diff --git "a/checkpoint-1984320/trainer_state.json" "b/checkpoint-1984320/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1984320/trainer_state.json" @@ -0,0 +1,23483 @@ +{ + "best_metric": 3.8636131286621094, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/superlative-quantifier/transformer/4/checkpoints/checkpoint-915840", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 1984320, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 11.0538, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8148, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1895, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9764, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8108, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7001, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6017, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5273, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4508, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4119, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3616, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3115, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2729, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2256, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1867, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1552, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1153, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0953, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.06, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0461, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0247, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 4.9905, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9635, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9441, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9328, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.9047, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8826, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8632, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8646, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8267, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8195, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.8144, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7965, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7827, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7806, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7606, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7547, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.7215, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 4.7195, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 4.6989, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 4.6939, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6886, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6818, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6606, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6649, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6488, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.65, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6486, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6183, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.6064, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.6179, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.6162, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5919, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5858, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5844, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.564, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5726, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5469, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5554, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5482, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5454, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.52, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5378, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.5088, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946349590497149e-05, + "loss": 4.5185, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945510995746097e-05, + "loss": 4.5176, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.5094, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4903, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4826, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4797, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 4.4915, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404794272397856e-05, + "loss": 4.4851, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4665, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4791, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4807, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.463, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4603, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4521, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.452, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4337, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4356, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4317, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4447, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.4321, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.4108, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.4172, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.414, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.4189, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926231505873767e-05, + "loss": 4.413, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925394549003088e-05, + "loss": 4.4, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924555954252036e-05, + "loss": 4.4002, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923717359500984e-05, + "loss": 4.3916, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.3813, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3762, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3801, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920364618377149e-05, + "loss": 4.3892, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919526023626097e-05, + "loss": 4.3795, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918687428875045e-05, + "loss": 4.3645, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917848834123993e-05, + "loss": 4.365, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.3709, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916173282502262e-05, + "loss": 4.3711, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.91533468775121e-05, + "loss": 4.3621, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914496093000158e-05, + "loss": 4.3582, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913657498249106e-05, + "loss": 4.348, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912818903498054e-05, + "loss": 4.3565, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911980308747002e-05, + "loss": 4.3344, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911143351876323e-05, + "loss": 4.3399, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.3439, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3347, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.3317, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3328, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3244, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3285, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052748264993326e-05, + "loss": 4.3245, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.90443623174828e-05, + "loss": 4.317, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903597636997228e-05, + "loss": 4.3265, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.3236, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019237232558704e-05, + "loss": 4.3166, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010851285048184e-05, + "loss": 4.3207, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900246533753767e-05, + "loss": 4.3079, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899407939002715e-05, + "loss": 4.3075, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985693442516624e-05, + "loss": 4.2983, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977307495006104e-05, + "loss": 4.2993, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968921547495584e-05, + "loss": 4.2978, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2977, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.294, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.2958, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2942, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.2813, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2887, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891023629372567e-05, + "loss": 4.2891, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.2713, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2616, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888509482999785e-05, + "loss": 4.2706, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887670888248733e-05, + "loss": 4.2837, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886832293497681e-05, + "loss": 4.284, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.268, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2674, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.2733, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.2722, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.2656, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.2565, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.8809654060010626e-05, + "loss": 4.2592, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.8801268112500106e-05, + "loss": 4.2545, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.8792882164989586e-05, + "loss": 4.2508, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2613, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.2442, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876772432245803e-05, + "loss": 4.2561, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875933837494751e-05, + "loss": 4.2517, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875096880624072e-05, + "loss": 4.2348, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.220964431762695, + "eval_runtime": 303.1793, + "eval_samples_per_second": 1258.632, + "eval_steps_per_second": 39.333, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.87425828587302e-05, + "loss": 4.2391, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873419691121968e-05, + "loss": 4.2309, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.242, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2332, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870905544749185e-05, + "loss": 4.2376, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870066949998133e-05, + "loss": 4.2232, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869228355247081e-05, + "loss": 4.2183, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.2064, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675528036253507e-05, + "loss": 4.2353, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667142088742986e-05, + "loss": 4.2232, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865875614123246e-05, + "loss": 4.2166, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865037019372194e-05, + "loss": 4.224, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642000625015155e-05, + "loss": 4.2093, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633614677504635e-05, + "loss": 4.2059, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862522872999411e-05, + "loss": 4.2034, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861684278248359e-05, + "loss": 4.2011, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860845683497307e-05, + "loss": 4.2007, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860007088746255e-05, + "loss": 4.196, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859168493995203e-05, + "loss": 4.2071, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858329899244151e-05, + "loss": 4.2126, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574913044930995e-05, + "loss": 4.196, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.1889, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.1905, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549771581203164e-05, + "loss": 4.1945, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541385633692644e-05, + "loss": 4.187, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532999686182124e-05, + "loss": 4.1768, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524613738671604e-05, + "loss": 4.1796, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.1905, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.1658, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.1725, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849108632743325e-05, + "loss": 4.1775, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.1775, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847431443241221e-05, + "loss": 4.1813, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846594486370543e-05, + "loss": 4.1732, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.1711, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844917296868439e-05, + "loss": 4.1777, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844078702117387e-05, + "loss": 4.1536, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843241745246708e-05, + "loss": 4.1631, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.1503, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841564555744604e-05, + "loss": 4.1544, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840725960993552e-05, + "loss": 4.1552, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839889004122873e-05, + "loss": 4.1588, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839050409371821e-05, + "loss": 4.1562, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382118146207687e-05, + "loss": 4.1495, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373732198697167e-05, + "loss": 4.15, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.8365346251186646e-05, + "loss": 4.154, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835697668247986e-05, + "loss": 4.1548, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834859073496934e-05, + "loss": 4.1401, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834020478745882e-05, + "loss": 4.1343, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331818839948295e-05, + "loss": 4.1474, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832344927124151e-05, + "loss": 4.1547, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831506332373099e-05, + "loss": 4.137, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830667737622047e-05, + "loss": 4.137, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298291428709944e-05, + "loss": 4.1356, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289905481199424e-05, + "loss": 4.128, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828153591249264e-05, + "loss": 4.1336, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827314996498212e-05, + "loss": 4.1216, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.82647640174716e-05, + "loss": 4.1335, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825637806996108e-05, + "loss": 4.1329, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248008501254296e-05, + "loss": 4.1282, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823962255374377e-05, + "loss": 4.114, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823123660623325e-05, + "loss": 4.1348, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822285065872273e-05, + "loss": 4.1094, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214481090015945e-05, + "loss": 4.1242, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820609514250542e-05, + "loss": 4.1273, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.81977091949949e-05, + "loss": 4.1231, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818932324748438e-05, + "loss": 4.1085, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180953678777594e-05, + "loss": 4.1076, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172567731267074e-05, + "loss": 4.1061, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164181783756554e-05, + "loss": 4.1156, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155795836246034e-05, + "loss": 4.1186, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814742626753924e-05, + "loss": 4.1109, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813904032002872e-05, + "loss": 4.1197, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.81306543725182e-05, + "loss": 4.1193, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812226842500768e-05, + "loss": 4.1167, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811389885630089e-05, + "loss": 4.1025, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810551290879037e-05, + "loss": 4.1117, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809712696127985e-05, + "loss": 4.1095, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808874101376933e-05, + "loss": 4.092, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808037144506255e-05, + "loss": 4.1087, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807198549755203e-05, + "loss": 4.0956, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806359955004151e-05, + "loss": 4.1176, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805521360253099e-05, + "loss": 4.1048, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.8046844033824197e-05, + "loss": 4.0826, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.8038458086313677e-05, + "loss": 4.1004, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.8030072138803156e-05, + "loss": 4.0902, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.8021686191292636e-05, + "loss": 4.1041, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.8013316622585846e-05, + "loss": 4.0961, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004930675075325e-05, + "loss": 4.0906, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996544727564805e-05, + "loss": 4.0927, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988158780054285e-05, + "loss": 4.0844, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979789211347494e-05, + "loss": 4.0779, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797140326383698e-05, + "loss": 4.0773, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796301731632646e-05, + "loss": 4.0837, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795464774761967e-05, + "loss": 4.0933, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794626180010915e-05, + "loss": 4.0837, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793787585259863e-05, + "loss": 4.0743, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792948990508811e-05, + "loss": 4.0754, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792110395757759e-05, + "loss": 4.0828, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791271801006707e-05, + "loss": 4.0874, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790433206255655e-05, + "loss": 4.0797, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789594611504603e-05, + "loss": 4.0764, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788757654633924e-05, + "loss": 4.0727, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787919059882872e-05, + "loss": 4.0804, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.78708046513182e-05, + "loss": 4.059, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786241870380768e-05, + "loss": 4.0722, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854049135100895e-05, + "loss": 4.0753, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845663187590375e-05, + "loss": 4.0669, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837277240079855e-05, + "loss": 4.0632, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828891292569335e-05, + "loss": 4.0659, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820505345058815e-05, + "loss": 4.0647, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812119397548295e-05, + "loss": 4.0641, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803749828841504e-05, + "loss": 4.0659, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795363881330984e-05, + "loss": 4.0625, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786977933820464e-05, + "loss": 4.0735, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.7778591986309944e-05, + "loss": 4.0714, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777022241760315e-05, + "loss": 4.0662, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776183647009263e-05, + "loss": 4.0666, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775345052258212e-05, + "loss": 4.0617, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.77450645750716e-05, + "loss": 4.0594, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773667862756108e-05, + "loss": 4.0525, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772829268005055e-05, + "loss": 4.0525, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771990673254003e-05, + "loss": 4.0575, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771152078502951e-05, + "loss": 4.0588, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770315121632272e-05, + "loss": 4.0555, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.76947652688122e-05, + "loss": 4.0561, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768637932130168e-05, + "loss": 4.0527, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.76780097525949e-05, + "loss": 4.0524, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766962380508437e-05, + "loss": 4.0509, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766123785757386e-05, + "loss": 4.0602, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765285191006334e-05, + "loss": 4.0422, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764448234135655e-05, + "loss": 4.0328, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.7636096393846026e-05, + "loss": 4.0396, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.7627710446335506e-05, + "loss": 4.0573, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.7619324498824986e-05, + "loss": 4.0544, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7610954930118195e-05, + "loss": 4.0492, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602568982607675e-05, + "loss": 4.0428, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594183035097155e-05, + "loss": 4.053, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.7585797087586635e-05, + "loss": 4.0502, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577427518879844e-05, + "loss": 4.0471, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569041571369324e-05, + "loss": 4.0394, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756065562385881e-05, + "loss": 4.0412, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755226967634829e-05, + "loss": 4.043, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543916486445236e-05, + "loss": 4.0315, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535530538934716e-05, + "loss": 4.0513, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527144591424196e-05, + "loss": 4.0327, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751875864391367e-05, + "loss": 4.0425, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751037269640315e-05, + "loss": 4.0412, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750198674889263e-05, + "loss": 4.0286, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.048327445983887, + "eval_runtime": 302.7368, + "eval_samples_per_second": 1260.471, + "eval_steps_per_second": 39.391, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749360080138211e-05, + "loss": 4.0323, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748521485387159e-05, + "loss": 4.0275, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747682890636107e-05, + "loss": 4.0353, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746844295885055e-05, + "loss": 4.0317, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.746005701134003e-05, + "loss": 4.0392, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745167106382951e-05, + "loss": 4.0241, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744328511631899e-05, + "loss": 4.0214, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434899168808475e-05, + "loss": 4.0089, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426513221297955e-05, + "loss": 4.0413, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7418127273787435e-05, + "loss": 4.0279, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740974132627691e-05, + "loss": 4.0169, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401371757570124e-05, + "loss": 4.0348, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739301856766706e-05, + "loss": 4.0142, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738463262015654e-05, + "loss": 4.0194, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737624667264602e-05, + "loss": 4.009, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.73678607251355e-05, + "loss": 4.0105, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735947477762498e-05, + "loss": 4.0167, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735108883011446e-05, + "loss": 4.0064, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734270288260394e-05, + "loss": 4.0225, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733431693509343e-05, + "loss": 4.0253, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732593098758291e-05, + "loss": 4.0143, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731754504007238e-05, + "loss": 4.0101, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730915909256186e-05, + "loss": 4.0095, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730078952385508e-05, + "loss": 4.0139, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729240357634456e-05, + "loss": 4.0046, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728401762883403e-05, + "loss": 4.0047, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727563168132351e-05, + "loss": 3.9978, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726726211261673e-05, + "loss": 4.0162, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725887616510621e-05, + "loss": 3.988, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725049021759568e-05, + "loss": 4.0005, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724210427008517e-05, + "loss": 4.0056, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723373470137838e-05, + "loss": 4.0066, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225348753867856e-05, + "loss": 4.0055, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216962806357336e-05, + "loss": 4.0036, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208576858846816e-05, + "loss": 3.9995, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200190911336296e-05, + "loss": 4.01, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191804963825775e-05, + "loss": 3.9899, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183419016315255e-05, + "loss": 3.9959, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175033068804735e-05, + "loss": 3.981, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166663500097945e-05, + "loss": 3.9908, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158277552587424e-05, + "loss": 3.9856, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149891605076904e-05, + "loss": 3.999, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141505657566384e-05, + "loss": 3.9916, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.71331360888596e-05, + "loss": 3.9882, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712475014134908e-05, + "loss": 3.9918, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711636419383856e-05, + "loss": 3.9931, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710797824632804e-05, + "loss": 3.9946, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709960867762125e-05, + "loss": 3.9798, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709122273011073e-05, + "loss": 3.9734, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708283678260021e-05, + "loss": 3.9945, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707445083508969e-05, + "loss": 3.9948, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.70660812663829e-05, + "loss": 3.9833, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705769531887238e-05, + "loss": 3.9834, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704930937136186e-05, + "loss": 3.9764, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704092342385134e-05, + "loss": 3.9761, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032553855144554e-05, + "loss": 3.9821, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024167907634034e-05, + "loss": 3.9706, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015781960123514e-05, + "loss": 3.9817, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007396012612994e-05, + "loss": 3.9812, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.69990264439062e-05, + "loss": 3.9749, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699064049639568e-05, + "loss": 3.9665, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698225454888516e-05, + "loss": 3.9873, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697386860137464e-05, + "loss": 3.9627, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696549903266785e-05, + "loss": 3.976, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695711308515733e-05, + "loss": 3.9765, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694872713764681e-05, + "loss": 3.9786, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694034119013629e-05, + "loss": 3.9612, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693198800023324e-05, + "loss": 3.9644, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692360205272272e-05, + "loss": 3.9558, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.69152161052122e-05, + "loss": 3.9725, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906830157701677e-05, + "loss": 3.9762, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898444210191157e-05, + "loss": 3.9704, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890058262680636e-05, + "loss": 3.9741, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881672315170116e-05, + "loss": 3.9755, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873286367659596e-05, + "loss": 3.9791, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864933177756535e-05, + "loss": 3.9599, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856547230246015e-05, + "loss": 3.9712, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848161282735495e-05, + "loss": 3.9747, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683977533522498e-05, + "loss": 3.9537, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683138938771446e-05, + "loss": 3.9688, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682300344020394e-05, + "loss": 3.9583, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681461749269342e-05, + "loss": 3.9806, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.68062315451829e-05, + "loss": 3.9672, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679786197647611e-05, + "loss": 3.9479, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678947602896559e-05, + "loss": 3.9605, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678109008145507e-05, + "loss": 3.9591, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677270413394455e-05, + "loss": 3.9695, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676433456523776e-05, + "loss": 3.9617, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675594861772724e-05, + "loss": 3.9562, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674756267021672e-05, + "loss": 3.9575, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.67391767227062e-05, + "loss": 3.9529, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730807153999415e-05, + "loss": 3.948, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722421206488895e-05, + "loss": 3.9418, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6714035258978375e-05, + "loss": 3.9548, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705649311467855e-05, + "loss": 3.9641, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697263363957335e-05, + "loss": 3.955, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688877416446815e-05, + "loss": 3.9441, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668049146893629e-05, + "loss": 3.947, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667210552142577e-05, + "loss": 3.9515, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663735952718984e-05, + "loss": 3.9628, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665535000520846e-05, + "loss": 3.9521, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664696405769794e-05, + "loss": 3.9509, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663857811018742e-05, + "loss": 3.9432, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663020854148063e-05, + "loss": 3.9565, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662182259397011e-05, + "loss": 3.9309, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661343664645959e-05, + "loss": 3.9487, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660505069894907e-05, + "loss": 3.9466, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659668113024229e-05, + "loss": 3.9462, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658829518273176e-05, + "loss": 3.938, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657990923522124e-05, + "loss": 3.9436, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657153966651446e-05, + "loss": 3.9419, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656315371900393e-05, + "loss": 3.9424, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.6554784150297146e-05, + "loss": 3.9449, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546398202786626e-05, + "loss": 3.9431, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6538012255276106e-05, + "loss": 3.9487, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529626307765586e-05, + "loss": 3.9494, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.65212567390588e-05, + "loss": 3.9481, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651287079154828e-05, + "loss": 3.9475, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650448484403776e-05, + "loss": 3.9415, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6496098896527235e-05, + "loss": 3.9366, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487712949016715e-05, + "loss": 3.9366, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479327001506195e-05, + "loss": 3.9369, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470941053995675e-05, + "loss": 3.9325, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462555106485155e-05, + "loss": 3.9438, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454185537778364e-05, + "loss": 3.9354, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644581596907158e-05, + "loss": 3.9422, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643743002156106e-05, + "loss": 3.9364, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642904407405054e-05, + "loss": 3.9341, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642065812654002e-05, + "loss": 3.9321, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.64122721790295e-05, + "loss": 3.9485, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640390261032271e-05, + "loss": 3.9269, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639551666281219e-05, + "loss": 3.9242, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638713071530167e-05, + "loss": 3.9208, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637874476779115e-05, + "loss": 3.9386, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637035882028063e-05, + "loss": 3.9418, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636197287277011e-05, + "loss": 3.9382, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635358692525959e-05, + "loss": 3.9289, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634520097774907e-05, + "loss": 3.9428, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633683140904228e-05, + "loss": 3.933, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632844546153176e-05, + "loss": 3.9377, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320059514021244e-05, + "loss": 3.9269, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311673566510724e-05, + "loss": 3.931, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303303997803934e-05, + "loss": 3.9314, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629493442909714e-05, + "loss": 3.9189, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628654848158662e-05, + "loss": 3.94, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.62781625340761e-05, + "loss": 3.9298, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626977658656558e-05, + "loss": 3.9294, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626139063905506e-05, + "loss": 3.9314, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625302107034827e-05, + "loss": 3.9187, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.972667694091797, + "eval_runtime": 303.7984, + "eval_samples_per_second": 1256.066, + "eval_steps_per_second": 39.253, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624463512283775e-05, + "loss": 3.9271, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623624917532723e-05, + "loss": 3.9212, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622786322781671e-05, + "loss": 3.9253, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621949365910993e-05, + "loss": 3.9225, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621110771159941e-05, + "loss": 3.9371, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620272176408889e-05, + "loss": 3.9171, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619433581657837e-05, + "loss": 3.9129, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618594986906785e-05, + "loss": 3.9052, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6177580300361056e-05, + "loss": 3.9321, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.6169194352850536e-05, + "loss": 3.9273, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160808405340016e-05, + "loss": 3.9075, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.6152422457829496e-05, + "loss": 3.93, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6144069267926434e-05, + "loss": 3.9131, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613568332041592e-05, + "loss": 3.9148, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.61272973729054e-05, + "loss": 3.91, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611891142539488e-05, + "loss": 3.9071, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611052547788436e-05, + "loss": 3.9117, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610213953037384e-05, + "loss": 3.9066, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609375358286332e-05, + "loss": 3.9205, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.60853676353528e-05, + "loss": 3.9203, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607698168784228e-05, + "loss": 3.9164, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606861211913549e-05, + "loss": 3.9109, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606022617162497e-05, + "loss": 3.9043, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605184022411445e-05, + "loss": 3.9166, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604345427660393e-05, + "loss": 3.9034, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603508470789714e-05, + "loss": 3.9063, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602669876038662e-05, + "loss": 3.9002, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.60183128128761e-05, + "loss": 3.9157, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009926865365585e-05, + "loss": 3.8921, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.6001540917855065e-05, + "loss": 3.9007, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5993171349148274e-05, + "loss": 3.9105, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.5984785401637754e-05, + "loss": 3.906, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.5976399454127234e-05, + "loss": 3.9096, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5968013506616714e-05, + "loss": 3.9077, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959643937909923e-05, + "loss": 3.9033, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.5951257990399403e-05, + "loss": 3.9118, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594287204288888e-05, + "loss": 3.8983, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593448609537836e-05, + "loss": 3.8927, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5926100147867836e-05, + "loss": 3.8885, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591771420035732e-05, + "loss": 3.8948, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590934463165054e-05, + "loss": 3.8913, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590095868414001e-05, + "loss": 3.9058, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589257273662949e-05, + "loss": 3.8965, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588418678911897e-05, + "loss": 3.8939, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587580084160845e-05, + "loss": 3.9022, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586741489409793e-05, + "loss": 3.8935, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585904532539114e-05, + "loss": 3.9054, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585065937788062e-05, + "loss": 3.8875, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.58422734303701e-05, + "loss": 3.8733, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583388748285958e-05, + "loss": 3.9066, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582550153534906e-05, + "loss": 3.9004, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581713196664228e-05, + "loss": 3.8975, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580874601913176e-05, + "loss": 3.8897, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580036007162124e-05, + "loss": 3.8862, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579197412411072e-05, + "loss": 3.8839, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.57835881766002e-05, + "loss": 3.8918, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.5775218607893406e-05, + "loss": 3.8816, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.5766832660382886e-05, + "loss": 3.8887, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758446712872366e-05, + "loss": 3.8962, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5750060765361846e-05, + "loss": 3.8848, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741674817851326e-05, + "loss": 3.876, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733305249144535e-05, + "loss": 3.8998, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724919301634015e-05, + "loss": 3.8743, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716533354123495e-05, + "loss": 3.8809, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5708147406612975e-05, + "loss": 3.8912, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569976145910246e-05, + "loss": 3.893, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569139189039567e-05, + "loss": 3.8727, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568300594288515e-05, + "loss": 3.8783, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567461999537463e-05, + "loss": 3.8638, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566623404786411e-05, + "loss": 3.889, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565784810035359e-05, + "loss": 3.8856, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.56494785316468e-05, + "loss": 3.8837, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564109258413628e-05, + "loss": 3.8846, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563270663662576e-05, + "loss": 