": 3.3632, + "step": 2299392 + }, + { + "epoch": 0.0, + "learning_rate": 1.2347095677764726e-05, + "loss": 3.3742, + "step": 2299904 + }, + { + "epoch": 0.0, + "learning_rate": 1.2338709730254206e-05, + "loss": 3.3657, + "step": 2300416 + }, + { + "epoch": 0.0, + "learning_rate": 1.2330340161547417e-05, + "loss": 3.372, + "step": 2300928 + }, + { + "epoch": 0.0, + "learning_rate": 1.2321954214036897e-05, + "loss": 3.3689, + "step": 2301440 + }, + { + "epoch": 0.0, + "learning_rate": 1.2313568266526378e-05, + "loss": 3.3761, + "step": 2301952 + }, + { + "epoch": 0.0, + "learning_rate": 1.2305182319015857e-05, + "loss": 3.3639, + "step": 2302464 + }, + { + "epoch": 0.0, + "learning_rate": 1.2296812750309068e-05, + "loss": 3.3613, + "step": 2302976 + }, + { + "epoch": 0.0, + "learning_rate": 1.228842680279855e-05, + "loss": 3.3723, + "step": 2303488 + }, + { + "epoch": 0.0, + "learning_rate": 1.2280040855288029e-05, + "loss": 3.3555, + "step": 2304000 + }, + { + "epoch": 0.0, + "learning_rate": 1.2271654907777507e-05, + "loss": 3.3599, + "step": 2304512 + }, + { + "epoch": 0.01, + "learning_rate": 1.226328533907072e-05, + "loss": 3.3694, + "step": 2305024 + }, + { + "epoch": 0.01, + "learning_rate": 1.22548993915602e-05, + "loss": 3.3663, + "step": 2305536 + }, + { + "epoch": 0.01, + "learning_rate": 1.224651344404968e-05, + "loss": 3.3654, + "step": 2306048 + }, + { + "epoch": 0.01, + "learning_rate": 1.223812749653916e-05, + "loss": 3.3732, + "step": 2306560 + }, + { + "epoch": 0.01, + "learning_rate": 1.222975792783237e-05, + "loss": 3.364, + "step": 2307072 + }, + { + "epoch": 0.01, + "learning_rate": 1.222137198032185e-05, + "loss": 3.3673, + "step": 2307584 + }, + { + "epoch": 0.01, + "learning_rate": 1.221298603281133e-05, + "loss": 3.3677, + "step": 2308096 + }, + { + "epoch": 0.01, + "learning_rate": 1.2204616464104541e-05, + "loss": 3.3502, + "step": 2308608 + }, + { + "epoch": 0.01, + "learning_rate": 1.2196230516594021e-05, + "loss": 3.3648, + "step": 2309120 + }, + { + "epoch": 0.01, + "learning_rate": 1.2187844569083503e-05, + "loss": 3.3549, + "step": 2309632 + }, + { + "epoch": 0.01, + "learning_rate": 1.2179458621572981e-05, + "loss": 3.3605, + "step": 2310144 + }, + { + "epoch": 0.01, + "learning_rate": 1.2171072674062461e-05, + "loss": 3.3579, + "step": 2310656 + }, + { + "epoch": 0.01, + "learning_rate": 1.2162686726551941e-05, + "loss": 3.3712, + "step": 2311168 + }, + { + "epoch": 0.01, + "learning_rate": 1.2154300779041421e-05, + "loss": 3.3637, + "step": 2311680 + }, + { + "epoch": 0.01, + "learning_rate": 1.2145914831530901e-05, + "loss": 3.3695, + "step": 2312192 + }, + { + "epoch": 0.01, + "learning_rate": 1.2137545262824113e-05, + "loss": 3.3679, + "step": 2312704 + }, + { + "epoch": 0.01, + "learning_rate": 1.2129159315313593e-05, + "loss": 3.3648, + "step": 2313216 + }, + { + "epoch": 0.01, + "learning_rate": 1.2120773367803072e-05, + "loss": 3.361, + "step": 2313728 + }, + { + "epoch": 0.01, + "learning_rate": 1.2112387420292552e-05, + "loss": 3.3486, + "step": 2314240 + }, + { + "epoch": 0.01, + "learning_rate": 1.2104017851585764e-05, + "loss": 3.3617, + "step": 2314752 + }, + { + "epoch": 0.01, + "learning_rate": 1.2095631904075244e-05, + "loss": 3.3654, + "step": 2315264 + }, + { + "epoch": 0.01, + "learning_rate": 1.2087245956564722e-05, + "loss": 3.3647, + "step": 2315776 + }, + { + "epoch": 0.01, + "learning_rate": 1.2078860009054204e-05, + "loss": 3.364, + "step": 2316288 + }, + { + "epoch": 0.01, + "learning_rate": 1.2070490440347415e-05, + "loss": 3.3519, + "step": 2316800 + }, + { + "epoch": 0.01, + "learning_rate": 1.2062104492836895e-05, + "loss": 3.3571, + "step": 2317312 + }, + { + "epoch": 