full-transformer-4 / checkpoint-1831680 /trainer_state.json
abhinavp's picture
Training in progress, epoch 0, checkpoint
7158bc2 verified
{
"best_metric": 3.8422842025756836,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/full2/transformer/4/checkpoints/checkpoint-992160",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 1831680,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 10.9805,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8324,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.184,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9727,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8087,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.6998,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.5979,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5283,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4424,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.3934,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3425,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3175,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 5.2617,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.198,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1749,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1372,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1058,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0793,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0555,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0135,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0075,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9731,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9517,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9226,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9224,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.8946,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8678,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8505,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8323,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8219,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.7996,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.7937,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7791,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 4.7634,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 4.7628,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7483,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7333,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 4.7069,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 4.7019,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 4.6847,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.683,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.667,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.662,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963951890867376e-05,
"loss": 4.6443,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 4.6513,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6347,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6373,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6264,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.5989,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.95892359812181e-05,
"loss": 4.5917,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 4.6049,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 4.5888,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 4.5752,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5591,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5642,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5467,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5599,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.5259,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5379,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5356,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5144,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948863736869932e-05,
"loss": 4.5277,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.4994,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.5,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4879,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945510995746097e-05,
"loss": 4.5047,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.475,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4804,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4644,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 4.4626,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.475,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.940482703000532e-05,
"loss": 4.4673,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396441082494794e-05,
"loss": 4.4583,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388055134984274e-05,
"loss": 4.4585,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379669187473754e-05,
"loss": 4.4644,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 4.4384,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936291367125644e-05,
"loss": 4.4529,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935452772374592e-05,
"loss": 4.4258,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.93461417762354e-05,
"loss": 4.4248,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933775582872488e-05,
"loss": 4.4258,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 4.4268,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 4.4189,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.4268,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 4.4095,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 4.3901,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 4.392,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 4.4038,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927068462744446e-05,
"loss": 4.39,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.92623314375414e-05,
"loss": 4.3897,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925394549003088e-05,
"loss": 4.3922,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924555954252036e-05,
"loss": 4.3744,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923717359500984e-05,
"loss": 4.3807,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.9228804026303046e-05,
"loss": 4.3743,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922041807879253e-05,
"loss": 4.3787,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921203213128201e-05,
"loss": 4.3763,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920364618377149e-05,
"loss": 4.3719,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919526023626097e-05,
"loss": 4.3519,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918687428875045e-05,
"loss": 4.3564,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917848834123993e-05,
"loss": 4.35,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917010239372941e-05,
"loss": 4.354,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916171644621889e-05,
"loss": 4.358,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915333049870837e-05,
"loss": 4.3379,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.3419,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.3442,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912818903498054e-05,
"loss": 4.3374,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911980308747002e-05,
"loss": 4.3254,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.911143351876323e-05,
"loss": 4.3287,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910304757125272e-05,
"loss": 4.3175,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.90946616237422e-05,
"loss": 4.3164,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908627567623168e-05,
"loss": 4.3145,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.3132,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.3086,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.3128,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.3046,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.90443623174828e-05,
"loss": 4.3076,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903597636997228e-05,
"loss": 4.3148,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.9027606801265495e-05,
"loss": 4.3095,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019220853754975e-05,
"loss": 4.3039,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010834906244455e-05,
"loss": 4.2956,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002448958733935e-05,
"loss": 4.2949,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994063011223415e-05,
"loss": 4.2921,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985677063712895e-05,
"loss": 4.2807,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977307495006104e-05,
"loss": 4.2835,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968921547495584e-05,
"loss": 4.2796,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960535599985064e-05,
"loss": 4.2852,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952149652474544e-05,
"loss": 4.2751,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.2819,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2743,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.2689,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.2643,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.2798,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.271,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.2631,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888509482999785e-05,
"loss": 4.2634,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887672526129106e-05,
"loss": 4.2665,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886833931378054e-05,
"loss": 4.2628,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885995336627002e-05,
"loss": 4.2654,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515674187595e-05,
"loss": 4.2533,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884318147124898e-05,
"loss": 4.2539,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883479552373846e-05,
"loss": 4.2529,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.2442,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.2401,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.8809654060010626e-05,
"loss": 4.2406,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.8801268112500106e-05,
"loss": 4.2432,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.8792882164989586e-05,
"loss": 4.2335,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878449621747907e-05,
"loss": 4.2442,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877612664877228e-05,
"loss": 4.2358,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876774070126176e-05,
"loss": 4.2385,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875935475375124e-05,
"loss": 4.2409,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875098518504445e-05,
"loss": 4.2223,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.1935296058654785,
"eval_runtime": 325.8734,
"eval_samples_per_second": 1170.979,
"eval_steps_per_second": 36.594,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874259923753393e-05,
"loss": 4.2119,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873421329002341e-05,
"loss": 4.2082,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872582734251289e-05,
"loss": 4.2325,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871744139500237e-05,
"loss": 4.2148,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870905544749185e-05,
"loss": 4.22,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870066949998133e-05,
"loss": 4.2137,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869228355247081e-05,
"loss": 4.2064,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683913983764027e-05,
"loss": 4.1981,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675544415057236e-05,
"loss": 4.207,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667158467546716e-05,
"loss": 4.1993,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658772520036196e-05,
"loss": 4.2215,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.8650386572525676e-05,
"loss": 4.2072,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642017003818885e-05,
"loss": 4.1878,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633631056308365e-05,
"loss": 4.1899,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.8625245108797845e-05,
"loss": 4.1915,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.8616859161287324e-05,
"loss": 4.1789,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.8608473213776804e-05,
"loss": 4.1928,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860008726626628e-05,
"loss": 4.1895,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.8591701318755764e-05,
"loss": 4.1763,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.8583315371245244e-05,
"loss": 4.2004,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574929423734724e-05,
"loss": 4.1796,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856655985502793e-05,
"loss": 4.1808,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.855817390751741e-05,
"loss": 4.1713,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.854978796000689e-05,
"loss": 4.1927,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854140201249637e-05,
"loss": 4.169,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853301606498585e-05,
"loss": 4.17,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852463011747533e-05,
"loss": 4.1652,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851626054876854e-05,
"loss": 4.165,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850787460125802e-05,
"loss": 4.1628,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.84994886537475e-05,
"loss": 4.16,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849110270623698e-05,
"loss": 4.164,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848271675872646e-05,
"loss": 4.1629,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847433081121595e-05,
"loss": 4.1598,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846594486370543e-05,
"loss": 4.1656,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845757529499864e-05,
"loss": 4.1593,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844918934748812e-05,
"loss": 4.1607,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.84408033999776e-05,
"loss": 4.1445,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843241745246708e-05,
"loss": 4.1472,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842404788376029e-05,
"loss": 4.1381,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841566193624977e-05,
"loss": 4.1468,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840727598873925e-05,
"loss": 4.1372,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839889004122873e-05,
"loss": 4.1469,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.8390520472521936e-05,
"loss": 4.1311,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.8382134525011416e-05,
"loss": 4.1482,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83737485775009e-05,
"loss": 4.1424,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836536262999038e-05,
"loss": 4.1412,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835697668247986e-05,
"loss": 4.1382,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834859073496934e-05,
"loss": 4.1236,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834022116626255e-05,
"loss": 4.124,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833183521875203e-05,
"loss": 4.1397,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832344927124151e-05,
"loss": 4.1294,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831506332373099e-05,
"loss": 4.1253,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830667737622047e-05,
"loss": 4.1164,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829830780751368e-05,
"loss": 4.1259,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828992186000316e-05,
"loss": 4.1078,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828153591249264e-05,
"loss": 4.1318,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.827314996498212e-05,
"loss": 4.1029,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.82647640174716e-05,
"loss": 4.1217,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256394448764816e-05,
"loss": 4.12,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8248008501254296e-05,
"loss": 4.1052,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823962255374377e-05,
"loss": 4.1197,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823123660623325e-05,
"loss": 4.1068,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.822285065872273e-05,
"loss": 4.1061,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214481090015945e-05,
"loss": 4.0938,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820609514250542e-05,
"loss": 4.12,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.81977091949949e-05,
"loss": 4.0924,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818932324748438e-05,
"loss": 4.1048,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.8180953678777594e-05,
"loss": 4.0853,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.8172567731267074e-05,
"loss": 4.096,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.8164181783756554e-05,
"loss": 4.1067,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155795836246034e-05,
"loss": 4.1041,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814742626753924e-05,
"loss": 4.0997,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.813904032002872e-05,
"loss": 4.1043,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.81306543725182e-05,
"loss": 4.1083,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812226842500768e-05,