3.8899, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562432068911524e-05, + "loss": 3.8948, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561593474160472e-05, + "loss": 3.8733, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560756517289793e-05, + "loss": 3.8847, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.5599179225387415e-05, + "loss": 3.8883, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590793277876895e-05, + "loss": 3.8669, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.5582407330366375e-05, + "loss": 3.8854, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557402138285585e-05, + "loss": 3.8752, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556563543534533e-05, + "loss": 3.8907, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557265866638544e-05, + "loss": 3.8837, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.5548879919128024e-05, + "loss": 3.8649, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.55404939716175e-05, + "loss": 3.8748, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553210802410698e-05, + "loss": 3.8724, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552372207659646e-05, + "loss": 3.887, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.5515352507889666e-05, + "loss": 3.8748, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550696656037915e-05, + "loss": 3.871, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549858061286863e-05, + "loss": 3.8747, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549019466535811e-05, + "loss": 3.8734, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548182509665132e-05, + "loss": 3.8671, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.54734391491408e-05, + "loss": 3.8571, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546505320163028e-05, + "loss": 3.8726, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545666725411976e-05, + "loss": 3.8818, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544829768541297e-05, + "loss": 3.8794, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543991173790245e-05, + "loss": 3.8554, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543152579039193e-05, + "loss": 3.8678, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542313984288141e-05, + "loss": 3.8683, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541475389537089e-05, + "loss": 3.8795, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406384326664106e-05, + "loss": 3.8696, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5397998379153586e-05, + "loss": 3.8714, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389612431643066e-05, + "loss": 3.8628, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5381226484132546e-05, + "loss": 3.8764, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372840536622026e-05, + "loss": 3.8505, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364470967915235e-05, + "loss": 3.8697, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5356085020404715e-05, + "loss": 3.8645, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347699072894195e-05, + "loss": 3.8665, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339313125383675e-05, + "loss": 3.8583, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330927177873155e-05, + "loss": 3.8688, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322557609166364e-05, + "loss": 3.8579, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314171661655844e-05, + "loss": 3.8644, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305785714145324e-05, + "loss": 3.8658, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297399766634804e-05, + "loss": 3.8653, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5289013819124284e-05, + "loss": 3.8726, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.52806442504175e-05, + "loss": 3.8723, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527225830290698e-05, + "loss": 3.8681, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526387235539646e-05, + "loss": 3.8717, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525548640788594e-05, + "loss": 3.8669, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524711683917915e-05, + "loss": 3.8585, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523873089166863e-05, + "loss": 3.8572, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523034494415811e-05, + "loss": 3.8598, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522195899664759e-05, + "loss": 3.8601, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.52135894279408e-05, + "loss": 3.8672, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520520348043028e-05, + "loss": 3.8595, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519681753291976e-05, + "loss": 3.8651, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518843158540924e-05, + "loss": 3.8585, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.5180062016702454e-05, + "loss": 3.8582, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171676069191934e-05, + "loss": 3.8569, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.5163290121681414e-05, + "loss": 3.8708, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.5154904174170894e-05, + "loss": 3.8556, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.5146518226660373e-05, + "loss": 3.8486, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513814865795358e-05, + "loss": 3.8445, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512976271044306e-05, + "loss": 3.8613, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512137676293254e-05, + "loss": 3.8642, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511299081542202e-05, + "loss": 3.8645, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510462124671523e-05, + "loss": 3.8566, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509623529920471e-05, + "loss": 3.8676, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508784935169419e-05, + "loss": 3.8584, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507946340418368e-05, + "loss": 3.8615, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507109383547689e-05, + "loss": 3.8543, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506270788796637e-05, + "loss": 3.857, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505432194045585e-05, + "loss": 3.8588, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504593599294533e-05, + "loss": 3.8448, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.5037566424238536e-05, + "loss": 3.8662, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.5029180476728016e-05, + "loss": 3.86, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.5020794529217496e-05, + "loss": 3.8534, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012408581706976e-05, + "loss": 3.8559, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.5004039013000185e-05, + "loss": 3.8523, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9304020404815674, + "eval_runtime": 303.1632, + "eval_samples_per_second": 1258.698, + "eval_steps_per_second": 39.335, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995653065489665e-05, + "loss": 3.8496, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987267117979145e-05, + "loss": 3.8491, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497888117046863e-05, + "loss": 3.8556, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970495222958105e-05, + "loss": 3.8514, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4962109275447585e-05, + "loss": 3.864, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953723327937065e-05, + "loss": 3.8489, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945337380426545e-05, + "loss": 3.839, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936951432916025e-05, + "loss": 3.8384, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928581864209234e-05, + "loss": 3.8567, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920195916698714e-05, + "loss": 3.8549, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911809969188194e-05, + "loss": 3.8388, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903424021677674e-05, + "loss": 3.8562, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489505445297088e-05, + "loss": 3.8443, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488666850546037e-05, + "loss": 3.846, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487828255794985e-05, + "loss": 3.8385, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486989661043933e-05, + "loss": 3.8385, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486152704173254e-05, + "loss": 3.838, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485314109422202e-05, + "loss": 3.8359, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.48447551467115e-05, + "loss": 3.8524, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483636919920098e-05, + "loss": 3.8507, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482798325169046e-05, + "loss": 3.8471, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481961368298367e-05, + "loss": 3.8417, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481122773547315e-05, + "loss": 3.837, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480284178796263e-05, + "loss": 3.845, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479445584045211e-05, + "loss": 3.837, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478608627174532e-05, + "loss": 3.8382, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.47777003242348e-05, + "loss": 3.8301, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476931437672428e-05, + "loss": 3.8431, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476092842921376e-05, + "loss": 3.8294, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475255886050697e-05, + "loss": 3.8261, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474417291299645e-05, + "loss": 3.8439, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473578696548593e-05, + "loss": 3.8356, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472740101797541e-05, + "loss": 3.8459, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471903144926862e-05, + "loss": 3.8439, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.47106455017581e-05, + "loss": 3.8326, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470225955424758e-05, + "loss": 3.8452, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469387360673706e-05, + "loss": 3.8358, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468550403803028e-05, + "loss": 3.8243, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467711809051976e-05, + "loss": 3.8207, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466873214300924e-05, + "loss": 3.8282, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466034619549872e-05, + "loss": 3.8271, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.46519602479882e-05, + "loss": 3.8401, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.4643590679281406e-05, + "loss": 3.8298, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4635204731770886e-05, + "loss": 3.828, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626818784260366e-05, + "loss": 3.8372, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618432836749846e-05, + "loss": 3.8305, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4610063268043055e-05, + "loss": 3.8363, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601677320532535e-05, + "loss": 3.8224, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593291373022015e-05, + "loss": 3.8061, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584905425511495e-05, + "loss": 3.8424, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576519478000975e-05, + "loss": 3.8391, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456814990929419e-05, + "loss": 3.8322, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455976396178367e-05, + "loss": 3.8246, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455137801427315e-05, + "loss": 3.8217, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454299206676263e-05, + "loss": 3.8177, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453462249805584e-05, + "loss": 3.8263, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452623655054532e-05, + "loss": 3.82, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.45178506030348e-05, + "loss": 3.8235, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450946465552428e-05, + "loss": 3.8318, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450109508681749e-05, + "loss": 3.8232, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449270913930697e-05, + "loss": 3.812, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448432319179645e-05, + "loss": 3.8363, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447593724428593e-05, + "loss": 3.811, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446755129677541e-05, + "loss": 3.8131, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4459181728068624e-05, + "loss": 3.8327, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450795780558104e-05, + "loss": 3.8331, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442409833047584e-05, + "loss": 3.8057, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443402388553706e-05, + "loss": 3.817, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442563793802654e-05, + "loss": 3.8019, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441726836931975e-05, + "loss": 3.8244, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440888242180923e-05, + "loss": 3.828, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.4400496474298706e-05, + "loss": 3.8177, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.4392110526788186e-05, + "loss": 3.8226, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.4383724579277666e-05, + "loss": 3.8245, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437535501057088e-05, + "loss": 3.8354, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436696906306036e-05, + "loss": 3.8103, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435858311554984e-05, + "loss": 3.8247, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435019716803932e-05, + "loss": 3.8281, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434182759933253e-05, + "loss": 3.805, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433344165182201e-05, + "loss": 3.8272, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432505570431149e-05, + "loss": 3.817, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431666975680097e-05, + "loss": 3.8286, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430830018809418e-05, + "loss": 3.8236, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429991424058366e-05, + "loss": 3.8069, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429152829307314e-05, + "loss": 3.8088, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428314234556262e-05, + "loss": 3.8114, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274772776855836e-05, + "loss": 3.8294, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266386829345316e-05, + "loss": 3.8137, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4258000881834796e-05, + "loss": 3.8098, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249614934324276e-05, + "loss": 3.8132, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241245365617485e-05, + "loss": 3.8162, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232859418106965e-05, + "loss": 3.8065, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224473470596445e-05, + "loss": 3.7966, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216087523085925e-05, + "loss": 3.8131, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207717954379134e-05, + "loss": 3.8208, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199332006868614e-05, + "loss": 3.8196, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190946059358094e-05, + "loss": 3.7979, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182560111847573e-05, + "loss": 3.8093, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417419054314079e-05, + "loss": 3.811, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416580459563027e-05, + "loss": 3.8176, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415741864811975e-05, + "loss": 3.8158, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414903270060923e-05, + "loss": 3.811, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414066313190244e-05, + "loss": 3.8052, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413227718439192e-05, + "loss": 3.8171, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.41238912368814e-05, + "loss": 3.7926, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411550528937088e-05, + "loss": 3.8115, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410711934186036e-05, + "loss": 3.8035, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409874977315357e-05, + "loss": 3.813, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409036382564305e-05, + "loss": 3.7956, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408197787813253e-05, + "loss": 3.8116, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407359193062201e-05, + "loss": 3.8026, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406522236191522e-05, + "loss": 3.8071, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.40568364144047e-05, + "loss": 3.807, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404845046689418e-05, + "loss": 3.8068, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404006451938366e-05, + "loss": 3.8127, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403169495067687e-05, + "loss": 3.8174, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402330900316635e-05, + "loss": 3.8111, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401492305565583e-05, + "loss": 3.8133, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400653710814531e-05, + "loss": 3.8107, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399816753943852e-05, + "loss": 3.8019, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.3989781591928e-05, + "loss": 3.7961, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398139564441748e-05, + "loss": 3.8075, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397300969690696e-05, + "loss": 3.801, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396464012820018e-05, + "loss": 3.8089, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956254180689657e-05, + "loss": 3.8041, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.3947868233179137e-05, + "loss": 3.8081, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939482285668617e-05, + "loss": 3.8026, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3931112716961826e-05, + "loss": 3.8019, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922726769451306e-05, + "loss": 3.7988, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914340821940786e-05, + "loss": 3.813, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905954874430265e-05, + "loss": 3.8035, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897585305723475e-05, + "loss": 3.7935, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889199358212955e-05, + "loss": 3.7864, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880813410702434e-05, + "loss": 3.8078, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872427463191914e-05, + "loss": 3.8069, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3864041515681394e-05, + "loss": 3.8082, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385567194697461e-05, + "loss": 3.8033, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384728599946409e-05, + "loss": 3.8095, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383890005195357e-05, + "loss": 3.8032, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383051410444305e-05, + "loss": 3.8083, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382214453573626e-05, + "loss": 3.7965, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381375858822574e-05, + "loss": 3.8014, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380537264071522e-05, + "loss": 3.8003, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.37969866932047e-05, + "loss": 3.7954, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378861712449791e-05, + "loss": 3.8092, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378023117698739e-05, + "loss": 3.8056, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377184522947687e-05, + "loss": 3.8019, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376345928196635e-05, + "loss": 3.7999, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3755089713259564e-05, + "loss": 3.8009, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.906316041946411, + "eval_runtime": 305.0368, + "eval_samples_per_second": 1250.967, + "eval_steps_per_second": 39.094, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746703765749044e-05, + "loss": 3.7959, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3738317818238524e-05, + "loss": 3.7932, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.3729931870728004e-05, + "loss": 3.8006, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372156230202121e-05, + "loss": 3.7964, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371317635451069e-05, + "loss": 3.81, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370479040700017e-05, + "loss": 3.7954, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369640445948965e-05, + "loss": 3.7889, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368803489078286e-05, + "loss": 3.7844, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367964894327234e-05, + "loss": 3.803, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367126299576182e-05, + "loss": 3.7998, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.36628770482513e-05, + "loss": 3.7903, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365450747954452e-05, + "loss": 3.8009, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364613791083773e-05, + "loss": 3.7946, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363775196332721e-05, + "loss": 3.7921, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.3629366015816687e-05, + "loss": 3.7862, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.3620980068306167e-05, + "loss": 3.7822, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.3612594120795647e-05, + "loss": 3.7867, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.3604208173285126e-05, + "loss": 3.7838, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.3595822225774606e-05, + "loss": 3.7965, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358743627826408e-05, + "loss": 3.8001, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.3579066709557295e-05, + "loss": 3.7966, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.3570680762046775e-05, + "loss": 3.7908, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.3562294814536255e-05, + "loss": 3.7868, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.3553908867025735e-05, + "loss": 3.79, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354553929831895e-05, + "loss": 3.7838, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353715335080843e-05, + "loss": 3.7899, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.3528767403297904e-05, + "loss": 3.7749, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3520381455787384e-05, + "loss": 3.7933, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.35120118870806e-05, + "loss": 3.7816, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350362593957008e-05, + "loss": 3.774, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349523999205955e-05, + "loss": 3.7858, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348685404454903e-05, + "loss": 3.7908, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347848447584225e-05, + "loss": 3.7956, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.347009852833173e-05, + "loss": 3.7884, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346171258082121e-05, + "loss": 3.7825, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345332663331069e-05, + "loss": 3.7931, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444957064603905e-05, + "loss": 3.7897, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343657111709338e-05, + "loss": 3.7707, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342818516958286e-05, + "loss": 3.7715, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341979922207234e-05, + "loss": 3.775, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3411429653365554e-05, + "loss": 3.7783, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340304370585503e-05, + "loss": 3.7871, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339465775834451e-05, + "loss": 3.7809, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338627181083399e-05, + "loss": 3.7748, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.33779022421272e-05, + "loss": 3.7867, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336951629461668e-05, + "loss": 3.7794, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336113034710616e-05, + "loss": 3.7904, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335274439959564e-05, + "loss": 3.7715, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334437483088885e-05, + "loss": 3.7521, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333598888337833e-05, + "loss": 3.7954, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332760293586781e-05, + "loss": 3.7865, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331921698835729e-05, + "loss": 3.7854, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.33108474196505e-05, + "loss": 3.7799, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330246147213998e-05, + "loss": 3.7749, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329407552462946e-05, + "loss": 3.7671, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328568957711894e-05, + "loss": 3.7751, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.3277320008412156e-05, + "loss": 3.7715, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.3268934060901636e-05, + "loss": 3.7761, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.3260548113391116e-05, + "loss": 3.7803, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.3252162165880596e-05, + "loss": 3.7734, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.3243792597173805e-05, + "loss": 3.7646, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.3235406649663285e-05, + "loss": 3.7854, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.3227020702152765e-05, + "loss": 3.7662, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.3218634754642245e-05, + "loss": 3.7648, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.3210265185935454e-05, + "loss": 3.7814, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.3201879238424934e-05, + "loss": 3.7821, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3193493290914414e-05, + "loss": 3.7571, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3185107343403894e-05, + "loss": 3.7702, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.3176721395893374e-05, + "loss": 3.7556, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316835182718659e-05, + "loss": 3.7738, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315996587967607e-05, + "loss": 3.7774, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315157993216555e-05, + "loss": 3.7725, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314319398465503e-05, + "loss": 3.7733, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313482441594824e-05, + "loss": 3.7763, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312643846843772e-05, + "loss": 3.7849, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.31180525209272e-05, + "loss": 3.7636, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310966657341668e-05, + "loss": 3.7804, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310129700470989e-05, + "loss": 3.7768, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309291105719937e-05, + "loss": 3.7575, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308452510968885e-05, + "loss": 3.7797, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307613916217833e-05, + "loss": 3.7687, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.3067769593471544e-05, + "loss": 3.7809, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.3059383645961024e-05, + "loss": 3.777, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3050997698450504e-05, + "loss": 3.7629, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042611750939984e-05, + "loss": 3.7586, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303424218223319e-05, + "loss": 3.7651, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302585623472267e-05, + "loss": 3.7828, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301747028721215e-05, + "loss": 3.7661, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300908433970163e-05, + "loss": 3.7648, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300071477099484e-05, + "loss": 3.7652, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299232882348432e-05, + "loss": 3.7701, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.29839428759738e-05, + "loss": 3.7615, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297555692846328e-05, + "loss": 3.7483, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.29671873597565e-05, + "loss": 3.7655, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295880141224598e-05, + "loss": 3.7743, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295041546473546e-05, + "loss": 3.7747, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294202951722494e-05, + "loss": 3.7541, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.2933659948518146e-05, + "loss": 3.7603, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.2925274001007626e-05, + "loss": 3.7657, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.2916888053497106e-05, + "loss": 3.7683, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.2908502105986586e-05, + "loss": 3.7736, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.2900132537279795e-05, + "loss": 3.7616, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.2891746589769275e-05, + "loss": 3.764, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.2883360642258755e-05, + "loss": 3.7689, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.2874974694748235e-05, + "loss": 3.7488, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286660512604145e-05, + "loss": 3.763, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285821917853093e-05, + "loss": 3.756, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284983323102041e-05, + "loss": 3.7683, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284144728350989e-05, + "loss": 3.7508, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.28330777148031e-05, + "loss": 3.7663, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282469176729258e-05, + "loss": 3.755, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281630581978206e-05, + "loss": 3.7629, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280791987227154e-05, + "loss": 3.7607, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279955030356475e-05, + "loss": 3.7649, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279116435605423e-05, + "loss": 3.7636, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278277840854371e-05, + "loss": 3.7737, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277439246103319e-05, + "loss": 3.7667, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2766022892326405e-05, + "loss": 3.7693, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757636944815885e-05, + "loss": 3.7599, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2749250997305365e-05, + "loss": 3.7624, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.2740865049794845e-05, + "loss": 3.7507, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.2732495481088054e-05, + "loss": 3.7572, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.2724109533577534e-05, + "loss": 3.7581, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.2715723586067014e-05, + "loss": 3.7623, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.2707337638556494e-05, + "loss": 3.7631, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.26989680698497e-05, + "loss": 3.7601, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269058212233918e-05, + "loss": 3.7562, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268219617482866e-05, + "loss": 3.7605, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267381022731814e-05, + "loss": 3.7562, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266544065861136e-05, + "loss": 3.7631, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265705471110084e-05, + "loss": 3.7586, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264866876359032e-05, + "loss": 3.7533, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.26402828160798e-05, + "loss": 3.7397, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263191324737301e-05, + "loss": 3.7668, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262352729986249e-05, + "loss": 3.7612, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261514135235197e-05, + "loss": 3.7657, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260675540484145e-05, + "loss": 3.7578, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2598385836134656e-05, + "loss": 3.764, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2589999888624136e-05, + "loss": 3.7595, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581613941113616e-05, + "loss": 3.7689, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.2573227993603096e-05, + "loss": 3.752, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256485842489631e-05, + "loss": 3.7574, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255647247738579e-05, + "loss": 3.7569, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254808652987527e-05, + "loss": 3.7551, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253970058236475e-05, + "loss": 3.7672, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253133101365796e-05, + "loss": 3.7567, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252294506614744e-05, + "loss": 3.7642, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251455911863692e-05, + "loss": 3.7517, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.25061731711264e-05, + "loss": 3.7572, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.8900606632232666, + "eval_runtime": 304.1235, + "eval_samples_per_second": 1254.724, + "eval_steps_per_second": 39.211, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249780360241961e-05, + "loss": 3.7574, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248941765490909e-05, + "loss": 3.7509, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248103170739857e-05, + "loss": 3.7565, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247264575988805e-05, + "loss": 3.754, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246425981237753e-05, + "loss": 3.7659, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245587386486701e-05, + "loss": 3.751, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244748791735649e-05, + "loss": 3.7479, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243910196984597e-05, + "loss": 3.7419, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243073240113918e-05, + "loss": 3.7589, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242234645362866e-05, + "loss": 3.7576, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241396050611814e-05, + "loss": 3.7466, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240557455860762e-05, + "loss": 3.7585, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.2397221368704564e-05, + "loss": 3.752, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388835421194044e-05, + "loss": 3.7488, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380449473683524e-05, + "loss": 3.7416, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2372063526173004e-05, + "loss": 3.7411, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363677578662484e-05, + "loss": 3.7457, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355291631151963e-05, + "loss": 3.745, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346905683641443e-05, + "loss": 3.752, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233851973613092e-05, + "loss": 3.7579, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233015016742413e-05, + "loss": 3.7551, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232176421991361e-05, + "loss": 3.75, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231337827240309e-05, + "loss": 3.7449, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230499232489257e-05, + "loss": 3.7451, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229662275618578e-05, + "loss": 3.7453, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228823680867526e-05, + "loss": 3.7507, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227985086116474e-05, + "loss": 3.7291, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227146491365422e-05, + "loss": 3.755, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226309534494744e-05, + "loss": 3.7417, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225470939743692e-05, + "loss": 3.7318, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.22463234499264e-05, + "loss": 3.7429, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223793750241588e-05, + "loss": 3.753, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2229567933709086e-05, + "loss": 3.7478, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2221181986198566e-05, + "loss": 3.7511, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212796038688046e-05, + "loss": 3.7388, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2204410091177526e-05, + "loss": 3.7535, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2196040522470735e-05, + "loss": 3.7476, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187654574960215e-05, + "loss": 3.7295, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2179268627449695e-05, + "loss": 3.7323, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170882679939175e-05, + "loss": 3.7336, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216251311123239e-05, + "loss": 3.739, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215412716372187e-05, + "loss": 3.7482, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214574121621135e-05, + "loss": 3.7386, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213735526870083e-05, + "loss": 3.7365, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212898569999404e-05, + "loss": 3.7432, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212059975248352e-05, + "loss": 3.7352, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112213804973e-05, + "loss": 3.7508, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210384423626621e-05, + "loss": 3.7353, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209545828875569e-05, + "loss": 3.7093, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208707234124517e-05, + "loss": 3.7531, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207868639373465e-05, + "loss": 3.7468, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070316825027865e-05, + "loss": 3.7445, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061930877517345e-05, + "loss": 3.7375, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2053544930006824e-05, + "loss": 3.7341, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045158982496304e-05, + "loss": 3.7272, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036789413789514e-05, + "loss": 3.7374, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028403466278993e-05, + "loss": 3.7321, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2020017518768473e-05, + "loss": 3.7334, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011631571257953e-05, + "loss": 3.7388, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200326200255116e-05, + "loss": 3.7359, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199487605504064e-05, + "loss": 3.7244, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198649010753012e-05, + "loss": 3.7446, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.19781041600196e-05, + "loss": 3.7247, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196973459131281e-05, + "loss": 3.7281, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.19613486438023e-05, + "loss": 3.7418, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195296269629178e-05, + "loss": 3.7427, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194457674878126e-05, + "loss": 3.7198, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193620718007447e-05, + "loss": 3.7279, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192782123256395e-05, + "loss": 3.7159, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191943528505343e-05, + "loss": 3.7359, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191104933754291e-05, + "loss": 3.7387, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902679768836116e-05, + "loss": 3.7353, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1894293821325596e-05, + "loss": 3.7333, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885907873815076e-05, + "loss": 3.7374, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1877521926304556e-05, + "loss": 3.7458, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1869152357597765e-05, + "loss": 3.7249, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186076641008725e-05, + "loss": 3.7384, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185238046257673e-05, + "loss": 3.7374, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184399451506621e-05, + "loss": 3.7209, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183562494635942e-05, + "loss": 3.7381, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.18272389988489e-05, + "loss": 3.7357, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181885305133838e-05, + "loss": 3.7373, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181046710382786e-05, + "loss": 3.739, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180209753512107e-05, + "loss": 3.7239, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179371158761055e-05, + "loss": 3.7235, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178532564010003e-05, + "loss": 3.7282, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177693969258951e-05, + "loss": 3.7377, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176857012388272e-05, + "loss": 3.7277, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760184176372206e-05, + "loss": 3.7263, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751798228861685e-05, + "loss": 3.7288, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743412281351165e-05, + "loss": 3.7323, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1735042712644375e-05, + "loss": 3.7234, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726656765133854e-05, + "loss": 3.7108, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1718270817623334e-05, + "loss": 3.7289, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.1709884870112814e-05, + "loss": 3.7315, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1701515301406023e-05, + "loss": 3.7352, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693129353895503e-05, + "loss": 3.7171, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684743406384983e-05, + "loss": 3.7223, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167635745887446e-05, + "loss": 3.7291, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166798789016767e-05, + "loss": 3.7295, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165960194265716e-05, + "loss": 3.7355, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165121599514664e-05, + "loss": 3.7256, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164283004763612e-05, + "loss": 3.7245, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163446047892933e-05, + "loss": 3.7316, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162607453141881e-05, + "loss": 3.7116, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161768858390829e-05, + "loss": 3.7256, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.16093190152015e-05, + "loss": 3.7139, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160093306769098e-05, + "loss": 3.7354, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159254712018046e-05, + "loss": 