0.01, + "learning_rate": 1.2053718545326375e-05, + "loss": 3.352, + "step": 2317824 + }, + { + "epoch": 0.01, + "learning_rate": 1.2045332597815855e-05, + "loss": 3.3805, + "step": 2318336 + }, + { + "epoch": 0.01, + "learning_rate": 1.2036963029109067e-05, + "loss": 3.3515, + "step": 2318848 + }, + { + "epoch": 0.01, + "learning_rate": 1.2028577081598545e-05, + "loss": 3.3773, + "step": 2319360 + }, + { + "epoch": 0.01, + "learning_rate": 1.2020191134088025e-05, + "loss": 3.3605, + "step": 2319872 + }, + { + "epoch": 0.01, + "learning_rate": 1.2011805186577505e-05, + "loss": 3.3517, + "step": 2320384 + }, + { + "epoch": 0.01, + "learning_rate": 1.2003435617870718e-05, + "loss": 3.364, + "step": 2320896 + }, + { + "epoch": 0.01, + "learning_rate": 1.1995049670360196e-05, + "loss": 3.3581, + "step": 2321408 + }, + { + "epoch": 0.01, + "learning_rate": 1.1986663722849676e-05, + "loss": 3.3558, + "step": 2321920 + }, + { + "epoch": 0.01, + "learning_rate": 1.1978277775339158e-05, + "loss": 3.3485, + "step": 2322432 + }, + { + "epoch": 0.01, + "learning_rate": 1.1969908206632367e-05, + "loss": 3.3732, + "step": 2322944 + }, + { + "epoch": 0.01, + "learning_rate": 1.1961522259121848e-05, + "loss": 3.3571, + "step": 2323456 + }, + { + "epoch": 0.01, + "learning_rate": 1.1953136311611328e-05, + "loss": 3.3568, + "step": 2323968 + }, + { + "epoch": 0.01, + "learning_rate": 1.1944750364100807e-05, + "loss": 3.3484, + "step": 2324480 + }, + { + "epoch": 0.01, + "learning_rate": 1.1936380795394019e-05, + "loss": 3.3589, + "step": 2324992 + }, + { + "epoch": 0.01, + "learning_rate": 1.1927994847883499e-05, + "loss": 3.3654, + "step": 2325504 + }, + { + "epoch": 0.01, + "learning_rate": 1.1919608900372979e-05, + "loss": 3.3633, + "step": 2326016 + }, + { + "epoch": 0.01, + "learning_rate": 1.1911222952862457e-05, + "loss": 3.3601, + "step": 2326528 + }, + { + "epoch": 0.01, + "learning_rate": 1.19028697629594e-05, + "loss": 3.3651, + "step": 2327040 + }, + { + "epoch": 0.01, + "learning_rate": 1.189448381544888e-05, + "loss": 3.3679, + "step": 2327552 + }, + { + "epoch": 0.01, + "learning_rate": 1.1886097867938362e-05, + "loss": 3.3597, + "step": 2328064 + }, + { + "epoch": 0.01, + "learning_rate": 1.187771192042784e-05, + "loss": 3.3606, + "step": 2328576 + }, + { + "epoch": 0.01, + "learning_rate": 1.186932597291732e-05, + "loss": 3.3567, + "step": 2329088 + }, + { + "epoch": 0.01, + "learning_rate": 1.1860940025406802e-05, + "loss": 3.3589, + "step": 2329600 + }, + { + "epoch": 0.01, + "learning_rate": 1.185255407789628e-05, + "loss": 3.3632, + "step": 2330112 + }, + { + "epoch": 0.01, + "learning_rate": 1.184416813038576e-05, + "loss": 3.363, + "step": 2330624 + }, + { + "epoch": 0.01, + "learning_rate": 1.1835798561678973e-05, + "loss": 3.3677, + "step": 2331136 + }, + { + "epoch": 0.01, + "learning_rate": 1.1827428992972184e-05, + "loss": 3.3686, + "step": 2331648 + }, + { + "epoch": 0.01, + "learning_rate": 1.1819043045461663e-05, + "loss": 3.3613, + "step": 2332160 + }, + { + "epoch": 0.01, + "learning_rate": 1.1810657097951143e-05, + "loss": 3.3482, + "step": 2332672 + }, + { + "epoch": 0.01, + "learning_rate": 1.1802271150440623e-05, + "loss": 3.3578, + "step": 2333184 + }, + { + "epoch": 0.01, + "learning_rate": 1.1793885202930103e-05, + "loss": 3.3665, + "step": 2333696 + }, + { + "epoch": 0.01, + "learning_rate": 1.1785515634223314e-05, + "loss": 3.3588, + "step": 2334208 + }, + { + "epoch": 0.01, + "learning_rate": 1.1777129686712794e-05, + "loss": 3.3606, + "step": 2334720 + }, + { + "epoch": 0.01, + "learning_rate": 1.1768743739202274e-05, + "loss": 3.371, + "step": 2335232 + }, + { + "epoch": 0.02, + "learning_rate": 1.1760357791691754e-05, + "loss": 