"loss": 4.0941,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811389885630089e-05,
"loss": 4.1042,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810551290879037e-05,
"loss": 4.0894,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809712696127985e-05,
"loss": 4.0883,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808874101376933e-05,
"loss": 4.086,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808037144506255e-05,
"loss": 4.0933,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807198549755203e-05,
"loss": 4.0942,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806359955004151e-05,
"loss": 4.0988,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805521360253099e-05,
"loss": 4.0903,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.8046844033824197e-05,
"loss": 4.0694,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.8038458086313677e-05,
"loss": 4.0723,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.8030072138803156e-05,
"loss": 4.0871,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.8021686191292636e-05,
"loss": 4.0792,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.8013316622585846e-05,
"loss": 4.0771,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.8004930675075325e-05,
"loss": 4.0859,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996544727564805e-05,
"loss": 4.0701,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.7988158780054285e-05,
"loss": 4.0743,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.7979772832543765e-05,
"loss": 4.0742,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797140326383698e-05,
"loss": 4.0824,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796301731632646e-05,
"loss": 4.0802,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795463136881594e-05,
"loss": 4.0854,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794624542130542e-05,
"loss": 4.0603,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793787585259863e-05,
"loss": 4.0686,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792948990508811e-05,
"loss": 4.069,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792110395757759e-05,
"loss": 4.0677,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791271801006707e-05,
"loss": 4.0806,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790434844136028e-05,
"loss": 4.0595,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789596249384976e-05,
"loss": 4.0641,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788757654633924e-05,
"loss": 4.0712,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787919059882872e-05,
"loss": 4.0679,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870821030121935e-05,
"loss": 4.0515,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862451461415144e-05,
"loss": 4.0635,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7854065513904624e-05,
"loss": 4.0544,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845679566394104e-05,
"loss": 4.0515,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837293618883584e-05,
"loss": 4.0512,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828907671373064e-05,
"loss": 4.0513,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820521723862544e-05,
"loss": 4.0502,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812135776352024e-05,
"loss": 4.0604,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803749828841504e-05,
"loss": 4.0456,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779538026013471e-05,
"loss": 4.0545,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778699431262419e-05,
"loss": 4.0663,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777860836511367e-05,
"loss": 4.0581,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777022241760315e-05,
"loss": 4.0562,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776185284889637e-05,
"loss": 4.0516,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775346690138585e-05,
"loss": 4.0446,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774508095387533e-05,
"loss": 4.0473,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773669500636481e-05,
"loss": 4.0414,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772832543765802e-05,
"loss": 4.0413,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.77199394901475e-05,
"loss": 4.042,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771155354263698e-05,
"loss": 4.0492,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770316759512646e-05,
"loss": 4.0449,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769478164761594e-05,
"loss": 4.0435,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768639570010542e-05,
"loss": 4.0439,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.76780097525949e-05,
"loss": 4.033,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.7669640183888106e-05,
"loss": 4.0355,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.7661254236377586e-05,
"loss": 4.0512,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765286828886707e-05,
"loss": 4.0462,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764448234135655e-05,
"loss": 4.0421,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763611277264976e-05,
"loss": 4.0359,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762772682513924e-05,
"loss": 4.0423,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761934087762872e-05,
"loss": 4.0389,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610954930118195e-05,
"loss": 4.0481,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760258536141141e-05,
"loss": 4.0365,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759419941390089e-05,
"loss": 4.0341,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758581346639037e-05,
"loss": 4.034,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.7577427518879844e-05,
"loss": 4.0301,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756905795017306e-05,
"loss": 4.023,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756067200266254e-05,
"loss": 4.0306,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755228605515202e-05,
"loss": 4.0336,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.75439001076415e-05,
"loss": 4.0192,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753551416013098e-05,
"loss": 4.038,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527144591424196e-05,
"loss": 4.028,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751875864391367e-05,
"loss": 4.0275,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751037269640315e-05,
"loss": 4.0324,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750198674889263e-05,
"loss": 4.0184,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.025674343109131,
"eval_runtime": 314.4245,
"eval_samples_per_second": 1213.617,
"eval_steps_per_second": 37.926,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493617180185845e-05,
"loss": 4.0076,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748523123267532e-05,
"loss": 4.0067,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.74768452851648e-05,
"loss": 4.0314,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746845933765428e-05,
"loss": 4.0168,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460073390143764e-05,
"loss": 4.0273,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451687442633244e-05,
"loss": 4.0127,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443301495122724e-05,
"loss": 4.0154,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434915547612204e-05,
"loss": 4.0023,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426529600101684e-05,
"loss": 4.0144,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7418143652591164e-05,
"loss": 4.009,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409757705080644e-05,
"loss": 4.0272,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401371757570124e-05,
"loss": 4.0176,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739303494647079e-05,
"loss": 3.9975,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738464899896027e-05,
"loss": 4.0011,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737626305144975e-05,
"loss": 4.0078,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736787710393923e-05,
"loss": 3.9917,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735949115642871e-05,
"loss": 4.0058,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.73511052089182e-05,
"loss": 4.0042,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734271926140768e-05,
"loss": 3.9967,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733433331389716e-05,
"loss": 4.0227,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732594736638664e-05,
"loss": 3.9985,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731756141887612e-05,
"loss": 4.0031,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.73091754713656e-05,
"loss": 3.9938,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730080590265881e-05,
"loss": 4.0128,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729241995514829e-05,
"loss": 3.9887,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728403400763777e-05,
"loss": 3.9965,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727564806012725e-05,
"loss": 3.9891,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.7267278491420456e-05,
"loss": 3.9941,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258892543909936e-05,
"loss": 3.9883,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.7250506596399416e-05,
"loss": 3.9898,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724213702769263e-05,
"loss": 3.9939,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723375108018211e-05,
"loss": 3.9945,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722536513267159e-05,
"loss": 3.99,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721697918516107e-05,
"loss": 4.0017,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720859323765055e-05,
"loss": 3.9882,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720020729014003e-05,
"loss": 3.9949,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.7191821342629505e-05,
"loss": 3.9806,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183435395118985e-05,
"loss": 3.985,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.71750658264122e-05,
"loss": 3.9729,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716667987890168e-05,
"loss": 3.9872,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158293931391154e-05,
"loss": 3.9739,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149907983880634e-05,
"loss": 3.9855,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714153841517385e-05,
"loss": 3.9734,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713315246766333e-05,
"loss": 3.9851,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712476652015281e-05,
"loss": 3.9889,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711638057264229e-05,
"loss": 3.9807,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7108011003935505e-05,
"loss": 3.9829,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709962505642498e-05,
"loss": 3.9672,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709123910891446e-05,
"loss": 3.9703,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708285316140394e-05,
"loss": 3.985,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074483592697154e-05,
"loss": 3.9743,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706609764518663e-05,
"loss": 3.9736,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705771169767611e-05,
"loss": 3.9624,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704932575016559e-05,
"loss": 3.9748,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.70409561814588e-05,
"loss": 3.952,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703257023394828e-05,
"loss": 3.9849,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702418428643776e-05,
"loss": 3.9522,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701579833892724e-05,
"loss": 3.9724,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700742877022045e-05,
"loss": 3.9732,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699904282270993e-05,
"loss": 3.9574,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699065687519941e-05,
"loss": 3.9755,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698227092768889e-05,
"loss": 3.9582,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.69739013589821e-05,
"loss": 3.9595,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696551541147158e-05,
"loss": 3.9485,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695712946396106e-05,
"loss": 3.9739,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694874351645054e-05,
"loss": 3.9518,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694037394774376e-05,
"loss": 3.9615,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693198800023324e-05,
"loss": 3.9465,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692360205272272e-05,
"loss": 3.95,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.69152161052122e-05,
"loss": 3.9638,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.6906846536505406e-05,
"loss": 3.9657,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.6898460588994886e-05,
"loss": 3.9547,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.6890074641484366e-05,
"loss": 3.9697,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.6881688693973846e-05,
"loss": 3.9667,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873319125267055e-05,
"loss": 3.9585,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686494955656027e-05,
"loss": 3.9597,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685656360904975e-05,
"loss": 3.958,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.684817766153923e-05,
"loss": 3.9521,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683979171402871e-05,
"loss": 3.9509,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683140576651819e-05,
"loss": 3.9555,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682301981900767e-05,
"loss": 3.9599,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681463387149715e-05,
"loss": 3.9677,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680624792398663e-05,
"loss": 3.9531,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679787835527984e-05,
"loss": 3.9325,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678949240776932e-05,
"loss": 3.9413,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.67811064602588e-05,
"loss": 3.9539,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677272051274828e-05,
"loss": 3.9474,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676435094404149e-05,
"loss": 3.9442,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675596499653097e-05,
"loss": 3.9528,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674757904902045e-05,
"loss": 3.9448,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739193101509935e-05,
"loss": 3.9385,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730823532803144e-05,
"loss": 3.9473,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722437585292624e-05,
"loss": 3.9538,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6714051637782104e-05,
"loss": 3.948,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705665690271584e-05,
"loss": 3.9552,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669729612156479e-05,
"loss": 3.938,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668891017405427e-05,
"loss": 3.9412,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668052422654375e-05,
"loss": 3.9413,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667213827903323e-05,
"loss": 3.9456,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666376871032644e-05,
"loss": 3.9527,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665538276281592e-05,
"loss": 3.9359,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.66469968153054e-05,
"loss": 3.9366,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663861086779488e-05,
"loss": 3.9436,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.66302412990881e-05,
"loss": 3.9462,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662185535157758e-05,
"loss": 3.9283,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661348578287079e-05,
"loss": 3.9375,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660509983536027e-05,
"loss": 3.9363,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659671388784975e-05,
"loss": 3.93,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658832794033923e-05,
"loss": 3.9281,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579941992828707e-05,
"loss": 3.9303,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.6571556045318187e-05,
"loss": 3.9333,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.6563170097807667e-05,
"loss": 3.9376,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.6554784150297146e-05,
"loss": 3.9268,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.6546414581590356e-05,
"loss": 3.9346,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.6538028634079836e-05,
"loss": 3.9443,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652964268656932e-05,
"loss": 3.9446,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.65212567390588e-05,
"loss": 3.9347,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651288717035201e-05,
"loss": 3.9353,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650450122284149e-05,
"loss": 3.9294,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649611527533097e-05,
"loss": 3.9322,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648772932782045e-05,
"loss": 3.9214,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647935975911366e-05,
"loss": 3.9234,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647097381160314e-05,