3.7125, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158416117266994e-05, + "loss": 3.7279, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575791603963146e-05, + "loss": 3.719, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.1567405656452626e-05, + "loss": 3.7227, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155901970894211e-05, + "loss": 3.7246, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155063376143159e-05, + "loss": 3.7283, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.15422641927248e-05, + "loss": 3.724, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153387824521428e-05, + "loss": 3.7361, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152549229770376e-05, + "loss": 3.7242, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151710635019324e-05, + "loss": 3.7383, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150873678148645e-05, + "loss": 3.7224, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150035083397593e-05, + "loss": 3.7226, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149196488646541e-05, + "loss": 3.7187, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148357893895489e-05, + "loss": 3.7176, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.14752093702481e-05, + "loss": 3.7189, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146682342273758e-05, + "loss": 3.7285, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458437475227067e-05, + "loss": 3.7228, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1450051527716546e-05, + "loss": 3.7263, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441681959009756e-05, + "loss": 3.7222, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1433296011499236e-05, + "loss": 3.7236, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424910063988715e-05, + "loss": 3.7252, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1416524116478195e-05, + "loss": 3.7236, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1408154547771405e-05, + "loss": 3.7197, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399768600260884e-05, + "loss": 3.7184, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1391382652750364e-05, + "loss": 3.7041, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382996705239844e-05, + "loss": 3.7306, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1374627136533054e-05, + "loss": 3.7257, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1366241189022533e-05, + "loss": 3.7317, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135785524151202e-05, + "loss": 3.7181, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.13494692940015e-05, + "loss": 3.7282, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134109972529471e-05, + "loss": 3.7248, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133271377778419e-05, + "loss": 3.7328, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132432783027367e-05, + "loss": 3.7144, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131594188276314e-05, + "loss": 3.7167, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130757231405636e-05, + "loss": 3.7219, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129918636654584e-05, + "loss": 3.7211, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129080041903532e-05, + "loss": 3.7254, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128241447152479e-05, + "loss": 3.723, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127404490281801e-05, + "loss": 3.7274, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126565895530749e-05, + "loss": 3.7158, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125727300779697e-05, + "loss": 3.7252, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.880248546600342, + "eval_runtime": 305.526, + "eval_samples_per_second": 1248.964, + "eval_steps_per_second": 39.031, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124888706028645e-05, + "loss": 3.7156, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.124051749157966e-05, + "loss": 3.7177, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123213154406914e-05, + "loss": 3.7144, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.1223745596558616e-05, + "loss": 3.7196, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1215359649048096e-05, + "loss": 3.7298, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120699008034131e-05, + "loss": 3.7168, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119860413283079e-05, + "loss": 3.7139, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.1190218185320265e-05, + "loss": 3.7109, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.1181832237809745e-05, + "loss": 3.7172, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117346266910296e-05, + "loss": 3.7237, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116507672159244e-05, + "loss": 3.7092, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115669077408192e-05, + "loss": 3.7206, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114832120537514e-05, + "loss": 3.7222, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139935257864617e-05, + "loss": 3.7107, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113154931035409e-05, + "loss": 3.7095, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112316336284357e-05, + "loss": 3.7047, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111477741533305e-05, + "loss": 3.7104, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110639146782253e-05, + "loss": 3.7071, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109800552031201e-05, + "loss": 3.7117, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108961957280149e-05, + "loss": 3.7268, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.10812500040947e-05, + "loss": 3.7212, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107286405658418e-05, + "loss": 3.7156, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106447810907366e-05, + "loss": 3.7091, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1056092161563145e-05, + "loss": 3.71, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.1047722592856354e-05, + "loss": 3.7116, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.1039336645345834e-05, + "loss": 3.7146, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030950697835314e-05, + "loss": 3.6955, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.1022564750324794e-05, + "loss": 3.7196, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1014195181618e-05, + "loss": 3.7091, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100580923410748e-05, + "loss": 3.7002, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099742328659696e-05, + "loss": 3.7029, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098903733908644e-05, + "loss": 3.721, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.098066777037965e-05, + "loss": 3.7167, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097228182286913e-05, + "loss": 3.7141, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096389587535861e-05, + "loss": 3.7043, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.09555099278481e-05, + "loss": 3.7142, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094714035914131e-05, + "loss": 3.7174, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093875441163079e-05, + "loss": 3.6979, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.093036846412027e-05, + "loss": 3.6974, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092198251660975e-05, + "loss": 3.6978, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091361294790296e-05, + "loss": 3.704, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090522700039244e-05, + "loss": 3.7117, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089684105288192e-05, + "loss": 3.7091, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0888471484175126e-05, + "loss": 3.7003, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.0880085536664606e-05, + "loss": 3.7077, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.0871699589154086e-05, + "loss": 3.7033, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.0863313641643566e-05, + "loss": 3.7139, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085494407293678e-05, + "loss": 3.7058, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084655812542626e-05, + "loss": 3.6749, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083817217791574e-05, + "loss": 3.7166, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082978623040522e-05, + "loss": 3.7119, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082141666169843e-05, + "loss": 3.7141, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081303071418791e-05, + "loss": 3.7023, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080464476667739e-05, + "loss": 3.6986, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079625881916687e-05, + "loss": 3.6989, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078788925046008e-05, + "loss": 3.7029, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077950330294956e-05, + "loss": 3.7027, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077111735543904e-05, + "loss": 3.694, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076273140792852e-05, + "loss": 3.7077, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0754361839221735e-05, + "loss": 3.7061, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745975891711215e-05, + "loss": 3.69, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0737589944200695e-05, + "loss": 3.7093, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.0729203996690175e-05, + "loss": 3.693, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.0720834427983384e-05, + "loss": 3.6924, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.0712464859276593e-05, + "loss": 3.7063, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.0704078911766073e-05, + "loss": 3.7117, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069569296425555e-05, + "loss": 3.6862, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068730701674503e-05, + "loss": 3.6977, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067892106923451e-05, + "loss": 3.6818, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067053512172399e-05, + "loss": 3.7014, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066216555301721e-05, + "loss": 3.7057, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065377960550669e-05, + "loss": 3.7033, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064539365799617e-05, + "loss": 3.6977, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063700771048565e-05, + "loss": 3.7033, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062862176297513e-05, + "loss": 3.7171, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.062023581546461e-05, + "loss": 3.6902, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061184986795409e-05, + "loss": 3.7092, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.06034802992473e-05, + "loss": 3.7059, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059509435173678e-05, + "loss": 3.6881, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.058670840422626e-05, + "loss": 3.7054, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.057832245671574e-05, + "loss": 3.7029, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056993650920522e-05, + "loss": 3.7037, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.05615505616947e-05, + "loss": 3.7099, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055316461418418e-05, + "loss": 3.6863, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054477866667366e-05, + "loss": 3.6895, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.0536409097966874e-05, + "loss": 3.6949, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052802315045635e-05, + "loss": 3.7057, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051963720294583e-05, + "loss": 3.6944, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051126763423904e-05, + "loss": 3.6987, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.0502881686728516e-05, + "loss": 3.6992, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.0494495739217996e-05, + "loss": 3.6932, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.0486109791707476e-05, + "loss": 3.6942, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047774022300069e-05, + "loss": 3.6777, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.0469354275490165e-05, + "loss": 3.6949, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046096832797965e-05, + "loss": 3.6993, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045258238046913e-05, + "loss": 3.7064, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044421281176235e-05, + "loss": 3.6848, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043582686425182e-05, + "loss": 3.6881, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.04274409167413e-05, + "loss": 3.6955, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041905496923078e-05, + "loss": 3.6968, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.041068540052399e-05, + "loss": 3.7014, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040229945301347e-05, + "loss": 3.6982, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039391350550295e-05, + "loss": 3.6936, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038552755799243e-05, + "loss": 3.695, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037715798928564e-05, + "loss": 3.6857, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036877204177512e-05, + "loss": 3.6903, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.0360386094264605e-05, + "loss": 3.686, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.0352000146754085e-05, + "loss": 3.7039, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0343630578047294e-05, + "loss": 3.6811, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.0335244630536774e-05, + "loss": 3.6959, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.0326858683026254e-05, + "loss": 3.6875, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0318472735515734e-05, + "loss": 3.6951, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.031010316680894e-05, + "loss": 3.6927, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030171721929842e-05, + "loss": 3.6946, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.02933312717879e-05, + "loss": 3.6933, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028494532427738e-05, + "loss": 3.7073, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027657575557059e-05, + "loss": 3.6915, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026818980806007e-05, + "loss": 3.7065, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025980386054955e-05, + "loss": 3.6911, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025143429184277e-05, + "loss": 3.6909, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024304834433225e-05, + "loss": 3.6865, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023466239682173e-05, + "loss": 3.6914, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022627644931121e-05, + "loss": 3.6847, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021789050180069e-05, + "loss": 3.6962, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020950455429017e-05, + "loss": 3.6873, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020113498558338e-05, + "loss": 3.6946, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019274903807286e-05, + "loss": 3.6949, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018436309056234e-05, + "loss": 3.6886, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175977143051817e-05, + "loss": 3.6934, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0167591195541297e-05, + "loss": 3.6974, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0159205248030776e-05, + "loss": 3.6846, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0150819300520256e-05, + "loss": 3.6909, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.0142433353009736e-05, + "loss": 3.6709, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013406378430295e-05, + "loss": 3.6983, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012567783679243e-05, + "loss": 3.694, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011729188928191e-05, + "loss": 3.6992, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010892232057512e-05, + "loss": 3.6872, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.01005363730646e-05, + "loss": 3.6972, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009215042555408e-05, + "loss": 3.693, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008376447804356e-05, + "loss": 3.6998, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007537853053304e-05, + "loss": 3.6842, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006699258302252e-05, + "loss": 3.6887, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.0058606635512e-05, + "loss": 3.6899, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.0050220688001474e-05, + "loss": 3.6945, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004185111929469e-05, + "loss": 3.6933, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003346517178418e-05, + "loss": 3.69, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002507922427366e-05, + "loss": 3.6978, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001669327676313e-05, + "loss": 3.6828, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.0008323708056346e-05, + "loss": 3.699, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.872364044189453, + "eval_runtime": 305.8283, + "eval_samples_per_second": 1247.73, + "eval_steps_per_second": 38.992, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.9999937760545826e-05, + "loss": 3.6859, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.99915518130353e-05, + "loss": 3.6834, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998316586552478e-05, + "loss": 3.687, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997477991801426e-05, + "loss": 3.6894, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996639397050374e-05, + "loss": 3.6999, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995800802299322e-05, + "loss": 3.6869, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.99496220754827e-05, + "loss": 3.6815, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994123612797218e-05, + "loss": 3.6813, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.9932866559265395e-05, + "loss": 3.6872, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.9924496990558604e-05, + "loss": 3.6952, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.9916111043048084e-05, + "loss": 3.6827, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.9907725095537564e-05, + "loss": 3.6892, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989935552683077e-05, + "loss": 3.6922, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989096957932025e-05, + "loss": 3.6801, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988258363180973e-05, + "loss": 3.6788, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987419768429921e-05, + "loss": 3.6751, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986581173678869e-05, + "loss": 3.6816, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985742578927817e-05, + "loss": 3.6768, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984903984176765e-05, + "loss": 3.6856, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984065389425713e-05, + "loss": 3.6952, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983226794674661e-05, + "loss": 3.6923, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.98238819992361e-05, + "loss": 3.6819, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981549605172558e-05, + "loss": 3.6814, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980711010421506e-05, + "loss": 3.6802, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979874053550827e-05, + "loss": 3.6796, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979035458799775e-05, + "loss": 3.6853, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978196864048723e-05, + "loss": 3.6681, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977358269297671e-05, + "loss": 3.6885, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976521312426992e-05, + "loss": 3.6799, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.97568271767594e-05, + "loss": 3.6668, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974844122924888e-05, + "loss": 3.6742, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.974005528173836e-05, + "loss": 3.6901, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.97317020918353e-05, + "loss": 3.6901, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972331614432478e-05, + "loss": 3.6843, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971493019681426e-05, + "loss": 3.6769, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970654424930374e-05, + "loss": 3.6779, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969815830179322e-05, + "loss": 3.6925, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.96897723542827e-05, + "loss": 3.6696, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968138640677218e-05, + "loss": 3.6673, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967300045926166e-05, + "loss": 3.6722, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966463089055487e-05, + "loss": 3.6713, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965624494304435e-05, + "loss": 3.6812, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964785899553383e-05, + "loss": 3.6741, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963947304802331e-05, + "loss": 3.6791, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963110347931652e-05, + "loss": 3.6745, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9622717531806e-05, + "loss": 3.6722, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9614331584295486e-05, + "loss": 3.6881, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960594563678496e-05, + "loss": 3.6719, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9597576068078175e-05, + "loss": 3.651, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.9589206499371384e-05, + "loss": 3.6861, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.9580820551860864e-05, + "loss": 3.6782, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.9572434604350344e-05, + "loss": 3.6861, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.9564048656839824e-05, + "loss": 3.6757, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9555662709329304e-05, + "loss": 3.6683, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9547276761818784e-05, + "loss": 3.6662, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953890719311199e-05, + "loss": 3.6716, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953052124560147e-05, + "loss": 3.6782, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952213529809095e-05, + "loss": 3.6633, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951374935058043e-05, + "loss": 3.6828, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950536340306991e-05, + "loss": 3.6751, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949697745555939e-05, + "loss": 3.6633, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948859150804887e-05, + "loss": 3.6807, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.948020556053835e-05, + "loss": 3.6659, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947183599183156e-05, + "loss": 3.6637, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946345004432104e-05, + "loss": 3.6754, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945508047561426e-05, + "loss": 3.685, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944669452810373e-05, + "loss": 3.6522, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943830858059321e-05, + "loss": 3.6717, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942992263308269e-05, + "loss": 3.6557, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942153668557218e-05, + "loss": 3.673, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941316711686539e-05, + "loss": 3.6785, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940478116935487e-05, + "loss": 3.6692, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939639522184435e-05, + "loss": 3.6743, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938800927433383e-05, + "loss": 3.6716, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937962332682331e-05, + "loss": 3.6905, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937123737931279e-05, + "loss": 3.6605, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.9362867810605996e-05, + "loss": 3.6802, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.9354481863095476e-05, + "loss": 3.6735, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9346095915584956e-05, + "loss": 3.6639, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9337709968074436e-05, + "loss": 3.6768, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329340399367645e-05, + "loss": 3.6724, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932095445185713e-05, + "loss": 3.6757, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931256850434661e-05, + "loss": 3.6808, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930418255683609e-05, + "loss": 3.6574, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929579660932557e-05, + "loss": 3.6633, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928742704061878e-05, + "loss": 3.6673, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927904109310826e-05, + "loss": 3.6779, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927065514559774e-05, + "loss": 3.6641, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926226919808722e-05, + "loss": 3.6702, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.92538832505767e-05, + "loss": 3.6741, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924551368186991e-05, + "loss": 3.6668, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923712773435939e-05, + "loss": 3.6656, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922874178684887e-05, + "loss": 3.6507, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922035583933835e-05, + "loss": 3.6667, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921196989182783e-05, + "loss": 3.6718, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9203583944317316e-05, + "loss": 3.6768, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9195197996806796e-05, + "loss": 3.6585, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918681204929627e-05, + "loss": 3.6603, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178442480589485e-05, + "loss": 3.6654, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9170056533078965e-05, + "loss": 3.6727, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161670585568445e-05, + "loss": 3.6729, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915328463805792e-05, + "loss": 3.6685, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144915069351134e-05, + "loss": 3.6693, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9136529121840614e-05, + "loss": 3.6634, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912814317433009e-05, + "loss": 3.6601, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.91197736056233e-05, + "loss": 3.659, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911138765811278e-05, + "loss": 3.6619, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910300171060226e-05, + "loss": 3.6764, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909461576309174e-05, + "loss": 3.6539, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908624619438496e-05, + "loss": 3.6645, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907787662567817e-05, + "loss": 3.6576, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906949067816765e-05, + "loss": 3.6705, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906110473065713e-05, + "loss": 3.666, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905271878314661e-05, + "loss": 3.6674, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904433283563609e-05, + "loss": 3.6647, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035963266929297e-05, + "loss": 3.6786, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027577319418777e-05, + "loss": 3.6674, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9019191371908257e-05, + "loss": 3.6753, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010805424397736e-05, + "loss": 3.6659, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900243585569095e-05, + "loss": 3.6639, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899404990818043e-05, + "loss": 3.6598, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898566396066991e-05, + "loss": 3.6624, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897727801315939e-05, + "loss": 3.6569, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.8968892065648865e-05, + "loss": 3.6693, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8960506118138345e-05, + "loss": 3.6624, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895213654943156e-05, + "loss": 3.6678, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8943750601921034e-05, + "loss": 3.6645, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8935364654410514e-05, + "loss": 3.6662, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8926978706899994e-05, + "loss": 3.6644, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.8918592759389474e-05, + "loss": 3.6724, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.8910206811878954e-05, + "loss": 3.656, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890183724317217e-05, + "loss": 3.665, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889345129566165e-05, + "loss": 3.6391, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888506534815113e-05, + "loss": 3.6737, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887667940064061e-05, + "loss": 3.6668, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886829345313009e-05, + "loss": 3.6753, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.88599238844233e-05, + "loss": 3.6572, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885153793691278e-05, + "loss": 3.6718, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884315198940226e-05, + "loss": 3.6648, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883476604189174e-05, + "loss": 3.6765, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882638009438122e-05, + "loss": 3.6577, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.88179941468707e-05, + "loss": 3.6606, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880960819936018e-05, + "loss": 3.6617, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8801238630653395e-05, + "loss": 3.6729, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792852683142875e-05, + "loss": 3.662, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8784466735632355e-05, + "loss": 3.6629, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8776080788121834e-05, + "loss": 3.6716, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.8767711219415044e-05, + "loss": 3.6612, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8759325271904524e-05, + "loss": 3.6697, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8685142993927, + "eval_runtime": 326.8665, + "eval_samples_per_second": 1167.422, + "eval_steps_per_second": 36.483, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750939324394004e-05, + "loss": 3.6535, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742553376883483e-05, + "loss": 3.6626, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8734167429372963e-05, + "loss": 3.6564, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872578148186244e-05, + "loss": 3.6659, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871739553435192e-05, + "loss": 3.676, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870902596564513e-05, + "loss": 3.6559, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870064001813461e-05, + "loss": 3.654, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869225407062409e-05, + "loss": 3.6561, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868386812311358e-05, + "loss": 3.6629, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867549855440679e-05, + "loss": 3.6679, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866711260689627e-05, + "loss": 3.6556, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865872665938575e-05, + "loss": 3.6625, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865034071187522e-05, + "loss": 3.6681, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.86419547643647e-05, + "loss": 3.6556, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863356881685418e-05, + "loss": 3.6518, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.86251992481474e-05, + "loss": 3.6448, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861681330063687e-05, + "loss": 3.6571, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860842735312635e-05, + "loss": 3.6526, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.860004140561583e-05, + "loss": 3.6536, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859165545810532e-05, + "loss": 3.6679, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.8583285889398526e-05, + "loss": 3.666, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.8574899941888006e-05, + "loss": 3.6587, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8566513994377486e-05, + "loss": 3.6552, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.8558128046866966e-05, + "loss": 3.6552, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8549742099356446e-05, + "loss": 3.6582, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.8541356151845926e-05, + "loss": 3.6581, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.8532970204335406e-05, + "loss": 3.6411, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.8524600635628615e-05, + "loss": 3.6617, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.8516214688118095e-05, + "loss": 3.6573, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8507828740607575e-05, + "loss": 3.6409, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.8499442793097055e-05, + "loss": 3.6503, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849107322439027e-05, + "loss": 3.6577, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848268727687975e-05, + "loss": 3.6615, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847430132936923e-05, + "loss": 3.6612, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846591538185871e-05, + "loss": 3.6548, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845752943434819e-05, + "loss": 3.6493, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844914348683767e-05, + "loss": 3.6677, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.844077391813088e-05, + "loss": 3.6425, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843238797062036e-05, + "loss": 3.642, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842400202310984e-05, + "loss": 3.646, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841561607559932e-05, + "loss": 3.6479, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.84072301280888e-05, + "loss": 3.6551, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839884418057828e-05, + "loss": 3.6482, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839047461187149e-05, + "loss": 3.6531, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838208866436097e-05, + "loss": 3.6503, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837370271685045e-05, + "loss": 3.6471, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8365316769339935e-05, + "loss": 3.659, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356930821829415e-05, + "loss": 3.6524, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834854487431889e-05, + "loss": 3.6276, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8340175305612104e-05, + "loss": 3.6564, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331789358101584e-05, + "loss": 3.6569, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832340341059106e-05, + "loss": 3.6621, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831501746308054e-05, + "loss": 3.6484, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830663151557002e-05, + "loss": 3.6449, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829826194686323e-05, + "loss": 3.637, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8289875999352706e-05, + "loss": 3.648, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.8281490051842186e-05, + "loss": 3.6531, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827310410433167e-05, + "loss": 3.639, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826471815682115e-05, + "loss": 3.6533, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825633220931063e-05, + "loss": 3.6487, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824794626180011e-05, + "loss": 3.6408, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823957669309332e-05, + "loss": 3.6489, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.82311907455828e-05, + "loss": 3.6413, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822280479807228e-05, + "loss": 3.6418, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821441885056176e-05, + "loss": 3.6449, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820604928185497e-05, + "loss": 3.6576, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819766333434445e-05, + "loss": 3.6344, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818929376563766e-05, + "loss": 3.6485, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818090781812714e-05, + "loss": 3.6255, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8172521870616626e-05, + "loss": 3.6488, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8164135923106106e-05, + "loss": 3.6531, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8155766354399315e-05, + "loss": 3.6476, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8147380406888795e-05, + "loss": 3.6433, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8138994459378275e-05, + "loss": 3.6504, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.8130608511867755e-05, + "loss": 3.6625, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.8122222564357235e-05, + "loss": 3.6375, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.8113852995650444e-05, + "loss": 3.6576, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.8105467048139924e-05, + "loss": 3.6452, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.8097081100629404e-05, + "loss": 3.6406, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.8088695153118884e-05, + "loss": 3.6516, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808032558441209e-05, + "loss": 3.6464, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807193963690158e-05, + "loss": 3.6534, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806355368939106e-05, + "loss": 3.6579, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805516774188054e-05, + "loss": 3.6313, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804678179437002e-05, + "loss": 3.6398, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803841222566323e-05, + "loss": 3.6398, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.803002627815271e-05, + "loss": 3.6547, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802164033064219e-05, + "loss": 3.6376, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801325438313167e-05, + "loss": 3.6483, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800486843562115e-05, + "loss": 3.6464, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799649886691436e-05, + "loss": 3.6431, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798811291940384e-05, + "loss": 3.6396, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797972697189332e-05, + "loss": 3.6296, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.79713410243828e-05, + "loss": 3.6398, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7962971455676014e-05, + "loss": 3.6497, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7954585508165494e-05, + "loss": 3.6557, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7946199560654974e-05, + "loss": 3.6318, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7937813613144454e-05, + "loss": 3.6376, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7929427665633933e-05, + "loss": 3.6432, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792105809692714e-05, + "loss": 3.6459, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791267214941662e-05, + "loss": 3.6486, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.79042862019061e-05, + "loss": 3.645, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789590025439558e-05, + "loss": 3.6426, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788751430688506e-05, + "loss": 3.64, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787914473817827e-05, + "loss": 3.6414, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787075879066775e-05, + "loss": 3.6315, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786237284315723e-05, + "loss": 3.6387, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785398689564671e-05, + "loss": 3.6489, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784560094813619e-05, + "loss": 3.6337, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783721500062567e-05, + "loss": 3.6389, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782884543191889e-05, + "loss": 3.6336, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782045948440837e-05, + "loss": 3.6443, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781207353689784e-05, + "loss": 3.6416, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780368758938732e-05, + "loss": 3.6424, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.7795318020680536e-05, + "loss": 3.643, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.7786932073170016e-05, + "loss": 3.6562, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777854612565949e-05, + "loss": 3.6418, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777016017814897e-05, + "loss": 3.6476, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.7761790609442185e-05, + "loss": 3.647, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.7753404661931665e-05, + "loss": 3.6364, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.7745018714421145e-05, + "loss": 3.6397, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.7736632766910625e-05, + "loss": 3.632, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.7728246819400105e-05, + "loss": 3.6331, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719877250693314e-05, + "loss": 3.642, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.7711491303182794e-05, + "loss": 3.64, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.7703105355672274e-05, + "loss": 3.6447, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.7694719408161754e-05, + "loss": 3.6391, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.7686333460651234e-05, + "loss": 3.6467, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767796389194444e-05, + "loss": 3.636, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766957794443392e-05, + "loss": 3.6478, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.76611919969234e-05, + "loss": 3.6356, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765280604941289e-05, + "loss": 3.641, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.76444364807061e-05, + "loss": 3.6154, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763605053319558e-05, + "loss": 3.6499, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762766458568506e-05, + "loss": 3.6386, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761927863817454e-05, + "loss": 3.6532, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.761090906946775e-05, + "loss": 3.6346, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760252312195723e-05, + "loss": 3.646, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759413717444671e-05, + "loss": 3.6399, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758575122693619e-05, + "loss": 3.6572, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757736527942567e-05, + "loss": 3.6342, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756897933191515e-05, + "loss": 3.6359, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.7560609763208356e-05, + "loss": 