3.3631, + "step": 2335744 + }, + { + "epoch": 0.02, + "learning_rate": 1.1751971844181234e-05, + "loss": 3.3593, + "step": 2336256 + }, + { + "epoch": 0.02, + "learning_rate": 1.1743585896670714e-05, + "loss": 3.3592, + "step": 2336768 + }, + { + "epoch": 0.02, + "learning_rate": 1.1735199949160194e-05, + "loss": 3.3688, + "step": 2337280 + }, + { + "epoch": 0.02, + "learning_rate": 1.1726830380453405e-05, + "loss": 3.3614, + "step": 2337792 + }, + { + "epoch": 0.02, + "learning_rate": 1.1718444432942885e-05, + "loss": 3.3746, + "step": 2338304 + }, + { + "epoch": 0.02, + "learning_rate": 1.1710058485432365e-05, + "loss": 3.349, + "step": 2338816 + }, + { + "epoch": 0.02, + "learning_rate": 1.1701672537921845e-05, + "loss": 3.3678, + "step": 2339328 + }, + { + "epoch": 0.02, + "learning_rate": 1.1693286590411324e-05, + "loss": 3.3689, + "step": 2339840 + }, + { + "epoch": 0.02, + "learning_rate": 1.1684900642900804e-05, + "loss": 3.3639, + "step": 2340352 + }, + { + "epoch": 0.02, + "learning_rate": 1.1676514695390284e-05, + "loss": 3.3626, + "step": 2340864 + }, + { + "epoch": 0.02, + "learning_rate": 1.1668128747879764e-05, + "loss": 3.3625, + "step": 2341376 + }, + { + "epoch": 0.02, + "learning_rate": 1.1659759179172975e-05, + "loss": 3.3578, + "step": 2341888 + }, + { + "epoch": 0.02, + "learning_rate": 1.1651373231662457e-05, + "loss": 3.3598, + "step": 2342400 + }, + { + "epoch": 0.02, + "learning_rate": 1.1642987284151935e-05, + "loss": 3.355, + "step": 2342912 + }, + { + "epoch": 0.02, + "learning_rate": 1.1634601336641415e-05, + "loss": 3.356, + "step": 2343424 + }, + { + "epoch": 0.02, + "learning_rate": 1.1626231767934627e-05, + "loss": 3.3568, + "step": 2343936 + }, + { + "epoch": 0.02, + "learning_rate": 1.1617845820424107e-05, + "loss": 3.364, + "step": 2344448 + }, + { + "epoch": 0.02, + "learning_rate": 1.1609476251717318e-05, + "loss": 3.3605, + "step": 2344960 + }, + { + "epoch": 0.02, + "learning_rate": 1.1601090304206798e-05, + "loss": 3.3511, + "step": 2345472 + }, + { + "epoch": 0.02, + "learning_rate": 1.1592704356696278e-05, + "loss": 3.351, + "step": 2345984 + }, + { + "epoch": 0.02, + "learning_rate": 1.1584318409185758e-05, + "loss": 3.3652, + "step": 2346496 + }, + { + "epoch": 0.02, + "learning_rate": 1.1575932461675238e-05, + "loss": 3.3723, + "step": 2347008 + }, + { + "epoch": 0.02, + "learning_rate": 1.1567546514164718e-05, + "loss": 3.3628, + "step": 2347520 + }, + { + "epoch": 0.02, + "learning_rate": 1.1559160566654198e-05, + "loss": 3.3641, + "step": 2348032 + }, + { + "epoch": 0.02, + "learning_rate": 1.1550790997947409e-05, + "loss": 3.3718, + "step": 2348544 + }, + { + "epoch": 0.02, + "learning_rate": 1.1542405050436889e-05, + "loss": 3.3656, + "step": 2349056 + }, + { + "epoch": 0.02, + "learning_rate": 1.1534019102926369e-05, + "loss": 3.3555, + "step": 2349568 + }, + { + "epoch": 0.02, + "learning_rate": 1.1525633155415849e-05, + "loss": 3.3578, + "step": 2350080 + }, + { + "epoch": 0.02, + "learning_rate": 1.1517247207905329e-05, + "loss": 3.3631, + "step": 2350592 + }, + { + "epoch": 0.02, + "learning_rate": 1.1508861260394809e-05, + "loss": 3.3699, + "step": 2351104 + }, + { + "epoch": 0.02, + "learning_rate": 1.1500475312884288e-05, + "loss": 3.3419, + "step": 2351616 + }, + { + "epoch": 0.02, + "learning_rate": 1.14921057441775e-05, + "loss": 3.3624, + "step": 2352128 + }, + { + "epoch": 0.02, + "learning_rate": 1.148371979666698e-05, + "loss": 3.3563, + "step": 2352640 + }, + { + "epoch": 0.02, + "learning_rate": 1.147533384915646e-05, + "loss": 3.3591, + "step": 2353152 + }, + { + "epoch": 0.02, + "learning_rate": 1.1466947901645939e-05, + "loss": 3.3639, + "step": 2353664 + }, + { + "epoch": 