"loss": 3.9266,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646258786409262e-05,
"loss": 3.9359,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.64542019165821e-05,
"loss": 3.9263,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644581596907158e-05,
"loss": 3.9287,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643743002156106e-05,
"loss": 3.9282,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642904407405054e-05,
"loss": 3.919,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.6420674505343756e-05,
"loss": 3.9205,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412288557833236e-05,
"loss": 3.9386,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640390261032271e-05,
"loss": 3.9383,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639551666281219e-05,
"loss": 3.9273,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6387147094105405e-05,
"loss": 3.9233,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637876114659488e-05,
"loss": 3.9269,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637037519908436e-05,
"loss": 3.9302,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636198925157384e-05,
"loss": 3.94,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353619682867054e-05,
"loss": 3.9247,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634523373535653e-05,
"loss": 3.9206,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633686416664974e-05,
"loss": 3.9223,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632847821913923e-05,
"loss": 3.9215,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.632009227162871e-05,
"loss": 3.9168,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631170632411818e-05,
"loss": 3.9208,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630332037660766e-05,
"loss": 3.9246,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629493442909714e-05,
"loss": 3.914,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628654848158662e-05,
"loss": 3.9259,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.62781625340761e-05,
"loss": 3.9252,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626979296536931e-05,
"loss": 3.9181,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626140701785879e-05,
"loss": 3.923,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625302107034827e-05,
"loss": 3.9091,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.9514849185943604,
"eval_runtime": 305.0841,
"eval_samples_per_second": 1250.773,
"eval_steps_per_second": 39.088,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624463512283775e-05,
"loss": 3.9116,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623626555413097e-05,
"loss": 3.9003,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622787960662045e-05,
"loss": 3.9269,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.621949365910993e-05,
"loss": 3.9105,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621110771159941e-05,
"loss": 3.9257,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.6202738142892616e-05,
"loss": 3.9058,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.6194352195382096e-05,
"loss": 3.9148,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.6185966247871576e-05,
"loss": 3.8954,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.6177596679164785e-05,
"loss": 3.9147,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.6169210731654265e-05,
"loss": 3.9029,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.6160824784143745e-05,
"loss": 3.9237,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.6152438836633225e-05,
"loss": 3.9155,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.6144069267926434e-05,
"loss": 3.8947,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613568332041592e-05,
"loss": 3.9,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.61272973729054e-05,
"loss": 3.9071,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611891142539488e-05,
"loss": 3.8929,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611052547788436e-05,
"loss": 3.9022,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610213953037384e-05,
"loss": 3.9041,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609375358286332e-05,
"loss": 3.8968,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.60853676353528e-05,
"loss": 3.9244,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607698168784228e-05,
"loss": 3.9,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606859574033176e-05,
"loss": 3.9021,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.606020979282124e-05,
"loss": 3.9,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605184022411445e-05,
"loss": 3.9098,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604345427660393e-05,
"loss": 3.8946,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.603506832909341e-05,
"loss": 3.8997,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602669876038662e-05,
"loss": 3.8932,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.60183128128761e-05,
"loss": 3.8971,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009926865365585e-05,
"loss": 3.8923,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.6001540917855065e-05,
"loss": 3.8925,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599315497034454e-05,
"loss": 3.8951,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.5984785401637754e-05,
"loss": 3.9004,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.5976399454127234e-05,
"loss": 3.8997,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.5968013506616714e-05,
"loss": 3.9016,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595962755910619e-05,
"loss": 3.8923,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.5951257990399403e-05,
"loss": 3.8998,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594287204288888e-05,
"loss": 3.8826,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593448609537836e-05,
"loss": 3.8959,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.5926100147867836e-05,
"loss": 3.8786,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591773057916105e-05,
"loss": 3.8901,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590934463165054e-05,
"loss": 3.8811,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590095868414001e-05,
"loss": 3.8956,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589257273662949e-05,
"loss": 3.8822,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.588418678911897e-05,
"loss": 3.8889,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587580084160845e-05,
"loss": 3.8989,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.586741489409793e-05,
"loss": 3.8918,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585902894658741e-05,
"loss": 3.8941,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585065937788062e-05,
"loss": 3.8753,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.58422734303701e-05,
"loss": 3.8772,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583388748285958e-05,
"loss": 3.8916,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582551791415279e-05,
"loss": 3.8872,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581713196664228e-05,
"loss": 3.8809,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580874601913176e-05,
"loss": 3.8746,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.5800376450424966e-05,
"loss": 3.8852,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.5791990502914446e-05,
"loss": 3.8685,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.5783604555403926e-05,
"loss": 3.8853,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.5775218607893406e-05,
"loss": 3.8686,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.5766832660382886e-05,
"loss": 3.8797,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.5758446712872366e-05,
"loss": 3.888,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.5750060765361846e-05,
"loss": 3.8678,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.5741691196655055e-05,
"loss": 3.8831,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.5733305249144535e-05,
"loss": 3.8735,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.5724919301634015e-05,
"loss": 3.8711,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.5716533354123495e-05,
"loss": 3.8674,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.5708147406612975e-05,
"loss": 3.8811,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569977783790619e-05,
"loss": 3.866,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.569139189039567e-05,
"loss": 3.875,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568300594288515e-05,
"loss": 3.8623,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567461999537463e-05,
"loss": 3.8624,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566623404786411e-05,
"loss": 3.8753,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565784810035359e-05,
"loss": 3.8828,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564946215284307e-05,
"loss": 3.8678,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564107620533255e-05,
"loss": 3.8848,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563270663662576e-05,
"loss": 3.88,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.562432068911524e-05,
"loss": 3.8723,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561595112040845e-05,
"loss": 3.877,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560756517289793e-05,
"loss": 3.8728,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.5599179225387415e-05,
"loss": 3.8682,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.5590793277876895e-05,
"loss": 3.8696,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.5582423709170104e-05,
"loss": 3.8732,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.5574037761659584e-05,
"loss": 3.8794,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.5565651814149064e-05,
"loss": 3.8738,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.5557265866638544e-05,
"loss": 3.8725,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.5548879919128024e-05,
"loss": 3.8526,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554051035042123e-05,
"loss": 3.8562,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553212440291071e-05,
"loss": 3.8694,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552373845540019e-05,
"loss": 3.8679,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.5515352507889666e-05,
"loss": 3.8632,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550696656037915e-05,
"loss": 3.8683,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549859699167237e-05,
"loss": 3.8638,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.549021104416185e-05,
"loss": 3.8582,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548182509665132e-05,
"loss": 3.8644,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.54734391491408e-05,
"loss": 3.8703,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546506958043402e-05,
"loss": 3.8683,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.54566836329235e-05,
"loss": 3.8776,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544829768541297e-05,
"loss": 3.8607,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543991173790245e-05,
"loss": 3.8593,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543152579039193e-05,
"loss": 3.8634,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542313984288141e-05,
"loss": 3.8655,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541475389537089e-05,
"loss": 3.8731,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540636794786037e-05,
"loss": 3.8583,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.5397998379153586e-05,
"loss": 3.86,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.5389628810446796e-05,
"loss": 3.8631,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.5381242862936275e-05,
"loss": 3.8672,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372856915425755e-05,
"loss": 3.8513,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364470967915235e-05,
"loss": 3.86,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5356085020404715e-05,
"loss": 3.8586,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347699072894195e-05,
"loss": 3.8504,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.5339329504187404e-05,
"loss": 3.8463,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.5330943556676884e-05,
"loss": 3.855,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.5322557609166364e-05,
"loss": 3.8582,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.5314171661655844e-05,
"loss": 3.8568,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530580209294906e-05,
"loss": 3.8514,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.529741614543854e-05,
"loss": 3.8526,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528903019792802e-05,
"loss": 3.8694,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.52806442504175e-05,
"loss": 3.866,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527227468171071e-05,
"loss": 3.8619,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526388873420019e-05,
"loss": 3.8586,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525550278668967e-05,
"loss": 3.8531,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524711683917915e-05,
"loss": 3.8544,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523873089166863e-05,
"loss": 3.8461,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523036132296184e-05,
"loss": 3.8486,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522197537545132e-05,
"loss": 3.8507,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.52135894279408e-05,
"loss": 3.8593,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520520348043028e-05,
"loss": 3.8494,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519681753291976e-05,
"loss": 3.8573,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518843158540924e-05,
"loss": 3.849,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.5180045637898725e-05,
"loss": 3.8467,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.5171676069191934e-05,
"loss": 3.8456,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.5163290121681414e-05,
"loss": 3.8631,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.5154904174170894e-05,
"loss": 3.866,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.5146518226660373e-05,
"loss": 3.8523,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.5138132279149853e-05,
"loss": 3.8479,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.5129746331639333e-05,
"loss": 3.854,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.5121360384128807e-05,
"loss": 3.8507,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.5112974436618287e-05,
"loss": 3.8655,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.51046048679115e-05,
"loss": 3.8462,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.5096218920400976e-05,
"loss": 3.8514,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.508783297289046e-05,
"loss": 3.8467,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.507944702537994e-05,
"loss": 3.8555,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507106107786942e-05,
"loss": 3.8423,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.50626751303589e-05,
"loss": 3.8469,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505428918284838e-05,
"loss": 3.8519,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504591961414159e-05,
"loss": 3.8434,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.503753366663107e-05,
"loss": 3.8516,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502914771912055e-05,
"loss": 3.8544,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.502076177161003e-05,
"loss": 3.8453,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.501237582409951e-05,
"loss": 3.8487,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500400625539272e-05,
"loss": 3.845,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 3.9100821018218994,
"eval_runtime": 304.4947,
"eval_samples_per_second": 1253.194,
"eval_steps_per_second": 39.163,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.49956203078822e-05,
"loss": 3.8318,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498723436037168e-05,
"loss": 3.8295,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497884841286116e-05,
"loss": 3.8518,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.497046246535065e-05,
"loss": 3.8431,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496207651784013e-05,
"loss": 3.8567,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.495369057032961e-05,
"loss": 3.8342,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945304622819087e-05,
"loss": 3.8454,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.4936918675308567e-05,
"loss": 3.8256,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.4928549106601776e-05,
"loss": 3.8479,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.4920163159091256e-05,
"loss": 3.8327,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.4911777211580736e-05,
"loss": 3.8498,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.4903391264070216e-05,
"loss": 3.8478,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.4895021695363425e-05,
"loss": 3.8221,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.4886635747852905e-05,
"loss": 3.8362,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.4878249800342385e-05,
"loss": 3.8358,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.4869863852831864e-05,
"loss": 3.8237,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.4861477905321344e-05,
"loss": 3.8339,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.4853091957810824e-05,
"loss": 3.8337,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.4844706010300304e-05,
"loss": 3.8321,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.4836320062789784e-05,