3.6362, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755222381569784e-05, + "loss": 3.649, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754383786818732e-05, + "loss": 3.6389, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.75354519206768e-05, + "loss": 3.638, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752706597316628e-05, + "loss": 3.6446, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751869640445949e-05, + "loss": 3.6422, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751031045694897e-05, + "loss": 3.6434, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.866231918334961, + "eval_runtime": 310.76, + "eval_samples_per_second": 1227.928, + "eval_steps_per_second": 38.374, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750192450943845e-05, + "loss": 3.629, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749353856192793e-05, + "loss": 3.6384, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748515261441741e-05, + "loss": 3.6362, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747676666690689e-05, + "loss": 3.6395, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746838071939637e-05, + "loss": 3.653, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.746001115068958e-05, + "loss": 3.6323, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745162520317906e-05, + "loss": 3.6357, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744323925566854e-05, + "loss": 3.6313, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743485330815803e-05, + "loss": 3.6363, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742648373945124e-05, + "loss": 3.6428, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741809779194072e-05, + "loss": 3.6355, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.74097118444302e-05, + "loss": 3.6407, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.7401342275723406e-05, + "loss": 3.645, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7392956328212886e-05, + "loss": 3.6317, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.7384570380702366e-05, + "loss": 3.6264, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.7376184433191846e-05, + "loss": 3.6216, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736779848568132e-05, + "loss": 3.6353, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.73594125381708e-05, + "loss": 3.6294, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735102659066028e-05, + "loss": 3.6314, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7342640643149765e-05, + "loss": 3.6423, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7334254695639245e-05, + "loss": 3.6442, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7325885126932455e-05, + "loss": 3.6361, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7317499179421934e-05, + "loss": 3.6304, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7309113231911414e-05, + "loss": 3.632, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.7300727284400894e-05, + "loss": 3.6346, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.7292341336890374e-05, + "loss": 3.6348, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7283955389379854e-05, + "loss": 3.6174, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727558582067306e-05, + "loss": 3.6382, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726719987316254e-05, + "loss": 3.6353, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725881392565202e-05, + "loss": 3.6173, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.72504279781415e-05, + "loss": 3.6273, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724205840943472e-05, + "loss": 3.6362, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.72336724619242e-05, + "loss": 3.6335, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722528651441368e-05, + "loss": 3.6425, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721690056690316e-05, + "loss": 3.6302, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720853099819637e-05, + "loss": 3.6249, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.720014505068585e-05, + "loss": 3.6485, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719175910317533e-05, + "loss": 3.6153, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718337315566481e-05, + "loss": 3.6206, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717500358695802e-05, + "loss": 3.624, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.71666176394475e-05, + "loss": 3.6231, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715823169193698e-05, + "loss": 3.6275, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714984574442646e-05, + "loss": 3.6293, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714147617571967e-05, + "loss": 3.6317, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713309022820915e-05, + "loss": 3.6271, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712470428069863e-05, + "loss": 3.6241, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711631833318811e-05, + "loss": 3.6358, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710794876448132e-05, + "loss": 3.6289, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.70995628169708e-05, + "loss": 3.6092, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709117686946028e-05, + "loss": 3.6329, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708279092194976e-05, + "loss": 3.632, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707440497443924e-05, + "loss": 3.6397, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706603540573245e-05, + "loss": 3.6252, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705764945822193e-05, + "loss": 3.6259, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704926351071141e-05, + "loss": 3.6144, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704087756320089e-05, + "loss": 3.6209, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.7032507994494106e-05, + "loss": 3.6342, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7024122046983586e-05, + "loss": 3.6175, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7015736099473066e-05, + "loss": 3.6299, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.7007350151962546e-05, + "loss": 3.6269, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6998980583255755e-05, + "loss": 3.6208, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6990594635745235e-05, + "loss": 3.6285, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6982208688234715e-05, + "loss": 3.6173, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6973822740724195e-05, + "loss": 3.6215, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.6965436793213675e-05, + "loss": 3.6218, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6957067224506884e-05, + "loss": 3.6362, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.6948681276996364e-05, + "loss": 3.613, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.6940295329485844e-05, + "loss": 3.6263, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.6931909381975324e-05, + "loss": 3.6045, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692353981326854e-05, + "loss": 3.624, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691515386575802e-05, + "loss": 3.6284, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.69067679182475e-05, + "loss": 3.6307, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689838197073698e-05, + "loss": 3.622, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.689001240203019e-05, + "loss": 3.625, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688162645451967e-05, + "loss": 3.6412, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687324050700915e-05, + "loss": 3.6156, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686485455949863e-05, + "loss": 3.6392, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685648499079184e-05, + "loss": 3.6199, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684809904328132e-05, + "loss": 3.6187, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.68397130957708e-05, + "loss": 3.6289, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683132714826028e-05, + "loss": 3.6223, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.6822957579553494e-05, + "loss": 3.6318, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.6814571632042974e-05, + "loss": 3.6349, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.6806185684532454e-05, + "loss": 3.6154, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679779973702193e-05, + "loss": 3.6123, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678941378951141e-05, + "loss": 3.6201, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678104422080462e-05, + "loss": 3.629, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.67726582732941e-05, + "loss": 3.6189, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.6764272325783576e-05, + "loss": 3.627, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6755886378273056e-05, + "loss": 3.6235, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674751680956627e-05, + "loss": 3.6227, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673913086205575e-05, + "loss": 3.6151, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673074491454523e-05, + "loss": 3.61, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672235896703471e-05, + "loss": 3.6151, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671398939832793e-05, + "loss": 3.6275, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.67056034508174e-05, + "loss": 3.63, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669721750330688e-05, + "loss": 3.6114, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668883155579636e-05, + "loss": 3.6152, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.6680461987089576e-05, + "loss": 3.6226, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667207603957905e-05, + "loss": 3.6268, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666369009206853e-05, + "loss": 3.6274, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665530414455801e-05, + "loss": 3.6203, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664691819704749e-05, + "loss": 3.6212, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663853224953697e-05, + "loss": 3.6192, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6630162680830185e-05, + "loss": 3.617, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6621776733319665e-05, + "loss": 3.613, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6613390785809145e-05, + "loss": 3.6181, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6605004838298625e-05, + "loss": 3.6229, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6596635269591834e-05, + "loss": 3.6121, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6588249322081314e-05, + "loss": 3.6177, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6579863374570794e-05, + "loss": 3.6137, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6571477427060274e-05, + "loss": 3.6184, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656310785835348e-05, + "loss": 3.622, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655472191084296e-05, + "loss": 3.6186, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654633596333244e-05, + "loss": 3.6203, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653795001582192e-05, + "loss": 3.6343, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652958044711514e-05, + "loss": 3.6229, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652119449960462e-05, + "loss": 3.6235, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.65128085520941e-05, + "loss": 3.6261, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650442260458358e-05, + "loss": 3.6162, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649605303587679e-05, + "loss": 3.6221, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648766708836627e-05, + "loss": 3.6074, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647928114085575e-05, + "loss": 3.6138, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647089519334523e-05, + "loss": 3.6211, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646250924583471e-05, + "loss": 3.6204, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645413967712792e-05, + "loss": 3.6187, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.64457537296174e-05, + "loss": 3.6192, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643736778210688e-05, + "loss": 3.6224, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6428981834596357e-05, + "loss": 3.6174, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642061226588957e-05, + "loss": 3.6241, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641222631837905e-05, + "loss": 3.6177, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640384037086853e-05, + "loss": 3.6152, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639545442335801e-05, + "loss": 3.5934, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638708485465122e-05, + "loss": 3.6306, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.63786989071407e-05, + "loss": 3.617, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637031295963018e-05, + "loss": 3.6313, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636192701211966e-05, + "loss": 3.6149, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635354106460914e-05, + "loss": 3.6206, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634515511709862e-05, + "loss": 3.6192, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633678554839183e-05, + "loss": 3.6365, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632839960088131e-05, + "loss": 3.6094, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.632001365337079e-05, + "loss": 3.6161, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631162770586028e-05, + "loss": 3.6176, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.6303258137153486e-05, + "loss": 3.6267, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6294872189642966e-05, + "loss": 3.6165, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.6286486242132446e-05, + "loss": 3.6191, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6278100294621926e-05, + "loss": 3.6192, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6269730725915135e-05, + "loss": 3.6252, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6261344778404615e-05, + "loss": 3.6209, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.864964485168457, + "eval_runtime": 303.6408, + "eval_samples_per_second": 1256.719, + "eval_steps_per_second": 39.273, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6252958830894095e-05, + "loss": 3.6109, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6244572883383575e-05, + "loss": 3.6146, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6236186935873055e-05, + "loss": 3.6148, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.6227817367166264e-05, + "loss": 3.6192, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.6219431419655744e-05, + "loss": 3.6268, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621104547214523e-05, + "loss": 3.6115, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620265952463471e-05, + "loss": 3.6176, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.6194273577124184e-05, + "loss": 3.6105, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.61859040084174e-05, + "loss": 3.6128, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617751806090688e-05, + "loss": 3.6207, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616913211339636e-05, + "loss": 3.616, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616074616588583e-05, + "loss": 3.6162, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615239297598278e-05, + "loss": 3.6278, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614400702847226e-05, + "loss": 3.6046, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613562108096174e-05, + "loss": 3.6067, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612723513345122e-05, + "loss": 3.6022, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.61188491859407e-05, + "loss": 3.6142, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6110463238430184e-05, + "loss": 3.6078, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610207729091966e-05, + "loss": 3.6125, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609369134340914e-05, + "loss": 3.6201, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608530539589862e-05, + "loss": 3.6212, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607693582719183e-05, + "loss": 3.6167, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6068549879681306e-05, + "loss": 3.6095, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.6060163932170786e-05, + "loss": 3.6113, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051777984660266e-05, + "loss": 3.6146, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.6043408415953475e-05, + "loss": 3.6117, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6035022468442955e-05, + "loss": 3.5992, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6026636520932435e-05, + "loss": 3.6152, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601825057342192e-05, + "loss": 3.6125, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.60098646259114e-05, + "loss": 3.5967, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600149505720461e-05, + "loss": 3.6074, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599310910969409e-05, + "loss": 3.6168, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598472316218357e-05, + "loss": 3.612, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597633721467305e-05, + "loss": 3.6217, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596796764596626e-05, + "loss": 3.6098, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595958169845574e-05, + "loss": 3.6067, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595119575094522e-05, + "loss": 3.63, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.59428098034347e-05, + "loss": 3.5923, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593442385592418e-05, + "loss": 3.602, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592605428721739e-05, + "loss": 3.6067, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.5917668339706876e-05, + "loss": 3.6015, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5909282392196356e-05, + "loss": 3.6043, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5900896444685836e-05, + "loss": 3.6149, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892526875979045e-05, + "loss": 3.6072, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5884140928468525e-05, + "loss": 3.6084, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5875754980958005e-05, + "loss": 3.6015, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5867369033447485e-05, + "loss": 3.6134, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858983085936965e-05, + "loss": 3.6117, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5850613517230174e-05, + "loss": 3.5875, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5842227569719654e-05, + "loss": 3.6122, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.5833841622209134e-05, + "loss": 3.6123, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.5825455674698614e-05, + "loss": 3.6146, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581708610599183e-05, + "loss": 3.6052, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580870015848131e-05, + "loss": 3.6034, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580031421097079e-05, + "loss": 3.5999, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579192826346027e-05, + "loss": 3.5993, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578355869475348e-05, + "loss": 3.6132, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577517274724296e-05, + "loss": 3.5964, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576678679973244e-05, + "loss": 3.6097, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575840085222192e-05, + "loss": 3.6048, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.575003128351513e-05, + "loss": 3.6014, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574164533600461e-05, + "loss": 3.6016, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573325938849409e-05, + "loss": 3.6026, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572487344098357e-05, + "loss": 3.6017, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571648749347305e-05, + "loss": 3.5941, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570811792476626e-05, + "loss": 3.6184, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569973197725574e-05, + "loss": 3.5994, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569134602974522e-05, + "loss": 3.5983, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.56829600822347e-05, + "loss": 3.5903, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567459051352791e-05, + "loss": 3.6022, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566620456601739e-05, + "loss": 3.6072, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565781861850687e-05, + "loss": 3.6086, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564943267099635e-05, + "loss": 3.6044, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564106310228956e-05, + "loss": 3.6042, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563267715477904e-05, + "loss": 3.6191, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562429120726852e-05, + "loss": 3.5968, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5615905259758e-05, + "loss": 3.619, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560753569105122e-05, + "loss": 3.6008, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.55991497435407e-05, + "loss": 3.5993, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5590763796030177e-05, + "loss": 3.6085, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5582377848519657e-05, + "loss": 3.6002, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5574008279812866e-05, + "loss": 3.6122, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.5565622332302346e-05, + "loss": 3.6181, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5557236384791826e-05, + "loss": 3.5993, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.5548850437281306e-05, + "loss": 3.5879, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.5540464489770785e-05, + "loss": 3.5998, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.5532094921063995e-05, + "loss": 3.6067, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5523708973553475e-05, + "loss": 3.5988, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5515323026042954e-05, + "loss": 3.6058, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.5506937078532434e-05, + "loss": 3.6045, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549856750982565e-05, + "loss": 3.6036, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549018156231513e-05, + "loss": 3.5958, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548179561480461e-05, + "loss": 3.5879, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473409667294083e-05, + "loss": 3.5976, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.54650400985873e-05, + "loss": 3.6015, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545665415107678e-05, + "loss": 3.616, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544826820356626e-05, + "loss": 3.5884, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543988225605573e-05, + "loss": 3.5966, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543151268734895e-05, + "loss": 3.6055, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542312673983843e-05, + "loss": 3.6017, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541474079232791e-05, + "loss": 3.6055, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540635484481739e-05, + "loss": 3.6015, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539796889730687e-05, + "loss": 3.603, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538958294979635e-05, + "loss": 3.5972, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538121338108956e-05, + "loss": 3.5978, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537282743357904e-05, + "loss": 3.5929, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536444148606852e-05, + "loss": 3.6009, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.5356055538558e-05, + "loss": 3.6051, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.5347685969851206e-05, + "loss": 3.5923, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.5339300022340686e-05, + "loss": 3.5957, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5330914074830166e-05, + "loss": 3.5885, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.5322528127319646e-05, + "loss": 3.5983, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531415855861286e-05, + "loss": 3.6031, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530577261110234e-05, + "loss": 3.6022, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529738666359182e-05, + "loss": 3.5988, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.52890007160813e-05, + "loss": 3.6086, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528063114737451e-05, + "loss": 3.6067, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527224519986399e-05, + "loss": 3.6069, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526385925235347e-05, + "loss": 3.6047, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525547330484295e-05, + "loss": 3.5974, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524710373613616e-05, + "loss": 3.5998, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523871778862564e-05, + "loss": 3.5891, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523033184111512e-05, + "loss": 3.5943, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.52219458936046e-05, + "loss": 3.6014, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521355994609408e-05, + "loss": 3.602, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.5205190377387295e-05, + "loss": 3.5999, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5196804429876775e-05, + "loss": 3.5984, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.5188418482366255e-05, + "loss": 3.6022, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.5180032534855735e-05, + "loss": 3.5946, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.5171662966148944e-05, + "loss": 3.6027, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5163277018638424e-05, + "loss": 3.5998, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5154891071127904e-05, + "loss": 3.5985, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5146505123617384e-05, + "loss": 3.5738, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513813555491059e-05, + "loss": 3.6084, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512974960740007e-05, + "loss": 3.5944, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512136365988955e-05, + "loss": 3.6106, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511297771237903e-05, + "loss": 3.5984, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510460814367225e-05, + "loss": 3.5964, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509622219616173e-05, + "loss": 3.6032, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508783624865121e-05, + "loss": 3.6125, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507945030114069e-05, + "loss": 3.5912, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507106435363017e-05, + "loss": 3.6012, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506269478492338e-05, + "loss": 3.5955, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505430883741286e-05, + "loss": 3.6038, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504592288990234e-05, + "loss": 3.6009, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503753694239182e-05, + "loss": 3.598, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502916737368503e-05, + "loss": 3.5976, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502078142617451e-05, + "loss": 3.6075, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501239547866399e-05, + "loss": 3.5995, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.8636131286621094, + "eval_runtime": 303.3801, + "eval_samples_per_second": 1257.799, + "eval_steps_per_second": 39.307, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500400953115347e-05, + "loss": 3.6011, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.4995623583642954e-05, + "loss": 3.5936, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.4987237636132434e-05, + "loss": 3.5921, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.4978851688621913e-05, + "loss": 3.6037, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970465741111393e-05, + "loss": 3.6019, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.49620961724046e-05, + "loss": 3.5993, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495371022489408e-05, + "loss": 3.5959, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494532427738356e-05, + "loss": 3.5873, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493693832987304e-05, + "loss": 3.5911, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492856876116625e-05, + "loss": 3.6088, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.492018281365573e-05, + "loss": 3.5956, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491179686614521e-05, + "loss": 3.5939, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490341091863469e-05, + "loss": 3.6128, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.48950413499279e-05, + "loss": 3.586, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488665540241739e-05, + "loss": 3.5856, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487826945490687e-05, + "loss": 3.5862, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486988350739634e-05, + "loss": 3.5933, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486149755988582e-05, + "loss": 3.5865, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.4853127991179036e-05, + "loss": 3.5943, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.4844742043668516e-05, + "loss": 3.6019, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483635609615799e-05, + "loss": 3.6007, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482797014864747e-05, + "loss": 3.5997, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.4819600579940685e-05, + "loss": 3.5859, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481121463243016e-05, + "loss": 3.5911, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.4802828684919645e-05, + "loss": 3.6, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4794442737409125e-05, + "loss": 3.5906, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4786056789898605e-05, + "loss": 3.5804, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4777687221191814e-05, + "loss": 3.5923, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4769301273681294e-05, + "loss": 3.595, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760915326170774e-05, + "loss": 3.5774, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4752529378660254e-05, + "loss": 3.5901, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474415980995346e-05, + "loss": 3.5919, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473577386244294e-05, + "loss": 3.5976, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472738791493242e-05, + "loss": 3.599, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.47190019674219e-05, + "loss": 3.591, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471063239871511e-05, + "loss": 3.5918, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470224645120459e-05, + "loss": 3.6062, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469386050369408e-05, + "loss": 3.5758, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468547455618356e-05, + "loss": 3.5818, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467710498747677e-05, + "loss": 3.5915, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466871903996625e-05, + "loss": 3.5791, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466033309245573e-05, + "loss": 3.588, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465194714494521e-05, + "loss": 3.5919, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464357757623842e-05, + "loss": 3.5881, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.46351916287279e-05, + "loss": 3.5886, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4626805681217377e-05, + "loss": 3.5858, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4618419733706857e-05, + "loss": 3.5913, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4610050165000066e-05, + "loss": 3.5992, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4601664217489546e-05, + "loss": 3.5656, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459329464878276e-05, + "loss": 3.5898, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458490870127224e-05, + "loss": 3.5971, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457652275376172e-05, + "loss": 3.5972, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.45681368062512e-05, + "loss": 3.5899, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455975085874068e-05, + "loss": 3.581, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455136491123016e-05, + "loss": 3.5835, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454297896371964e-05, + "loss": 3.5771, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453459301620912e-05, + "loss": 3.594, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.45262070686986e-05, + "loss": 3.5783, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451783749999181e-05, + "loss": 3.594, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450945155248129e-05, + "loss": 3.5823, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450106560497077e-05, + "loss": 3.584, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449267965746025e-05, + "loss": 3.5803, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.4484310088753466e-05, + "loss": 3.5858, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.4475924141242946e-05, + "loss": 3.5829, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.4467538193732426e-05, + "loss": 3.577, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4459152246221906e-05, + "loss": 3.5975, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4450782677515115e-05, + "loss": 3.5857, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.4442396730004595e-05, + "loss": 3.5779, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.4434010782494075e-05, + "loss": 3.5682, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.4425624834983555e-05, + "loss": 3.5894, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4417255266276764e-05, + "loss": 3.5853, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4408869318766244e-05, + "loss": 3.5943, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4400483371255724e-05, + "loss": 3.5834, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4392097423745204e-05, + "loss": 3.5894, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438372785503842e-05, + "loss": 3.5977, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.43753419075279e-05, + "loss": 3.5817, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436695596001738e-05, + "loss": 3.5975, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435857001250686e-05, + "loss": 3.5859, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435020044380007e-05, + "loss": 3.5802, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434181449628955e-05, + "loss": 3.5904, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433342854877903e-05, + "loss": 3.5839, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432504260126851e-05, + "loss": 3.5862, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431667303256172e-05, + "loss": 3.602, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.43082870850512e-05, + "loss": 3.5833, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429990113754068e-05, + "loss": 3.5705, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429151519003016e-05, + "loss": 3.5813, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428314562132337e-05, + "loss": 3.5853, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427475967381285e-05, + "loss": 3.5865, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426637372630233e-05, + "loss": 3.5853, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425798777879181e-05, + "loss": 3.5879, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424961821008502e-05, + "loss": 3.5875, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.42412322625745e-05, + "loss": 3.5765, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423284631506398e-05, + "loss": 3.5685, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422446036755346e-05, + "loss": 3.5808, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421609079884667e-05, + "loss": 3.5818, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420770485133615e-05, + "loss": 3.5991, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419931890382563e-05, + "loss": 3.5713, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419093295631511e-05, + "loss": 3.5765, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418256338760833e-05, + "loss": 3.5865, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417417744009781e-05, + "loss": 3.5857, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416579149258729e-05, + "loss": 3.5887, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415740554507677e-05, + "loss": 3.5831, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4149035976369976e-05, + "loss": 3.5793, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4140650028859456e-05, + "loss": 3.5828, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4132264081348936e-05, + "loss": 3.5781, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4123878133838416e-05, + "loss": 3.5752, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411549218632789e-05, + "loss": 3.5838, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4107122617621105e-05, + "loss": 3.5879, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.4098736670110585e-05, + "loss": 3.5753, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4090350722600065e-05, + "loss": 3.5757, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408198115389328e-05, + "loss": 3.5752, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407359520638276e-05, + "loss": 3.5799, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406520925887224e-05, + "loss": 3.5842, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4056823311361714e-05, + "loss": 3.5829, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404845374265493e-05, + "loss": 3.5792, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.404006779514441e-05, + "loss": 3.5881, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403168184763389e-05, + "loss": 3.5935, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402329590012336e-05, + "loss": 3.5847, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401492633141658e-05, + "loss": 3.5898, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400654038390606e-05, + "loss": 3.5828, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399815443639554e-05, + "loss": 3.5778, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398976848888502e-05, + "loss": 3.5712, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.3981398920178234e-05, + "loss": 3.5789, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.3973012972667714e-05, + "loss": 3.5816, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396462702515719e-05, + "loss": 3.5831, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395624107764667e-05, + "loss": 3.586, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394785513013615e-05, + "loss": 3.579, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393948556142936e-05, + "loss": 3.5825, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3931099613918836e-05, + "loss": 3.576, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3922713666408316e-05, + "loss": 3.5874, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3914327718897796e-05, + "loss": 3.58, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390595815019101e-05, + "loss": 3.5839, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897572202680485e-05, + "loss": 3.5569, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388918625516997e-05, + "loss": 3.5863, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388080030765945e-05, + "loss": 3.5814, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387243073895266e-05, + "loss": 3.5905, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386404479144214e-05, + "loss": 3.5815, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385565884393162e-05, + "loss": 3.5753, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.38472728964211e-05, + "loss": 3.587, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383890332771431e-05, + "loss": 3.5982, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383051738020379e-05, + "loss": 3.5723, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382213143269327e-05, + "loss": 3.5852, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381374548518275e-05, + "loss": 3.5792, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380537591647596e-05, + "loss": 3.5861, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379698996896544e-05, + "loss": 3.5841, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788604021454926e-05, + "loss": 3.579, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3780218073944406e-05, + "loss": 3.5806, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3771848505237615e-05, + "loss": 3.5874, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3763462557727095e-05, + "loss": 3.5856, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.864362955093384, + "eval_runtime": 303.6267, + "eval_samples_per_second": 1256.777, + "eval_steps_per_second": 39.275, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.3755076610216575e-05, + "loss": 3.5726, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.3746690662706055e-05, + "loss": 3.5789, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.3738321093999264e-05, + "loss": 3.5744, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.3729935146488744e-05, + "loss": 3.5873, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3721549198978224e-05, + "loss": 3.5877, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.3713163251467704e-05, + "loss": 3.5762, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370479368276091e-05, + "loss": 3.579, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369640773525039e-05, + "loss": 3.5695, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368802178773988e-05, + "loss": 3.5767, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367963584022936e-05, + "loss": 3.5873, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367126627152257e-05, + "loss": 3.5756, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366288032401205e-05, + "loss": 3.5806, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365451075530526e-05, + "loss": 3.5911, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364612480779474e-05, + "loss": 3.5704, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363773886028422e-05, + "loss": 3.5684, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.36293529127737e-05, + "loss": 3.5677, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362096696526318e-05, + "loss": 3.5777, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361258101775266e-05, + "loss": 3.5696, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360419507024214e-05, + "loss": 3.5753, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359580912273162e-05, + "loss": 3.5821, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.35874231752211e-05, + "loss": 3.5853, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357905360651431e-05, + "loss": 3.5793, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357066765900379e-05, + "loss": 3.5716, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356228171149327e-05, + "loss": 3.5713, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355389576398275e-05, + "loss": 3.5866, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354552619527596e-05, + "loss": 