0.02, + "learning_rate": 1.1458561954135419e-05, + "loss": 3.3633, + "step": 2354176 + }, + { + "epoch": 0.02, + "learning_rate": 1.1450176006624899e-05, + "loss": 3.349, + "step": 2354688 + }, + { + "epoch": 0.02, + "learning_rate": 1.1441790059114379e-05, + "loss": 3.356, + "step": 2355200 + }, + { + "epoch": 0.02, + "learning_rate": 1.1433404111603859e-05, + "loss": 3.3687, + "step": 2355712 + }, + { + "epoch": 0.02, + "learning_rate": 1.14250509217008e-05, + "loss": 3.3622, + "step": 2356224 + }, + { + "epoch": 0.02, + "learning_rate": 1.1416664974190282e-05, + "loss": 3.3722, + "step": 2356736 + }, + { + "epoch": 0.02, + "learning_rate": 1.1408279026679762e-05, + "loss": 3.3554, + "step": 2357248 + }, + { + "epoch": 0.02, + "learning_rate": 1.139989307916924e-05, + "loss": 3.3652, + "step": 2357760 + }, + { + "epoch": 0.02, + "learning_rate": 1.1391507131658722e-05, + "loss": 3.3676, + "step": 2358272 + }, + { + "epoch": 0.02, + "learning_rate": 1.1383121184148202e-05, + "loss": 3.3617, + "step": 2358784 + }, + { + "epoch": 0.02, + "learning_rate": 1.137473523663768e-05, + "loss": 3.3568, + "step": 2359296 + }, + { + "epoch": 0.02, + "learning_rate": 1.136634928912716e-05, + "loss": 3.3602, + "step": 2359808 + }, + { + "epoch": 0.02, + "learning_rate": 1.1357979720420373e-05, + "loss": 3.3732, + "step": 2360320 + }, + { + "epoch": 0.02, + "learning_rate": 1.1349593772909853e-05, + "loss": 3.3719, + "step": 2360832 + }, + { + "epoch": 0.02, + "learning_rate": 1.1341207825399331e-05, + "loss": 3.3634, + "step": 2361344 + }, + { + "epoch": 0.02, + "learning_rate": 1.1332821877888813e-05, + "loss": 3.3531, + "step": 2361856 + }, + { + "epoch": 0.02, + "learning_rate": 1.1324452309182023e-05, + "loss": 3.365, + "step": 2362368 + }, + { + "epoch": 0.02, + "learning_rate": 1.1316082740475236e-05, + "loss": 3.354, + "step": 2362880 + }, + { + "epoch": 0.02, + "learning_rate": 1.1307696792964714e-05, + "loss": 3.3491, + "step": 2363392 + }, + { + "epoch": 0.02, + "learning_rate": 1.1299310845454194e-05, + "loss": 3.3718, + "step": 2363904 + }, + { + "epoch": 0.02, + "learning_rate": 1.1290924897943674e-05, + "loss": 3.3565, + "step": 2364416 + }, + { + "epoch": 0.02, + "learning_rate": 1.1282538950433154e-05, + "loss": 3.3703, + "step": 2364928 + }, + { + "epoch": 0.02, + "learning_rate": 1.1274169381726365e-05, + "loss": 3.3542, + "step": 2365440 + }, + { + "epoch": 0.03, + "eval_loss": 3.864666700363159, + "eval_runtime": 303.7319, + "eval_samples_per_second": 1256.342, + "eval_steps_per_second": 39.262, + "step": 2365920 + }, + { + "epoch": 1.0, + "learning_rate": 1.1265783434215846e-05, + "loss": 3.3479, + "step": 2365952 + }, + { + "epoch": 1.0, + "learning_rate": 1.1257397486705326e-05, + "loss": 3.3544, + "step": 2366464 + }, + { + "epoch": 1.0, + "learning_rate": 1.1249011539194805e-05, + "loss": 3.3597, + "step": 2366976 + }, + { + "epoch": 1.0, + "learning_rate": 1.1240625591684285e-05, + "loss": 3.3699, + "step": 2367488 + }, + { + "epoch": 1.0, + "learning_rate": 1.1232239644173766e-05, + "loss": 3.3682, + "step": 2368000 + }, + { + "epoch": 1.0, + "learning_rate": 1.1223853696663245e-05, + "loss": 3.363, + "step": 2368512 + }, + { + "epoch": 1.0, + "learning_rate": 1.1215467749152725e-05, + "loss": 3.3532, + "step": 2369024 + }, + { + "epoch": 1.0, + "learning_rate": 1.1207098180445937e-05, + "loss": 3.351, + "step": 2369536 + }, + { + "epoch": 1.0, + "learning_rate": 1.1198712232935417e-05, + "loss": 3.3516, + "step": 2370048 + }, + { + "epoch": 1.0, + "learning_rate": 1.1190326285424895e-05, + "loss": 3.3641, + "step": 2370560 + }, + { + "epoch": 1.0, + "learning_rate": 1.1181940337914377e-05, + "loss": 3.354, + "step": 2371072 + }, + { + "epoch": 1.0, + "learning_rate": 1.1173570769207588e-05, + "loss": 3.3758, + "step": 2371584 + }, + { + "epoch": 1.0, + "learning_rate": 1.11652012005008e-05, + "loss": 3.3726, + "step": 2372096 + }, + { + "epoch": 1.0, + "learning_rate": 1.1156815252990278e-05, + "loss": 3.3483, + "step": 2372608 + }, + { + "epoch": 1.0, + "learning_rate": 1.1148429305479758e-05, + "loss": 3.3474, + "step": 2373120 + }, + { + "epoch": 1.0, + "learning_rate": 1.1140043357969238e-05, + "loss": 3.3456, + "step": 2373632 + }, + { + "epoch": 1.0, + "learning_rate": 1.1131657410458718e-05, + "loss": 3.3628, + "step": 2374144 + }, + { + "epoch": 1.0, + "learning_rate": 1.1123271462948198e-05, + "loss": 3.3539, + "step": 2374656 + }, + { + "epoch": 1.0, + "learning_rate": 1.1114885515437678e-05, + "loss": 3.3536, + "step": 2375168 + }, + { + "epoch": 1.0, + "learning_rate": 1.1106499567927158e-05, + "loss": 3.3474, + "step": 2375680 + }, + { + "epoch": 1.0, + "learning_rate": 1.1098129999220369e-05, + "loss": 3.3707, + "step": 2376192 + }, + { + "epoch": 1.0, + "learning_rate": 1.1089744051709849e-05, + "loss": 3.3542, + "step": 2376704 + }, + { + "epoch": 1.0, + "learning_rate": 1.108135810419933e-05, + "loss": 3.3632, + "step": 2377216 + }, + { + "epoch": 1.0, + "learning_rate": 1.1072972156688809e-05, + "loss": 3.3596, + "step": 2377728 + }, + { + "epoch": 1.0, + "learning_rate": 1.106460258798202e-05, + "loss": 3.3702, + "step": 2378240 + }, + { + "epoch": 1.0, + "learning_rate": 1.1056216640471501e-05, + "loss": 3.3506, + "step": 2378752 + }, + { + "epoch": 1.0, + "learning_rate": 1.1047830692960981e-05, + "loss": 3.3544, + "step": 2379264 + }, + { + "epoch": 1.0, + "learning_rate": 1.103944474545046e-05, + "loss": 3.3549, + "step": 2379776 + }, + { + "epoch": 1.0, + "learning_rate": 1.1031075176743672e-05, + "loss": 3.3582, + "step": 2380288 + }, + { + "epoch": 1.0, + "learning_rate": 1.1022689229233152e-05, + "loss": 3.3496, + "step": 2380800 + }, + { + "epoch": 1.01, + "learning_rate": 1.101430328172263e-05, + "loss": 3.3563, + "step": 2381312 + }, + { + "epoch": 1.01, + "learning_rate": 1.1005917334212112e-05, + "loss": 3.3584, + "step": 2381824 + }, + { + "epoch": 1.01, + "learning_rate": 1.0997547765505323e-05, + "loss": 3.3553, + "step": 2382336 + }, + { + "epoch": 1.01, + "learning_rate": 1.0989161817994803e-05, + "loss": 3.3627, + "step": 2382848 + }, + { + "epoch": 1.01, + "learning_rate": 1.0980775870484283e-05, + "loss": 3.3525, + "step": 2383360 + }, + { + "epoch": 1.01, + "learning_rate": 1.0972389922973762e-05, + "loss": 3.3571, + "step": 2383872 + }, + { + "epoch": 1.01, + "learning_rate": 1.0964020354266973e-05, + "loss": 3.3562, + "step": 2384384 + }, + { + "epoch": 1.01, + "learning_rate": 1.0955634406756455e-05, + "loss": 3.3463, + "step": 2384896 + }, + { + "epoch": 1.01, + "learning_rate": 1.0947248459245933e-05, + "loss": 3.3546, + "step": 2385408 + }, + { + "epoch": 1.01, + "learning_rate": 1.0938878890539146e-05, + "loss": 3.3439, + "step": 2385920 + }, + { + "epoch": 1.01, + "learning_rate": 1.0930492943028626e-05, + "loss": 3.3527, + "step": 2386432 + }, + { + "epoch": 1.01, + "learning_rate": 1.0922123374321836e-05, + "loss": 3.349, + "step": 2386944 + }, + { + "epoch": 1.01, + "learning_rate": 1.0913737426811316e-05, + "loss": 3.3637, + "step": 2387456 + }, + { + "epoch": 1.01, + "learning_rate": 1.0905351479300796e-05, + "loss": 3.3546, + "step": 2387968 + }, + { + "epoch": 1.01, + "learning_rate": 1.0896965531790276e-05, + "loss": 3.3583, + "step": 2388480 + }, + { + "epoch": 1.01, + "learning_rate": 1.0888579584279755e-05, + "loss": 3.3621, + "step": 2388992 + }, + { + "epoch": 1.01, + "learning_rate": 