"loss": 3.8522,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.4827934115279264e-05,
"loss": 3.8304,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481956454657247e-05,
"loss": 3.8342,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481117859906195e-05,
"loss": 3.8341,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480279265155143e-05,
"loss": 3.8406,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479440670404091e-05,
"loss": 3.8268,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478603713533412e-05,
"loss": 3.8397,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.47776511878236e-05,
"loss": 3.8226,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476926524031308e-05,
"loss": 3.8294,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476087929280256e-05,
"loss": 3.8231,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475249334529205e-05,
"loss": 3.8281,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474410739778153e-05,
"loss": 3.8266,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473573782907474e-05,
"loss": 3.8366,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472735188156422e-05,
"loss": 3.833,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.47189659340537e-05,
"loss": 3.8373,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471057998654318e-05,
"loss": 3.825,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470221041783639e-05,
"loss": 3.8353,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469382447032587e-05,
"loss": 3.8221,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468543852281535e-05,
"loss": 3.8238,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467705257530483e-05,
"loss": 3.8154,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.4668683006598036e-05,
"loss": 3.8247,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.4660297059087516e-05,
"loss": 3.818,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.4651911111577e-05,
"loss": 3.8309,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464352516406648e-05,
"loss": 3.8187,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463513921655596e-05,
"loss": 3.8219,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.462675326904544e-05,
"loss": 3.8371,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461838370033865e-05,
"loss": 3.8269,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.460999775282813e-05,
"loss": 3.826,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.460161180531761e-05,
"loss": 3.8161,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.459322585780709e-05,
"loss": 3.8076,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.45848562891003e-05,
"loss": 3.8292,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457647034158978e-05,
"loss": 3.8236,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.456808439407926e-05,
"loss": 3.8166,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.455969844656874e-05,
"loss": 3.8156,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.4551328877861956e-05,
"loss": 3.8248,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.4542942930351436e-05,
"loss": 3.8026,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.4534556982840916e-05,
"loss": 3.8248,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.4526171035330396e-05,
"loss": 3.8039,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.4517785087819876e-05,
"loss": 3.8198,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.4509415519113085e-05,
"loss": 3.8226,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.4501029571602565e-05,
"loss": 3.8095,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.4492643624092045e-05,
"loss": 3.8159,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.4484257676581525e-05,
"loss": 3.8134,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.4475871729071e-05,
"loss": 3.8065,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.4467502160364214e-05,
"loss": 3.8109,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.4459116212853694e-05,
"loss": 3.8153,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.4450730265343174e-05,
"loss": 3.8086,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.4442344317832654e-05,
"loss": 3.8117,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.4433958370322134e-05,
"loss": 3.8028,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442558880161535e-05,
"loss": 3.7995,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441720285410482e-05,
"loss": 3.814,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.44088169065943e-05,
"loss": 3.8232,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440043095908378e-05,
"loss": 3.8063,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439204501157326e-05,
"loss": 3.8257,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438367544286647e-05,
"loss": 3.8208,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437528949535595e-05,
"loss": 3.8101,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436690354784543e-05,
"loss": 3.814,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435851760033491e-05,
"loss": 3.8174,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.435014803162813e-05,
"loss": 3.8082,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434176208411761e-05,
"loss": 3.8079,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433337613660709e-05,
"loss": 3.8156,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432499018909657e-05,
"loss": 3.8139,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431660424158605e-05,
"loss": 3.814,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.4308234672879257e-05,
"loss": 3.8106,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.4299848725368737e-05,
"loss": 3.7936,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.4291462777858217e-05,
"loss": 3.7957,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.4283076830347696e-05,
"loss": 3.8087,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.4274707261640906e-05,
"loss": 3.8098,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4266321314130386e-05,
"loss": 3.805,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.4257935366619865e-05,
"loss": 3.8059,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249549419109345e-05,
"loss": 3.8022,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.424116347159883e-05,
"loss": 3.8015,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423279390289204e-05,
"loss": 3.8069,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422440795538152e-05,
"loss": 3.8055,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.4216022007871e-05,
"loss": 3.8131,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420763606036048e-05,
"loss": 3.8137,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419926649165369e-05,
"loss": 3.8086,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.419088054414317e-05,
"loss": 3.7978,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418249459663265e-05,
"loss": 3.8097,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.417410864912213e-05,
"loss": 3.805,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416572270161161e-05,
"loss": 3.8142,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415735313290482e-05,
"loss": 3.8022,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.41489671853943e-05,
"loss": 3.7953,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414058123788378e-05,
"loss": 3.8116,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.4132195290373266e-05,
"loss": 3.807,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.4123825721666475e-05,
"loss": 3.797,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.4115439774155955e-05,
"loss": 3.804,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4107053826645435e-05,
"loss": 3.8024,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.4098667879134915e-05,
"loss": 3.7865,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.4090298310428124e-05,
"loss": 3.7909,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.4081912362917604e-05,
"loss": 3.8025,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.4073526415407084e-05,
"loss": 3.799,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.4065140467896564e-05,
"loss": 3.799,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405677089918977e-05,
"loss": 3.7955,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404838495167925e-05,
"loss": 3.7943,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.403999900416873e-05,
"loss": 3.8155,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403161305665822e-05,
"loss": 3.8105,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402324348795143e-05,
"loss": 3.8047,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401485754044091e-05,
"loss": 3.8019,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400647159293039e-05,
"loss": 3.7947,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399808564541987e-05,
"loss": 3.7964,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398971607671308e-05,
"loss": 3.7912,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398133012920256e-05,
"loss": 3.7957,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397294418169204e-05,
"loss": 3.7941,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396455823418152e-05,
"loss": 3.806,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.3956188665474726e-05,
"loss": 3.7941,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.3947802717964206e-05,
"loss": 3.7998,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.3939416770453686e-05,
"loss": 3.7953,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393103082294317e-05,
"loss": 3.7921,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392266125423638e-05,
"loss": 3.7926,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391427530672586e-05,
"loss": 3.8039,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.390588935921534e-05,
"loss": 3.8108,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.389750341170482e-05,
"loss": 3.8013,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388913384299803e-05,
"loss": 3.7908,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388074789548751e-05,
"loss": 3.8022,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387236194797699e-05,
"loss": 3.7943,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386397600046647e-05,
"loss": 3.8074,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.385559005295595e-05,
"loss": 3.7956,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384722048424916e-05,
"loss": 3.7947,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383883453673864e-05,
"loss": 3.7917,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383044858922813e-05,
"loss": 3.8031,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382206264171761e-05,
"loss": 3.7862,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.3813693073010816e-05,
"loss": 3.7929,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.3805307125500296e-05,
"loss": 3.7964,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.3796921177989776e-05,
"loss": 3.7902,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.3788535230479256e-05,
"loss": 3.7975,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.3780165661772465e-05,
"loss": 3.7987,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771779714261945e-05,
"loss": 3.7939,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763393766751425e-05,
"loss": 3.7905,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.37550078192409e-05,
"loss": 3.7943,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.885098934173584,
"eval_runtime": 303.3818,
"eval_samples_per_second": 1257.791,
"eval_steps_per_second": 39.307,
"step": 381600
},
{
"epoch": 0.0,
"learning_rate": 4.3746638250534114e-05,
"loss": 3.7821,
"step": 381952
},
{
"epoch": 0.0,
"learning_rate": 4.3738252303023594e-05,
"loss": 3.7754,
"step": 382464
},
{
"epoch": 0.0,
"learning_rate": 4.372986635551308e-05,
"loss": 3.7986,
"step": 382976
},
{
"epoch": 0.0,
"learning_rate": 4.3721480408002554e-05,
"loss": 3.793,
"step": 383488
},
{
"epoch": 0.0,
"learning_rate": 4.3713094460492034e-05,
"loss": 3.8,
"step": 384000
},
{
"epoch": 0.0,
"learning_rate": 4.3704708512981514e-05,
"loss": 3.7852,
"step": 384512
},
{
"epoch": 0.0,
"learning_rate": 4.3696322565470993e-05,
"loss": 3.789,
"step": 385024
},
{
"epoch": 0.0,
"learning_rate": 4.3687936617960473e-05,
"loss": 3.7773,
"step": 385536
},
{
"epoch": 0.0,
"learning_rate": 4.367956704925368e-05,
"loss": 3.7891,
"step": 386048
},
{
"epoch": 0.0,
"learning_rate": 4.36711974805469e-05,
"loss": 3.7873,
"step": 386560
},
{
"epoch": 0.0,
"learning_rate": 4.366281153303637e-05,
"loss": 3.7956,
"step": 387072
},
{
"epoch": 0.0,
"learning_rate": 4.365442558552585e-05,
"loss": 3.7947,
"step": 387584
},
{
"epoch": 0.0,
"learning_rate": 4.364603963801533e-05,
"loss": 3.7699,
"step": 388096
},
{
"epoch": 0.0,
"learning_rate": 4.363765369050482e-05,
"loss": 3.7841,
"step": 388608
},
{
"epoch": 0.0,
"learning_rate": 4.36292677429943e-05,
"loss": 3.7862,
"step": 389120
},
{
"epoch": 0.0,
"learning_rate": 4.362088179548378e-05,
"loss": 3.7736,
"step": 389632
},
{
"epoch": 0.0,
"learning_rate": 4.361249584797326e-05,
"loss": 3.7808,
"step": 390144
},
{
"epoch": 0.0,
"learning_rate": 4.360412627926647e-05,
"loss": 3.7821,
"step": 390656
},
{
"epoch": 0.0,
"learning_rate": 4.359574033175595e-05,
"loss": 3.7811,
"step": 391168
},
{
"epoch": 0.0,
"learning_rate": 4.358735438424543e-05,
"loss": 3.7967,
"step": 391680
},
{
"epoch": 0.0,
"learning_rate": 4.357896843673491e-05,
"loss": 3.7812,
"step": 392192
},
{
"epoch": 0.0,
"learning_rate": 4.3570598868028116e-05,
"loss": 3.787,
"step": 392704
},
{
"epoch": 0.0,
"learning_rate": 4.3562212920517596e-05,
"loss": 3.7819,
"step": 393216
},
{
"epoch": 0.0,
"learning_rate": 4.3553826973007076e-05,
"loss": 3.788,
"step": 393728
},
{
"epoch": 0.0,
"learning_rate": 4.3545441025496556e-05,
"loss": 3.777,
"step": 394240
},
{
"epoch": 0.0,
"learning_rate": 4.353707145678977e-05,
"loss": 3.7853,
"step": 394752
},
{
"epoch": 0.0,
"learning_rate": 4.352868550927925e-05,
"loss": 3.7771,
"step": 395264
},
{
"epoch": 0.0,
"learning_rate": 4.352029956176873e-05,
"loss": 3.7759,
"step": 395776
},
{
"epoch": 0.0,
"learning_rate": 4.351191361425821e-05,
"loss": 3.7743,
"step": 396288
},
{
"epoch": 0.0,
"learning_rate": 4.350352766674769e-05,
"loss": 3.7775,
"step": 396800
},
{
"epoch": 0.01,
"learning_rate": 4.34951580980409e-05,
"loss": 3.7766,
"step": 397312
},
{
"epoch": 0.01,
"learning_rate": 4.348677215053038e-05,
"loss": 3.7836,
"step": 397824
},
{
"epoch": 0.01,
"learning_rate": 4.347838620301986e-05,
"loss": 3.7861,
"step": 398336
},
{
"epoch": 0.01,
"learning_rate": 4.347000025550934e-05,
"loss": 3.785,
"step": 398848
},
{
"epoch": 0.01,
"learning_rate": 4.346163068680255e-05,
"loss": 3.7745,
"step": 399360
},
{
"epoch": 0.01,
"learning_rate": 4.345324473929203e-05,
"loss": 3.7822,
"step": 399872
},
{
"epoch": 0.01,
"learning_rate": 4.344485879178151e-05,
"loss": 3.7746,
"step": 400384
},
{
"epoch": 0.01,
"learning_rate": 4.343647284427099e-05,
"loss": 3.7755,
"step": 400896
},
{
"epoch": 0.01,
"learning_rate": 4.3428103275564206e-05,
"loss": 3.7643,
"step": 401408
},
{
"epoch": 0.01,
"learning_rate": 4.3419717328053685e-05,
"loss": 3.7715,
"step": 401920
},
{
"epoch": 0.01,
"learning_rate": 4.3411331380543165e-05,
"loss": 3.7726,
"step": 402432
},
{
"epoch": 0.01,
"learning_rate": 4.3402945433032645e-05,
"loss": 3.7801,
"step": 402944
},
{
"epoch": 0.01,
"learning_rate": 4.3394575864325854e-05,
"loss": 3.77,
"step": 403456
},
{
"epoch": 0.01,
"learning_rate": 4.3386189916815334e-05,
"loss": 3.7711,
"step": 403968
},
{
"epoch": 0.01,
"learning_rate": 4.3377803969304814e-05,
"loss": 3.7882,
"step": 404480
},
{
"epoch": 0.01,
"learning_rate": 4.3369418021794294e-05,
"loss": 3.7767,
"step": 404992
},
{
"epoch": 0.01,
"learning_rate": 4.3361048453087503e-05,
"loss": 3.7794,
"step": 405504
},
{
"epoch": 0.01,
"learning_rate": 4.3352662505576983e-05,
"loss": 3.7684,
"step": 406016
},
{
"epoch": 0.01,
"learning_rate": 4.334427655806646e-05,
"loss": 3.7548,
"step": 406528
},
{
"epoch": 0.01,
"learning_rate": 4.333589061055594e-05,
"loss": 3.7794,
"step": 407040
},
{
"epoch": 0.01,
"learning_rate": 4.332752104184916e-05,
"loss": 3.7768,
"step": 407552
},
{
"epoch": 0.01,
"learning_rate": 4.331913509433864e-05,
"loss": 3.767,
"step": 408064
},
{
"epoch": 0.01,
"learning_rate": 4.331074914682812e-05,
"loss": 3.7674,
"step": 408576
},
{
"epoch": 0.01,
"learning_rate": 4.33023631993176e-05,
"loss": 3.7783,
"step": 409088
},
{
"epoch": 0.01,
"learning_rate": 4.329399363061081e-05,
"loss": 3.7496,
"step": 409600
},
{
"epoch": 0.01,
"learning_rate": 4.328560768310029e-05,
"loss": 3.776,
"step": 410112
},
{
"epoch": 0.01,
"learning_rate": 4.327722173558977e-05,
"loss": 3.7595,
"step": 410624
},
{
"epoch": 0.01,
"learning_rate": 4.326883578807925e-05,
"loss": 3.7672,
"step": 411136
},
{
"epoch": 0.01,
"learning_rate": 4.326044984056873e-05,
"loss": 3.7759,
"step": 411648
},
{
"epoch": 0.01,
"learning_rate": 4.325208027186194e-05,
"loss": 3.7655,
"step": 412160
},
{
"epoch": 0.01,
"learning_rate": 4.324369432435142e-05,
"loss": 3.7644,
"step": 412672
},
{
"epoch": 0.01,
"learning_rate": 4.32353083768409e-05,
"loss": 3.7692,
"step": 413184
},
{
"epoch": 0.01,
"learning_rate": 4.322692242933038e-05,
"loss": 3.7589,
"step": 413696
},
{
"epoch": 0.01,
"learning_rate": 4.321855286062359e-05,
"loss": 3.7586,
"step": 414208
},
{
"epoch": 0.01,
"learning_rate": 4.321016691311307e-05,
"loss": 3.7684,
"step": 414720
},
{
"epoch": 0.01,
"learning_rate": 4.320178096560255e-05,
"loss": 3.7657,
"step": 415232
},
{