3.5731, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353714024776544e-05, + "loss": 3.5629, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352875430025492e-05, + "loss": 3.5776, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.35203683527444e-05, + "loss": 3.5707, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351199878403761e-05, + "loss": 3.5637, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350361283652709e-05, + "loss": 3.5724, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349522688901657e-05, + "loss": 3.5742, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348684094150605e-05, + "loss": 3.5793, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347847137279927e-05, + "loss": 3.5817, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.347008542528875e-05, + "loss": 3.5755, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346169947777823e-05, + "loss": 3.5736, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3453313530267707e-05, + "loss": 3.5891, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3444943961560916e-05, + "loss": 3.5605, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.3436558014050396e-05, + "loss": 3.5663, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.3428172066539876e-05, + "loss": 3.5707, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.3419786119029356e-05, + "loss": 3.5571, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.3411416550322565e-05, + "loss": 3.5727, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.3403030602812045e-05, + "loss": 3.5756, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.3394644655301525e-05, + "loss": 3.5718, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.3386258707791004e-05, + "loss": 3.57, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.3377872760280484e-05, + "loss": 3.5722, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.33695031915737e-05, + "loss": 3.5736, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336111724406318e-05, + "loss": 3.5803, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335273129655266e-05, + "loss": 3.5492, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334436172784587e-05, + "loss": 3.5669, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333597578033535e-05, + "loss": 3.5819, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332758983282483e-05, + "loss": 3.5797, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331920388531431e-05, + "loss": 3.5717, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331081793780379e-05, + "loss": 3.5618, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330243199029326e-05, + "loss": 3.5659, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329404604278274e-05, + "loss": 3.5599, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328566009527222e-05, + "loss": 3.5779, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327727414776171e-05, + "loss": 3.5624, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326890457905492e-05, + "loss": 3.5731, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.32605186315444e-05, + "loss": 3.5655, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325213268403388e-05, + "loss": 3.5691, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324374673652336e-05, + "loss": 3.5638, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323537716781657e-05, + "loss": 3.5713, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322699122030605e-05, + "loss": 3.5633, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321860527279553e-05, + "loss": 3.5566, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.321021932528501e-05, + "loss": 3.5797, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.3201849756578216e-05, + "loss": 3.5726, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.3193463809067696e-05, + "loss": 3.5583, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.3185077861557176e-05, + "loss": 3.5542, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.3176691914046656e-05, + "loss": 3.5685, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316832234533987e-05, + "loss": 3.5675, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315993639782935e-05, + "loss": 3.5804, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315155045031883e-05, + "loss": 3.5652, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314316450280831e-05, + "loss": 3.571, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313477855529779e-05, + "loss": 3.58, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.3126408986591e-05, + "loss": 3.5618, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311802303908048e-05, + "loss": 3.5772, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310963709156996e-05, + "loss": 3.5753, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310125114405944e-05, + "loss": 3.5647, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309288157535265e-05, + "loss": 3.5693, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308449562784213e-05, + "loss": 3.5658, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307610968033161e-05, + "loss": 3.5747, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3067723732821096e-05, + "loss": 3.5841, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.3059354164114305e-05, + "loss": 3.5651, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3050968216603785e-05, + "loss": 3.5532, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3042582269093265e-05, + "loss": 3.5645, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.3034196321582745e-05, + "loss": 3.5683, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.3025826752875954e-05, + "loss": 3.5704, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.3017440805365434e-05, + "loss": 3.5706, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.3009054857854914e-05, + "loss": 3.566, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.3000668910344394e-05, + "loss": 3.5727, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.29922993416376e-05, + "loss": 3.5574, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298391339412708e-05, + "loss": 3.5522, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297552744661656e-05, + "loss": 3.5632, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296714149910605e-05, + "loss": 3.563, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295877193039926e-05, + "loss": 3.5764, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295038598288874e-05, + "loss": 3.5621, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294200003537822e-05, + "loss": 3.5575, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.29336140878677e-05, + "loss": 3.5713, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292524451916091e-05, + "loss": 3.5647, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291685857165039e-05, + "loss": 3.5722, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290847262413987e-05, + "loss": 3.5695, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.290008667662935e-05, + "loss": 3.5631, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289171710792256e-05, + "loss": 3.5648, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288333116041204e-05, + "loss": 3.5675, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287494521290152e-05, + "loss": 3.5573, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.2866559265391004e-05, + "loss": 3.5633, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285818969668421e-05, + "loss": 3.5712, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284980374917369e-05, + "loss": 3.5601, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284141780166317e-05, + "loss": 3.5569, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283303185415265e-05, + "loss": 3.5576, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282466228544586e-05, + "loss": 3.5621, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281627633793534e-05, + "loss": 3.5695, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280789039042482e-05, + "loss": 3.5656, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.27995044429143e-05, + "loss": 3.5613, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279113487420751e-05, + "loss": 3.5735, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278274892669699e-05, + "loss": 3.5724, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277436297918647e-05, + "loss": 3.5684, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276597703167596e-05, + "loss": 3.5748, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.2757607462969166e-05, + "loss": 3.5641, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2749221515458646e-05, + "loss": 3.5618, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.2740835567948126e-05, + "loss": 3.5536, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.2732449620437606e-05, + "loss": 3.5631, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2724080051730815e-05, + "loss": 3.5575, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.2715694104220295e-05, + "loss": 3.5682, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2707308156709775e-05, + "loss": 3.5714, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.2698922209199255e-05, + "loss": 3.5647, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.2690552640492464e-05, + "loss": 3.5633, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.2682166692981944e-05, + "loss": 3.5588, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2673780745471424e-05, + "loss": 3.572, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266539479796091e-05, + "loss": 3.5664, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265702522925412e-05, + "loss": 3.565, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.26486392817436e-05, + "loss": 3.5402, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.264025333423308e-05, + "loss": 3.5658, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263186738672256e-05, + "loss": 3.5665, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262349781801577e-05, + "loss": 3.5729, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261511187050525e-05, + "loss": 3.5652, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260672592299473e-05, + "loss": 3.5581, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259833997548421e-05, + "loss": 3.5658, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258997040677742e-05, + "loss": 3.5814, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.25815844592669e-05, + "loss": 3.5571, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257319851175638e-05, + "loss": 3.5679, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.2564812564245865e-05, + "loss": 3.5632, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.2556442995539074e-05, + "loss": 3.5666, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.2548057048028554e-05, + "loss": 3.567, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.2539671100518034e-05, + "loss": 3.5668, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.2531285153007514e-05, + "loss": 3.5609, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252291558430072e-05, + "loss": 3.5735, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.25145296367902e-05, + "loss": 3.5649, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.8664543628692627, + "eval_runtime": 307.9813, + "eval_samples_per_second": 1239.007, + "eval_steps_per_second": 38.72, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250614368927968e-05, + "loss": 3.5659, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249775774176916e-05, + "loss": 3.5619, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248937179425864e-05, + "loss": 3.5552, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2480985846748116e-05, + "loss": 3.5704, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247261627804133e-05, + "loss": 3.5688, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246423033053081e-05, + "loss": 3.5668, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245584438302029e-05, + "loss": 3.5589, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244745843550977e-05, + "loss": 3.5519, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243908886680299e-05, + "loss": 3.559, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243070291929247e-05, + "loss": 3.5729, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242231697178194e-05, + "loss": 3.558, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241393102427142e-05, + "loss": 3.5613, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.2405561455564636e-05, + "loss": 3.5746, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.2397175508054116e-05, + "loss": 3.556, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238878956054359e-05, + "loss": 3.5537, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238040361303307e-05, + "loss": 3.5495, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237201766552255e-05, + "loss": 3.5579, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.2363648096815765e-05, + "loss": 3.553, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2355262149305245e-05, + "loss": 3.5588, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2346876201794725e-05, + "loss": 3.5649, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338490254284205e-05, + "loss": 3.5748, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2330120685577414e-05, + "loss": 3.5619, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321734738066894e-05, + "loss": 3.557, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2313348790556374e-05, + "loss": 3.5563, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2304962843045854e-05, + "loss": 3.5637, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229659327433906e-05, + "loss": 3.56, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228820732682854e-05, + "loss": 3.5481, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227982137931802e-05, + "loss": 3.5581, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.22714354318075e-05, + "loss": 3.5546, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226306586310072e-05, + "loss": 3.5493, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.22546799155902e-05, + "loss": 3.5509, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224629396807968e-05, + "loss": 3.5623, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223790802056916e-05, + "loss": 3.558, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222953845186237e-05, + "loss": 3.5663, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222115250435185e-05, + "loss": 3.5602, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221276655684133e-05, + "loss": 3.5564, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220438060933081e-05, + "loss": 3.567, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219601104062402e-05, + "loss": 3.5491, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.21876250931135e-05, + "loss": 3.5541, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217923914560298e-05, + "loss": 3.5503, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.217085319809246e-05, + "loss": 3.5422, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216248362938567e-05, + "loss": 3.5556, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215409768187515e-05, + "loss": 3.56, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214571173436463e-05, + "loss": 3.5532, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213732578685411e-05, + "loss": 3.555, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212893983934359e-05, + "loss": 3.555, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.21205702706368e-05, + "loss": 3.5607, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211218432312628e-05, + "loss": 3.5579, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210379837561576e-05, + "loss": 3.5375, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209542880690897e-05, + "loss": 3.5503, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208704285939845e-05, + "loss": 3.5643, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207865691188793e-05, + "loss": 3.5639, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207027096437741e-05, + "loss": 3.555, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.20618850168669e-05, + "loss": 3.5445, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205349906935638e-05, + "loss": 3.5528, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204511312184586e-05, + "loss": 3.5462, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203672717433534e-05, + "loss": 3.5569, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202834122682482e-05, + "loss": 3.5463, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.2019971658118026e-05, + "loss": 3.5591, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.2011585710607506e-05, + "loss": 3.5538, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.2003199763096986e-05, + "loss": 3.5499, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1994813815586466e-05, + "loss": 3.5441, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.1986444246879675e-05, + "loss": 3.5572, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.1978058299369155e-05, + "loss": 3.5452, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.1969672351858635e-05, + "loss": 3.5447, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.1961286404348115e-05, + "loss": 3.5595, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195291683564133e-05, + "loss": 3.5565, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194453088813081e-05, + "loss": 3.5454, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193614494062029e-05, + "loss": 3.5367, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192775899310977e-05, + "loss": 3.5513, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191938942440298e-05, + "loss": 3.5525, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191100347689246e-05, + "loss": 3.5615, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190261752938194e-05, + "loss": 3.5502, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189423158187142e-05, + "loss": 3.5582, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188586201316463e-05, + "loss": 3.5588, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187747606565411e-05, + "loss": 3.5512, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186909011814359e-05, + "loss": 3.5582, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186070417063307e-05, + "loss": 3.554, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1852334601926284e-05, + "loss": 3.5555, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1843948654415764e-05, + "loss": 3.5522, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1835562706905244e-05, + "loss": 3.5521, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1827176759394724e-05, + "loss": 3.5554, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181880719068793e-05, + "loss": 3.5668, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.181042124317741e-05, + "loss": 3.5497, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180203529566689e-05, + "loss": 3.5377, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1793649348156366e-05, + "loss": 3.5505, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178527977944958e-05, + "loss": 3.5515, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177689383193906e-05, + "loss": 3.5552, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176850788442854e-05, + "loss": 3.5566, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.176012193691802e-05, + "loss": 3.5499, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175175236821124e-05, + "loss": 3.5546, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174336642070072e-05, + "loss": 3.5409, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173498047319019e-05, + "loss": 3.5384, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172659452567967e-05, + "loss": 3.5449, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171822495697289e-05, + "loss": 3.5471, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170983900946237e-05, + "loss": 3.5608, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170145306195184e-05, + "loss": 3.5474, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169306711444132e-05, + "loss": 3.5396, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1684697545734536e-05, + "loss": 3.5594, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1676311598224016e-05, + "loss": 3.5514, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.1667925650713496e-05, + "loss": 3.5579, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.1659539703202976e-05, + "loss": 3.552, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165117013449619e-05, + "loss": 3.544, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1642784186985665e-05, + "loss": 3.5515, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1634398239475145e-05, + "loss": 3.5534, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1626012291964625e-05, + "loss": 3.5369, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161764272325784e-05, + "loss": 3.55, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1609256775747314e-05, + "loss": 3.5526, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.1600870828236794e-05, + "loss": 3.545, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1592484880726274e-05, + "loss": 3.5411, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158411531201949e-05, + "loss": 3.5467, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157572936450896e-05, + "loss": 3.5434, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156734341699845e-05, + "loss": 3.5522, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155895746948793e-05, + "loss": 3.5515, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155058790078114e-05, + "loss": 3.5466, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154220195327062e-05, + "loss": 3.5574, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.15338160057601e-05, + "loss": 3.5593, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152543005824958e-05, + "loss": 3.5522, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151706048954279e-05, + "loss": 3.5562, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150867454203227e-05, + "loss": 3.5502, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150028859452175e-05, + "loss": 3.5481, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149190264701123e-05, + "loss": 3.5366, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1483533078304436e-05, + "loss": 3.5489, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.1475147130793916e-05, + "loss": 3.545, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1466761183283396e-05, + "loss": 3.5534, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145837523577288e-05, + "loss": 3.5516, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.145000566706609e-05, + "loss": 3.5521, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144161971955557e-05, + "loss": 3.5459, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143323377204505e-05, + "loss": 3.5426, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142484782453453e-05, + "loss": 3.5571, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141647825582774e-05, + "loss": 3.554, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140809230831722e-05, + "loss": 3.5501, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.13997063608067e-05, + "loss": 3.5253, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139132041329618e-05, + "loss": 3.5469, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138295084458939e-05, + "loss": 3.5521, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137456489707887e-05, + "loss": 3.5583, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136617894956835e-05, + "loss": 3.5487, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135779300205784e-05, + "loss": 3.5401, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1349423433351046e-05, + "loss": 3.551, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.1341037485840526e-05, + "loss": 3.5643, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.1332651538330006e-05, + "loss": 3.5467, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1324265590819486e-05, + "loss": 3.5496, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1315896022112695e-05, + "loss": 3.5467, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1307510074602175e-05, + "loss": 3.552, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1299124127091655e-05, + "loss": 3.5498, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290738179581135e-05, + "loss": 3.5494, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1282368610874344e-05, + "loss": 3.5416, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1273982663363824e-05, + "loss": 3.5625, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1265596715853304e-05, + "loss": 3.5473, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8657422065734863, + "eval_runtime": 440.7489, + "eval_samples_per_second": 865.779, + "eval_steps_per_second": 27.056, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125721076834279e-05, + "loss": 3.5435, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1248841199636e-05, + "loss": 3.5467, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124045525212548e-05, + "loss": 3.5384, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123206930461496e-05, + "loss": 3.5559, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122368335710444e-05, + "loss": 3.5537, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121531378839765e-05, + "loss": 3.5551, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120692784088713e-05, + "loss": 3.5418, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119854189337661e-05, + "loss": 3.536, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.119015594586609e-05, + "loss": 3.5391, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.11817863771593e-05, + "loss": 3.5638, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117340042964878e-05, + "loss": 3.542, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116501448213826e-05, + "loss": 3.5461, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.1156628534627744e-05, + "loss": 3.5554, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114825896592095e-05, + "loss": 3.5462, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113987301841043e-05, + "loss": 3.5355, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113148707089991e-05, + "loss": 3.5391, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112310112338939e-05, + "loss": 3.537, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.11147315546826e-05, + "loss": 3.539, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110634560717208e-05, + "loss": 3.5451, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109795965966156e-05, + "loss": 3.5486, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108957371215104e-05, + "loss": 3.5602, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108120414344425e-05, + "loss": 3.5479, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107281819593373e-05, + "loss": 3.5433, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106443224842321e-05, + "loss": 3.5404, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.10560463009127e-05, + "loss": 3.5498, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104767673220591e-05, + "loss": 3.54, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103929078469539e-05, + "loss": 3.5348, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103090483718487e-05, + "loss": 3.5404, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102251888967435e-05, + "loss": 3.5433, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.1014149320967556e-05, + "loss": 3.5313, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.1005763373457036e-05, + "loss": 3.5335, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.0997377425946516e-05, + "loss": 3.5497, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.0988991478435996e-05, + "loss": 3.5439, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0980621909729205e-05, + "loss": 3.5474, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0972235962218685e-05, + "loss": 3.5507, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0963850014708165e-05, + "loss": 3.5422, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095546406719765e-05, + "loss": 3.549, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094709449849086e-05, + "loss": 3.5345, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093870855098034e-05, + "loss": 3.5369, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.093032260346982e-05, + "loss": 3.5337, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.09219366559593e-05, + "loss": 3.5336, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091356708725251e-05, + "loss": 3.5349, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090518113974199e-05, + "loss": 3.5498, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089679519223147e-05, + "loss": 3.5333, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088840924472095e-05, + "loss": 3.5427, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.088002329721043e-05, + "loss": 3.5379, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087165372850364e-05, + "loss": 3.5439, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086326778099312e-05, + "loss": 3.5444, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.0854881833482605e-05, + "loss": 3.5237, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.0846495885972085e-05, + "loss": 3.5344, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.0838126317265294e-05, + "loss": 3.5469, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.0829740369754774e-05, + "loss": 3.5498, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.0821354422244254e-05, + "loss": 3.5377, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.0812968474733734e-05, + "loss": 3.5347, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080459890602694e-05, + "loss": 3.5394, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079621295851642e-05, + "loss": 3.5293, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.07878270110059e-05, + "loss": 3.5405, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077944106349538e-05, + "loss": 3.5311, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077107149478859e-05, + "loss": 3.5451, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076268554727807e-05, + "loss": 3.5368, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075429959976755e-05, + "loss": 3.5383, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074591365225704e-05, + "loss": 3.5268, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073754408355025e-05, + "loss": 3.5431, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072915813603973e-05, + "loss": 3.527, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072077218852921e-05, + "loss": 3.534, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071238624101869e-05, + "loss": 3.5422, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.07040166723119e-05, + "loss": 3.5448, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069563072480138e-05, + "loss": 3.5285, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068724477729086e-05, + "loss": 3.5254, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067885882978034e-05, + "loss": 3.5357, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.0670489261073546e-05, + "loss": 3.5368, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.0662103313563026e-05, + "loss": 3.5473, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.0653717366052506e-05, + "loss": 3.5328, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064533141854199e-05, + "loss": 3.5459, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.06369618498352e-05, + "loss": 3.5424, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062857590232468e-05, + "loss": 3.5384, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.062018995481416e-05, + "loss": 3.5434, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0611804007303635e-05, + "loss": 3.5401, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060343443859685e-05, + "loss": 3.5403, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059504849108633e-05, + "loss": 3.5347, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058666254357581e-05, + "loss": 3.5377, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0578276596065284e-05, + "loss": 3.5401, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.05699070273585e-05, + "loss": 3.5526, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056152107984798e-05, + "loss": 3.5338, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055313513233746e-05, + "loss": 3.5304, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054474918482694e-05, + "loss": 3.5271, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0536379616120155e-05, + "loss": 3.537, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0527993668609635e-05, + "loss": 3.536, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051960772109911e-05, + "loss": 3.5431, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0511221773588588e-05, + "loss": 3.5342, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502852204881804e-05, + "loss": 3.5398, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494466257371284e-05, + "loss": 3.5268, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.048608030986076e-05, + "loss": 3.5251, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.047769436235024e-05, + "loss": 3.5263, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469324793643456e-05, + "loss": 3.5314, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460938846132936e-05, + "loss": 3.5451, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.045255289862241e-05, + "loss": 3.5398, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.044416695111189e-05, + "loss": 3.5255, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435797382405105e-05, + "loss": 3.5399, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427411434894582e-05, + "loss": 3.5383, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0419025487384062e-05, + "loss": 3.5399, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410639539873542e-05, + "loss": 3.5376, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0402269971166758e-05, + "loss": 3.5292, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393884023656234e-05, + "loss": 3.5355, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0385498076145714e-05, + "loss": 3.54, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0377112128635194e-05, + "loss": 3.521, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368742559928403e-05, + "loss": 3.5319, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360356612417883e-05, + "loss": 3.5407, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0351970664907363e-05, + "loss": 3.527, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0343584717396843e-05, + "loss": 3.5267, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0335215148690056e-05, + "loss": 3.533, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326829201179536e-05, + "loss": 3.5274, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318443253669016e-05, + "loss": 3.5407, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0310057306158496e-05, + "loss": 3.5349, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301687737451705e-05, + "loss": 3.5273, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293301789941188e-05, + "loss": 3.5457, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284915842430668e-05, + "loss": 3.5437, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276529894920148e-05, + "loss": 3.537, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0268160326213357e-05, + "loss": 3.5422, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259774378702837e-05, + "loss": 3.5379, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251388431192317e-05, + "loss": 3.5316, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0243002483681797e-05, + "loss": 3.5266, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.023463291497501e-05, + "loss": 3.5278, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.022624696746449e-05, + "loss": 3.5319, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.021786101995397e-05, + "loss": 3.5373, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.020947507244345e-05, + "loss": 3.5326, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.020110550373666e-05, + "loss": 3.5413, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192719556226142e-05, + "loss": 3.5319, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018433360871562e-05, + "loss": 3.5272, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.01759476612051e-05, + "loss": 3.5394, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016757809249831e-05, + "loss": 3.5396, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015919214498779e-05, + "loss": 3.5327, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.015080619747727e-05, + "loss": 3.5149, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.014242024996675e-05, + "loss": 3.5306, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0134050681259963e-05, + "loss": 3.5384, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125664733749443e-05, + "loss": 3.5407, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117278786238923e-05, + "loss": 3.5315, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108892838728403e-05, + "loss": 3.5273, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100523270021612e-05, + "loss": 3.5382, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0092137322511092e-05, + "loss": 3.5485, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083751375000575e-05, + "loss": 3.5327, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075365427490055e-05, + "loss": 3.5357, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066995858783264e-05, + "loss": 3.5338, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058609911272744e-05, + "loss": 3.5369, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0050223963762224e-05, + "loss": 3.535, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041838016251704e-05, + "loss": 3.5419, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033468447544917e-05, + "loss": 3.527, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0025082500034397e-05, + "loss": 3.5457, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016696552523877e-05, + "loss": 3.533, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0008310605013357e-05, + "loss": 3.5272, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.8663249015808105, + "eval_runtime": 374.475, + "eval_samples_per_second": 1019.003, + "eval_steps_per_second": 31.845, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999924657502837e-05, + "loss": 3.5322, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991538709992316e-05, + "loss": 3.5257, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9983152762481796e-05, + "loss": 3.5413, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.997478319377501e-05, + "loss": 3.537, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.996639724626449e-05, + "loss": 3.543, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.995801129875397e-05, + "loss": 3.5271, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.994962535124345e-05, + "loss": 3.5216, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9941255782536658e-05, + "loss": 3.5248, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932869835026138e-05, + "loss": 3.5478, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992448388751562e-05, + "loss": 3.5323, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.99160979400051e-05, + "loss": 3.5276, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990771199249458e-05, + "loss": 3.539, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.989934242378779e-05, + "loss": 3.5326, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.989095647627727e-05, + "loss": 3.5229, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.988257052876675e-05, + "loss": 3.5268, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987418458125623e-05, + "loss": 3.52, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865815012549443e-05, + "loss": 3.5252, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9857429065038923e-05, + "loss": 3.5263, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9849043117528402e-05, + "loss": 3.5368, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840657170017882e-05, + "loss": 3.5459, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.983228760131109e-05, + "loss": 3.5319, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823901653800575e-05, + "loss": 3.5242, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815515706290055e-05, + "loss": 3.5292, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9807129758779535e-05, + "loss": 3.5369, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798760190072744e-05, + "loss": 3.5231, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790374242562224e-05, + "loss": 3.523, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9781988295051704e-05, + "loss": 3.5228, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773602347541184e-05, + "loss": 3.536, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9765232778834396e-05, + "loss": 3.5133, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756846831323876e-05, + "loss": 3.5198, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748460883813356e-05, + "loss": 3.5343, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9740074936302836e-05, + "loss": 3.5333, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731705367596045e-05, + "loss": 3.5326, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.972331942008553e-05, + "loss": 3.5367, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.971493347257501e-05, + "loss": 3.5262, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.970654752506448e-05, + "loss": 3.5339, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9698177956357698e-05, + "loss": 3.5197, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689792008847177e-05, + "loss": 3.5246, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681406061336657e-05, + "loss": 3.5188, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9673020113826134e-05, + "loss": 3.5184, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.966465054511935e-05, + "loss": 3.5222, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.965626459760883e-05, + "loss": 3.5344, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.964787865009831e-05, + "loss": 3.5205, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639492702587783e-05, + "loss": 3.5265, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9631123133881e-05, + "loss": 3.5231, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622737186370482e-05, + "loss": 3.5291, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9614351238859955e-05, + "loss": 3.5303, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605965291349435e-05, + "loss": 3.5143, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.959759572264265e-05, + "loss": 3.5153, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.958920977513213e-05, + "loss": 3.5322, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580823827621608e-05, + "loss": 3.5363, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572437880111088e-05, + "loss": 3.5214, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9564068311404304e-05, + "loss": 3.5225, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555682363893784e-05, + "loss": 3.5258, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9547296416383257e-05, + "loss": 3.5131, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538910468872737e-05, + "loss": 3.5222, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530540900165953e-05, + "loss": 3.5174, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.952215495265543e-05, + "loss": 