1.0880193636769236e-05, + "loss": 3.3524, + "step": 2389504 + }, + { + "epoch": 1.01, + "learning_rate": 1.0871807689258716e-05, + "loss": 3.3499, + "step": 2390016 + }, + { + "epoch": 1.01, + "learning_rate": 1.0863421741748194e-05, + "loss": 3.339, + "step": 2390528 + }, + { + "epoch": 1.01, + "learning_rate": 1.0855052173041407e-05, + "loss": 3.3546, + "step": 2391040 + }, + { + "epoch": 1.01, + "learning_rate": 1.0846666225530887e-05, + "loss": 3.3526, + "step": 2391552 + }, + { + "epoch": 1.01, + "learning_rate": 1.0838280278020367e-05, + "loss": 3.3534, + "step": 2392064 + }, + { + "epoch": 1.01, + "learning_rate": 1.0829894330509847e-05, + "loss": 3.3549, + "step": 2392576 + }, + { + "epoch": 1.01, + "learning_rate": 1.0821524761803058e-05, + "loss": 3.3405, + "step": 2393088 + }, + { + "epoch": 1.01, + "learning_rate": 1.0813138814292537e-05, + "loss": 3.3493, + "step": 2393600 + }, + { + "epoch": 1.01, + "learning_rate": 1.0804752866782019e-05, + "loss": 3.342, + "step": 2394112 + }, + { + "epoch": 1.01, + "learning_rate": 1.0796366919271497e-05, + "loss": 3.3693, + "step": 2394624 + }, + { + "epoch": 1.01, + "learning_rate": 1.0787997350564708e-05, + "loss": 3.3425, + "step": 2395136 + }, + { + "epoch": 1.01, + "learning_rate": 1.077961140305419e-05, + "loss": 3.3697, + "step": 2395648 + }, + { + "epoch": 1.01, + "learning_rate": 1.0771225455543668e-05, + "loss": 3.351, + "step": 2396160 + }, + { + "epoch": 1.01, + "learning_rate": 1.0762839508033148e-05, + "loss": 3.3398, + "step": 2396672 + }, + { + "epoch": 1.01, + "learning_rate": 1.075446993932636e-05, + "loss": 3.3561, + "step": 2397184 + }, + { + "epoch": 1.01, + "learning_rate": 1.074608399181584e-05, + "loss": 3.3511, + "step": 2397696 + }, + { + "epoch": 1.01, + "learning_rate": 1.0737698044305319e-05, + "loss": 3.3441, + "step": 2398208 + }, + { + "epoch": 1.01, + "learning_rate": 1.07293120967948e-05, + "loss": 3.339, + "step": 2398720 + }, + { + "epoch": 1.01, + "learning_rate": 1.0720942528088011e-05, + "loss": 3.3634, + "step": 2399232 + }, + { + "epoch": 1.01, + "learning_rate": 1.0712556580577491e-05, + "loss": 3.3485, + "step": 2399744 + }, + { + "epoch": 1.01, + "learning_rate": 1.0704170633066971e-05, + "loss": 3.3449, + "step": 2400256 + }, + { + "epoch": 1.01, + "learning_rate": 1.0695784685556451e-05, + "loss": 3.3408, + "step": 2400768 + }, + { + "epoch": 1.01, + "learning_rate": 1.0687415116849662e-05, + "loss": 3.3505, + "step": 2401280 + }, + { + "epoch": 1.01, + "learning_rate": 1.0679029169339142e-05, + "loss": 3.3558, + "step": 2401792 + }, + { + "epoch": 1.01, + "learning_rate": 1.0670659600632353e-05, + "loss": 3.3527, + "step": 2402304 + }, + { + "epoch": 1.01, + "learning_rate": 1.0662273653121833e-05, + "loss": 3.3475, + "step": 2402816 + }, + { + "epoch": 1.01, + "learning_rate": 1.0653887705611314e-05, + "loss": 3.3545, + "step": 2403328 + }, + { + "epoch": 1.01, + "learning_rate": 1.0645501758100792e-05, + "loss": 3.3585, + "step": 2403840 + }, + { + "epoch": 1.01, + "learning_rate": 1.0637115810590272e-05, + "loss": 3.35, + "step": 2404352 + }, + { + "epoch": 1.01, + "learning_rate": 1.0628729863079754e-05, + "loss": 3.3512, + "step": 2404864 + }, + { + "epoch": 1.01, + "learning_rate": 1.0620343915569232e-05, + "loss": 3.3529, + "step": 2405376 + }, + { + "epoch": 1.01, + "learning_rate": 1.0611957968058712e-05, + "loss": 3.3487, + "step": 2405888 + }, + { + "epoch": 1.01, + "learning_rate": 1.0603588399351925e-05, + "loss": 3.3536, + "step": 2406400 + }, + { + "epoch": 1.01, + "learning_rate": 1.0595202451841405e-05, + "loss": 3.3529, + "step": 2406912 + }, + { + "epoch": 1.01, + "learning_rate": 1.0586816504330883e-05, + "loss": 3.3567, + "step": 2407424 + }, + { + "epoch": 1.01, + "learning_rate": 1.0578430556820363e-05, + "loss": 3.3632, + "step": 2407936 + }, + { + "epoch": 1.01, + "learning_rate": 1.0570060988113575e-05, + "loss": 3.3501, + "step": 2408448 + }, + { + "epoch": 1.01, + "learning_rate": 1.0561675040603054e-05, + "loss": 3.3399, + "step": 2408960 + }, + { + "epoch": 1.01, + "learning_rate": 1.0553305471896266e-05, + "loss": 3.3458, + "step": 2409472 + }, + { + "epoch": 1.01, + "learning_rate": 1.0544919524385746e-05, + "loss": 3.359, + "step": 2409984 + }, + { + "epoch": 1.01, + "learning_rate": 1.0536533576875226e-05, + "loss": 3.3531, + "step": 2410496 + }, + { + "epoch": 1.01, + "learning_rate": 1.0528147629364706e-05, + "loss": 3.3484, + "step": 2411008 + }, + { + "epoch": 1.01, + "learning_rate": 1.0519761681854186e-05, + "loss": 3.3577, + "step": 2411520 + }, + { + "epoch": 1.02, + "learning_rate": 1.0511375734343666e-05, + "loss": 3.3567, + "step": 2412032 + }, + { + "epoch": 1.02, + "learning_rate": 1.0502989786833144e-05, + "loss": 3.3465, + "step": 2412544 + }, + { + "epoch": 1.02, + "learning_rate": 1.0494603839322626e-05, + "loss": 3.3473, + "step": 2413056 + }, + { + "epoch": 1.02, + "learning_rate": 1.0486234270615837e-05, + "loss": 3.3617, + "step": 2413568 + }, + { + "epoch": 1.02, + "learning_rate": 1.0477848323105317e-05, + "loss": 3.3474, + "step": 2414080 + }, + { + "epoch": 1.02, + "learning_rate": 1.0469462375594797e-05, + "loss": 3.3637, + "step": 2414592 + }, + { + "epoch": 1.02, + "learning_rate": 1.0461076428084277e-05, + "loss": 3.3446, + "step": 2415104 + }, + { + "epoch": 1.02, + "learning_rate": 1.0452706859377489e-05, + "loss": 3.3561, + "step": 2415616 + }, + { + "epoch": 1.02, + "learning_rate": 1.0444320911866969e-05, + "loss": 3.3612, + "step": 2416128 + }, + { + "epoch": 1.02, + "learning_rate": 1.0435934964356447e-05, + "loss": 3.3519, + "step": 2416640 + }, + { + "epoch": 1.02, + "learning_rate": 1.0427549016845927e-05, + "loss": 3.3571, + "step": 2417152 + }, + { + "epoch": 1.02, + "learning_rate": 1.041917944813914e-05, + "loss": 3.3523, + "step": 2417664 + }, + { + "epoch": 1.02, + "learning_rate": 1.0410793500628618e-05, + "loss": 3.3477, + "step": 2418176 + }, + { + "epoch": 1.02, + "learning_rate": 1.0402407553118098e-05, + "loss": 3.3474, + "step": 2418688 + }, + { + "epoch": 1.02, + "learning_rate": 1.039402160560758e-05, + "loss": 3.3492, + "step": 2419200 + }, + { + "epoch": 1.02, + "learning_rate": 1.038565203690079e-05, + "loss": 3.3449, + "step": 2419712 + }, + { + "epoch": 1.02, + "learning_rate": 1.037726608939027e-05, + "loss": 3.3505, + "step": 2420224 + }, + { + "epoch": 1.02, + "learning_rate": 1.036888014187975e-05, + "loss": 3.3576, + "step": 2420736 + }, + { + "epoch": 1.02, + "learning_rate": 1.0360510573172961e-05, + "loss": 3.35, + "step": 2421248 + }, + { + "epoch": 1.02, + "learning_rate": 1.0352124625662443e-05, + "loss": 3.3406, + "step": 2421760 + }, + { + "epoch": 1.02, + "learning_rate": 1.0343738678151921e-05, + "loss": 3.3434, + "step": 2422272 + }, + { + "epoch": 1.02, + "learning_rate": 1.0335352730641401e-05, + "loss": 3.353, + "step": 2422784 + }, + { + "epoch": 1.02, + "learning_rate": 1.0326966783130881e-05, + "loss": 3.3647, + "step": 2423296 + }, + { + "epoch": 1.02, + "learning_rate": 1.031858083562036e-05, + "loss": 3.3538, + "step": 2423808 + }, + { + "epoch": 1.02, + "learning_rate": 1.031019488810984e-05, + "loss": 3.3549, + "step": 2424320 + }, + { + "epoch": 1.02, + "learning_rate": 1.0301825319403052e-05, + "loss": 3.3575, + "step": 2424832 + }, + { + "epoch": 1.02, + "learning_rate": 1.0293439371892533e-05, + "loss": 3.3634, + "step": 2425344 + }, + { + "epoch": 1.02, + "learning_rate": 