"epoch": 0.01,
"learning_rate": 4.319339501809203e-05,
"loss": 3.7601,
"step": 415744
},
{
"epoch": 0.01,
"learning_rate": 4.318502544938524e-05,
"loss": 3.7577,
"step": 416256
},
{
"epoch": 0.01,
"learning_rate": 4.317663950187472e-05,
"loss": 3.7527,
"step": 416768
},
{
"epoch": 0.01,
"learning_rate": 4.31682535543642e-05,
"loss": 3.7627,
"step": 417280
},
{
"epoch": 0.01,
"learning_rate": 4.315986760685368e-05,
"loss": 3.7718,
"step": 417792
},
{
"epoch": 0.01,
"learning_rate": 4.315149803814689e-05,
"loss": 3.7607,
"step": 418304
},
{
"epoch": 0.01,
"learning_rate": 4.314311209063637e-05,
"loss": 3.7786,
"step": 418816
},
{
"epoch": 0.01,
"learning_rate": 4.313472614312585e-05,
"loss": 3.7753,
"step": 419328
},
{
"epoch": 0.01,
"learning_rate": 4.312634019561533e-05,
"loss": 3.7655,
"step": 419840
},
{
"epoch": 0.01,
"learning_rate": 4.3117970626908546e-05,
"loss": 3.7609,
"step": 420352
},
{
"epoch": 0.01,
"learning_rate": 4.3109584679398026e-05,
"loss": 3.7733,
"step": 420864
},
{
"epoch": 0.01,
"learning_rate": 4.3101198731887506e-05,
"loss": 3.7628,
"step": 421376
},
{
"epoch": 0.01,
"learning_rate": 4.309281278437698e-05,
"loss": 3.7598,
"step": 421888
},
{
"epoch": 0.01,
"learning_rate": 4.3084443215670195e-05,
"loss": 3.7688,
"step": 422400
},
{
"epoch": 0.01,
"learning_rate": 4.3076057268159675e-05,
"loss": 3.7651,
"step": 422912
},
{
"epoch": 0.01,
"learning_rate": 4.3067671320649155e-05,
"loss": 3.7695,
"step": 423424
},
{
"epoch": 0.01,
"learning_rate": 4.305928537313863e-05,
"loss": 3.7647,
"step": 423936
},
{
"epoch": 0.01,
"learning_rate": 4.3050915804431844e-05,
"loss": 3.75,
"step": 424448
},
{
"epoch": 0.01,
"learning_rate": 4.3042529856921324e-05,
"loss": 3.7472,
"step": 424960
},
{
"epoch": 0.01,
"learning_rate": 4.3034143909410804e-05,
"loss": 3.7618,
"step": 425472
},
{
"epoch": 0.01,
"learning_rate": 4.3025757961900284e-05,
"loss": 3.7648,
"step": 425984
},
{
"epoch": 0.01,
"learning_rate": 4.30173883931935e-05,
"loss": 3.76,
"step": 426496
},
{
"epoch": 0.01,
"learning_rate": 4.300900244568298e-05,
"loss": 3.7582,
"step": 427008
},
{
"epoch": 0.02,
"learning_rate": 4.300061649817245e-05,
"loss": 3.7603,
"step": 427520
},
{
"epoch": 0.02,
"learning_rate": 4.299223055066193e-05,
"loss": 3.7515,
"step": 428032
},
{
"epoch": 0.02,
"learning_rate": 4.298386098195515e-05,
"loss": 3.7648,
"step": 428544
},
{
"epoch": 0.02,
"learning_rate": 4.297547503444463e-05,
"loss": 3.7562,
"step": 429056
},
{
"epoch": 0.02,
"learning_rate": 4.29670890869341e-05,
"loss": 3.7676,
"step": 429568
},
{
"epoch": 0.02,
"learning_rate": 4.295870313942358e-05,
"loss": 3.7716,
"step": 430080
},
{
"epoch": 0.02,
"learning_rate": 4.29503335707168e-05,
"loss": 3.7621,
"step": 430592
},
{
"epoch": 0.02,
"learning_rate": 4.294194762320628e-05,
"loss": 3.7541,
"step": 431104
},
{
"epoch": 0.02,
"learning_rate": 4.293356167569576e-05,
"loss": 3.7604,
"step": 431616
},
{
"epoch": 0.02,
"learning_rate": 4.292517572818524e-05,
"loss": 3.7598,
"step": 432128
},
{
"epoch": 0.02,
"learning_rate": 4.2916806159478454e-05,
"loss": 3.7712,
"step": 432640
},
{
"epoch": 0.02,
"learning_rate": 4.290842021196793e-05,
"loss": 3.7559,
"step": 433152
},
{
"epoch": 0.02,
"learning_rate": 4.290003426445741e-05,
"loss": 3.7532,
"step": 433664
},
{
"epoch": 0.02,
"learning_rate": 4.289164831694689e-05,
"loss": 3.766,
"step": 434176
},
{
"epoch": 0.02,
"learning_rate": 4.28832787482401e-05,
"loss": 3.7597,
"step": 434688
},
{
"epoch": 0.02,
"learning_rate": 4.2874892800729576e-05,
"loss": 3.7542,
"step": 435200
},
{
"epoch": 0.02,
"learning_rate": 4.2866506853219056e-05,
"loss": 3.7588,
"step": 435712
},
{
"epoch": 0.02,
"learning_rate": 4.2858120905708536e-05,
"loss": 3.7539,
"step": 436224
},
{
"epoch": 0.02,
"learning_rate": 4.284975133700175e-05,
"loss": 3.7485,
"step": 436736
},
{
"epoch": 0.02,
"learning_rate": 4.2841365389491225e-05,
"loss": 3.7407,
"step": 437248
},
{
"epoch": 0.02,
"learning_rate": 4.283297944198071e-05,
"loss": 3.7578,
"step": 437760
},
{
"epoch": 0.02,
"learning_rate": 4.282459349447019e-05,
"loss": 3.7557,
"step": 438272
},
{
"epoch": 0.02,
"learning_rate": 4.28162239257634e-05,
"loss": 3.7535,
"step": 438784
},
{
"epoch": 0.02,
"learning_rate": 4.280783797825288e-05,
"loss": 3.7512,
"step": 439296
},
{
"epoch": 0.02,
"learning_rate": 4.279945203074236e-05,
"loss": 3.7468,
"step": 439808
},
{
"epoch": 0.02,
"learning_rate": 4.279106608323184e-05,
"loss": 3.7703,
"step": 440320
},
{
"epoch": 0.02,
"learning_rate": 4.278269651452505e-05,
"loss": 3.7653,
"step": 440832
},
{
"epoch": 0.02,
"learning_rate": 4.277431056701453e-05,
"loss": 3.7619,
"step": 441344
},
{
"epoch": 0.02,
"learning_rate": 4.276592461950401e-05,
"loss": 3.7593,
"step": 441856
},
{
"epoch": 0.02,
"learning_rate": 4.275753867199349e-05,
"loss": 3.7499,
"step": 442368
},
{
"epoch": 0.02,
"learning_rate": 4.27491691032867e-05,
"loss": 3.7526,
"step": 442880
},
{
"epoch": 0.02,
"learning_rate": 4.274078315577618e-05,
"loss": 3.7473,
"step": 443392
},
{
"epoch": 0.02,
"learning_rate": 4.2732397208265665e-05,
"loss": 3.7498,
"step": 443904
},
{
"epoch": 0.02,
"learning_rate": 4.2724011260755145e-05,
"loss": 3.7543,
"step": 444416
},
{
"epoch": 0.02,
"learning_rate": 4.2715641692048354e-05,
"loss": 3.7571,
"step": 444928
},
{
"epoch": 0.02,
"learning_rate": 4.2707255744537834e-05,
"loss": 3.7541,
"step": 445440
},
{
"epoch": 0.02,
"learning_rate": 4.2698869797027314e-05,
"loss": 3.7518,
"step": 445952
},
{
"epoch": 0.02,
"learning_rate": 4.2690483849516794e-05,
"loss": 3.7531,
"step": 446464
},
{
"epoch": 0.02,
"learning_rate": 4.268211428081e-05,
"loss": 3.7492,
"step": 446976
},
{
"epoch": 0.02,
"learning_rate": 4.267372833329948e-05,
"loss": 3.7503,
"step": 447488
},
{
"epoch": 0.02,
"learning_rate": 4.266534238578896e-05,
"loss": 3.7541,
"step": 448000
},
{
"epoch": 0.02,
"learning_rate": 4.265695643827844e-05,
"loss": 3.7664,
"step": 448512
},
{
"epoch": 0.02,
"learning_rate": 4.264858686957165e-05,
"loss": 3.762,
"step": 449024
},
{
"epoch": 0.02,
"learning_rate": 4.264020092206113e-05,
"loss": 3.7463,
"step": 449536
},
{
"epoch": 0.02,
"learning_rate": 4.263181497455062e-05,
"loss": 3.759,
"step": 450048
},
{
"epoch": 0.02,
"learning_rate": 4.26234290270401e-05,
"loss": 3.7547,
"step": 450560
},
{
"epoch": 0.02,
"learning_rate": 4.261505945833331e-05,
"loss": 3.7598,
"step": 451072
},
{
"epoch": 0.02,
"learning_rate": 4.260667351082279e-05,
"loss": 3.7538,
"step": 451584
},
{
"epoch": 0.02,
"learning_rate": 4.259828756331227e-05,
"loss": 3.7556,
"step": 452096
},
{
"epoch": 0.02,
"learning_rate": 4.258990161580175e-05,
"loss": 3.7487,
"step": 452608
},
{
"epoch": 0.02,
"learning_rate": 4.258153204709496e-05,
"loss": 3.7558,
"step": 453120
},
{
"epoch": 0.02,
"learning_rate": 4.257314609958444e-05,
"loss": 3.744,
"step": 453632
},
{
"epoch": 0.02,
"learning_rate": 4.256476015207392e-05,
"loss": 3.7505,
"step": 454144
},
{
"epoch": 0.02,
"learning_rate": 4.25563742045634e-05,
"loss": 3.75,
"step": 454656
},
{
"epoch": 0.02,
"learning_rate": 4.2548004635856606e-05,
"loss": 3.7508,
"step": 455168
},
{
"epoch": 0.02,
"learning_rate": 4.2539618688346086e-05,
"loss": 3.7559,
"step": 455680
},
{
"epoch": 0.02,
"learning_rate": 4.253123274083557e-05,
"loss": 3.75,
"step": 456192
},
{
"epoch": 0.02,
"learning_rate": 4.252284679332505e-05,
"loss": 3.7594,
"step": 456704
},
{
"epoch": 0.02,
"learning_rate": 4.251447722461826e-05,
"loss": 3.7431,
"step": 457216
},
{
"epoch": 0.02,
"learning_rate": 4.250609127710774e-05,
"loss": 3.7537,
"step": 457728
},
{
"epoch": 0.03,
"eval_loss": 3.868818759918213,
"eval_runtime": 303.073,
"eval_samples_per_second": 1259.073,
"eval_steps_per_second": 39.347,
"step": 457920
},
{
"epoch": 1.0,
"learning_rate": 4.249770532959722e-05,
"loss": 3.7498,
"step": 458240
},
{
"epoch": 1.0,
"learning_rate": 4.24893193820867e-05,
"loss": 3.7289,
"step": 458752
},
{
"epoch": 1.0,
"learning_rate": 4.248094981337991e-05,
"loss": 3.7578,
"step": 459264
},
{
"epoch": 1.0,
"learning_rate": 4.247256386586939e-05,
"loss": 3.7491,
"step": 459776
},
{
"epoch": 1.0,
"learning_rate": 4.246417791835887e-05,
"loss": 3.759,
"step": 460288
},
{
"epoch": 1.0,
"learning_rate": 4.245579197084835e-05,
"loss": 3.7431,
"step": 460800
},
{
"epoch": 1.0,
"learning_rate": 4.244742240214156e-05,
"loss": 3.7422,
"step": 461312
},
{
"epoch": 1.0,
"learning_rate": 4.243903645463104e-05,
"loss": 3.7405,
"step": 461824
},
{
"epoch": 1.0,
"learning_rate": 4.243065050712052e-05,
"loss": 3.7459,
"step": 462336
},
{
"epoch": 1.0,
"learning_rate": 4.2422280938413735e-05,
"loss": 3.7441,
"step": 462848
},
{
"epoch": 1.0,
"learning_rate": 4.2413894990903215e-05,
"loss": 3.7526,
"step": 463360
},
{
"epoch": 1.0,
"learning_rate": 4.2405509043392695e-05,
"loss": 3.7548,
"step": 463872
},
{
"epoch": 1.0,
"learning_rate": 4.2397123095882175e-05,
"loss": 3.7302,
"step": 464384
},
{
"epoch": 1.0,
"learning_rate": 4.2388737148371655e-05,
"loss": 3.7379,
"step": 464896
},
{
"epoch": 1.0,
"learning_rate": 4.2380351200861135e-05,
"loss": 3.7457,
"step": 465408
},
{
"epoch": 1.0,
"learning_rate": 4.2371965253350615e-05,
"loss": 3.732,
"step": 465920
},
{
"epoch": 1.0,
"learning_rate": 4.2363579305840095e-05,
"loss": 3.7388,
"step": 466432
},
{
"epoch": 1.0,
"learning_rate": 4.2355209737133304e-05,
"loss": 3.7385,
"step": 466944
},
{
"epoch": 1.0,
"learning_rate": 4.2346823789622784e-05,
"loss": 3.7388,
"step": 467456
},
{
"epoch": 1.0,
"learning_rate": 4.2338437842112264e-05,
"loss": 3.7553,
"step": 467968
},
{
"epoch": 1.0,
"learning_rate": 4.2330051894601744e-05,
"loss": 3.7439,
"step": 468480
},
{
"epoch": 1.0,
"learning_rate": 4.232168232589496e-05,
"loss": 3.7442,
"step": 468992
},
{
"epoch": 1.0,
"learning_rate": 4.231329637838444e-05,
"loss": 3.7401,
"step": 469504
},
{
"epoch": 1.0,
"learning_rate": 4.230491043087392e-05,
"loss": 3.7468,
"step": 470016
},
{
"epoch": 1.0,
"learning_rate": 4.22965244833634e-05,
"loss": 3.7374,
"step": 470528
},
{
"epoch": 1.0,
"learning_rate": 4.228815491465661e-05,
"loss": 3.7438,
"step": 471040
},
{
"epoch": 1.0,
"learning_rate": 4.227976896714609e-05,
"loss": 3.7349,
"step": 471552
},
{
"epoch": 1.0,
"learning_rate": 4.227138301963557e-05,
"loss": 3.7335,
"step": 472064
},
{
"epoch": 1.0,
"learning_rate": 4.226299707212505e-05,
"loss": 3.7353,
"step": 472576
},
{
"epoch": 1.0,
"learning_rate": 4.225462750341826e-05,
"loss": 3.7368,
"step": 473088
},
{
"epoch": 1.01,
"learning_rate": 4.224624155590774e-05,
"loss": 3.7389,
"step": 473600
},
{
"epoch": 1.01,
"learning_rate": 4.223785560839722e-05,
"loss": 3.7407,
"step": 474112
},
{
"epoch": 1.01,
"learning_rate": 4.22294696608867e-05,
"loss": 3.7467,
"step": 474624
},
{
"epoch": 1.01,
"learning_rate": 4.2221100092179914e-05,
"loss": 3.7476,
"step": 475136
},
{
"epoch": 1.01,
"learning_rate": 4.2212714144669394e-05,
"loss": 3.7343,
"step": 475648
},
{
"epoch": 1.01,
"learning_rate": 4.2204328197158874e-05,
"loss": 3.7398,
"step": 476160
},
{
"epoch": 1.01,
"learning_rate": 4.2195942249648353e-05,
"loss": 3.7383,
"step": 476672
},
{
"epoch": 1.01,
"learning_rate": 4.218757268094156e-05,
"loss": 3.7333,
"step": 477184
},
{
"epoch": 1.01,
"learning_rate": 4.217918673343104e-05,
"loss": 3.7225,
"step": 477696
},
{
"epoch": 1.01,
"learning_rate": 4.217080078592052e-05,
"loss": 3.7322,
"step": 478208
},
{
"epoch": 1.01,
"learning_rate": 4.216241483841e-05,
"loss": 3.7326,
"step": 478720
},
{
"epoch": 1.01,
"learning_rate": 4.215404526970321e-05,
"loss": 3.7375,
"step": 479232
},
{
"epoch": 1.01,
"learning_rate": 4.214565932219269e-05,
"loss": 3.7306,
"step": 479744
},
{
"epoch": 1.01,
"learning_rate": 4.213727337468217e-05,
"loss": 3.7318,
"step": 480256
},
{
"epoch": 1.01,
"learning_rate": 4.212888742717165e-05,
"loss": 3.7511,
"step": 480768
},
{
"epoch": 1.01,
"learning_rate": 4.212051785846487e-05,
"loss": 3.7368,
"step": 481280
},
{
"epoch": 1.01,
"learning_rate": 4.211213191095435e-05,
"loss": 3.7412,
"step": 481792
},
{
"epoch": 1.01,
"learning_rate": 4.210374596344383e-05,
"loss": 3.7266,
"step": 482304
},
{
"epoch": 1.01,
"learning_rate": 4.209536001593331e-05,
"loss": 3.7173,
"step": 482816
},
{
"epoch": 1.01,
"learning_rate": 4.2086990447226516e-05,
"loss": 3.7435,
"step": 483328
},
{
"epoch": 1.01,
"learning_rate": 4.2078604499715996e-05,
"loss": 3.7336,
"step": 483840
},
{
"epoch": 1.01,
"learning_rate": 4.2070218552205476e-05,
"loss": 3.7286,
"step": 484352
},
{
"epoch": 1.01,
"learning_rate": 4.206183260469495e-05,
"loss": 3.7297,
"step": 484864
},
{
"epoch": 1.01,
"learning_rate": 4.2053479414791894e-05,
"loss": 3.7355,
"step": 485376
},
{
"epoch": 1.01,
"learning_rate": 4.2045093467281374e-05,
"loss": 3.7111,
"step": 485888
},
{
"epoch": 1.01,
"learning_rate": 4.2036707519770854e-05,
"loss": 3.7323,
"step": 486400
},
{
"epoch": 1.01,
"learning_rate": 4.2028321572260334e-05,
"loss": 3.7244,
"step": 486912
},
{
"epoch": 1.01,
"learning_rate": 4.201993562474982e-05,
"loss": 3.7234,
"step": 487424
},
{
"epoch": 1.01,
"learning_rate": 4.20115496772393e-05,
"loss": 3.7404,
"step": 487936
},
{
"epoch": 1.01,
"learning_rate": 4.200316372972878e-05,
"loss": 3.7275,
"step": 488448
},
{
"epoch": 1.01,
"learning_rate": 4.1994777782218254e-05,
"loss": 3.7222,
"step": 488960
},
{
"epoch": 1.01,
"learning_rate": 4.198640821351147e-05,
"loss": 3.7332,
"step": 489472
},
{
"epoch": 1.01,
"learning_rate": 4.197802226600095e-05,
"loss": 3.7212,
"step": 489984
},
{
"epoch": 1.01,
"learning_rate": 4.196963631849042e-05,
"loss": 3.7232,
"step": 490496
},
{
"epoch": 1.01,
"learning_rate": 4.19612503709799e-05,
"loss": 3.7246,
"step": 491008
},
{
"epoch": 1.01,
"learning_rate": 4.195288080227312e-05,
"loss": 3.7244,
"step": 491520
},
{
"epoch": 1.01,
"learning_rate": 4.19444948547626e-05,
"loss": 3.7258,
"step": 492032
},
{
"epoch": 1.01,
"learning_rate": 4.193610890725207e-05,
"loss": 3.7201,
"step": 492544
},
{
"epoch": 1.01,
"learning_rate": 4.192772295974156e-05,
"loss": 3.7099,
"step": 493056
},
{
"epoch": 1.01,
"learning_rate": 4.1919353391034775e-05,
"loss": 3.7234,
"step": 493568
},
{
"epoch": 1.01,
"learning_rate": 4.191096744352425e-05,
"loss": 3.7363,
"step": 494080
},
{
"epoch": 1.01,
"learning_rate": 4.190258149601373e-05,
"loss": 3.7204,
"step": 494592
},
{
"epoch": 1.01,
"learning_rate": 4.189419554850321e-05,
"loss": 3.743,
"step": 495104
},
{
"epoch": 1.01,
"learning_rate": 4.1885825979796424e-05,
"loss": 3.7354,
"step": 495616
},
{
"epoch": 1.01,
"learning_rate": 4.18774400322859e-05,
"loss": 3.734,
"step": 496128
},
{
"epoch": 1.01,
"learning_rate": 4.186905408477538e-05,
"loss": 3.7182,
"step": 496640
},
{
"epoch": 1.01,
"learning_rate": 4.186066813726486e-05,
"loss": 3.7357,
"step": 497152
},
{
"epoch": 1.01,
"learning_rate": 4.185229856855807e-05,
"loss": 3.7258,
"step": 497664
},
{
"epoch": 1.01,
"learning_rate": 4.1843912621047546e-05,
"loss": 3.7195,
"step": 498176
},
{
"epoch": 1.01,
"learning_rate": 4.1835526673537026e-05,
"loss": 3.7339,
"step": 498688
},
{
"epoch": 1.01,
"learning_rate": 4.182714072602651e-05,
"loss": 3.7284,
"step": 499200
},
{
"epoch": 1.01,
"learning_rate": 4.181877115731972e-05,
"loss": 3.7295,
"step": 499712
},
{
"epoch": 1.01,
"learning_rate": 4.18103852098092e-05,
"loss": 3.7278,
"step": 500224
},
{
"epoch": 1.01,
"learning_rate": 4.180199926229868e-05,
"loss": 3.7078,
"step": 500736
},
{
"epoch": 1.01,
"learning_rate": 4.179361331478816e-05,
"loss": 3.709,
"step": 501248
},
{
"epoch": 1.01,
"learning_rate": 4.178524374608137e-05,
"loss": 3.721,
"step": 501760
},
{
"epoch": 1.01,
"learning_rate": 4.177685779857085e-05,
"loss": 3.7283,
"step": 502272
},
{
"epoch": 1.01,
"learning_rate": 4.176847185106033e-05,
"loss": 3.7233,
"step": 502784
},
{
"epoch": 1.01,
"learning_rate": 4.176008590354981e-05,
"loss": 3.719,
"step": 503296
},
{
"epoch": 1.02,
"learning_rate": 4.175171633484302e-05,
"loss": 3.7236,
"step": 503808
},
{
"epoch": 1.02,
"learning_rate": 4.17433303873325e-05,
"loss": 3.7154,
"step": 504320
},
{
"epoch": 1.02,
"learning_rate": 4.173494443982198e-05,
"loss": 3.7234,
"step": 504832
},
{
"epoch": 1.02,
"learning_rate": 4.1726558492311466e-05,
"loss": 3.717,
"step": 505344
},
{
"epoch": 1.02,
"learning_rate": 4.1718188923604675e-05,
"loss": 3.7361,
"step": 505856
},
{
"epoch": 1.02,
"learning_rate": 4.1709802976094155e-05,
"loss": 3.7364,
"step": 506368
},
{
"epoch": 1.02,
"learning_rate": 4.1701417028583635e-05,
"loss": 3.7257,
"step": 506880
},
{
"epoch": 1.02,
"learning_rate": 4.1693031081073115e-05,
"loss": 3.7182,
"step": 507392
},
{
"epoch": 1.02,
"learning_rate": 4.1684661512366324e-05,
"loss": 3.7256,
"step": 507904
},
{
"epoch": 1.02,
"learning_rate": 4.1676275564855804e-05,
"loss": 3.7185,
"step": 508416
},
{
"epoch": 1.02,
"learning_rate": 4.1667889617345284e-05,
"loss": 3.7368,
"step": 508928
},
{
"epoch": 1.02,
"learning_rate": 4.1659503669834764e-05,
"loss": 3.7174,
"step": 509440
},
{
"epoch": 1.02,
"learning_rate": 4.165113410112797e-05,
"loss": 3.7196,
"step": 509952
},
{
"epoch": 1.02,
"learning_rate": 4.164274815361745e-05,
"loss": 3.7262,
"step": 510464
},
{
"epoch": 1.02,
"learning_rate": 4.163436220610693e-05,
"loss": 3.7247,
"step": 510976
},
{
"epoch": 1.02,
"learning_rate": 4.162597625859642e-05,
"loss": 3.7126,
"step": 511488
},
{
"epoch": 1.02,
"learning_rate": 4.161760668988963e-05,
"loss": 3.7229,
"step": 512000
},
{
"epoch": 1.02,
"learning_rate": 4.160922074237911e-05,
"loss": 3.7146,
"step": 512512
},
{
"epoch": 1.02,
"learning_rate": 4.160083479486859e-05,
"loss": 3.7106,
"step": 513024
},
{
"epoch": 1.02,
"learning_rate": 4.159244884735807e-05,
"loss": 3.7054,
"step": 513536
},
{
"epoch": 1.02,
"learning_rate": 4.158407927865128e-05,
"loss": 3.7197,
"step": 514048
},
{
"epoch": 1.02,
"learning_rate": 4.157569333114076e-05,
"loss": 3.7201,