3.5293, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.951376900514491e-05, + "loss": 3.5237, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.950538305763439e-05, + "loss": 3.5252, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9497013488927605e-05, + "loss": 3.5115, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.948862754141708e-05, + "loss": 3.5315, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.948024159390656e-05, + "loss": 3.5122, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.947185564639604e-05, + "loss": 3.5217, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463486077689257e-05, + "loss": 3.529, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.945510013017873e-05, + "loss": 3.5322, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944671418266821e-05, + "loss": 3.5119, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943832823515769e-05, + "loss": 3.5128, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9429958666450903e-05, + "loss": 3.5146, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421572718940383e-05, + "loss": 3.527, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9413186771429863e-05, + "loss": 3.5261, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404800823919343e-05, + "loss": 3.5196, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396431255212552e-05, + "loss": 3.5324, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9388045307702035e-05, + "loss": 3.534, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379659360191515e-05, + "loss": 3.5243, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9371273412680995e-05, + "loss": 3.5281, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9362903843974204e-05, + "loss": 3.5258, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9354517896463684e-05, + "loss": 3.5297, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9346131948953164e-05, + "loss": 3.5172, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337746001442644e-05, + "loss": 3.5252, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329376432735856e-05, + "loss": 3.5224, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320990485225336e-05, + "loss": 3.5393, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312604537714816e-05, + "loss": 3.5239, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9304218590204296e-05, + "loss": 3.5103, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295849021497505e-05, + "loss": 3.5159, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287463073986985e-05, + "loss": 3.5207, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.927907712647647e-05, + "loss": 3.5286, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.927069117896595e-05, + "loss": 3.5269, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262321610259158e-05, + "loss": 3.5197, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253935662748638e-05, + "loss": 3.5245, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245549715238118e-05, + "loss": 3.5145, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9237163767727598e-05, + "loss": 3.5095, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.922879419902081e-05, + "loss": 3.5105, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.922040825151029e-05, + "loss": 3.523, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.921202230399977e-05, + "loss": 3.5281, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.920363635648925e-05, + "loss": 3.5245, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.919526678778246e-05, + "loss": 3.5125, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.918688084027194e-05, + "loss": 3.5208, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178494892761422e-05, + "loss": 3.5252, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9170108945250902e-05, + "loss": 3.5257, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.916173937654411e-05, + "loss": 3.5232, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.915335342903359e-05, + "loss": 3.5179, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.914496748152307e-05, + "loss": 3.5167, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.913658153401255e-05, + "loss": 3.5271, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9128211965305764e-05, + "loss": 3.5094, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119826017795244e-05, + "loss": 3.5155, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111440070284724e-05, + "loss": 3.5282, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9103054122774204e-05, + "loss": 3.5156, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094684554067413e-05, + "loss": 3.511, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086298606556893e-05, + "loss": 3.5191, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9077912659046376e-05, + "loss": 3.5162, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069526711535856e-05, + "loss": 3.5218, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9061157142829065e-05, + "loss": 3.5206, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052771195318545e-05, + "loss": 3.516, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044385247808025e-05, + "loss": 3.5284, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035999300297505e-05, + "loss": 3.5294, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027629731590717e-05, + "loss": 3.5206, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9019243784080197e-05, + "loss": 3.5337, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010857836569677e-05, + "loss": 3.521, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002471889059157e-05, + "loss": 3.5168, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8994102320352366e-05, + "loss": 3.5123, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985716372841846e-05, + "loss": 3.5159, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.897733042533133e-05, + "loss": 3.5172, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.896894447782081e-05, + "loss": 3.522, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.896057490911402e-05, + "loss": 3.5209, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.89521889616035e-05, + "loss": 3.5251, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.894380301409298e-05, + "loss": 3.52, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.893541706658246e-05, + "loss": 3.5119, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892704749787567e-05, + "loss": 3.5237, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.891866155036515e-05, + "loss": 3.5261, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.891027560285463e-05, + "loss": 3.5174, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.890188965534411e-05, + "loss": 3.5046, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.889352008663732e-05, + "loss": 3.5136, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.88851341391268e-05, + "loss": 3.527, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876748191616283e-05, + "loss": 3.5276, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8868362244105763e-05, + "loss": 3.5133, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859992675398972e-05, + "loss": 3.5158, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851606727888452e-05, + "loss": 3.5278, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8843220780377932e-05, + "loss": 3.5289, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834834832867412e-05, + "loss": 3.5236, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826465264160625e-05, + "loss": 3.519, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8818079316650105e-05, + "loss": 3.5198, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809693369139585e-05, + "loss": 3.5228, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801307421629065e-05, + "loss": 3.5183, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792937852922274e-05, + "loss": 3.5286, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784551905411754e-05, + "loss": 3.516, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8776165957901237e-05, + "loss": 3.5307, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767780010390717e-05, + "loss": 3.5206, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759410441683926e-05, + "loss": 3.5108, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.867910385131836, + "eval_runtime": 303.6491, + "eval_samples_per_second": 1256.684, + "eval_steps_per_second": 39.272, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8751024494173406e-05, + "loss": 3.5188, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742638546662886e-05, + "loss": 3.5134, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8734252599152366e-05, + "loss": 3.5263, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.872588303044558e-05, + "loss": 3.5223, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871749708293506e-05, + "loss": 3.5283, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.870911113542454e-05, + "loss": 3.5119, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.870072518791402e-05, + "loss": 3.5105, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8692355619207227e-05, + "loss": 3.5047, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8683969671696707e-05, + "loss": 3.5361, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.867558372418619e-05, + "loss": 3.5206, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866719777667567e-05, + "loss": 3.5124, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.865882820796888e-05, + "loss": 3.5251, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.865044226045836e-05, + "loss": 3.5172, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.864205631294784e-05, + "loss": 3.5129, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.863367036543732e-05, + "loss": 3.5095, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8625300796730532e-05, + "loss": 3.5104, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8616914849220012e-05, + "loss": 3.5096, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8608528901709492e-05, + "loss": 3.512, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8600142954198972e-05, + "loss": 3.5241, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.859177338549218e-05, + "loss": 3.532, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858338743798166e-05, + "loss": 3.5176, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8575001490471144e-05, + "loss": 3.5102, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566615542960624e-05, + "loss": 3.515, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8558245974253833e-05, + "loss": 3.5211, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549860026743313e-05, + "loss": 3.5133, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541474079232793e-05, + "loss": 3.508, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8533088131722273e-05, + "loss": 3.51, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524718563015486e-05, + "loss": 3.5227, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8516332615504966e-05, + "loss": 3.4976, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8507946667994446e-05, + "loss": 3.505, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8499560720483926e-05, + "loss": 3.5205, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8491191151777135e-05, + "loss": 3.5179, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482805204266615e-05, + "loss": 3.5249, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8474419256756095e-05, + "loss": 3.5162, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8466033309245578e-05, + "loss": 3.5131, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457663740538787e-05, + "loss": 3.5228, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8449277793028267e-05, + "loss": 3.5038, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8440891845517747e-05, + "loss": 3.5129, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8432505898007224e-05, + "loss": 3.5035, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.842413632930044e-05, + "loss": 3.5067, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.841575038178992e-05, + "loss": 3.509, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.84073644342794e-05, + "loss": 3.5192, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398978486768873e-05, + "loss": 3.5136, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.839060891806209e-05, + "loss": 3.509, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.838222297055157e-05, + "loss": 3.5147, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.837383702304105e-05, + "loss": 3.518, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8365451075530525e-05, + "loss": 3.5156, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835708150682374e-05, + "loss": 3.5031, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.834869555931322e-05, + "loss": 3.5, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8340309611802694e-05, + "loss": 3.5162, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331923664292177e-05, + "loss": 3.5227, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323554095585393e-05, + "loss": 3.5108, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8315168148074873e-05, + "loss": 3.5098, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306782200564346e-05, + "loss": 3.5089, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8298396253053826e-05, + "loss": 3.5032, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8290026684347042e-05, + "loss": 3.5088, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281640736836522e-05, + "loss": 3.5043, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8273254789326e-05, + "loss": 3.5145, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.826486884181548e-05, + "loss": 3.5137, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8256499273108694e-05, + "loss": 3.5111, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8248113325598168e-05, + "loss": 3.4978, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239727378087648e-05, + "loss": 3.5196, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8231357809380863e-05, + "loss": 3.4985, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8222971861870347e-05, + "loss": 3.5073, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.821458591435982e-05, + "loss": 3.5167, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.82061999668493e-05, + "loss": 3.5171, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197830398142516e-05, + "loss": 3.4997, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8189444450631996e-05, + "loss": 3.4999, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8181058503121472e-05, + "loss": 3.5006, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172672555610952e-05, + "loss": 3.5099, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8164302986904168e-05, + "loss": 3.5144, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.815591703939364e-05, + "loss": 3.5096, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.814753109188312e-05, + "loss": 3.5159, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.81391451443726e-05, + "loss": 3.5148, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130775575665817e-05, + "loss": 3.5136, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122389628155294e-05, + "loss": 3.5057, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8114003680644774e-05, + "loss": 3.5167, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105617733134254e-05, + "loss": 3.5167, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.809724816442747e-05, + "loss": 3.4999, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8088862216916946e-05, + "loss": 3.5186, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080476269406426e-05, + "loss": 3.5056, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8072090321895906e-05, + "loss": 3.5273, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063720753189115e-05, + "loss": 3.51, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8055334805678595e-05, + "loss": 3.4915, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8046948858168075e-05, + "loss": 3.5081, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8038562910657555e-05, + "loss": 3.5023, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8030193341950767e-05, + "loss": 3.5174, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8021807394440247e-05, + "loss": 3.5108, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8013421446929727e-05, + "loss": 3.5088, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8005035499419207e-05, + "loss": 3.5107, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996665930712416e-05, + "loss": 3.5009, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.79882799832019e-05, + "loss": 3.4975, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.797989403569138e-05, + "loss": 3.4976, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.797150808818086e-05, + "loss": 3.5093, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.796313851947407e-05, + "loss": 3.5171, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.795475257196355e-05, + "loss": 3.5109, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.794636662445303e-05, + "loss": 3.4985, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.793798067694251e-05, + "loss": 3.5084, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.792961110823572e-05, + "loss": 3.5085, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.79212251607252e-05, + "loss": 3.5144, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.791283921321468e-05, + "loss": 3.5078, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.790445326570416e-05, + "loss": 3.5042, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.789608369699737e-05, + "loss": 3.507, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887697749486853e-05, + "loss": 3.5138, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7879311801976333e-05, + "loss": 3.4947, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870925854465813e-05, + "loss": 3.5078, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862556285759022e-05, + "loss": 3.5109, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7854170338248502e-05, + "loss": 3.5023, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7845784390737982e-05, + "loss": 3.4949, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7837398443227462e-05, + "loss": 3.5063, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7829028874520675e-05, + "loss": 3.5029, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820642927010155e-05, + "loss": 3.5061, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7812256979499635e-05, + "loss": 3.5092, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7803871031989115e-05, + "loss": 3.502, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795501463282324e-05, + "loss": 3.5172, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7787115515771807e-05, + "loss": 3.5176, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778729568261287e-05, + "loss": 3.5078, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7770343620750767e-05, + "loss": 3.5156, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761974052043976e-05, + "loss": 3.5105, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753588104533456e-05, + "loss": 3.5025, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7745202157022936e-05, + "loss": 3.4984, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736816209512416e-05, + "loss": 3.5008, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.772844664080563e-05, + "loss": 3.5045, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.772006069329511e-05, + "loss": 3.5121, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.771167474578459e-05, + "loss": 3.5068, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7703288798274068e-05, + "loss": 3.5093, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694919229567277e-05, + "loss": 3.5021, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.768653328205676e-05, + "loss": 3.5057, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.767814733454624e-05, + "loss": 3.5058, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.766976138703572e-05, + "loss": 3.5151, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.766139181832893e-05, + "loss": 3.5052, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.765300587081841e-05, + "loss": 3.4912, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.764461992330789e-05, + "loss": 3.4968, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7636250354601102e-05, + "loss": 3.5127, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627864407090582e-05, + "loss": 3.5119, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7619478459580062e-05, + "loss": 3.5044, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7611092512069542e-05, + "loss": 3.5008, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602706564559022e-05, + "loss": 3.5166, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.759433699585223e-05, + "loss": 3.5125, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7585951048341714e-05, + "loss": 3.5118, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577565100831194e-05, + "loss": 3.5053, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7569195532124403e-05, + "loss": 3.5044, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560809584613883e-05, + "loss": 3.5076, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7552423637103363e-05, + "loss": 3.5013, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7544037689592843e-05, + "loss": 3.5173, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535668120886056e-05, + "loss": 3.5026, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7527282173375536e-05, + "loss": 3.5158, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518896225865016e-05, + "loss": 3.5076, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510510278354496e-05, + "loss": 3.4989, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.870880365371704, + "eval_runtime": 306.9534, + "eval_samples_per_second": 1243.156, + "eval_steps_per_second": 38.85, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7502124330843976e-05, + "loss": 3.5078, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493738383333456e-05, + "loss": 3.5017, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485352435822936e-05, + "loss": 3.5086, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476966488312415e-05, + "loss": 3.5084, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468596919605628e-05, + "loss": 3.5193, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7460210972095108e-05, + "loss": 3.5003, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451825024584588e-05, + "loss": 3.4979, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443455455877797e-05, + "loss": 3.4909, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7435069508367277e-05, + "loss": 3.5223, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426683560856757e-05, + "loss": 3.5077, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.741829761334624e-05, + "loss": 3.4944, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.740991166583572e-05, + "loss": 3.517, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.740154209712893e-05, + "loss": 3.5007, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.739315614961841e-05, + "loss": 3.5007, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.738477020210789e-05, + "loss": 3.4954, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.737638425459737e-05, + "loss": 3.4975, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.736801468589058e-05, + "loss": 3.4991, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.735962873838006e-05, + "loss": 3.4942, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.735124279086954e-05, + "loss": 3.5121, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.734285684335902e-05, + "loss": 3.5163, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.733448727465223e-05, + "loss": 3.5041, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.732610132714171e-05, + "loss": 3.5004, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317715379631194e-05, + "loss": 3.5038, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7309345810924403e-05, + "loss": 3.5078, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300959863413883e-05, + "loss": 3.4997, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292573915903363e-05, + "loss": 3.4992, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7284187968392843e-05, + "loss": 3.4926, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275818399686055e-05, + "loss": 3.5098, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7267432452175535e-05, + "loss": 3.4829, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7259046504665015e-05, + "loss": 3.4953, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250660557154495e-05, + "loss": 3.5064, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7242290988447704e-05, + "loss": 3.508, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233905040937184e-05, + "loss": 3.5097, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225519093426664e-05, + "loss": 3.5055, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.721713314591614e-05, + "loss": 3.4973, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208763577209357e-05, + "loss": 3.5108, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7200377629698837e-05, + "loss": 3.4949, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191991682188317e-05, + "loss": 3.4993, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183605734677793e-05, + "loss": 3.4874, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.717523616597101e-05, + "loss": 3.4927, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.716685021846049e-05, + "loss": 3.4909, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158464270949962e-05, + "loss": 3.5086, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7150078323439442e-05, + "loss": 3.4976, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141708754732658e-05, + "loss": 3.4974, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7133322807222138e-05, + "loss": 3.5026, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124936859711614e-05, + "loss": 3.5042, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116550912201094e-05, + "loss": 3.5025, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.710818134349431e-05, + "loss": 3.4896, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.709979539598379e-05, + "loss": 3.483, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7091409448473263e-05, + "loss": 3.5082, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7083023500962747e-05, + "loss": 3.5064, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074653932255963e-05, + "loss": 3.4985, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7066267984745436e-05, + "loss": 3.4966, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057882037234916e-05, + "loss": 3.4919, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049496089724396e-05, + "loss": 3.4929, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.704112652101761e-05, + "loss": 3.4971, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032740573507088e-05, + "loss": 3.4924, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024354625996568e-05, + "loss": 3.5016, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015968678486048e-05, + "loss": 3.4995, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007599109779264e-05, + "loss": 3.4928, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6999213162268737e-05, + "loss": 3.4865, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990827214758217e-05, + "loss": 3.5067, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.69824412672477e-05, + "loss": 3.4874, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.697407169854091e-05, + "loss": 3.4968, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.696568575103039e-05, + "loss": 3.5019, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.695729980351987e-05, + "loss": 3.5049, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694891385600935e-05, + "loss": 3.4867, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940544287302562e-05, + "loss": 3.4896, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6932158339792042e-05, + "loss": 3.4834, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923772392281522e-05, + "loss": 3.4991, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6915386444771002e-05, + "loss": 3.5018, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.690701687606421e-05, + "loss": 3.4977, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.689863092855369e-05, + "loss": 3.5015, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.689024498104317e-05, + "loss": 3.5031, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881859033532654e-05, + "loss": 3.507, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873489464825863e-05, + "loss": 3.4925, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6865103517315343e-05, + "loss": 3.5038, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856717569804823e-05, + "loss": 3.507, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6848331622294303e-05, + "loss": 3.4865, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6839962053587516e-05, + "loss": 3.5033, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6831576106076996e-05, + "loss": 3.4921, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6823190158566475e-05, + "loss": 3.5146, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814804211055955e-05, + "loss": 3.4971, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6806434642349165e-05, + "loss": 3.479, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6798048694838645e-05, + "loss": 3.4921, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789662747328124e-05, + "loss": 3.4933, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6781276799817608e-05, + "loss": 3.504, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772907231110817e-05, + "loss": 3.4985, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764521283600297e-05, + "loss": 3.4955, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6756135336089777e-05, + "loss": 3.4952, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747749388579257e-05, + "loss": 3.492, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.673937981987247e-05, + "loss": 3.4875, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.673099387236195e-05, + "loss": 3.4815, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.672260792485143e-05, + "loss": 3.4967, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.671422197734091e-05, + "loss": 3.5023, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705852408634118e-05, + "loss": 3.4983, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697466461123598e-05, + "loss": 3.4873, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6689080513613078e-05, + "loss": 3.4946, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.668071094490629e-05, + "loss": 3.4933, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.667232499739577e-05, + "loss": 3.5052, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.666393904988525e-05, + "loss": 3.4934, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.665555310237473e-05, + "loss": 3.496, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664718353366794e-05, + "loss": 3.4927, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638797586157423e-05, + "loss": 3.501, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6630411638646903e-05, + "loss": 3.4804, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6622025691136383e-05, + "loss": 3.4959, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613639743625863e-05, + "loss": 3.4932, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6605270174919072e-05, + "loss": 3.4943, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596884227408552e-05, + "loss": 3.4815, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6588498279898032e-05, + "loss": 3.4926, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6580128711191244e-05, + "loss": 3.4919, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571742763680724e-05, + "loss": 3.4934, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6563356816170204e-05, + "loss": 3.4966, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554970868659684e-05, + "loss": 3.4923, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546601299952893e-05, + "loss": 3.5019, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6538215352442373e-05, + "loss": 3.5046, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529829404931857e-05, + "loss": 3.499, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521443457421336e-05, + "loss": 3.5024, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6513073888714546e-05, + "loss": 3.4971, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504687941204026e-05, + "loss": 3.488, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6496301993693506e-05, + "loss": 3.4899, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487916046182985e-05, + "loss": 3.4888, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479546477476198e-05, + "loss": 3.4894, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6471160529965678e-05, + "loss": 3.502, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462774582455158e-05, + "loss": 3.4908, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454388634944638e-05, + "loss": 3.5001, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6446019066237847e-05, + "loss": 3.4918, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437633118727327e-05, + "loss": 3.4909, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.642924717121681e-05, + "loss": 3.4902, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.642086122370629e-05, + "loss": 3.5043, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.64124916549995e-05, + "loss": 3.4903, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.640410570748898e-05, + "loss": 3.4853, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.639571975997846e-05, + "loss": 3.4802, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.638733381246794e-05, + "loss": 3.4994, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.637896424376115e-05, + "loss": 3.4986, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.637057829625063e-05, + "loss": 3.4943, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.636219234874011e-05, + "loss": 3.4889, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.635380640122959e-05, + "loss": 3.5052, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.63454368325228e-05, + "loss": 3.4973, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.633705088501228e-05, + "loss": 3.5024, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328664937501764e-05, + "loss": 3.4902, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320278989991244e-05, + "loss": 3.4923, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311909421284453e-05, + "loss": 3.4969, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303523473773933e-05, + "loss": 3.4857, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6295137526263413e-05, + "loss": 3.5029, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286751578752893e-05, + "loss": 3.4959, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6278382010046105e-05, + "loss": 3.4986, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6269996062535585e-05, + "loss": 3.4964, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6261610115025065e-05, + "loss": 3.4833, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.869953155517578, + "eval_runtime": 307.108, + "eval_samples_per_second": 1242.53, + "eval_steps_per_second": 38.83, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6253224167514545e-05, + "loss": 3.4931, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6244838220004025e-05, + "loss": 3.4906, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6236452272493505e-05, + "loss": 3.4935, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.6228066324982985e-05, + "loss": 3.4972, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6219696756276198e-05, + "loss": 3.5084, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6211310808765677e-05, + "loss": 3.4881, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6202924861255157e-05, + "loss": 3.4844, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6194538913744637e-05, + "loss": 3.4799, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6186169345037846e-05, + "loss": 3.5049, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6177783397527326e-05, + "loss": 3.4984, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.616939745001681e-05, + "loss": 3.4782, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.616101150250629e-05, + "loss": 3.5032, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152658312603228e-05, + "loss": 3.489, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6144272365092708e-05, + "loss": 3.4893, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6135886417582188e-05, + "loss": 3.4849, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.612750047007167e-05, + "loss": 3.4852, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.611911452256115e-05, + "loss": 3.4854, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.611072857505063e-05, + "loss": 3.4832, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.610234262754011e-05, + "loss": 3.4999, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.6093956680029584e-05, + "loss": 3.5018, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.60855871113228e-05, + "loss": 3.4948, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.607720116381228e-05, + "loss": 3.4878, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6068815216301763e-05, + "loss": 3.4861, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.6060429268791237e-05, + "loss": 3.4972, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6052059700084452e-05, + "loss": 3.4853, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6043673752573932e-05, + "loss": 3.489, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.603528780506341e-05, + "loss": 3.4808, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6026918236356625e-05, + "loss": 3.4951, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6018532288846105e-05, + "loss": 3.4739, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.6010146341335585e-05, + "loss": 3.4812, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.6001760393825058e-05, + "loss": 3.4955, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5993390825118274e-05, + "loss": 3.4927, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5985004877607754e-05, + "loss": 3.4945, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.5976618930097234e-05, + "loss": 3.4919, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.596823298258671e-05, + "loss": 3.4854, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5959863413879926e-05, + "loss": 3.4973, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5951477466369406e-05, + "loss": 3.4858, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.594309151885888e-05, + "loss": 3.4782, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5934705571348363e-05, + "loss": 3.4774, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.592633600264158e-05, + "loss": 3.482, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.591795005513106e-05, + "loss": 3.4782, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.590956410762053e-05, + "loss": 3.4955, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.590117816011001e-05, + "loss": 3.4852, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.5892808591403228e-05, + "loss": 3.4842, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5884422643892707e-05, + "loss": 3.4936, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5876036696382184e-05, + "loss": 3.4861, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5867650748871664e-05, + "loss": 3.4949, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.585928118016488e-05, + "loss": 3.4795, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5850895232654353e-05, + "loss": 3.4646, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5842509285143833e-05, + "loss": 3.4987, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5834123337633316e-05, + "loss": 3.4917, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.582577014773026e-05, + "loss": 3.492, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.581738420021974e-05, + "loss": 3.4826, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.580899825270922e-05, + "loss": 3.4795, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.58006123051987e-05, + "loss": 3.4807, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5792226357688178e-05, + "loss": 3.4843, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5783840410177658e-05, + "loss": 3.4824, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5775454462667138e-05, + "loss": 3.4834, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5767068515156618e-05, + "loss": 3.4927, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5758698946449827e-05, + "loss": 3.4813, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.5750312998939307e-05, + "loss": 3.4718, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5741927051428787e-05, + "loss": 3.4973, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.573354110391827e-05, + "loss": 3.4749, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.572517153521148e-05, + "loss": 3.4794, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.571678558770096e-05, + "loss": 3.4919, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.570839964019044e-05, + "loss": 3.4925, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.570001369267992e-05, + "loss": 3.4708, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.569164412397313e-05, + "loss": 3.4808, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.568325817646261e-05, + "loss": 3.4674, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.567487222895209e-05, + "loss": 3.4902, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.566648628144157e-05, + "loss": 3.4882, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.565811671273478e-05, + "loss": 3.4866, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.564973076522426e-05, + "loss": 3.488, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.564134481771374e-05, + "loss": 3.4905, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.563295887020322e-05, + "loss": 3.4972, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5624589301496433e-05, + "loss": 3.4774, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.5616203353985913e-05, + "loss": 3.4903, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5607817406475393e-05, + "loss": 3.491, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.5599431458964873e-05, + "loss": 3.473, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5591078269061818e-05, + "loss": 3.4913, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5582692321551298e-05, + "loss": 3.482, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5574306374040774e-05, + "loss": 3.4967, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5565920426530254e-05, + "loss": 3.4885, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5557534479019734e-05, + "loss": 3.4693, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5549148531509214e-05, + "loss": 3.4818, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5540762583998694e-05, + "loss": 3.4791, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5532376636488174e-05, + "loss": 3.4933, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.5524007067781386e-05, + "loss": 3.484, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5515621120270866e-05, + "loss": 3.4807, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5507235172760346e-05, + "loss": 3.4828, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5498849225249826e-05, + "loss": 