1.0285053424382011e-05, + "loss": 3.3436, + "step": 2425856 + }, + { + "epoch": 1.02, + "learning_rate": 1.0276667476871491e-05, + "loss": 3.3505, + "step": 2426368 + }, + { + "epoch": 1.02, + "learning_rate": 1.0268281529360971e-05, + "loss": 3.355, + "step": 2426880 + }, + { + "epoch": 1.02, + "learning_rate": 1.0259895581850451e-05, + "loss": 3.3568, + "step": 2427392 + }, + { + "epoch": 1.02, + "learning_rate": 1.0251509634339931e-05, + "loss": 3.3372, + "step": 2427904 + }, + { + "epoch": 1.02, + "learning_rate": 1.0243123686829411e-05, + "loss": 3.3484, + "step": 2428416 + }, + { + "epoch": 1.02, + "learning_rate": 1.0234754118122624e-05, + "loss": 3.347, + "step": 2428928 + }, + { + "epoch": 1.02, + "learning_rate": 1.0226368170612102e-05, + "loss": 3.3484, + "step": 2429440 + }, + { + "epoch": 1.02, + "learning_rate": 1.0217982223101582e-05, + "loss": 3.3491, + "step": 2429952 + }, + { + "epoch": 1.02, + "learning_rate": 1.0209596275591064e-05, + "loss": 3.3606, + "step": 2430464 + }, + { + "epoch": 1.02, + "learning_rate": 1.0201226706884273e-05, + "loss": 3.3405, + "step": 2430976 + }, + { + "epoch": 1.02, + "learning_rate": 1.0192840759373753e-05, + "loss": 3.3455, + "step": 2431488 + }, + { + "epoch": 1.02, + "learning_rate": 1.0184454811863234e-05, + "loss": 3.3517, + "step": 2432000 + }, + { + "epoch": 1.02, + "learning_rate": 1.0176085243156445e-05, + "loss": 3.358, + "step": 2432512 + }, + { + "epoch": 1.02, + "learning_rate": 1.0167699295645925e-05, + "loss": 3.3624, + "step": 2433024 + }, + { + "epoch": 1.02, + "learning_rate": 1.0159313348135405e-05, + "loss": 3.3458, + "step": 2433536 + }, + { + "epoch": 1.02, + "learning_rate": 1.0150927400624885e-05, + "loss": 3.353, + "step": 2434048 + }, + { + "epoch": 1.02, + "learning_rate": 1.0142541453114363e-05, + "loss": 3.3589, + "step": 2434560 + }, + { + "epoch": 1.02, + "learning_rate": 1.0134155505603845e-05, + "loss": 3.3528, + "step": 2435072 + }, + { + "epoch": 1.02, + "learning_rate": 1.0125769558093325e-05, + "loss": 3.3458, + "step": 2435584 + }, + { + "epoch": 1.02, + "learning_rate": 1.0117383610582805e-05, + "loss": 3.3523, + "step": 2436096 + }, + { + "epoch": 1.02, + "learning_rate": 1.0109014041876016e-05, + "loss": 3.3629, + "step": 2436608 + }, + { + "epoch": 1.02, + "learning_rate": 1.0100628094365496e-05, + "loss": 3.357, + "step": 2437120 + }, + { + "epoch": 1.02, + "learning_rate": 1.0092242146854975e-05, + "loss": 3.3587, + "step": 2437632 + }, + { + "epoch": 1.02, + "learning_rate": 1.0083856199344455e-05, + "loss": 3.3456, + "step": 2438144 + }, + { + "epoch": 1.02, + "learning_rate": 1.0075486630637666e-05, + "loss": 3.3523, + "step": 2438656 + }, + { + "epoch": 1.02, + "learning_rate": 1.0067117061930879e-05, + "loss": 3.3404, + "step": 2439168 + }, + { + "epoch": 1.02, + "learning_rate": 1.0058731114420359e-05, + "loss": 3.3426, + "step": 2439680 + }, + { + "epoch": 1.02, + "learning_rate": 1.0050345166909837e-05, + "loss": 3.3617, + "step": 2440192 + }, + { + "epoch": 1.02, + "learning_rate": 1.0041959219399317e-05, + "loss": 3.348, + "step": 2440704 + }, + { + "epoch": 1.02, + "learning_rate": 1.0033573271888799e-05, + "loss": 3.3587, + "step": 2441216 + }, + { + "epoch": 1.02, + "learning_rate": 1.002520370318201e-05, + "loss": 3.3483, + "step": 2441728 + }, + { + "epoch": 1.03, + "learning_rate": 1.001681775567149e-05, + "loss": 3.3415, + "step": 2442240 + }, + { + "epoch": 1.03, + "eval_loss": 3.865755319595337, + "eval_runtime": 302.0443, + "eval_samples_per_second": 1263.361, + "eval_steps_per_second": 39.481, + "step": 2442240 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.690742723362947e+18, + "trial_name": null, + "trial_params": null +}