"step": 514560
},
{
"epoch": 1.02,
"learning_rate": 4.156730738363024e-05,
"loss": 3.7132,
"step": 515072
},
{
"epoch": 1.02,
"learning_rate": 4.155892143611972e-05,
"loss": 3.7162,
"step": 515584
},
{
"epoch": 1.02,
"learning_rate": 4.155055186741293e-05,
"loss": 3.7119,
"step": 516096
},
{
"epoch": 1.02,
"learning_rate": 4.154216591990241e-05,
"loss": 3.7291,
"step": 516608
},
{
"epoch": 1.02,
"learning_rate": 4.153377997239189e-05,
"loss": 3.7314,
"step": 517120
},
{
"epoch": 1.02,
"learning_rate": 4.152539402488137e-05,
"loss": 3.7259,
"step": 517632
},
{
"epoch": 1.02,
"learning_rate": 4.151702445617458e-05,
"loss": 3.7222,
"step": 518144
},
{
"epoch": 1.02,
"learning_rate": 4.150863850866406e-05,
"loss": 3.714,
"step": 518656
},
{
"epoch": 1.02,
"learning_rate": 4.150025256115354e-05,
"loss": 3.7167,
"step": 519168
},
{
"epoch": 1.02,
"learning_rate": 4.149186661364302e-05,
"loss": 3.706,
"step": 519680
},
{
"epoch": 1.02,
"learning_rate": 4.148349704493623e-05,
"loss": 3.713,
"step": 520192
},
{
"epoch": 1.02,
"learning_rate": 4.147511109742571e-05,
"loss": 3.7169,
"step": 520704
},
{
"epoch": 1.02,
"learning_rate": 4.146672514991519e-05,
"loss": 3.7185,
"step": 521216
},
{
"epoch": 1.02,
"learning_rate": 4.145833920240467e-05,
"loss": 3.72,
"step": 521728
},
{
"epoch": 1.02,
"learning_rate": 4.144996963369788e-05,
"loss": 3.7161,
"step": 522240
},
{
"epoch": 1.02,
"learning_rate": 4.144158368618736e-05,
"loss": 3.7227,
"step": 522752
},
{
"epoch": 1.02,
"learning_rate": 4.143319773867684e-05,
"loss": 3.7124,
"step": 523264
},
{
"epoch": 1.02,
"learning_rate": 4.1424828169970056e-05,
"loss": 3.7186,
"step": 523776
},
{
"epoch": 1.02,
"learning_rate": 4.1416442222459536e-05,
"loss": 3.7165,
"step": 524288
},
{
"epoch": 1.02,
"learning_rate": 4.1408056274949016e-05,
"loss": 3.724,
"step": 524800
},
{
"epoch": 1.02,
"learning_rate": 4.1399670327438496e-05,
"loss": 3.7291,
"step": 525312
},
{
"epoch": 1.02,
"learning_rate": 4.1391300758731705e-05,
"loss": 3.7115,
"step": 525824
},
{
"epoch": 1.02,
"learning_rate": 4.1382914811221185e-05,
"loss": 3.7237,
"step": 526336
},
{
"epoch": 1.02,
"learning_rate": 4.1374528863710665e-05,
"loss": 3.7193,
"step": 526848
},
{
"epoch": 1.02,
"learning_rate": 4.1366142916200145e-05,
"loss": 3.7251,
"step": 527360
},
{
"epoch": 1.02,
"learning_rate": 4.1357773347493354e-05,
"loss": 3.7167,
"step": 527872
},
{
"epoch": 1.02,
"learning_rate": 4.1349387399982834e-05,
"loss": 3.7235,
"step": 528384
},
{
"epoch": 1.02,
"learning_rate": 4.1341001452472314e-05,
"loss": 3.7095,
"step": 528896
},
{
"epoch": 1.02,
"learning_rate": 4.1332615504961794e-05,
"loss": 3.7222,
"step": 529408
},
{
"epoch": 1.02,
"learning_rate": 4.132424593625501e-05,
"loss": 3.7062,
"step": 529920
},
{
"epoch": 1.02,
"learning_rate": 4.131585998874449e-05,
"loss": 3.7162,
"step": 530432
},
{
"epoch": 1.02,
"learning_rate": 4.130747404123397e-05,
"loss": 3.7145,
"step": 530944
},
{
"epoch": 1.02,
"learning_rate": 4.129908809372345e-05,
"loss": 3.7176,
"step": 531456
},
{
"epoch": 1.02,
"learning_rate": 4.129071852501666e-05,
"loss": 3.7164,
"step": 531968
},
{
"epoch": 1.02,
"learning_rate": 4.128233257750614e-05,
"loss": 3.7169,
"step": 532480
},
{
"epoch": 1.02,
"learning_rate": 4.127394662999562e-05,
"loss": 3.7212,
"step": 532992
},
{
"epoch": 1.02,
"learning_rate": 4.12655606824851e-05,
"loss": 3.708,
"step": 533504
},
{
"epoch": 1.02,
"learning_rate": 4.125719111377831e-05,
"loss": 3.7243,
"step": 534016
},
{
"epoch": 1.03,
"eval_loss": 3.8584983348846436,
"eval_runtime": 302.6085,
"eval_samples_per_second": 1261.006,
"eval_steps_per_second": 39.407,
"step": 534240
},
{
"epoch": 0.0,
"learning_rate": 4.124880516626779e-05,
"loss": 3.7075,
"step": 534528
},
{
"epoch": 0.0,
"learning_rate": 4.124041921875727e-05,
"loss": 3.6983,
"step": 535040
},
{
"epoch": 0.0,
"learning_rate": 4.123203327124675e-05,
"loss": 3.7167,
"step": 535552
},
{
"epoch": 0.0,
"learning_rate": 4.122364732373623e-05,
"loss": 3.7151,
"step": 536064
},
{
"epoch": 0.0,
"learning_rate": 4.1215261376225714e-05,
"loss": 3.7205,
"step": 536576
},
{
"epoch": 0.0,
"learning_rate": 4.1206875428715194e-05,
"loss": 3.7097,
"step": 537088
},
{
"epoch": 0.0,
"learning_rate": 4.1198489481204674e-05,
"loss": 3.7086,
"step": 537600
},
{
"epoch": 0.0,
"learning_rate": 4.1190103533694154e-05,
"loss": 3.7075,
"step": 538112
},
{
"epoch": 0.0,
"learning_rate": 4.118173396498736e-05,
"loss": 3.7114,
"step": 538624
},
{
"epoch": 0.0,
"learning_rate": 4.117336439628057e-05,
"loss": 3.7077,
"step": 539136
},
{
"epoch": 0.0,
"learning_rate": 4.116497844877005e-05,
"loss": 3.7174,
"step": 539648
},
{
"epoch": 0.0,
"learning_rate": 4.115659250125953e-05,
"loss": 3.7161,
"step": 540160
},
{
"epoch": 0.0,
"learning_rate": 4.114820655374901e-05,
"loss": 3.702,
"step": 540672
},
{
"epoch": 0.0,
"learning_rate": 4.113982060623849e-05,
"loss": 3.7008,
"step": 541184
},
{
"epoch": 0.0,
"learning_rate": 4.113143465872797e-05,
"loss": 3.7122,
"step": 541696
},
{
"epoch": 0.0,
"learning_rate": 4.112304871121745e-05,
"loss": 3.6944,
"step": 542208
},
{
"epoch": 0.0,
"learning_rate": 4.111466276370693e-05,
"loss": 3.7076,
"step": 542720
},
{
"epoch": 0.0,
"learning_rate": 4.110629319500015e-05,
"loss": 3.7052,
"step": 543232
},
{
"epoch": 0.0,
"learning_rate": 4.109790724748963e-05,
"loss": 3.7063,
"step": 543744
},
{
"epoch": 0.0,
"learning_rate": 4.10895212999791e-05,
"loss": 3.7162,
"step": 544256
},
{
"epoch": 0.0,
"learning_rate": 4.108113535246858e-05,
"loss": 3.7128,
"step": 544768
},
{
"epoch": 0.0,
"learning_rate": 4.10727657837618e-05,
"loss": 3.707,
"step": 545280
},
{
"epoch": 0.0,
"learning_rate": 4.106437983625127e-05,
"loss": 3.7072,
"step": 545792
},
{
"epoch": 0.0,
"learning_rate": 4.105599388874075e-05,
"loss": 3.7079,
"step": 546304
},
{
"epoch": 0.0,
"learning_rate": 4.104760794123023e-05,
"loss": 3.7045,
"step": 546816
},
{
"epoch": 0.0,
"learning_rate": 4.1039238372523446e-05,
"loss": 3.7122,
"step": 547328
},
{
"epoch": 0.0,
"learning_rate": 4.103085242501292e-05,
"loss": 3.7038,
"step": 547840
},
{
"epoch": 0.0,
"learning_rate": 4.1022466477502406e-05,
"loss": 3.6978,
"step": 548352
},
{
"epoch": 0.0,
"learning_rate": 4.101409690879562e-05,
"loss": 3.6993,
"step": 548864
},
{
"epoch": 0.0,
"learning_rate": 4.10057109612851e-05,
"loss": 3.7085,
"step": 549376
},
{
"epoch": 0.01,
"learning_rate": 4.0997325013774575e-05,
"loss": 3.7007,
"step": 549888
},
{
"epoch": 0.01,
"learning_rate": 4.0988939066264055e-05,
"loss": 3.7091,
"step": 550400
},
{
"epoch": 0.01,
"learning_rate": 4.0980553118753535e-05,
"loss": 3.7144,
"step": 550912
},
{
"epoch": 0.01,
"learning_rate": 4.0972183550046744e-05,
"loss": 3.7102,
"step": 551424
},
{
"epoch": 0.01,
"learning_rate": 4.0963797602536224e-05,
"loss": 3.6969,
"step": 551936
},
{
"epoch": 0.01,
"learning_rate": 4.0955411655025704e-05,
"loss": 3.7071,
"step": 552448
},
{
"epoch": 0.01,
"learning_rate": 4.094704208631892e-05,
"loss": 3.7055,
"step": 552960
},
{
"epoch": 0.01,
"learning_rate": 4.093865613880839e-05,
"loss": 3.6979,
"step": 553472
},
{
"epoch": 0.01,
"learning_rate": 4.093027019129787e-05,
"loss": 3.6896,
"step": 553984
},
{
"epoch": 0.01,
"learning_rate": 4.092188424378736e-05,
"loss": 3.6967,
"step": 554496
},
{
"epoch": 0.01,
"learning_rate": 4.0913514675080575e-05,
"loss": 3.7015,
"step": 555008
},
{
"epoch": 0.01,
"learning_rate": 4.090512872757005e-05,
"loss": 3.7041,
"step": 555520
},
{
"epoch": 0.01,
"learning_rate": 4.089674278005953e-05,
"loss": 3.6968,
"step": 556032
},
{
"epoch": 0.01,
"learning_rate": 4.088835683254901e-05,
"loss": 3.6981,
"step": 556544
},
{
"epoch": 0.01,
"learning_rate": 4.087998726384222e-05,
"loss": 3.7153,
"step": 557056
},
{
"epoch": 0.01,
"learning_rate": 4.08716013163317e-05,
"loss": 3.7034,
"step": 557568
},
{
"epoch": 0.01,
"learning_rate": 4.086321536882118e-05,
"loss": 3.7092,
"step": 558080
},
{
"epoch": 0.01,
"learning_rate": 4.085482942131066e-05,
"loss": 3.6939,
"step": 558592
},
{
"epoch": 0.01,
"learning_rate": 4.0846459852603867e-05,
"loss": 3.6814,
"step": 559104
},
{
"epoch": 0.01,
"learning_rate": 4.0838073905093346e-05,
"loss": 3.7124,
"step": 559616
},
{
"epoch": 0.01,
"learning_rate": 4.0829687957582826e-05,
"loss": 3.6999,
"step": 560128
},
{
"epoch": 0.01,
"learning_rate": 4.082130201007231e-05,
"loss": 3.6945,
"step": 560640
},
{
"epoch": 0.01,
"learning_rate": 4.081293244136552e-05,
"loss": 3.7016,
"step": 561152
},
{
"epoch": 0.01,
"learning_rate": 4.0804546493855e-05,
"loss": 3.6944,
"step": 561664
},
{
"epoch": 0.01,
"learning_rate": 4.079617692514822e-05,
"loss": 3.687,
"step": 562176
},
{
"epoch": 0.01,
"learning_rate": 4.078779097763769e-05,
"loss": 3.6935,
"step": 562688
},
{
"epoch": 0.01,
"learning_rate": 4.077940503012717e-05,
"loss": 3.6921,
"step": 563200
},
{
"epoch": 0.01,
"learning_rate": 4.077101908261665e-05,
"loss": 3.6935,
"step": 563712
},
{
"epoch": 0.01,
"learning_rate": 4.076263313510613e-05,
"loss": 3.7024,
"step": 564224
},
{
"epoch": 0.01,
"learning_rate": 4.075424718759561e-05,
"loss": 3.6935,
"step": 564736
},
{
"epoch": 0.01,
"learning_rate": 4.074586124008509e-05,
"loss": 3.6907,
"step": 565248
},
{
"epoch": 0.01,
"learning_rate": 4.07374916713783e-05,
"loss": 3.7026,
"step": 565760
},
{
"epoch": 0.01,
"learning_rate": 4.072910572386778e-05,
"loss": 3.6848,
"step": 566272
},
{
"epoch": 0.01,
"learning_rate": 4.072071977635726e-05,
"loss": 3.6898,
"step": 566784
},
{
"epoch": 0.01,
"learning_rate": 4.071233382884675e-05,
"loss": 3.6913,
"step": 567296
},
{
"epoch": 0.01,
"learning_rate": 4.0703964260139956e-05,
"loss": 3.6952,
"step": 567808
},
{
"epoch": 0.01,
"learning_rate": 4.0695578312629436e-05,
"loss": 3.6891,
"step": 568320
},
{
"epoch": 0.01,
"learning_rate": 4.0687192365118916e-05,
"loss": 3.6922,
"step": 568832
},
{
"epoch": 0.01,
"learning_rate": 4.0678806417608396e-05,
"loss": 3.6736,
"step": 569344
},
{
"epoch": 0.01,
"learning_rate": 4.0670436848901605e-05,
"loss": 3.6915,
"step": 569856
},
{
"epoch": 0.01,
"learning_rate": 4.0662050901391085e-05,
"loss": 3.7051,
"step": 570368
},
{
"epoch": 0.01,
"learning_rate": 4.0653664953880565e-05,
"loss": 3.6891,
"step": 570880
},
{
"epoch": 0.01,
"learning_rate": 4.0645279006370045e-05,
"loss": 3.709,
"step": 571392
},
{
"epoch": 0.01,
"learning_rate": 4.0636909437663254e-05,
"loss": 3.7001,
"step": 571904
},
{
"epoch": 0.01,
"learning_rate": 4.0628523490152734e-05,
"loss": 3.7042,
"step": 572416
},
{
"epoch": 0.01,
"learning_rate": 4.0620137542642214e-05,
"loss": 3.6883,
"step": 572928
},
{
"epoch": 0.01,
"learning_rate": 4.06117515951317e-05,
"loss": 3.7031,
"step": 573440
},
{
"epoch": 0.01,
"learning_rate": 4.060338202642491e-05,
"loss": 3.6948,
"step": 573952
},
{
"epoch": 0.01,
"learning_rate": 4.059499607891439e-05,
"loss": 3.6876,
"step": 574464
},
{
"epoch": 0.01,
"learning_rate": 4.058661013140387e-05,
"loss": 3.7036,
"step": 574976
},
{
"epoch": 0.01,
"learning_rate": 4.057822418389335e-05,
"loss": 3.6951,
"step": 575488
},
{
"epoch": 0.01,
"learning_rate": 4.056983823638283e-05,
"loss": 3.6977,
"step": 576000
},
{
"epoch": 0.01,
"learning_rate": 4.056145228887231e-05,
"loss": 3.6953,
"step": 576512
},
{
"epoch": 0.01,
"learning_rate": 4.055306634136179e-05,
"loss": 3.673,
"step": 577024
},
{
"epoch": 0.01,
"learning_rate": 4.0544696772655e-05,
"loss": 3.6836,
"step": 577536
},
{
"epoch": 0.01,
"learning_rate": 4.053631082514448e-05,
"loss": 3.6849,
"step": 578048
},
{
"epoch": 0.01,
"learning_rate": 4.052792487763396e-05,
"loss": 3.6982,
"step": 578560
},
{
"epoch": 0.01,
"learning_rate": 4.051953893012344e-05,
"loss": 3.6935,
"step": 579072
},
{
"epoch": 0.01,
"learning_rate": 4.0511169361416654e-05,
"loss": 3.6865,
"step": 579584
},
{
"epoch": 0.02,
"learning_rate": 4.0502783413906134e-05,
"loss": 3.6897,
"step": 580096
},
{
"epoch": 0.02,
"learning_rate": 4.0494397466395614e-05,
"loss": 3.6848,
"step": 580608
},
{
"epoch": 0.02,
"learning_rate": 4.0486011518885094e-05,
"loss": 3.6873,
"step": 581120
},
{
"epoch": 0.02,
"learning_rate": 4.04776419501783e-05,
"loss": 3.687,
"step": 581632
},
{
"epoch": 0.02,
"learning_rate": 4.046925600266778e-05,
"loss": 3.7025,
"step": 582144
},
{
"epoch": 0.02,
"learning_rate": 4.046087005515726e-05,
"loss": 3.709,
"step": 582656
},
{
"epoch": 0.02,
"learning_rate": 4.045248410764674e-05,
"loss": 3.6891,
"step": 583168
},
{
"epoch": 0.02,
"learning_rate": 4.044411453893995e-05,
"loss": 3.6861,
"step": 583680
},
{
"epoch": 0.02,
"learning_rate": 4.043572859142943e-05,
"loss": 3.6931,
"step": 584192
},
{
"epoch": 0.02,
"learning_rate": 4.042734264391891e-05,
"loss": 3.6866,
"step": 584704
},
{
"epoch": 0.02,
"learning_rate": 4.041895669640839e-05,
"loss": 3.7018,
"step": 585216
},
{
"epoch": 0.02,
"learning_rate": 4.041058712770161e-05,
"loss": 3.687,
"step": 585728
},
{
"epoch": 0.02,
"learning_rate": 4.040220118019109e-05,
"loss": 3.6896,
"step": 586240
},
{
"epoch": 0.02,
"learning_rate": 4.039381523268057e-05,
"loss": 3.6944,
"step": 586752
},
{
"epoch": 0.02,
"learning_rate": 4.038542928517005e-05,
"loss": 3.6948,
"step": 587264
},
{
"epoch": 0.02,
"learning_rate": 4.037705971646326e-05,
"loss": 3.6802,
"step": 587776
},
{
"epoch": 0.02,
"learning_rate": 4.036867376895274e-05,
"loss": 3.6909,
"step": 588288
},
{
"epoch": 0.02,
"learning_rate": 4.036028782144222e-05,
"loss": 3.6867,
"step": 588800
},
{
"epoch": 0.02,
"learning_rate": 4.03519018739317e-05,
"loss": 3.6788,
"step": 589312
},
{
"epoch": 0.02,
"learning_rate": 4.0343532305224906e-05,
"loss": 3.6759,
"step": 589824
},
{
"epoch": 0.02,
"learning_rate": 4.0335146357714386e-05,
"loss": 3.6873,
"step": 590336
},
{
"epoch": 0.02,
"learning_rate": 4.0326760410203866e-05,
"loss": 3.6898,
"step": 590848
},
{
"epoch": 0.02,
"learning_rate": 4.0318374462693346e-05,
"loss": 3.683,
"step": 591360
},
{
"epoch": 0.02,
"learning_rate": 4.031000489398656e-05,
"loss": 3.6863,
"step": 591872
},
{
"epoch": 0.02,
"learning_rate": 4.030161894647604e-05,
"loss": 3.681,
"step": 592384
},
{
"epoch": 0.02,
"learning_rate": 4.029323299896552e-05,
"loss": 3.7002,
"step": 592896
},
{
"epoch": 0.02,
"learning_rate": 4.0284847051455e-05,
"loss": 3.6995,
"step": 593408
},
{
"epoch": 0.02,
"learning_rate": 4.027647748274821e-05,
"loss": 3.6946,
"step": 593920
},
{
"epoch": 0.02,
"learning_rate": 4.026809153523769e-05,
"loss": 3.6899,
"step": 594432
},
{
"epoch": 0.02,
"learning_rate": 4.025970558772717e-05,
"loss": 3.678,
"step": 594944
},
{
"epoch": 0.02,
"learning_rate": 4.025131964021665e-05,
"loss": 3.6895,
"step": 595456
},
{
"epoch": 0.02,
"learning_rate": 4.024295007150986e-05,
"loss": 3.6764,
"step": 595968
},
{
"epoch": 0.02,
"learning_rate": 4.023456412399934e-05,
"loss": 3.6851,
"step": 596480
},
{
"epoch": 0.02,
"learning_rate": 4.022617817648882e-05,
"loss": 3.6823,
"step": 596992
},
{
"epoch": 0.02,
"learning_rate": 4.02177922289783e-05,
"loss": 3.6878,
"step": 597504
},
{
"epoch": 0.02,
"learning_rate": 4.0209422660271515e-05,
"loss": 3.6864,
"step": 598016
},
{
"epoch": 0.02,
"learning_rate": 4.0201036712760995e-05,
"loss": 3.6863,
"step": 598528
},
{
"epoch": 0.02,
"learning_rate": 4.0192650765250475e-05,
"loss": 3.6938,
"step": 599040
},
{
"epoch": 0.02,
"learning_rate": 4.018426481773995e-05,
"loss": 3.6811,
"step": 599552
},
{
"epoch": 0.02,
"learning_rate": 4.0175895249033164e-05,
"loss": 3.6859,
"step": 600064
},
{
"epoch": 0.02,
"learning_rate": 4.0167509301522644e-05,
"loss": 3.6879,
"step": 600576
},
{
"epoch": 0.02,
"learning_rate": 4.0159123354012124e-05,
"loss": 3.6902,
"step": 601088
},
{
"epoch": 0.02,
"learning_rate": 4.01507374065016e-05,
"loss": 3.6988,
"step": 601600
},
{
"epoch": 0.02,
"learning_rate": 4.014236783779481e-05,
"loss": 3.6799,
"step": 602112
},
{
"epoch": 0.02,
"learning_rate": 4.013398189028429e-05,
"loss": 3.694,
"step": 602624
},
{
"epoch": 0.02,
"learning_rate": 4.0125595942773766e-05,
"loss": 3.6877,
"step": 603136
},
{
"epoch": 0.02,
"learning_rate": 4.011722637406698e-05,
"loss": 3.6916,
"step": 603648
},
{
"epoch": 0.02,
"learning_rate": 4.010884042655647e-05,
"loss": 3.6844,
"step": 604160
},
{
"epoch": 0.02,
"learning_rate": 4.010045447904595e-05,
"loss": 3.6909,
"step": 604672
},
{
"epoch": 0.02,
"learning_rate": 4.009206853153542e-05,
"loss": 3.6807,
"step": 605184
},
{
"epoch": 0.02,
"learning_rate": 4.00836825840249e-05,
"loss": 3.6925,
"step": 605696
},
{
"epoch": 0.02,
"learning_rate": 4.007531301531812e-05,
"loss": 3.6731,
"step": 606208
},
{
"epoch": 0.02,
"learning_rate": 4.00669270678076e-05,
"loss": 3.6848,
"step": 606720
},
{
"epoch": 0.02,
"learning_rate": 4.005854112029707e-05,
"loss": 3.6884,
"step": 607232
},
{
"epoch": 0.02,
"learning_rate": 4.005017155159029e-05,
"loss": 3.6892,
"step": 607744
},
{
"epoch": 0.02,
"learning_rate": 4.004178560407977e-05,
"loss": 3.6836,
"step": 608256
},
{
"epoch": 0.02,
"learning_rate": 4.003339965656924e-05,
"loss": 3.6819,
"step": 608768
},
{
"epoch": 0.02,
"learning_rate": 4.002501370905872e-05,
"loss": 3.6946,
"step": 609280
},
{
"epoch": 0.02,
"learning_rate": 4.0016644140351936e-05,
"loss": 3.6755,
"step": 609792
},
{
"epoch": 0.02,
"learning_rate": 4.000825819284142e-05,
"loss": 3.6946,
"step": 610304
},
{
"epoch": 0.03,
"eval_loss": 3.8521711826324463,
"eval_runtime": 301.3919,
"eval_samples_per_second": 1266.096,
"eval_steps_per_second": 39.566,
"step": 610560
},
{
"epoch": 1.0,
"learning_rate": 3.9999872245330896e-05,
"loss": 3.676,
"step": 610816
},
{
"epoch": 1.0,
"learning_rate": 3.9991486297820376e-05,
"loss": 3.6743,
"step": 611328
},
{
"epoch": 1.0,
"learning_rate": 3.998311672911359e-05,
"loss": 3.6829,
"step": 611840
},
{
"epoch": 1.0,
"learning_rate": 3.9974730781603065e-05,
"loss": 3.6851,
"step": 612352
},
{
"epoch": 1.0,
"learning_rate": 3.9966344834092545e-05,