3.484, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5490479656543035e-05, + "loss": 3.4775, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.548209370903252e-05, + "loss": 3.4691, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5473707761522e-05, + "loss": 3.4823, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.546532181401148e-05, + "loss": 3.4904, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5456952245304688e-05, + "loss": 3.4904, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5448566297794168e-05, + "loss": 3.4702, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5440180350283648e-05, + "loss": 3.4855, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5431794402773128e-05, + "loss": 3.4789, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.542342483406634e-05, + "loss": 3.4909, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.541503888655582e-05, + "loss": 3.4809, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.54066529390453e-05, + "loss": 3.4827, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.539826699153478e-05, + "loss": 3.4792, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.538989742282799e-05, + "loss": 3.4893, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.5381511475317472e-05, + "loss": 3.4675, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.5373125527806952e-05, + "loss": 3.4847, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.5364739580296432e-05, + "loss": 3.4777, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.535637001158964e-05, + "loss": 3.4832, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.534798406407912e-05, + "loss": 3.4717, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.53395981165686e-05, + "loss": 3.4859, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.533121216905808e-05, + "loss": 3.4745, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5322842600351294e-05, + "loss": 3.4809, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5314456652840774e-05, + "loss": 3.4826, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5306070705330254e-05, + "loss": 3.479, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5297684757819734e-05, + "loss": 3.4907, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5289315189112943e-05, + "loss": 3.4899, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5280929241602426e-05, + "loss": 3.4838, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5272543294091906e-05, + "loss": 3.4929, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5264157346581386e-05, + "loss": 3.4849, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.5255787777874595e-05, + "loss": 3.4749, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5247401830364075e-05, + "loss": 3.4748, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5239015882853555e-05, + "loss": 3.4757, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5230629935343035e-05, + "loss": 3.4779, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5222260366636247e-05, + "loss": 3.4874, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5213874419125727e-05, + "loss": 3.48, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5205488471615207e-05, + "loss": 3.4883, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5197102524104687e-05, + "loss": 3.4785, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5188732955397896e-05, + "loss": 3.4785, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.518034700788738e-05, + "loss": 3.4781, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.517196106037686e-05, + "loss": 3.4925, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.516357511286634e-05, + "loss": 3.4818, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.515520554415955e-05, + "loss": 3.4698, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.514681959664903e-05, + "loss": 3.4664, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.513843364913851e-05, + "loss": 3.4854, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.513004770162799e-05, + "loss": 3.4872, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.51216781329212e-05, + "loss": 3.4859, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.511329218541068e-05, + "loss": 3.48, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.510490623790016e-05, + "loss": 3.4911, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.509652029038964e-05, + "loss": 3.483, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.508815072168285e-05, + "loss": 3.487, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5079764774172333e-05, + "loss": 3.4812, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5071378826661813e-05, + "loss": 3.4803, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5062992879151293e-05, + "loss": 3.487, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5054623310444502e-05, + "loss": 3.4707, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5046237362933982e-05, + "loss": 3.4903, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5037851415423462e-05, + "loss": 3.4875, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5029465467912942e-05, + "loss": 3.484, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5021095899206155e-05, + "loss": 3.4796, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5012709951695635e-05, + "loss": 3.4754, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.871534824371338, + "eval_runtime": 305.0593, + "eval_samples_per_second": 1250.875, + "eval_steps_per_second": 39.091, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.5004324004185115e-05, + "loss": 3.4809, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499593805667459e-05, + "loss": 3.4794, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498755210916407e-05, + "loss": 3.4833, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.497916616165355e-05, + "loss": 3.4818, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970796592946764e-05, + "loss": 3.4966, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962410645436244e-05, + "loss": 3.4792, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4954024697925724e-05, + "loss": 3.4712, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4945638750415204e-05, + "loss": 3.472, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4937269181708413e-05, + "loss": 3.4876, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928883234197896e-05, + "loss": 3.4861, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920497286687376e-05, + "loss": 3.4705, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4912111339176856e-05, + "loss": 3.4877, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903741770470065e-05, + "loss": 3.48, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895355822959545e-05, + "loss": 3.4774, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886969875449025e-05, + "loss": 3.4727, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878583927938505e-05, + "loss": 3.4723, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4870214359231717e-05, + "loss": 3.4697, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861828411721197e-05, + "loss": 3.4714, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853442464210677e-05, + "loss": 3.488, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4845056516700157e-05, + "loss": 3.4907, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836686947993366e-05, + "loss": 3.4847, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482830100048285e-05, + "loss": 3.4777, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.481991505297233e-05, + "loss": 3.4752, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.481152910546181e-05, + "loss": 3.4835, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.480315953675502e-05, + "loss": 3.4753, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.47947735892445e-05, + "loss": 3.4778, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.478638764173398e-05, + "loss": 3.4688, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.477801807302719e-05, + "loss": 3.4802, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.476963212551667e-05, + "loss": 3.4657, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.476124617800615e-05, + "loss": 3.4651, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.475286023049563e-05, + "loss": 3.4835, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.474449066178884e-05, + "loss": 3.478, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.473610471427832e-05, + "loss": 3.4877, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727718766767803e-05, + "loss": 3.4826, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719332819257283e-05, + "loss": 3.4708, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4710963250550492e-05, + "loss": 3.4846, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702577303039972e-05, + "loss": 3.4782, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4694191355529452e-05, + "loss": 3.4671, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685805408018932e-05, + "loss": 3.4637, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677435839312145e-05, + "loss": 3.4698, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4669049891801625e-05, + "loss": 3.467, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660663944291105e-05, + "loss": 3.4848, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4652277996780585e-05, + "loss": 3.4737, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4643908428073794e-05, + "loss": 3.4723, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4635522480563274e-05, + "loss": 3.4827, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4627136533052757e-05, + "loss": 3.4764, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618750585542237e-05, + "loss": 3.4799, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610381016835446e-05, + "loss": 3.466, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601995069324926e-05, + "loss": 3.4504, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593609121814406e-05, + "loss": 3.4876, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4585223174303886e-05, + "loss": 3.4818, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.457686998440083e-05, + "loss": 3.4793, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568484036890307e-05, + "loss": 3.4699, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4560098089379787e-05, + "loss": 3.4676, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551712141869267e-05, + "loss": 3.4648, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4543326194358747e-05, + "loss": 3.4706, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534940246848227e-05, + "loss": 3.4714, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.452655429933771e-05, + "loss": 3.4703, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4518168351827187e-05, + "loss": 3.4801, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.45097987831204e-05, + "loss": 3.471, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.450141283560988e-05, + "loss": 3.462, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.449302688809936e-05, + "loss": 3.4853, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484640940588836e-05, + "loss": 3.4621, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4476271371882052e-05, + "loss": 3.4636, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467885424371532e-05, + "loss": 3.4823, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.445949947686101e-05, + "loss": 3.4847, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.445111352935049e-05, + "loss": 3.4603, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.44427439606437e-05, + "loss": 3.4676, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.443435801313318e-05, + "loss": 3.4555, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.442597206562266e-05, + "loss": 3.4761, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.441758611811214e-05, + "loss": 3.4799, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4409216549405353e-05, + "loss": 3.4689, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4400830601894833e-05, + "loss": 3.4757, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439244465438431e-05, + "loss": 3.476, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.438405870687379e-05, + "loss": 3.4883, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375689138167006e-05, + "loss": 3.4657, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4367303190656482e-05, + "loss": 3.4793, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358917243145962e-05, + "loss": 3.4804, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4350531295635442e-05, + "loss": 3.46, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4342161726928655e-05, + "loss": 3.4822, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333775779418135e-05, + "loss": 3.4705, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325389831907615e-05, + "loss": 3.4813, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4317003884397095e-05, + "loss": 3.4783, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308634315690307e-05, + "loss": 3.4587, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4300248368179784e-05, + "loss": 3.4677, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291862420669264e-05, + "loss": 3.4649, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4283476473158743e-05, + "loss": 3.4836, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4275106904451956e-05, + "loss": 3.4692, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266720956941436e-05, + "loss": 3.4691, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258335009430916e-05, + "loss": 3.4699, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249949061920396e-05, + "loss": 3.4739, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241579493213605e-05, + "loss": 3.4645, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4233193545703088e-05, + "loss": 3.4556, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4224807598192568e-05, + "loss": 3.4738, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4216421650682048e-05, + "loss": 3.4777, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4208052081975257e-05, + "loss": 3.4809, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199666134464737e-05, + "loss": 3.4563, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4191280186954217e-05, + "loss": 3.4727, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182894239443697e-05, + "loss": 3.4691, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.417452467073691e-05, + "loss": 3.476, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.416613872322639e-05, + "loss": 3.4734, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.415775277571587e-05, + "loss": 3.4701, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.414936682820535e-05, + "loss": 3.4681, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.414099725949856e-05, + "loss": 3.4769, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132611311988042e-05, + "loss": 3.4553, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4124225364477522e-05, + "loss": 3.471, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115839416967002e-05, + "loss": 3.4627, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.410746984826021e-05, + "loss": 3.4739, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.409908390074969e-05, + "loss": 3.4542, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.409069795323917e-05, + "loss": 3.4736, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.408231200572865e-05, + "loss": 3.4642, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073942437021863e-05, + "loss": 3.471, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065556489511343e-05, + "loss": 3.4686, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4057170542000823e-05, + "loss": 3.4687, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4048784594490303e-05, + "loss": 3.4771, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4040415025783512e-05, + "loss": 3.4809, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4032029078272996e-05, + "loss": 3.4733, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023643130762476e-05, + "loss": 3.4785, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4015257183251956e-05, + "loss": 3.4738, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006887614545165e-05, + "loss": 3.4657, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998501667034645e-05, + "loss": 3.4581, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3990115719524125e-05, + "loss": 3.4682, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3981729772013604e-05, + "loss": 3.4657, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3973360203306817e-05, + "loss": 3.4733, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964974255796297e-05, + "loss": 3.4684, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956588308285777e-05, + "loss": 3.4747, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3948202360775257e-05, + "loss": 3.4677, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939832792068466e-05, + "loss": 3.4681, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.393144684455795e-05, + "loss": 3.4638, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.392306089704743e-05, + "loss": 3.478, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.391467494953691e-05, + "loss": 3.4737, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3906305380830118e-05, + "loss": 3.4606, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897919433319598e-05, + "loss": 3.4525, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889533485809078e-05, + "loss": 3.4743, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.388116391710229e-05, + "loss": 3.4716, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387277796959177e-05, + "loss": 3.4727, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386439202208125e-05, + "loss": 3.4693, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.385600607457073e-05, + "loss": 3.477, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.384763650586394e-05, + "loss": 3.4701, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.383925055835342e-05, + "loss": 3.4782, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.38308646108429e-05, + "loss": 3.4669, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.382247866333238e-05, + "loss": 3.4686, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3814109094625592e-05, + "loss": 3.4702, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3805723147115072e-05, + "loss": 3.465, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3797337199604552e-05, + "loss": 3.4772, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.378895125209403e-05, + "loss": 3.4758, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780581683387244e-05, + "loss": 3.4721, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3772195735876724e-05, + "loss": 3.4687, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763809788366204e-05, + "loss": 3.4681, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8735220432281494, + "eval_runtime": 309.0718, + "eval_samples_per_second": 1234.636, + "eval_steps_per_second": 38.583, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.375542384085568e-05, + "loss": 3.4714, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.374703789334516e-05, + "loss": 3.4661, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.373865194583464e-05, + "loss": 3.4694, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.373026599832412e-05, + "loss": 3.4709, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3721896429617333e-05, + "loss": 3.4839, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3713510482106813e-05, + "loss": 3.4668, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3705124534596293e-05, + "loss": 3.4596, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.3696738587085773e-05, + "loss": 3.4562, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.3688369018378982e-05, + "loss": 3.4751, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3679999449672198e-05, + "loss": 3.4717, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3671613502161678e-05, + "loss": 3.4635, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3663227554651155e-05, + "loss": 3.4728, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3654841607140634e-05, + "loss": 3.4694, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3646455659630114e-05, + "loss": 3.4656, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3638069712119594e-05, + "loss": 3.4631, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3629683764609074e-05, + "loss": 3.4568, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3621297817098558e-05, + "loss": 3.4615, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3612928248391767e-05, + "loss": 3.459, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3604542300881247e-05, + "loss": 3.4736, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3596156353370727e-05, + "loss": 3.4799, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3587770405860207e-05, + "loss": 3.4739, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.357940083715342e-05, + "loss": 3.4665, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.35710148896429e-05, + "loss": 3.4658, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.356262894213238e-05, + "loss": 3.4683, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.355424299462186e-05, + "loss": 3.4638, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3545873425915068e-05, + "loss": 3.468, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3537487478404548e-05, + "loss": 3.4526, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3529101530894028e-05, + "loss": 3.4698, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3520715583383508e-05, + "loss": 3.4598, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.351234601467672e-05, + "loss": 3.4535, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.35039600671662e-05, + "loss": 3.4666, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.349557411965568e-05, + "loss": 3.4721, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.348720455094889e-05, + "loss": 3.4764, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3478818603438373e-05, + "loss": 3.4693, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3470432655927853e-05, + "loss": 3.4563, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3462046708417333e-05, + "loss": 3.4724, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.3453677139710542e-05, + "loss": 3.4675, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3445291192200022e-05, + "loss": 3.4513, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3436905244689502e-05, + "loss": 3.4559, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3428519297178982e-05, + "loss": 3.4543, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3420149728472194e-05, + "loss": 3.4585, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3411763780961674e-05, + "loss": 3.4696, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3403377833451154e-05, + "loss": 3.4657, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.339499188594063e-05, + "loss": 3.4582, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3386622317233843e-05, + "loss": 3.4678, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3378236369723323e-05, + "loss": 3.461, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3369850422212806e-05, + "loss": 3.4738, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3361464474702283e-05, + "loss": 3.4554, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.3353094905995495e-05, + "loss": 3.435, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3344708958484975e-05, + "loss": 3.4789, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.3336323010974452e-05, + "loss": 3.4663, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3327937063463935e-05, + "loss": 3.4686, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3319567494757148e-05, + "loss": 3.4613, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3311181547246628e-05, + "loss": 3.4568, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3302795599736104e-05, + "loss": 3.4524, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3294409652225584e-05, + "loss": 3.4587, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.3286023704715064e-05, + "loss": 3.4602, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.3277637757204544e-05, + "loss": 3.4611, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3269251809694028e-05, + "loss": 3.4651, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3260882240987237e-05, + "loss": 3.4583, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3252496293476717e-05, + "loss": 3.4532, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3244110345966197e-05, + "loss": 3.4696, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3235724398455677e-05, + "loss": 3.4531, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.322735482974889e-05, + "loss": 3.451, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321896888223837e-05, + "loss": 3.4678, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.321058293472785e-05, + "loss": 3.4728, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.320219698721733e-05, + "loss": 3.4461, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3193827418510538e-05, + "loss": 3.4569, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3185441471000018e-05, + "loss": 3.4472, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.3177055523489498e-05, + "loss": 3.4606, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.316866957597898e-05, + "loss": 3.4661, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.316030000727219e-05, + "loss": 3.4625, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.315191405976167e-05, + "loss": 3.4621, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.314352811225115e-05, + "loss": 3.4662, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.313514216474063e-05, + "loss": 3.4736, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3126772596033843e-05, + "loss": 3.4544, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3118386648523323e-05, + "loss": 3.471, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3110000701012803e-05, + "loss": 3.4679, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3101614753502283e-05, + "loss": 3.4491, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.309324518479549e-05, + "loss": 3.47, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084875616088704e-05, + "loss": 3.4587, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3076489668578184e-05, + "loss": 3.4717, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3068103721067664e-05, + "loss": 3.4672, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059717773557144e-05, + "loss": 3.4509, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3051331826046624e-05, + "loss": 3.4506, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3042945878536104e-05, + "loss": 3.4541, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.303455993102558e-05, + "loss": 3.4716, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3026190362318796e-05, + "loss": 3.4556, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3017804414808276e-05, + "loss": 3.4603, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3009418467297756e-05, + "loss": 3.4565, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.3001032519787233e-05, + "loss": 3.4627, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2992662951080445e-05, + "loss": 3.4547, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2984277003569925e-05, + "loss": 3.4412, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2975891056059405e-05, + "loss": 3.4599, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2967505108548885e-05, + "loss": 3.4663, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2959135539842098e-05, + "loss": 3.4689, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2950749592331578e-05, + "loss": 3.4495, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2942363644821054e-05, + "loss": 3.4578, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2933977697310534e-05, + "loss": 3.4593, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.2925608128603747e-05, + "loss": 3.4611, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.291722218109323e-05, + "loss": 3.4655, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2908836233582707e-05, + "loss": 3.4547, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2900450286072187e-05, + "loss": 3.459, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.28920807173654e-05, + "loss": 3.4638, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2883694769854876e-05, + "loss": 3.447, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.287530882234436e-05, + "loss": 3.4567, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.286692287483384e-05, + "loss": 3.4509, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285855330612705e-05, + "loss": 3.4639, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.2850167358616528e-05, + "loss": 3.4447, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2841781411106008e-05, + "loss": 3.4627, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2833395463595488e-05, + "loss": 3.453, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.28250258948887e-05, + "loss": 3.4596, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.281663994737818e-05, + "loss": 3.4561, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.280825399986766e-05, + "loss": 3.4596, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.279986805235714e-05, + "loss": 3.4617, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.279149848365035e-05, + "loss": 3.4717, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.278311253613983e-05, + "loss": 3.4633, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2774726588629313e-05, + "loss": 3.4684, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2766340641118793e-05, + "loss": 3.4575, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2757971072412e-05, + "loss": 3.4583, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.274958512490148e-05, + "loss": 3.4464, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.274119917739096e-05, + "loss": 3.4542, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.273281322988044e-05, + "loss": 3.458, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2724443661173654e-05, + "loss": 3.4593, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2716057713663134e-05, + "loss": 3.4604, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707671766152614e-05, + "loss": 3.4586, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2699285818642094e-05, + "loss": 3.4547, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2690916249935303e-05, + "loss": 3.459, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2682530302424783e-05, + "loss": 3.4548, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.2674144354914266e-05, + "loss": 3.462, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2665758407403746e-05, + "loss": 3.4594, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2657388838696955e-05, + "loss": 3.4523, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2649002891186435e-05, + "loss": 3.4405, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2640616943675915e-05, + "loss": 3.4665, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.2632230996165395e-05, + "loss": 3.4589, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.2623861427458608e-05, + "loss": 3.4625, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2615475479948088e-05, + "loss": 3.4569, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2607089532437568e-05, + "loss": 3.4655, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598703584927048e-05, + "loss": 3.4576, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2590334016220257e-05, + "loss": 3.4689, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2581948068709737e-05, + "loss": 3.4543, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2573562121199217e-05, + "loss": 3.4565, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.25651761736887e-05, + "loss": 3.4587, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.255680660498191e-05, + "loss": 3.4579, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.254842065747139e-05, + "loss": 3.4689, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.254003470996087e-05, + "loss": 3.4591, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.253164876245035e-05, + "loss": 3.4677, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.252327919374356e-05, + "loss": 3.451, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.251489324623304e-05, + "loss": 3.4584, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.8749234676361084, + "eval_runtime": 302.0054, + "eval_samples_per_second": 1263.524, + "eval_steps_per_second": 39.486, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.250650729872252e-05, + "loss": 3.4556, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2498121351212e-05, + "loss": 3.4553, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.248975178250521e-05, + "loss": 3.4569, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.248136583499469e-05, + "loss": 3.459, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.247297988748417e-05, + "loss": 3.4714, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2464610318777383e-05, + "loss": 3.4546, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.2456224371266863e-05, + "loss": 3.4519, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.2447838423756343e-05, + "loss": 3.4472, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.2439452476245823e-05, + "loss": 3.4639, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.243108290753903e-05, + "loss": 3.4603, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2422696960028515e-05, + "loss": 3.4523, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2414311012517995e-05, + "loss": 3.4626, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2405925065007475e-05, + "loss": 3.458, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.239753911749695e-05, + "loss": 3.4518, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.238915316998643e-05, + "loss": 3.4492, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.238076722247591e-05, + "loss": 3.4462, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.237238127496539e-05, + "loss": 3.4488, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2364011706258604e-05, + "loss": 3.4496, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2355625758748084e-05, + "loss": 3.4618, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.2347239811237564e-05, + "loss": 3.4669, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.2338853863727044e-05, + "loss": 3.4623, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2330484295020253e-05, + "loss": 3.4567, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.2322098347509736e-05, + "loss": 3.4527, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.2313712399999216e-05, + "loss": 3.4541, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2305326452488696e-05, + "loss": 3.4521, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2296956883781905e-05, + "loss": 3.4577, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2288570936271385e-05, + "loss": 3.4386, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2280184988760865e-05, + "loss": 3.4608, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.2271799041250345e-05, + "loss": 3.4504, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.2263429472543557e-05, + "loss": 3.4429, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2255043525033037e-05, + "loss": 3.4525, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2246657577522517e-05, + "loss": 3.4621, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2238271630011997e-05, + "loss": 3.4595, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2229902061305206e-05, + "loss": 3.4606, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.222151611379469e-05, + "loss": 3.4449, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.221313016628417e-05, + "loss": 3.4598, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.220474421877365e-05, + "loss": 3.4559, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.219637465006686e-05, + "loss": 3.4414, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.218798870255634e-05, + "loss": 3.4449, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.217960275504582e-05, + "loss": 3.4437, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.217123318633903e-05, + "loss": 3.4479, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.216284723882851e-05, + "loss": 3.4593, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.215446129131799e-05, + "loss": 3.4511, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.214607534380747e-05, + "loss": 3.4488, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.213770577510068e-05, + "loss": 3.4548, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.212931982759016e-05, + "loss": 3.4494, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.212093388007964e-05, + "loss": 3.4621, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2112547932569123e-05, + "loss": 3.4464, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.2104178363862333e-05, + "loss": 3.421, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.2095792416351812e-05, + "loss": 3.4643, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.2087406468841292e-05, + "loss": 3.4556, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2079020521330772e-05, + "loss": 3.4581, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2070650952623985e-05, + "loss": 3.4504, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2062265005113465e-05, + "loss": 3.4482, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.2053879057602945e-05, + "loss": 3.4399, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.2045493110092425e-05, + "loss": 3.4474, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.20371071625819e-05, + "loss": 3.449, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.202872121507138e-05, + "loss": 3.4458, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.202033526756086e-05, + "loss": 3.4558, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.2011965698854077e-05, + "loss": 3.4493, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2003579751343554e-05, + "loss": 3.4392, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.1995193803833034e-05, + "loss": 3.4576, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.1986807856322514e-05, + "loss": 3.4424, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.1978438287615726e-05, + "loss": 3.4424, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.1970052340105206e-05, + "loss": 3.4573, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1961666392594686e-05, + "loss": 3.4591, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1953280445084166e-05, + "loss": 3.4368, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1944910876377375e-05, + "loss": 3.443, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.1936524928866855e-05, + "loss": 3.4359, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1928138981356335e-05, + "loss": 3.4506, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1919753033845815e-05, + "loss": 3.4564, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1911383465139027e-05, + "loss": 3.4519, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1902997517628507e-05, + "loss": 3.4503, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1894611570117987e-05, + "loss": 3.4518, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1886225622607467e-05, + "loss": 3.4629, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1877856053900676e-05, + "loss": 3.4464, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.186947010639016e-05, + "loss": 3.4595, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.186108415887964e-05, + "loss": 3.4546, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.185269821136912e-05, + "loss": 3.4403, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.184432864266233e-05, + "loss": 3.4554, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.183594269515181e-05, + "loss": 3.4538, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.182755674764129e-05, + "loss": 3.4546, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.181917080013077e-05, + "loss": 3.4578, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.181080123142398e-05, + "loss": 3.4394, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.180241528391346e-05, + "loss": 3.4403, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.179402933640294e-05, + "loss": 3.4446, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.178564338889242e-05, + "loss": 3.4559, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.177727382018563e-05, + "loss": 3.4476, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1768887872675113e-05, + "loss": 3.4457, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1760501925164593e-05, + "loss": 3.4491, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.1752115977654073e-05, + "loss": 3.4521, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.1743746408947282e-05, + "loss": 3.444, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.1735360461436762e-05, + "loss": 3.4316, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.1726974513926242e-05, + "loss": 3.4504, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1718588566415722e-05, + "loss": 3.4511, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1710218997708935e-05, + "loss": 3.4582, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1701833050198415e-05, + "loss": 3.4374, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1693447102687895e-05, + "loss": 3.4453, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.1685061155177375e-05, + "loss": 3.4471, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.1676691586470584e-05, + "loss": 3.4501, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.1668305638960064e-05, + "loss": 3.4551, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1659919691449547e-05, + "loss": 3.4468, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1651533743939027e-05, + "loss": 3.4468, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1643164175232236e-05, + "loss": 3.4518, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.1634778227721716e-05, + "loss": 3.4361, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.1626392280211196e-05, + "loss": 3.4457, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.1618006332700676e-05, + "loss": 3.4374, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.160963676399389e-05, + "loss": 3.457, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.160125081648337e-05, + "loss": 3.4326, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1592864868972848e-05, + "loss": 3.4509, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1584478921462325e-05, + "loss": 3.4428, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1576109352755537e-05, + "loss": 3.4451, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.1567723405245017e-05, + "loss": 3.4465, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.15593374577345e-05, + "loss": 3.4511, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.1550951510223977e-05, + "loss": 3.451, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.154258194151719e-05, + "loss": 3.4611, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.153419599400667e-05, + "loss": 3.4462, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.152581004649615e-05, + "loss": 3.4612, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.151742409898563e-05, + "loss": 3.4463, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1509054530278842e-05, + "loss": 3.445, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.1500668582768322e-05, + "loss": 3.4396, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.14922826352578e-05, + "loss": 