"loss": 3.6942,
"step": 612864
},
{
"epoch": 1.0,
"learning_rate": 3.9957958886582025e-05,
"loss": 3.6781,
"step": 613376
},
{
"epoch": 1.0,
"learning_rate": 3.994958931787524e-05,
"loss": 3.6842,
"step": 613888
},
{
"epoch": 1.0,
"learning_rate": 3.9941203370364714e-05,
"loss": 3.6792,
"step": 614400
},
{
"epoch": 1.0,
"learning_rate": 3.9932817422854194e-05,
"loss": 3.6786,
"step": 614912
},
{
"epoch": 1.0,
"learning_rate": 3.992444785414741e-05,
"loss": 3.6772,
"step": 615424
},
{
"epoch": 1.0,
"learning_rate": 3.991606190663689e-05,
"loss": 3.6862,
"step": 615936
},
{
"epoch": 1.0,
"learning_rate": 3.990767595912637e-05,
"loss": 3.6862,
"step": 616448
},
{
"epoch": 1.0,
"learning_rate": 3.989929001161585e-05,
"loss": 3.6714,
"step": 616960
},
{
"epoch": 1.0,
"learning_rate": 3.989090406410533e-05,
"loss": 3.67,
"step": 617472
},
{
"epoch": 1.0,
"learning_rate": 3.988251811659481e-05,
"loss": 3.6842,
"step": 617984
},
{
"epoch": 1.0,
"learning_rate": 3.987413216908429e-05,
"loss": 3.6633,
"step": 618496
},
{
"epoch": 1.0,
"learning_rate": 3.986574622157377e-05,
"loss": 3.678,
"step": 619008
},
{
"epoch": 1.0,
"learning_rate": 3.985737665286698e-05,
"loss": 3.674,
"step": 619520
},
{
"epoch": 1.0,
"learning_rate": 3.984899070535646e-05,
"loss": 3.6791,
"step": 620032
},
{
"epoch": 1.0,
"learning_rate": 3.984060475784594e-05,
"loss": 3.6817,
"step": 620544
},
{
"epoch": 1.0,
"learning_rate": 3.983223518913915e-05,
"loss": 3.6858,
"step": 621056
},
{
"epoch": 1.0,
"learning_rate": 3.982384924162863e-05,
"loss": 3.6807,
"step": 621568
},
{
"epoch": 1.0,
"learning_rate": 3.981546329411811e-05,
"loss": 3.6759,
"step": 622080
},
{
"epoch": 1.0,
"learning_rate": 3.9807077346607594e-05,
"loss": 3.6758,
"step": 622592
},
{
"epoch": 1.0,
"learning_rate": 3.97987077779008e-05,
"loss": 3.6779,
"step": 623104
},
{
"epoch": 1.0,
"learning_rate": 3.979032183039028e-05,
"loss": 3.6823,
"step": 623616
},
{
"epoch": 1.0,
"learning_rate": 3.978193588287976e-05,
"loss": 3.6736,
"step": 624128
},
{
"epoch": 1.0,
"learning_rate": 3.977354993536924e-05,
"loss": 3.6706,
"step": 624640
},
{
"epoch": 1.0,
"learning_rate": 3.976518036666245e-05,
"loss": 3.6747,
"step": 625152
},
{
"epoch": 1.0,
"learning_rate": 3.975679441915193e-05,
"loss": 3.6736,
"step": 625664
},
{
"epoch": 1.01,
"learning_rate": 3.974840847164141e-05,
"loss": 3.6701,
"step": 626176
},
{
"epoch": 1.01,
"learning_rate": 3.974002252413089e-05,
"loss": 3.6857,
"step": 626688
},
{
"epoch": 1.01,
"learning_rate": 3.97316529554241e-05,
"loss": 3.6817,
"step": 627200
},
{
"epoch": 1.01,
"learning_rate": 3.972326700791358e-05,
"loss": 3.6769,
"step": 627712
},
{
"epoch": 1.01,
"learning_rate": 3.971488106040306e-05,
"loss": 3.6705,
"step": 628224
},
{
"epoch": 1.01,
"learning_rate": 3.970649511289255e-05,
"loss": 3.6839,
"step": 628736
},
{
"epoch": 1.01,
"learning_rate": 3.969812554418576e-05,
"loss": 3.6751,
"step": 629248
},
{
"epoch": 1.01,
"learning_rate": 3.9689739596675237e-05,
"loss": 3.673,
"step": 629760
},
{
"epoch": 1.01,
"learning_rate": 3.9681353649164717e-05,
"loss": 3.6592,
"step": 630272
},
{
"epoch": 1.01,
"learning_rate": 3.9672984080457926e-05,
"loss": 3.6676,
"step": 630784
},
{
"epoch": 1.01,
"learning_rate": 3.9664598132947406e-05,
"loss": 3.6684,
"step": 631296
},
{
"epoch": 1.01,
"learning_rate": 3.9656212185436886e-05,
"loss": 3.676,
"step": 631808
},
{
"epoch": 1.01,
"learning_rate": 3.9647826237926366e-05,
"loss": 3.6691,
"step": 632320
},
{
"epoch": 1.01,
"learning_rate": 3.9639440290415845e-05,
"loss": 3.6688,
"step": 632832
},
{
"epoch": 1.01,
"learning_rate": 3.9631054342905325e-05,
"loss": 3.6839,
"step": 633344
},
{
"epoch": 1.01,
"learning_rate": 3.9622668395394805e-05,
"loss": 3.6744,
"step": 633856
},
{
"epoch": 1.01,
"learning_rate": 3.9614282447884285e-05,
"loss": 3.6837,
"step": 634368
},
{
"epoch": 1.01,
"learning_rate": 3.96059128791775e-05,
"loss": 3.6656,
"step": 634880
},
{
"epoch": 1.01,
"learning_rate": 3.959752693166698e-05,
"loss": 3.6496,
"step": 635392
},
{
"epoch": 1.01,
"learning_rate": 3.958914098415646e-05,
"loss": 3.6837,
"step": 635904
},
{
"epoch": 1.01,
"learning_rate": 3.958075503664594e-05,
"loss": 3.6736,
"step": 636416
},
{
"epoch": 1.01,
"learning_rate": 3.957238546793915e-05,
"loss": 3.6679,
"step": 636928
},
{
"epoch": 1.01,
"learning_rate": 3.956399952042863e-05,
"loss": 3.6682,
"step": 637440
},
{
"epoch": 1.01,
"learning_rate": 3.955561357291811e-05,
"loss": 3.6681,
"step": 637952
},
{
"epoch": 1.01,
"learning_rate": 3.954724400421132e-05,
"loss": 3.6562,
"step": 638464
},
{
"epoch": 1.01,
"learning_rate": 3.95388580567008e-05,
"loss": 3.6616,
"step": 638976
},
{
"epoch": 1.01,
"learning_rate": 3.953047210919028e-05,
"loss": 3.664,
"step": 639488
},
{
"epoch": 1.01,
"learning_rate": 3.952208616167976e-05,
"loss": 3.6647,
"step": 640000
},
{
"epoch": 1.01,
"learning_rate": 3.951370021416924e-05,
"loss": 3.6783,
"step": 640512
},
{
"epoch": 1.01,
"learning_rate": 3.950531426665872e-05,
"loss": 3.6651,
"step": 641024
},
{
"epoch": 1.01,
"learning_rate": 3.94969283191482e-05,
"loss": 3.6612,
"step": 641536
},
{
"epoch": 1.01,
"learning_rate": 3.9488558750441415e-05,
"loss": 3.679,
"step": 642048
},
{
"epoch": 1.01,
"learning_rate": 3.9480172802930895e-05,
"loss": 3.6534,
"step": 642560
},
{
"epoch": 1.01,
"learning_rate": 3.9471786855420375e-05,
"loss": 3.6602,
"step": 643072
},
{
"epoch": 1.01,
"learning_rate": 3.946340090790985e-05,
"loss": 3.664,
"step": 643584
},
{
"epoch": 1.01,
"learning_rate": 3.9455031339203064e-05,
"loss": 3.6668,
"step": 644096
},
{
"epoch": 1.01,
"learning_rate": 3.9446645391692544e-05,
"loss": 3.66,
"step": 644608
},
{
"epoch": 1.01,
"learning_rate": 3.9438259444182024e-05,
"loss": 3.6658,
"step": 645120
},
{
"epoch": 1.01,
"learning_rate": 3.94298734966715e-05,
"loss": 3.6473,
"step": 645632
},
{
"epoch": 1.01,
"learning_rate": 3.942150392796471e-05,
"loss": 3.661,
"step": 646144
},
{
"epoch": 1.01,
"learning_rate": 3.941311798045419e-05,
"loss": 3.6759,
"step": 646656
},
{
"epoch": 1.01,
"learning_rate": 3.940473203294367e-05,
"loss": 3.6594,
"step": 647168
},
{
"epoch": 1.01,
"learning_rate": 3.939634608543315e-05,
"loss": 3.6813,
"step": 647680
},
{
"epoch": 1.01,
"learning_rate": 3.938797651672637e-05,
"loss": 3.6729,
"step": 648192
},
{
"epoch": 1.01,
"learning_rate": 3.937959056921585e-05,
"loss": 3.6781,
"step": 648704
},
{
"epoch": 1.01,
"learning_rate": 3.937120462170532e-05,
"loss": 3.6575,
"step": 649216
},
{
"epoch": 1.01,
"learning_rate": 3.93628186741948e-05,
"loss": 3.6732,
"step": 649728
},
{
"epoch": 1.01,
"learning_rate": 3.935444910548802e-05,
"loss": 3.6698,
"step": 650240
},
{
"epoch": 1.01,
"learning_rate": 3.93460631579775e-05,
"loss": 3.6559,
"step": 650752
},
{
"epoch": 1.01,
"learning_rate": 3.933767721046697e-05,
"loss": 3.6766,
"step": 651264
},
{
"epoch": 1.01,
"learning_rate": 3.932929126295645e-05,
"loss": 3.6676,
"step": 651776
},
{
"epoch": 1.01,
"learning_rate": 3.9320921694249666e-05,
"loss": 3.6678,
"step": 652288
},
{
"epoch": 1.01,
"learning_rate": 3.9312535746739146e-05,
"loss": 3.6685,
"step": 652800
},
{
"epoch": 1.01,
"learning_rate": 3.9304149799228626e-05,
"loss": 3.6488,
"step": 653312
},
{
"epoch": 1.01,
"learning_rate": 3.9295763851718106e-05,
"loss": 3.6536,
"step": 653824
},
{
"epoch": 1.01,
"learning_rate": 3.928739428301132e-05,
"loss": 3.6608,
"step": 654336
},
{
"epoch": 1.01,
"learning_rate": 3.9279008335500795e-05,
"loss": 3.6672,
"step": 654848
},
{
"epoch": 1.01,
"learning_rate": 3.9270622387990275e-05,
"loss": 3.6642,
"step": 655360
},
{
"epoch": 1.01,
"learning_rate": 3.9262236440479755e-05,
"loss": 3.658,
"step": 655872
},
{
"epoch": 1.02,
"learning_rate": 3.925386687177297e-05,
"loss": 3.6615,
"step": 656384
},
{
"epoch": 1.02,
"learning_rate": 3.9245480924262444e-05,
"loss": 3.6608,
"step": 656896
},
{
"epoch": 1.02,
"learning_rate": 3.9237094976751924e-05,
"loss": 3.659,
"step": 657408
},
{
"epoch": 1.02,
"learning_rate": 3.9228709029241404e-05,
"loss": 3.66,
"step": 657920
},
{
"epoch": 1.02,
"learning_rate": 3.922033946053461e-05,
"loss": 3.6768,
"step": 658432
},
{
"epoch": 1.02,
"learning_rate": 3.92119535130241e-05,
"loss": 3.6768,
"step": 658944
},
{
"epoch": 1.02,
"learning_rate": 3.920356756551358e-05,
"loss": 3.6671,
"step": 659456
},
{
"epoch": 1.02,
"learning_rate": 3.919518161800306e-05,
"loss": 3.6549,
"step": 659968
},
{
"epoch": 1.02,
"learning_rate": 3.918681204929627e-05,
"loss": 3.6646,
"step": 660480
},
{
"epoch": 1.02,
"learning_rate": 3.917842610178575e-05,
"loss": 3.6595,
"step": 660992
},
{
"epoch": 1.02,
"learning_rate": 3.917004015427523e-05,
"loss": 3.6745,
"step": 661504
},
{
"epoch": 1.02,
"learning_rate": 3.916165420676471e-05,
"loss": 3.661,
"step": 662016
},
{
"epoch": 1.02,
"learning_rate": 3.915328463805792e-05,
"loss": 3.6612,
"step": 662528
},
{
"epoch": 1.02,
"learning_rate": 3.91448986905474e-05,
"loss": 3.6639,
"step": 663040
},
{
"epoch": 1.02,
"learning_rate": 3.913651274303688e-05,
"loss": 3.6701,
"step": 663552
},
{
"epoch": 1.02,
"learning_rate": 3.912812679552636e-05,
"loss": 3.6544,
"step": 664064
},
{
"epoch": 1.02,
"learning_rate": 3.91197736056233e-05,
"loss": 3.6636,
"step": 664576
},
{
"epoch": 1.02,
"learning_rate": 3.911138765811278e-05,
"loss": 3.6559,
"step": 665088
},
{
"epoch": 1.02,
"learning_rate": 3.910300171060226e-05,
"loss": 3.6557,
"step": 665600
},
{
"epoch": 1.02,
"learning_rate": 3.909461576309174e-05,
"loss": 3.65,
"step": 666112
},
{
"epoch": 1.02,
"learning_rate": 3.908622981558122e-05,
"loss": 3.6581,
"step": 666624
},
{
"epoch": 1.02,
"learning_rate": 3.90778438680707e-05,
"loss": 3.6582,
"step": 667136
},
{
"epoch": 1.02,
"learning_rate": 3.906945792056018e-05,
"loss": 3.662,
"step": 667648
},
{
"epoch": 1.02,
"learning_rate": 3.906107197304966e-05,
"loss": 3.6599,
"step": 668160
},
{
"epoch": 1.02,
"learning_rate": 3.905270240434287e-05,
"loss": 3.6545,
"step": 668672
},
{
"epoch": 1.02,
"learning_rate": 3.904431645683235e-05,
"loss": 3.6686,
"step": 669184
},
{
"epoch": 1.02,
"learning_rate": 3.903593050932183e-05,
"loss": 3.6751,
"step": 669696
},
{
"epoch": 1.02,
"learning_rate": 3.902754456181131e-05,
"loss": 3.6625,
"step": 670208
},
{
"epoch": 1.02,
"learning_rate": 3.901917499310452e-05,
"loss": 3.6706,
"step": 670720
},
{
"epoch": 1.02,
"learning_rate": 3.9010789045594e-05,
"loss": 3.6486,
"step": 671232
},
{
"epoch": 1.02,
"learning_rate": 3.900240309808349e-05,
"loss": 3.6635,
"step": 671744
},
{
"epoch": 1.02,
"learning_rate": 3.899401715057297e-05,
"loss": 3.6556,
"step": 672256
},
{
"epoch": 1.02,
"learning_rate": 3.8985647581866176e-05,
"loss": 3.6547,
"step": 672768
},
{
"epoch": 1.02,
"learning_rate": 3.8977261634355656e-05,
"loss": 3.6541,
"step": 673280
},
{
"epoch": 1.02,
"learning_rate": 3.8968875686845136e-05,
"loss": 3.6585,
"step": 673792
},
{
"epoch": 1.02,
"learning_rate": 3.8960489739334616e-05,
"loss": 3.6609,
"step": 674304
},
{
"epoch": 1.02,
"learning_rate": 3.8952120170627825e-05,
"loss": 3.6584,
"step": 674816
},
{
"epoch": 1.02,
"learning_rate": 3.8943734223117305e-05,
"loss": 3.6673,
"step": 675328
},
{
"epoch": 1.02,
"learning_rate": 3.8935348275606785e-05,
"loss": 3.6586,
"step": 675840
},
{
"epoch": 1.02,
"learning_rate": 3.8926962328096265e-05,
"loss": 3.6526,
"step": 676352
},
{
"epoch": 1.02,
"learning_rate": 3.8918592759389474e-05,
"loss": 3.6635,
"step": 676864
},
{
"epoch": 1.02,
"learning_rate": 3.8910206811878954e-05,
"loss": 3.6653,
"step": 677376
},
{
"epoch": 1.02,
"learning_rate": 3.890182086436844e-05,
"loss": 3.6722,
"step": 677888
},
{
"epoch": 1.02,
"learning_rate": 3.889343491685792e-05,
"loss": 3.6504,
"step": 678400
},
{
"epoch": 1.02,
"learning_rate": 3.888506534815113e-05,
"loss": 3.6696,
"step": 678912
},
{
"epoch": 1.02,
"learning_rate": 3.887667940064061e-05,
"loss": 3.6608,
"step": 679424
},
{
"epoch": 1.02,
"learning_rate": 3.886829345313009e-05,
"loss": 3.6654,
"step": 679936
},
{
"epoch": 1.02,
"learning_rate": 3.885990750561957e-05,
"loss": 3.6606,
"step": 680448
},
{
"epoch": 1.02,
"learning_rate": 3.885153793691278e-05,
"loss": 3.6602,
"step": 680960
},
{
"epoch": 1.02,
"learning_rate": 3.884315198940226e-05,
"loss": 3.6532,
"step": 681472
},
{
"epoch": 1.02,
"learning_rate": 3.883476604189174e-05,
"loss": 3.6673,
"step": 681984
},
{
"epoch": 1.02,
"learning_rate": 3.882639647318495e-05,
"loss": 3.649,
"step": 682496
},
{
"epoch": 1.02,
"learning_rate": 3.881801052567443e-05,
"loss": 3.6577,
"step": 683008
},
{
"epoch": 1.02,
"learning_rate": 3.880962457816391e-05,
"loss": 3.6619,
"step": 683520
},
{
"epoch": 1.02,
"learning_rate": 3.8801238630653395e-05,
"loss": 3.6653,
"step": 684032
},
{
"epoch": 1.02,
"learning_rate": 3.8792869061946604e-05,
"loss": 3.6536,
"step": 684544
},
{
"epoch": 1.02,
"learning_rate": 3.8784483114436084e-05,
"loss": 3.6555,
"step": 685056
},
{
"epoch": 1.02,
"learning_rate": 3.8776097166925564e-05,
"loss": 3.6644,
"step": 685568
},
{
"epoch": 1.02,
"learning_rate": 3.8767711219415044e-05,
"loss": 3.6558,
"step": 686080
},
{
"epoch": 1.02,
"learning_rate": 3.875934165070825e-05,
"loss": 3.6634,
"step": 686592
},
{
"epoch": 1.03,
"eval_loss": 3.8472349643707275,
"eval_runtime": 302.0965,
"eval_samples_per_second": 1263.143,
"eval_steps_per_second": 39.474,
"step": 686880
},
{
"epoch": 0.0,
"learning_rate": 3.875095570319773e-05,
"loss": 3.6379,
"step": 687104
},
{
"epoch": 0.0,
"learning_rate": 3.874256975568721e-05,
"loss": 3.6505,
"step": 687616
},
{
"epoch": 0.0,
"learning_rate": 3.873418380817669e-05,
"loss": 3.6563,
"step": 688128
},
{
"epoch": 0.0,
"learning_rate": 3.872579786066617e-05,
"loss": 3.6593,
"step": 688640
},
{
"epoch": 0.0,
"learning_rate": 3.871741191315565e-05,
"loss": 3.6669,
"step": 689152
},
{
"epoch": 0.0,
"learning_rate": 3.870902596564513e-05,
"loss": 3.6505,
"step": 689664
},
{
"epoch": 0.0,
"learning_rate": 3.870064001813461e-05,
"loss": 3.6577,
"step": 690176
},
{
"epoch": 0.0,
"learning_rate": 3.869225407062409e-05,
"loss": 3.6564,
"step": 690688
},
{
"epoch": 0.0,
"learning_rate": 3.868388450191731e-05,
"loss": 3.6487,
"step": 691200
},
{
"epoch": 0.0,
"learning_rate": 3.867551493321052e-05,
"loss": 3.6545,
"step": 691712
},
{
"epoch": 0.0,
"learning_rate": 3.86671289857e-05,
"loss": 3.6591,
"step": 692224
},
{
"epoch": 0.0,
"learning_rate": 3.865874303818948e-05,
"loss": 3.6572,
"step": 692736
},
{
"epoch": 0.0,
"learning_rate": 3.865035709067896e-05,
"loss": 3.6545,
"step": 693248
},
{
"epoch": 0.0,
"learning_rate": 3.8641987521972166e-05,
"loss": 3.639,
"step": 693760
},
{
"epoch": 0.0,
"learning_rate": 3.8633601574461646e-05,
"loss": 3.658,
"step": 694272
},
{
"epoch": 0.0,
"learning_rate": 3.8625215626951126e-05,
"loss": 3.6374,
"step": 694784
},
{
"epoch": 0.0,
"learning_rate": 3.8616829679440606e-05,
"loss": 3.6501,
"step": 695296
},
{
"epoch": 0.0,
"learning_rate": 3.8608443731930086e-05,
"loss": 3.6528,
"step": 695808
},
{
"epoch": 0.0,
"learning_rate": 3.8600057784419566e-05,
"loss": 3.6495,
"step": 696320
},
{
"epoch": 0.0,
"learning_rate": 3.8591671836909046e-05,
"loss": 3.6553,
"step": 696832
},
{
"epoch": 0.0,
"learning_rate": 3.8583285889398526e-05,
"loss": 3.6615,
"step": 697344
},
{
"epoch": 0.0,
"learning_rate": 3.857491632069174e-05,
"loss": 3.6571,
"step": 697856
},
{
"epoch": 0.0,
"learning_rate": 3.856653037318122e-05,
"loss": 3.6525,
"step": 698368
},
{
"epoch": 0.0,
"learning_rate": 3.8558144425670695e-05,
"loss": 3.6463,
"step": 698880
},
{
"epoch": 0.0,
"learning_rate": 3.8549758478160175e-05,
"loss": 3.6541,
"step": 699392
},
{
"epoch": 0.0,
"learning_rate": 3.854138890945339e-05,
"loss": 3.6539,
"step": 699904
},
{
"epoch": 0.0,
"learning_rate": 3.853300296194287e-05,
"loss": 3.6519,
"step": 700416
},
{
"epoch": 0.0,
"learning_rate": 3.8524617014432344e-05,
"loss": 3.6467,
"step": 700928
},
{
"epoch": 0.0,
"learning_rate": 3.8516231066921824e-05,
"loss": 3.6451,
"step": 701440
},
{
"epoch": 0.0,
"learning_rate": 3.850786149821504e-05,
"loss": 3.6514,
"step": 701952
},
{
"epoch": 0.01,
"learning_rate": 3.849947555070452e-05,
"loss": 3.6385,
"step": 702464
},
{
"epoch": 0.01,
"learning_rate": 3.8491089603194e-05,
"loss": 3.6585,
"step": 702976
},
{
"epoch": 0.01,
"learning_rate": 3.848270365568348e-05,
"loss": 3.6562,
"step": 703488
},
{
"epoch": 0.01,
"learning_rate": 3.8474334086976695e-05,
"loss": 3.6536,
"step": 704000
},
{
"epoch": 0.01,
"learning_rate": 3.846594813946617e-05,
"loss": 3.6444,
"step": 704512
},
{
"epoch": 0.01,
"learning_rate": 3.8457578570759385e-05,
"loss": 3.6532,
"step": 705024
},
{
"epoch": 0.01,
"learning_rate": 3.8449192623248865e-05,
"loss": 3.6507,
"step": 705536
},
{
"epoch": 0.01,
"learning_rate": 3.8440806675738344e-05,
"loss": 3.6463,
"step": 706048
},
{
"epoch": 0.01,
"learning_rate": 3.843242072822782e-05,
"loss": 3.6397,
"step": 706560
},
{
"epoch": 0.01,
"learning_rate": 3.8424051159521034e-05,
"loss": 3.6412,
"step": 707072
},
{
"epoch": 0.01,
"learning_rate": 3.8415665212010513e-05,
"loss": 3.6408,
"step": 707584
},
{
"epoch": 0.01,
"learning_rate": 3.8407279264499993e-05,
"loss": 3.6502,
"step": 708096
},
{
"epoch": 0.01,
"learning_rate": 3.839889331698947e-05,
"loss": 3.6434,
"step": 708608
},
{
"epoch": 0.01,
"learning_rate": 3.839050736947895e-05,
"loss": 3.6442,
"step": 709120
},
{
"epoch": 0.01,
"learning_rate": 3.838212142196843e-05,
"loss": 3.6579,
"step": 709632
},
{
"epoch": 0.01,
"learning_rate": 3.837373547445791e-05,
"loss": 3.6497,
"step": 710144
},
{
"epoch": 0.01,
"learning_rate": 3.836534952694739e-05,
"loss": 3.6569,
"step": 710656
},
{
"epoch": 0.01,
"learning_rate": 3.83569799582406e-05,
"loss": 3.6444,
"step": 711168
},
{
"epoch": 0.01,
"learning_rate": 3.834859401073008e-05,
"loss": 3.6266,
"step": 711680
},
{
"epoch": 0.01,
"learning_rate": 3.834020806321956e-05,