3.441, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.148389668774728e-05, + "loss": 3.4425, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.147552711904049e-05, + "loss": 3.4526, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.146714117152997e-05, + "loss": 3.445, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.145875522401945e-05, + "loss": 3.4506, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.145036927650893e-05, + "loss": 3.4449, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1441999707802143e-05, + "loss": 3.4469, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.1433613760291623e-05, + "loss": 3.4477, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.14252278127811e-05, + "loss": 3.4441, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1416858244074316e-05, + "loss": 3.4466, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.1408472296563796e-05, + "loss": 3.4436, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1400086349053272e-05, + "loss": 3.4286, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.1391700401542752e-05, + "loss": 3.4536, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.1383330832835965e-05, + "loss": 3.4485, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.1374944885325445e-05, + "loss": 3.4523, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.1366558937814925e-05, + "loss": 3.4421, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1358172990304405e-05, + "loss": 3.4554, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1349803421597617e-05, + "loss": 3.45, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.1341417474087097e-05, + "loss": 3.4609, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1333031526576574e-05, + "loss": 3.443, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1324645579066054e-05, + "loss": 3.4436, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.131627601035927e-05, + "loss": 3.4481, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1307890062848746e-05, + "loss": 3.4489, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1299504115338226e-05, + "loss": 3.4516, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1291118167827706e-05, + "loss": 3.4498, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.128274859912092e-05, + "loss": 3.4545, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.12743626516104e-05, + "loss": 3.442, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.1265976704099878e-05, + "loss": 3.4535, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.8758039474487305, + "eval_runtime": 305.6764, + "eval_samples_per_second": 1248.349, + "eval_steps_per_second": 39.012, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1257590756589358e-05, + "loss": 3.4497, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1249204809078838e-05, + "loss": 3.4484, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1240818861568318e-05, + "loss": 3.4395, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232432914057798e-05, + "loss": 3.4473, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1224063345351007e-05, + "loss": 3.4598, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215677397840487e-05, + "loss": 3.4446, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.120729145032997e-05, + "loss": 3.4405, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.119890550281945e-05, + "loss": 3.4421, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.119053593411266e-05, + "loss": 3.4479, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.118214998660214e-05, + "loss": 3.4539, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.117376403909162e-05, + "loss": 3.4404, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.11653780915811e-05, + "loss": 3.4495, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1157008522874312e-05, + "loss": 3.4519, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.1148622575363792e-05, + "loss": 3.4397, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1140236627853272e-05, + "loss": 3.4399, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.113185068034275e-05, + "loss": 3.437, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.112348111163596e-05, + "loss": 3.4384, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.111509516412544e-05, + "loss": 3.4387, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1106709216614924e-05, + "loss": 3.4442, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.10983232691044e-05, + "loss": 3.4599, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1089953700397613e-05, + "loss": 3.454, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1081567752887093e-05, + "loss": 3.4466, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1073181805376573e-05, + "loss": 3.4409, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1064795857866053e-05, + "loss": 3.4418, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1056426289159266e-05, + "loss": 3.4428, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1048040341648746e-05, + "loss": 3.4464, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1039654394138222e-05, + "loss": 3.428, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1031268446627702e-05, + "loss": 3.4502, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.1022898877920915e-05, + "loss": 3.4403, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.1014512930410394e-05, + "loss": 3.4337, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.1006126982899874e-05, + "loss": 3.4343, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0997741035389354e-05, + "loss": 3.4549, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0989371466682567e-05, + "loss": 3.4492, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0980985519172047e-05, + "loss": 3.4481, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972599571661523e-05, + "loss": 3.4341, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0964213624151007e-05, + "loss": 3.4481, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.095584405544422e-05, + "loss": 3.4493, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0947458107933696e-05, + "loss": 3.4324, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0939072160423176e-05, + "loss": 3.4333, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0930702591716388e-05, + "loss": 3.4316, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0922316644205868e-05, + "loss": 3.4378, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0913930696695348e-05, + "loss": 3.4444, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0905544749184828e-05, + "loss": 3.4446, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.089717518047804e-05, + "loss": 3.4374, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.088878923296752e-05, + "loss": 3.4435, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0880403285456997e-05, + "loss": 3.4407, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0872017337946477e-05, + "loss": 3.4471, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0863647769239693e-05, + "loss": 3.4395, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.085526182172917e-05, + "loss": 3.4117, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.084687587421865e-05, + "loss": 3.4523, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.083848992670813e-05, + "loss": 3.4452, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0830120358001342e-05, + "loss": 3.4504, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0821750789294554e-05, + "loss": 3.4373, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0813364841784034e-05, + "loss": 3.4339, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0804978894273514e-05, + "loss": 3.4345, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0796592946762994e-05, + "loss": 3.4355, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.078820699925247e-05, + "loss": 3.4403, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.077982105174195e-05, + "loss": 3.4322, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.077143510423143e-05, + "loss": 3.4442, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.076304915672091e-05, + "loss": 3.439, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754679588014123e-05, + "loss": 3.4277, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0746293640503603e-05, + "loss": 3.4452, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0737907692993083e-05, + "loss": 3.4332, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.0729538124286292e-05, + "loss": 3.4301, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0721152176775772e-05, + "loss": 3.4451, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0712766229265255e-05, + "loss": 3.4491, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0704380281754735e-05, + "loss": 3.426, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0696010713047945e-05, + "loss": 3.4344, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687624765537424e-05, + "loss": 3.424, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0679238818026904e-05, + "loss": 3.4402, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0670852870516384e-05, + "loss": 3.445, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0662483301809597e-05, + "loss": 3.4407, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0654097354299077e-05, + "loss": 3.4363, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0645711406788557e-05, + "loss": 3.441, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0637325459278037e-05, + "loss": 3.4545, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0628955890571246e-05, + "loss": 3.4311, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0620569943060726e-05, + "loss": 3.4493, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.061218399555021e-05, + "loss": 3.4453, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.060379804803969e-05, + "loss": 3.4281, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0595428479332898e-05, + "loss": 3.4458, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.058705891062611e-05, + "loss": 3.4429, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0578672963115587e-05, + "loss": 3.4429, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.057028701560507e-05, + "loss": 3.4487, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.056190106809455e-05, + "loss": 3.4251, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.055351512058403e-05, + "loss": 3.4309, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.054512917307351e-05, + "loss": 3.4324, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.053674322556299e-05, + "loss": 3.4453, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.052835727805247e-05, + "loss": 3.4359, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.051998770934568e-05, + "loss": 3.4404, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0511601761835163e-05, + "loss": 3.4396, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0503215814324643e-05, + "loss": 3.4345, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.0494846245617852e-05, + "loss": 3.4345, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0486460298107332e-05, + "loss": 3.4203, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0478074350596812e-05, + "loss": 3.4363, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0469688403086292e-05, + "loss": 3.4408, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0461318834379504e-05, + "loss": 3.4485, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0452932886868984e-05, + "loss": 3.4271, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0444546939358464e-05, + "loss": 3.4329, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0436160991847944e-05, + "loss": 3.4359, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.0427791423141153e-05, + "loss": 3.4381, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0419405475630633e-05, + "loss": 3.4411, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0411019528120116e-05, + "loss": 3.4394, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402633580609593e-05, + "loss": 3.4374, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0394264011902806e-05, + "loss": 3.4382, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0385878064392285e-05, + "loss": 3.4298, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.0377492116881765e-05, + "loss": 3.4322, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.0369106169371245e-05, + "loss": 3.4298, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0360736600664458e-05, + "loss": 3.4477, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0352350653153938e-05, + "loss": 3.4211, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0343964705643418e-05, + "loss": 3.4376, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.0335578758132894e-05, + "loss": 3.4303, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.0327209189426107e-05, + "loss": 3.4392, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.0318823241915587e-05, + "loss": 3.4342, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.0310437294405067e-05, + "loss": 3.4378, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.0302051346894547e-05, + "loss": 3.4374, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.029368177818776e-05, + "loss": 3.4497, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.028529583067724e-05, + "loss": 3.4345, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0276909883166716e-05, + "loss": 3.4504, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.0268523935656196e-05, + "loss": 3.435, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.026015436694941e-05, + "loss": 3.4349, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.025176841943889e-05, + "loss": 3.4298, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0243382471928368e-05, + "loss": 3.4355, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0234996524417848e-05, + "loss": 3.43, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.022662695571106e-05, + "loss": 3.4404, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.021824100820054e-05, + "loss": 3.4322, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.020985506069002e-05, + "loss": 3.44, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.02014691131795e-05, + "loss": 3.4388, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0193099544472713e-05, + "loss": 3.4332, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.018471359696219e-05, + "loss": 3.437, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.017632764945167e-05, + "loss": 3.4399, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.016794170194115e-05, + "loss": 3.4329, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0159572133234365e-05, + "loss": 3.4374, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0151186185723842e-05, + "loss": 3.4154, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0142800238213322e-05, + "loss": 3.4436, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0134414290702802e-05, + "loss": 3.437, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.012604472199601e-05, + "loss": 3.4411, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0117658774485494e-05, + "loss": 3.4317, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0109272826974974e-05, + "loss": 3.4417, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0100886879464454e-05, + "loss": 3.4375, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0092517310757663e-05, + "loss": 3.4478, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0084131363247143e-05, + "loss": 3.4305, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0075745415736623e-05, + "loss": 3.4349, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0067359468226103e-05, + "loss": 3.4339, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0058989899519316e-05, + "loss": 3.4411, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0050603952008795e-05, + "loss": 3.4396, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0042218004498275e-05, + "loss": 3.4351, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0033832056987755e-05, + "loss": 3.4461, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0025462488280964e-05, + "loss": 3.4275, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0017076540770448e-05, + "loss": 3.4454, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.876594305038452, + "eval_runtime": 302.6885, + "eval_samples_per_second": 1260.672, + "eval_steps_per_second": 39.397, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.0008690593259928e-05, + "loss": 3.4287, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 2.0000321024553137e-05, + "loss": 3.4342, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.9991935077042617e-05, + "loss": 3.4353, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9983549129532097e-05, + "loss": 3.4389, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.9975163182021577e-05, + "loss": 3.4495, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.996679361331479e-05, + "loss": 3.4329, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.995840766580427e-05, + "loss": 3.4296, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.995002171829375e-05, + "loss": 3.4293, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.994163577078323e-05, + "loss": 3.4338, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.9933266202076438e-05, + "loss": 3.4447, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.9924880254565918e-05, + "loss": 3.431, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.99164943070554e-05, + "loss": 3.4359, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.990810835954488e-05, + "loss": 3.4409, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.989972241203436e-05, + "loss": 3.4282, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.989133646452384e-05, + "loss": 3.4271, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.9882950517013318e-05, + "loss": 3.4246, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.9874564569502798e-05, + "loss": 3.4296, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.986619500079601e-05, + "loss": 3.4279, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.985780905328549e-05, + "loss": 3.4368, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.984942310577497e-05, + "loss": 3.4457, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.984103715826445e-05, + "loss": 3.4414, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.9832667589557663e-05, + "loss": 3.4332, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.982428164204714e-05, + "loss": 3.4291, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.981589569453662e-05, + "loss": 3.4302, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9807509747026103e-05, + "loss": 3.4308, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9799140178319315e-05, + "loss": 3.4349, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.979075423080879e-05, + "loss": 3.4191, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.978236828329827e-05, + "loss": 3.4387, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.977398233578775e-05, + "loss": 3.4304, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9765612767080964e-05, + "loss": 3.4193, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.9757226819570444e-05, + "loss": 3.4255, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.9748840872059924e-05, + "loss": 3.4432, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9740454924549404e-05, + "loss": 3.4412, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9732085355842613e-05, + "loss": 3.4363, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9723699408332093e-05, + "loss": 3.4253, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9715313460821573e-05, + "loss": 3.4291, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.9706927513311056e-05, + "loss": 3.4413, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9698557944604265e-05, + "loss": 3.4215, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9690171997093745e-05, + "loss": 3.421, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9681786049583225e-05, + "loss": 3.4238, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9673416480876434e-05, + "loss": 3.4252, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9665030533365918e-05, + "loss": 3.4363, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9656644585855398e-05, + "loss": 3.4291, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9648258638344878e-05, + "loss": 3.4343, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9639889069638087e-05, + "loss": 3.4278, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9631503122127567e-05, + "loss": 3.4268, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9623117174617047e-05, + "loss": 3.4413, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9614731227106527e-05, + "loss": 3.4273, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.960636165839974e-05, + "loss": 3.406, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.959797571088922e-05, + "loss": 3.4398, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.95895897633787e-05, + "loss": 3.432, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.958120381586818e-05, + "loss": 3.4401, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.9572834247161388e-05, + "loss": 3.4289, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.956444829965087e-05, + "loss": 3.4234, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.955606235214035e-05, + "loss": 3.4195, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.954767640462983e-05, + "loss": 3.4243, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.953929045711931e-05, + "loss": 3.4332, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.953090450960879e-05, + "loss": 3.4188, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.9522518562098268e-05, + "loss": 3.4354, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.9514132614587748e-05, + "loss": 3.4283, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.9505763045880964e-05, + "loss": 3.4178, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.9497377098370444e-05, + "loss": 3.4349, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.948899115085992e-05, + "loss": 3.4211, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.94806052033494e-05, + "loss": 3.418, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9472235634642613e-05, + "loss": 3.4324, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.946384968713209e-05, + "loss": 3.4411, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.9455463739621572e-05, + "loss": 3.4095, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.9447094170914785e-05, + "loss": 3.4273, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.9438708223404265e-05, + "loss": 3.4124, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.943032227589374e-05, + "loss": 3.427, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.942193632838322e-05, + "loss": 3.4357, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.9413566759676434e-05, + "loss": 3.4259, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.9405180812165917e-05, + "loss": 3.4324, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9396794864655394e-05, + "loss": 3.4275, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.9388408917144874e-05, + "loss": 3.4448, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.9380039348438086e-05, + "loss": 3.4173, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.9371653400927563e-05, + "loss": 3.4381, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.9363267453417043e-05, + "loss": 3.4294, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.9354881505906526e-05, + "loss": 3.4219, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.934651193719974e-05, + "loss": 3.4352, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.9338142368492948e-05, + "loss": 3.4309, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.9329756420982428e-05, + "loss": 3.4302, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.9321370473471908e-05, + "loss": 3.4397, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.9312984525961388e-05, + "loss": 3.4115, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.9304598578450868e-05, + "loss": 3.4212, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.9296212630940347e-05, + "loss": 3.4222, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9287826683429827e-05, + "loss": 3.4359, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.9279440735919307e-05, + "loss": 3.4237, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.9271071167212516e-05, + "loss": 3.4292, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9262685219701996e-05, + "loss": 3.4313, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.925429927219148e-05, + "loss": 3.4241, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.924591332468096e-05, + "loss": 3.4228, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.923754375597417e-05, + "loss": 3.41, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.922915780846365e-05, + "loss": 3.4247, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.922077186095313e-05, + "loss": 3.4299, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.921240229224634e-05, + "loss": 3.4366, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.920401634473582e-05, + "loss": 3.4173, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.91956303972253e-05, + "loss": 3.4221, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.918724444971478e-05, + "loss": 3.4251, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.917887488100799e-05, + "loss": 3.4316, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.917048893349747e-05, + "loss": 3.4281, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.916210298598695e-05, + "loss": 3.4289, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9153717038476433e-05, + "loss": 3.4301, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9145347469769643e-05, + "loss": 3.4244, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.9136961522259122e-05, + "loss": 3.4232, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.9128575574748602e-05, + "loss": 3.4182, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9120189627238082e-05, + "loss": 3.4196, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9111820058531295e-05, + "loss": 3.4346, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9103434111020775e-05, + "loss": 3.4136, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9095048163510255e-05, + "loss": 3.4245, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9086662215999735e-05, + "loss": 3.417, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9078292647292944e-05, + "loss": 3.4292, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.9069906699782424e-05, + "loss": 3.4233, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9061520752271904e-05, + "loss": 3.4279, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9053134804761387e-05, + "loss": 3.4247, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9044765236054596e-05, + "loss": 3.4393, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9036379288544076e-05, + "loss": 3.4278, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.9027993341033556e-05, + "loss": 3.4348, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.9019607393523036e-05, + "loss": 3.4284, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.901123782481625e-05, + "loss": 3.425, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.900285187730573e-05, + "loss": 3.4191, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.899446592979521e-05, + "loss": 3.4249, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.898607998228469e-05, + "loss": 3.4178, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.8977710413577898e-05, + "loss": 3.4285, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.8969324466067377e-05, + "loss": 3.4217, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.8960938518556857e-05, + "loss": 3.4306, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.895255257104634e-05, + "loss": 3.4238, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.894418300233955e-05, + "loss": 3.4268, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.893579705482903e-05, + "loss": 3.4239, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.892741110731851e-05, + "loss": 3.4298, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.8919025159807986e-05, + "loss": 3.4194, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.8910655591101202e-05, + "loss": 3.4277, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.8902269643590682e-05, + "loss": 3.4004, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.8893883696080162e-05, + "loss": 3.4327, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.888549774856964e-05, + "loss": 3.4278, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.887712817986285e-05, + "loss": 3.4329, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.886874223235233e-05, + "loss": 3.4178, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.886035628484181e-05, + "loss": 3.4325, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.885197033733129e-05, + "loss": 3.4236, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.8843600768624504e-05, + "loss": 3.438, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8835214821113983e-05, + "loss": 3.4189, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.882682887360346e-05, + "loss": 3.4235, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.881844292609294e-05, + "loss": 3.4211, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.8810073357386156e-05, + "loss": 3.4382, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.8801687409875636e-05, + "loss": 3.4243, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.8793301462365112e-05, + "loss": 3.4258, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.8784915514854592e-05, + "loss": 3.432, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8776545946147805e-05, + "loss": 3.4231, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8768159998637285e-05, + "loss": 3.4314, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.878993511199951, + "eval_runtime": 302.7715, + "eval_samples_per_second": 1260.327, + "eval_steps_per_second": 39.386, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8759774051126765e-05, + "loss": 3.4203, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8751388103616245e-05, + "loss": 3.4251, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8743002156105725e-05, + "loss": 3.4181, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734616208595205e-05, + "loss": 3.431, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8726246639888414e-05, + "loss": 3.4418, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8717860692377894e-05, + "loss": 3.4197, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8709474744867374e-05, + "loss": 3.4198, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8701088797356857e-05, + "loss": 3.4177, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8692719228650066e-05, + "loss": 3.4259, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8684333281139546e-05, + "loss": 3.4329, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8675947333629026e-05, + "loss": 3.419, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667561386118506e-05, + "loss": 3.4258, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.865919181741172e-05, + "loss": 3.4314, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.86508058699012e-05, + "loss": 3.4181, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.864241992239068e-05, + "loss": 3.4173, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8634033974880158e-05, + "loss": 3.4134, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8625664406173367e-05, + "loss": 3.4209, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8617278458662847e-05, + "loss": 3.4172, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8608892511152327e-05, + "loss": 3.4198, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.860050656364181e-05, + "loss": 3.4344, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.859213699493502e-05, + "loss": 3.432, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.85837510474245e-05, + "loss": 3.4245, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.857536509991398e-05, + "loss": 3.4198, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.856697915240346e-05, + "loss": 3.4199, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8558609583696672e-05, + "loss": 3.4229, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8550223636186152e-05, + "loss": 3.4236, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8541837688675632e-05, + "loss": 3.4082, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8533451741165112e-05, + "loss": 3.4275, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.852508217245832e-05, + "loss": 3.4229, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.85166962249478e-05, + "loss": 3.405, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.850831027743728e-05, + "loss": 3.4187, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.8499924329926764e-05, + "loss": 3.4253, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8491554761219973e-05, + "loss": 3.4293, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8483168813709453e-05, + "loss": 3.4304, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8474782866198933e-05, + "loss": 3.4178, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8466413297492142e-05, + "loss": 3.415, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8458027349981626e-05, + "loss": 3.4322, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8449641402471106e-05, + "loss": 3.4107, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8441255454960586e-05, + "loss": 3.4103, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8432885886253795e-05, + "loss": 3.4119, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8424499938743275e-05, + "loss": 3.4153, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8416113991232755e-05, + "loss": 3.421, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8407728043722235e-05, + "loss": 3.419, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8399358475015447e-05, + "loss": 3.4217, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8390972527504927e-05, + "loss": 3.4182, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8382586579994407e-05, + "loss": 3.4183, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8374217011287616e-05, + "loss": 3.4269, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8365831063777096e-05, + "loss": 3.4189, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.835744511626658e-05, + "loss": 3.3966, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.834905916875606e-05, + "loss": 3.4241, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8340673221245536e-05, + "loss": 3.4243, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8332287273735016e-05, + "loss": 3.4302, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.832391770502823e-05, + "loss": 3.4164, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.831553175751771e-05, + "loss": 3.4153, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.830714581000719e-05, + "loss": 3.4084, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8298759862496668e-05, + "loss": 3.4128, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.8290373914986148e-05, + "loss": 3.4225, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8281987967475628e-05, + "loss": 3.4111, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.8273602019965108e-05, + "loss": 3.4248, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8265216072454588e-05, + "loss": 3.4168, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8256846503747797e-05, + "loss": 3.412, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.824846055623728e-05, + "loss": 3.4201, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.824007460872676e-05, + "loss": 3.4107, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.823168866121624e-05, + "loss": 3.4119, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.822331909250945e-05, + "loss": 3.4162, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.821493314499893e-05, + "loss": 3.4284, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.820654719748841e-05, + "loss": 3.4057, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.819816124997789e-05, + "loss": 3.4165, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8189791681271102e-05, + "loss": 3.4001, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8181405733760582e-05, + "loss": 3.4186, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8173019786250062e-05, + "loss": 3.4225, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.816463383873954e-05, + "loss": 3.4197, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.815626427003275e-05, + "loss": 3.4159, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8147878322522234e-05, + "loss": 3.4186, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8139492375011714e-05, + "loss": 3.434, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8131122806304923e-05, + "loss": 3.412, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8122736858794403e-05, + "loss": 3.4296, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8114350911283883e-05, + "loss": 3.4151, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8105964963773363e-05, + "loss": 3.4137, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097579016262843e-05, + "loss": 3.4217, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8089225826359785e-05, + "loss": 3.4178, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8080839878849265e-05, + "loss": 3.4226, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8072453931338745e-05, + "loss": 3.4314, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8064067983828225e-05, + "loss": 3.4005, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8055682036317705e-05, + "loss": 3.4118, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8047296088807188e-05, + "loss": 3.4111, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8038910141296664e-05, + "loss": 3.4239, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8030524193786144e-05, + "loss": 3.41, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8022154625079357e-05, + "loss": 3.4214, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8013768677568833e-05, + "loss": 3.4187, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8005382730058313e-05, + "loss": 3.4134, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7996996782547797e-05, + "loss": 3.4116, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.798862721384101e-05, + "loss": 3.4032, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7980241266330486e-05, + "loss": 3.4116, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7971855318819966e-05, + "loss": 3.4197, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.7963485750113178e-05, + "loss": 3.4284, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7955099802602658e-05, + "loss": 3.4048, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.7946713855092138e-05, + "loss": 3.4131, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.7938327907581618e-05, + "loss": 3.4147, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.792995833887483e-05, + "loss": 3.4173, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7921572391364307e-05, + "loss": 3.4173, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7913186443853787e-05, + "loss": 3.4185, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7904800496343267e-05, + "loss": 3.4151, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7896430927636483e-05, + "loss": 3.4142, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.788804498012596e-05, + "loss": 3.4153, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.787965903261544e-05, + "loss": 3.4059, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.787127308510492e-05, + "loss": 3.4102, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7862903516398132e-05, + "loss": 3.423, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7854517568887612e-05, + "loss": 3.4059, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7846131621377092e-05, + "loss": 3.413, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7837745673866572e-05, + "loss": 3.4064, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.782937610515978e-05, + "loss": 3.4159, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.782099015764926e-05, + "loss": 3.4137, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.781260421013874e-05, + "loss": 3.4157, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.780421826262822e-05, + "loss": 3.4177, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7795848693921433e-05, + "loss": 3.4309, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7787462746410913e-05, + "loss": 3.4176, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7779076798900393e-05, + "loss": 3.4198, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7770690851389873e-05, + "loss": 3.4221, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7762321282683082e-05, + "loss": 3.4108, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7753935335172566e-05, + "loss": 3.4155, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7745549387662045e-05, + "loss": 3.4094, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7737163440151525e-05, + "loss": 3.4086, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7728793871444735e-05, + "loss": 3.4166, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7720407923934214e-05, + "loss": 3.4153, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7712021976423694e-05, + "loss": 3.42, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7703636028913174e-05, + "loss": 3.4114, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.7695266460206387e-05, + "loss": 3.4196, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7686880512695867e-05, + "loss": 3.4093, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7678494565185347e-05, + "loss": 3.4211, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7670108617674827e-05, + "loss": 3.4117, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7661739048968036e-05, + "loss": 3.4172, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.765335310145752e-05, + "loss": 3.389, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7644967153947e-05, + "loss": 3.4231, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.763658120643648e-05, + "loss": 3.4154, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7628211637729688e-05, + "loss": 3.4256, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7619825690219168e-05, + "loss": 3.4072, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7611439742708648e-05, + "loss": 3.4198, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7603053795198128e-05, + "loss": 3.4138, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.759468422649134e-05, + "loss": 3.4321, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.758629827898082e-05, + "loss": 3.4117, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.75779123314703e-05, + "loss": 3.4113, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.756952638395978e-05, + "loss": 3.4116, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.756115681525299e-05, + "loss": 3.4252, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7552770867742473e-05, + "loss": 3.415, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7544384920231953e-05, + "loss": 3.4141, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7535998972721433e-05, + "loss": 3.4199, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7527629404014642e-05, + "loss": 3.4181, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7519243456504122e-05, + "loss": 3.4185, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.8803250789642334, + "eval_runtime": 309.7966, + "eval_samples_per_second": 1231.747, + "eval_steps_per_second": 38.493, + "step": 1984320 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.325463329315414e+18, + "trial_name": null, + "trial_params": null +}