"loss": 3.6556,
"step": 712192
},
{
"epoch": 0.01,
"learning_rate": 3.833182211570904e-05,
"loss": 3.646,
"step": 712704
},
{
"epoch": 0.01,
"learning_rate": 3.832345254700225e-05,
"loss": 3.6475,
"step": 713216
},
{
"epoch": 0.01,
"learning_rate": 3.831506659949173e-05,
"loss": 3.6439,
"step": 713728
},
{
"epoch": 0.01,
"learning_rate": 3.830668065198121e-05,
"loss": 3.6422,
"step": 714240
},
{
"epoch": 0.01,
"learning_rate": 3.829831108327443e-05,
"loss": 3.6308,
"step": 714752
},
{
"epoch": 0.01,
"learning_rate": 3.828992513576391e-05,
"loss": 3.6397,
"step": 715264
},
{
"epoch": 0.01,
"learning_rate": 3.828153918825339e-05,
"loss": 3.6368,
"step": 715776
},
{
"epoch": 0.01,
"learning_rate": 3.827315324074287e-05,
"loss": 3.6388,
"step": 716288
},
{
"epoch": 0.01,
"learning_rate": 3.826476729323235e-05,
"loss": 3.6553,
"step": 716800
},
{
"epoch": 0.01,
"learning_rate": 3.825638134572183e-05,
"loss": 3.6394,
"step": 717312
},
{
"epoch": 0.01,
"learning_rate": 3.824799539821131e-05,
"loss": 3.6355,
"step": 717824
},
{
"epoch": 0.01,
"learning_rate": 3.823960945070079e-05,
"loss": 3.6571,
"step": 718336
},
{
"epoch": 0.01,
"learning_rate": 3.8231239881993996e-05,
"loss": 3.6277,
"step": 718848
},
{
"epoch": 0.01,
"learning_rate": 3.8222853934483476e-05,
"loss": 3.631,
"step": 719360
},
{
"epoch": 0.01,
"learning_rate": 3.8214467986972956e-05,
"loss": 3.6429,
"step": 719872
},
{
"epoch": 0.01,
"learning_rate": 3.8206098418266165e-05,
"loss": 3.6422,
"step": 720384
},
{
"epoch": 0.01,
"learning_rate": 3.8197712470755645e-05,
"loss": 3.633,
"step": 720896
},
{
"epoch": 0.01,
"learning_rate": 3.8189326523245125e-05,
"loss": 3.6429,
"step": 721408
},
{
"epoch": 0.01,
"learning_rate": 3.818094057573461e-05,
"loss": 3.6227,
"step": 721920
},
{
"epoch": 0.01,
"learning_rate": 3.817257100702782e-05,
"loss": 3.6342,
"step": 722432
},
{
"epoch": 0.01,
"learning_rate": 3.81641850595173e-05,
"loss": 3.6514,
"step": 722944
},
{
"epoch": 0.01,
"learning_rate": 3.815579911200678e-05,
"loss": 3.6376,
"step": 723456
},
{
"epoch": 0.01,
"learning_rate": 3.814741316449626e-05,
"loss": 3.6516,
"step": 723968
},
{
"epoch": 0.01,
"learning_rate": 3.813904359578947e-05,
"loss": 3.6469,
"step": 724480
},
{
"epoch": 0.01,
"learning_rate": 3.813067402708268e-05,
"loss": 3.6582,
"step": 724992
},
{
"epoch": 0.01,
"learning_rate": 3.812228807957216e-05,
"loss": 3.6322,
"step": 725504
},
{
"epoch": 0.01,
"learning_rate": 3.811390213206164e-05,
"loss": 3.6473,
"step": 726016
},
{
"epoch": 0.01,
"learning_rate": 3.810551618455112e-05,
"loss": 3.6469,
"step": 726528
},
{
"epoch": 0.01,
"learning_rate": 3.80971302370406e-05,
"loss": 3.6293,
"step": 727040
},
{
"epoch": 0.01,
"learning_rate": 3.808874428953008e-05,
"loss": 3.6533,
"step": 727552
},
{
"epoch": 0.01,
"learning_rate": 3.8080358342019565e-05,
"loss": 3.6413,
"step": 728064
},
{
"epoch": 0.01,
"learning_rate": 3.8071988773312774e-05,
"loss": 3.6464,
"step": 728576
},
{
"epoch": 0.01,
"learning_rate": 3.8063602825802254e-05,
"loss": 3.6442,
"step": 729088
},
{
"epoch": 0.01,
"learning_rate": 3.8055216878291734e-05,
"loss": 3.6294,
"step": 729600
},
{
"epoch": 0.01,
"learning_rate": 3.8046830930781214e-05,
"loss": 3.6245,
"step": 730112
},
{
"epoch": 0.01,
"learning_rate": 3.803846136207442e-05,
"loss": 3.6379,
"step": 730624
},
{
"epoch": 0.01,
"learning_rate": 3.803009179336763e-05,
"loss": 3.6441,
"step": 731136
},
{
"epoch": 0.01,
"learning_rate": 3.802170584585711e-05,
"loss": 3.6391,
"step": 731648
},
{
"epoch": 0.01,
"learning_rate": 3.801331989834659e-05,
"loss": 3.6328,
"step": 732160
},
{
"epoch": 0.02,
"learning_rate": 3.800493395083607e-05,
"loss": 3.6356,
"step": 732672
},
{
"epoch": 0.02,
"learning_rate": 3.799654800332555e-05,
"loss": 3.6403,
"step": 733184
},
{
"epoch": 0.02,
"learning_rate": 3.798816205581503e-05,
"loss": 3.6345,
"step": 733696
},
{
"epoch": 0.02,
"learning_rate": 3.797977610830452e-05,
"loss": 3.6312,
"step": 734208
},
{
"epoch": 0.02,
"learning_rate": 3.7971390160794e-05,
"loss": 3.6544,
"step": 734720
},
{
"epoch": 0.02,
"learning_rate": 3.796302059208721e-05,
"loss": 3.6525,
"step": 735232
},
{
"epoch": 0.02,
"learning_rate": 3.795463464457669e-05,
"loss": 3.6454,
"step": 735744
},
{
"epoch": 0.02,
"learning_rate": 3.794624869706617e-05,
"loss": 3.6293,
"step": 736256
},
{
"epoch": 0.02,
"learning_rate": 3.793786274955565e-05,
"loss": 3.6423,
"step": 736768
},
{
"epoch": 0.02,
"learning_rate": 3.792949318084886e-05,
"loss": 3.6349,
"step": 737280
},
{
"epoch": 0.02,
"learning_rate": 3.792110723333834e-05,
"loss": 3.6491,
"step": 737792
},
{
"epoch": 0.02,
"learning_rate": 3.791272128582782e-05,
"loss": 3.6378,
"step": 738304
},
{
"epoch": 0.02,
"learning_rate": 3.79043353383173e-05,
"loss": 3.6355,
"step": 738816
},
{
"epoch": 0.02,
"learning_rate": 3.7895965769610506e-05,
"loss": 3.6412,
"step": 739328
},
{
"epoch": 0.02,
"learning_rate": 3.7887579822099986e-05,
"loss": 3.6473,
"step": 739840
},
{
"epoch": 0.02,
"learning_rate": 3.787919387458947e-05,
"loss": 3.6292,
"step": 740352
},
{
"epoch": 0.02,
"learning_rate": 3.787080792707895e-05,
"loss": 3.6431,
"step": 740864
},
{
"epoch": 0.02,
"learning_rate": 3.786243835837216e-05,
"loss": 3.6274,
"step": 741376
},
{
"epoch": 0.02,
"learning_rate": 3.785406878966537e-05,
"loss": 3.6342,
"step": 741888
},
{
"epoch": 0.02,
"learning_rate": 3.784568284215485e-05,
"loss": 3.6265,
"step": 742400
},
{
"epoch": 0.02,
"learning_rate": 3.783729689464433e-05,
"loss": 3.6281,
"step": 742912
},
{
"epoch": 0.02,
"learning_rate": 3.782891094713381e-05,
"loss": 3.636,
"step": 743424
},
{
"epoch": 0.02,
"learning_rate": 3.782052499962329e-05,
"loss": 3.6384,
"step": 743936
},
{
"epoch": 0.02,
"learning_rate": 3.781213905211277e-05,
"loss": 3.6352,
"step": 744448
},
{
"epoch": 0.02,
"learning_rate": 3.7803753104602244e-05,
"loss": 3.6284,
"step": 744960
},
{
"epoch": 0.02,
"learning_rate": 3.7795367157091724e-05,
"loss": 3.645,
"step": 745472
},
{
"epoch": 0.02,
"learning_rate": 3.778699758838494e-05,
"loss": 3.6491,
"step": 745984
},
{
"epoch": 0.02,
"learning_rate": 3.7778628019678155e-05,
"loss": 3.6367,
"step": 746496
},
{
"epoch": 0.02,
"learning_rate": 3.7770242072167635e-05,
"loss": 3.6491,
"step": 747008
},
{
"epoch": 0.02,
"learning_rate": 3.7761856124657115e-05,
"loss": 3.6276,
"step": 747520
},
{
"epoch": 0.02,
"learning_rate": 3.7753470177146595e-05,
"loss": 3.6364,
"step": 748032
},
{
"epoch": 0.02,
"learning_rate": 3.7745084229636075e-05,
"loss": 3.632,
"step": 748544
},
{
"epoch": 0.02,
"learning_rate": 3.7736714660929284e-05,
"loss": 3.6283,
"step": 749056
},
{
"epoch": 0.02,
"learning_rate": 3.7728328713418764e-05,
"loss": 3.6321,
"step": 749568
},
{
"epoch": 0.02,
"learning_rate": 3.7719942765908244e-05,
"loss": 3.6347,
"step": 750080
},
{
"epoch": 0.02,
"learning_rate": 3.771155681839772e-05,
"loss": 3.6371,
"step": 750592
},
{
"epoch": 0.02,
"learning_rate": 3.77031708708872e-05,
"loss": 3.6335,
"step": 751104
},
{
"epoch": 0.02,
"learning_rate": 3.769478492337668e-05,
"loss": 3.6415,
"step": 751616
},
{
"epoch": 0.02,
"learning_rate": 3.7686398975866164e-05,
"loss": 3.6376,
"step": 752128
},
{
"epoch": 0.02,
"learning_rate": 3.7678013028355644e-05,
"loss": 3.6281,
"step": 752640
},
{
"epoch": 0.02,
"learning_rate": 3.766964345964885e-05,
"loss": 3.6388,
"step": 753152
},
{
"epoch": 0.02,
"learning_rate": 3.766127389094207e-05,
"loss": 3.6424,
"step": 753664
},
{
"epoch": 0.02,
"learning_rate": 3.765288794343155e-05,
"loss": 3.6461,
"step": 754176
},
{
"epoch": 0.02,
"learning_rate": 3.764450199592102e-05,
"loss": 3.6304,
"step": 754688
},
{
"epoch": 0.02,
"learning_rate": 3.76361160484105e-05,
"loss": 3.6468,
"step": 755200
},
{
"epoch": 0.02,
"learning_rate": 3.762773010089998e-05,
"loss": 3.6373,
"step": 755712
},
{
"epoch": 0.02,
"learning_rate": 3.761934415338946e-05,
"loss": 3.6417,
"step": 756224
},
{
"epoch": 0.02,
"learning_rate": 3.761095820587894e-05,
"loss": 3.6374,
"step": 756736
},
{
"epoch": 0.02,
"learning_rate": 3.760258863717215e-05,
"loss": 3.635,
"step": 757248
},
{
"epoch": 0.02,
"learning_rate": 3.759421906846537e-05,
"loss": 3.6301,
"step": 757760
},
{
"epoch": 0.02,
"learning_rate": 3.758583312095485e-05,
"loss": 3.646,
"step": 758272
},
{
"epoch": 0.02,
"learning_rate": 3.757744717344433e-05,
"loss": 3.6192,
"step": 758784
},
{
"epoch": 0.02,
"learning_rate": 3.756906122593381e-05,
"loss": 3.6374,
"step": 759296
},
{
"epoch": 0.02,
"learning_rate": 3.756067527842329e-05,
"loss": 3.6404,
"step": 759808
},
{
"epoch": 0.02,
"learning_rate": 3.7552305709716496e-05,
"loss": 3.6362,
"step": 760320
},
{
"epoch": 0.02,
"learning_rate": 3.7543919762205976e-05,
"loss": 3.6329,
"step": 760832
},
{
"epoch": 0.02,
"learning_rate": 3.7535533814695456e-05,
"loss": 3.6341,
"step": 761344
},
{
"epoch": 0.02,
"learning_rate": 3.7527147867184936e-05,
"loss": 3.6396,
"step": 761856
},
{
"epoch": 0.02,
"learning_rate": 3.7518761919674416e-05,
"loss": 3.6352,
"step": 762368
},
{
"epoch": 0.02,
"learning_rate": 3.7510392350967625e-05,
"loss": 3.6406,
"step": 762880
},
{
"epoch": 0.03,
"eval_loss": 3.8446197509765625,
"eval_runtime": 309.3343,
"eval_samples_per_second": 1233.588,
"eval_steps_per_second": 38.551,
"step": 763200
},
{
"epoch": 1.0,
"learning_rate": 3.7502006403457105e-05,
"loss": 3.624,
"step": 763392
},
{
"epoch": 1.0,
"learning_rate": 3.7493620455946585e-05,
"loss": 3.6252,
"step": 763904
},
{
"epoch": 1.0,
"learning_rate": 3.7485234508436064e-05,
"loss": 3.633,
"step": 764416
},
{
"epoch": 1.0,
"learning_rate": 3.747684856092555e-05,
"loss": 3.6352,
"step": 764928
},
{
"epoch": 1.0,
"learning_rate": 3.746847899221876e-05,
"loss": 3.6456,
"step": 765440
},
{
"epoch": 1.0,
"learning_rate": 3.746009304470824e-05,
"loss": 3.628,
"step": 765952
},
{
"epoch": 1.0,
"learning_rate": 3.745170709719772e-05,
"loss": 3.6343,
"step": 766464
},
{
"epoch": 1.0,
"learning_rate": 3.74433211496872e-05,
"loss": 3.6303,
"step": 766976
},
{
"epoch": 1.0,
"learning_rate": 3.743493520217668e-05,
"loss": 3.6274,
"step": 767488
},
{
"epoch": 1.0,
"learning_rate": 3.742656563346989e-05,
"loss": 3.6267,
"step": 768000
},
{
"epoch": 1.0,
"learning_rate": 3.741817968595937e-05,
"loss": 3.6343,
"step": 768512
},
{
"epoch": 1.0,
"learning_rate": 3.740979373844885e-05,
"loss": 3.6374,
"step": 769024
},
{
"epoch": 1.0,
"learning_rate": 3.740140779093833e-05,
"loss": 3.6354,
"step": 769536
},
{
"epoch": 1.0,
"learning_rate": 3.739303822223154e-05,
"loss": 3.6124,
"step": 770048
},
{
"epoch": 1.0,
"learning_rate": 3.738465227472102e-05,
"loss": 3.6344,
"step": 770560
},
{
"epoch": 1.0,
"learning_rate": 3.7376266327210505e-05,
"loss": 3.6132,
"step": 771072
},
{
"epoch": 1.0,
"learning_rate": 3.7367880379699985e-05,
"loss": 3.6289,
"step": 771584
},
{
"epoch": 1.0,
"learning_rate": 3.7359494432189465e-05,
"loss": 3.6252,
"step": 772096
},
{
"epoch": 1.0,
"learning_rate": 3.7351108484678945e-05,
"loss": 3.6256,
"step": 772608
},
{
"epoch": 1.0,
"learning_rate": 3.7342722537168425e-05,
"loss": 3.6335,
"step": 773120
},
{
"epoch": 1.0,
"learning_rate": 3.7334336589657905e-05,
"loss": 3.641,
"step": 773632
},
{
"epoch": 1.0,
"learning_rate": 3.7325967020951114e-05,
"loss": 3.634,
"step": 774144
},
{
"epoch": 1.0,
"learning_rate": 3.7317581073440594e-05,
"loss": 3.6282,
"step": 774656
},
{
"epoch": 1.0,
"learning_rate": 3.73092115047338e-05,
"loss": 3.6208,
"step": 775168
},
{
"epoch": 1.0,
"learning_rate": 3.730082555722328e-05,
"loss": 3.634,
"step": 775680
},
{
"epoch": 1.0,
"learning_rate": 3.729243960971276e-05,
"loss": 3.6306,
"step": 776192
},
{
"epoch": 1.0,
"learning_rate": 3.728405366220224e-05,
"loss": 3.6254,
"step": 776704
},
{
"epoch": 1.0,
"learning_rate": 3.727568409349546e-05,
"loss": 3.6262,
"step": 777216
},
{
"epoch": 1.0,
"learning_rate": 3.726729814598494e-05,
"loss": 3.6216,
"step": 777728
},
{
"epoch": 1.0,
"learning_rate": 3.725891219847442e-05,
"loss": 3.6295,
"step": 778240
},
{
"epoch": 1.01,
"learning_rate": 3.72505262509639e-05,
"loss": 3.6146,
"step": 778752
},
{
"epoch": 1.01,
"learning_rate": 3.724214030345338e-05,
"loss": 3.6368,
"step": 779264
},
{
"epoch": 1.01,
"learning_rate": 3.723375435594285e-05,
"loss": 3.6367,
"step": 779776
},
{
"epoch": 1.01,
"learning_rate": 3.722536840843233e-05,
"loss": 3.6282,
"step": 780288
},
{
"epoch": 1.01,
"learning_rate": 3.721699883972555e-05,
"loss": 3.6249,
"step": 780800
},
{
"epoch": 1.01,
"learning_rate": 3.720861289221503e-05,
"loss": 3.6243,
"step": 781312
},
{
"epoch": 1.01,
"learning_rate": 3.72002269447045e-05,
"loss": 3.6327,
"step": 781824
},
{
"epoch": 1.01,
"learning_rate": 3.719184099719398e-05,
"loss": 3.6266,
"step": 782336
},
{
"epoch": 1.01,
"learning_rate": 3.718345504968346e-05,
"loss": 3.6109,
"step": 782848
},
{
"epoch": 1.01,
"learning_rate": 3.7175085480976676e-05,
"loss": 3.6223,
"step": 783360
},
{
"epoch": 1.01,
"learning_rate": 3.7166699533466156e-05,
"loss": 3.6202,
"step": 783872
},
{
"epoch": 1.01,
"learning_rate": 3.7158313585955636e-05,
"loss": 3.6252,
"step": 784384
},
{
"epoch": 1.01,
"learning_rate": 3.7149927638445116e-05,
"loss": 3.6227,
"step": 784896
},
{
"epoch": 1.01,
"learning_rate": 3.7141541690934596e-05,
"loss": 3.6226,
"step": 785408
},
{
"epoch": 1.01,
"learning_rate": 3.7133155743424076e-05,
"loss": 3.6338,
"step": 785920
},
{
"epoch": 1.01,
"learning_rate": 3.7124769795913556e-05,
"loss": 3.6288,
"step": 786432
},
{
"epoch": 1.01,
"learning_rate": 3.7116400227206765e-05,
"loss": 3.6328,
"step": 786944
},
{
"epoch": 1.01,
"learning_rate": 3.7108014279696245e-05,
"loss": 3.6249,
"step": 787456
},
{
"epoch": 1.01,
"learning_rate": 3.7099628332185725e-05,
"loss": 3.5999,
"step": 787968
},
{
"epoch": 1.01,
"learning_rate": 3.7091242384675205e-05,
"loss": 3.6341,
"step": 788480
},
{
"epoch": 1.01,
"learning_rate": 3.7082856437164685e-05,
"loss": 3.6244,
"step": 788992
},
{
"epoch": 1.01,
"learning_rate": 3.7074470489654165e-05,
"loss": 3.6233,
"step": 789504
},
{
"epoch": 1.01,
"learning_rate": 3.7066084542143645e-05,
"loss": 3.6253,
"step": 790016
},
{
"epoch": 1.01,
"learning_rate": 3.7057698594633125e-05,
"loss": 3.6198,
"step": 790528
},
{
"epoch": 1.01,
"learning_rate": 3.704934540473007e-05,
"loss": 3.6078,
"step": 791040
},
{
"epoch": 1.01,
"learning_rate": 3.704095945721955e-05,
"loss": 3.6142,
"step": 791552
},
{
"epoch": 1.01,
"learning_rate": 3.703257350970903e-05,
"loss": 3.6195,
"step": 792064
},
{
"epoch": 1.01,
"learning_rate": 3.702418756219851e-05,
"loss": 3.6151,
"step": 792576
},
{
"epoch": 1.01,
"learning_rate": 3.701580161468799e-05,
"loss": 3.6312,
"step": 793088
},
{
"epoch": 1.01,
"learning_rate": 3.700741566717747e-05,
"loss": 3.6191,
"step": 793600
},
{
"epoch": 1.01,
"learning_rate": 3.699902971966695e-05,
"loss": 3.6142,
"step": 794112
},
{
"epoch": 1.01,
"learning_rate": 3.699064377215643e-05,
"loss": 3.6329,
"step": 794624
},
{
"epoch": 1.01,
"learning_rate": 3.698227420344964e-05,
"loss": 3.6081,
"step": 795136
},
{
"epoch": 1.01,
"learning_rate": 3.697388825593912e-05,
"loss": 3.6072,
"step": 795648
},
{
"epoch": 1.01,
"learning_rate": 3.69655023084286e-05,
"loss": 3.6241,
"step": 796160
},
{
"epoch": 1.01,
"learning_rate": 3.6957132739721814e-05,
"loss": 3.6168,
"step": 796672
},
{
"epoch": 1.01,
"learning_rate": 3.6948746792211294e-05,
"loss": 3.6095,
"step": 797184
},
{
"epoch": 1.01,
"learning_rate": 3.6940360844700774e-05,
"loss": 3.617,
"step": 797696
},
{
"epoch": 1.01,
"learning_rate": 3.6931974897190254e-05,
"loss": 3.6041,
"step": 798208
},
{
"epoch": 1.01,
"learning_rate": 3.692360532848346e-05,
"loss": 3.6131,
"step": 798720
},
{
"epoch": 1.01,
"learning_rate": 3.691521938097294e-05,
"loss": 3.6293,
"step": 799232
},
{
"epoch": 1.01,
"learning_rate": 3.690684981226615e-05,
"loss": 3.6159,
"step": 799744
},
{
"epoch": 1.01,
"learning_rate": 3.689846386475563e-05,
"loss": 3.6276,
"step": 800256
},
{
"epoch": 1.01,
"learning_rate": 3.689007791724511e-05,
"loss": 3.6227,
"step": 800768
},
{
"epoch": 1.01,
"learning_rate": 3.688169196973459e-05,
"loss": 3.6359,
"step": 801280
},
{
"epoch": 1.01,
"learning_rate": 3.687330602222407e-05,
"loss": 3.6112,
"step": 801792
},
{
"epoch": 1.01,
"learning_rate": 3.686492007471355e-05,
"loss": 3.6272,
"step": 802304
},
{
"epoch": 1.01,
"learning_rate": 3.685655050600677e-05,
"loss": 3.6244,
"step": 802816
},
{
"epoch": 1.01,
"learning_rate": 3.684816455849625e-05,
"loss": 3.6068,
"step": 803328
},
{
"epoch": 1.01,
"learning_rate": 3.683977861098573e-05,
"loss": 3.63,
"step": 803840
},
{
"epoch": 1.01,
"learning_rate": 3.683139266347521e-05,
"loss": 3.6214,
"step": 804352
},
{
"epoch": 1.01,
"learning_rate": 3.682300671596469e-05,
"loss": 3.6231,
"step": 804864
},
{
"epoch": 1.01,
"learning_rate": 3.681462076845416e-05,
"loss": 3.6242,
"step": 805376
},
{
"epoch": 1.01,
"learning_rate": 3.680625119974738e-05,
"loss": 3.608,
"step": 805888
},
{
"epoch": 1.01,
"learning_rate": 3.679786525223686e-05,
"loss": 3.5999,
"step": 806400
},
{
"epoch": 1.01,
"learning_rate": 3.678947930472634e-05,
"loss": 3.613,
"step": 806912
},
{
"epoch": 1.01,
"learning_rate": 3.678109335721581e-05,
"loss": 3.6237,
"step": 807424
},
{
"epoch": 1.01,
"learning_rate": 3.677270740970529e-05,
"loss": 3.6146,
"step": 807936
},
{
"epoch": 1.01,
"learning_rate": 3.6764337840998506e-05,
"loss": 3.6118,
"step": 808448
},
{
"epoch": 1.01,
"learning_rate": 3.6755951893487986e-05,
"loss": 3.6114,
"step": 808960
},
{
"epoch": 1.02,
"learning_rate": 3.6747565945977466e-05,
"loss": 3.6197,
"step": 809472
},
{
"epoch": 1.02,
"learning_rate": 3.6739179998466946e-05,
"loss": 3.6131,
"step": 809984
},
{
"epoch": 1.02,
"learning_rate": 3.6730794050956426e-05,
"loss": 3.6137,
"step": 810496
},
{
"epoch": 1.02,
"learning_rate": 3.6722408103445906e-05,
"loss": 3.6281,
"step": 811008
},
{
"epoch": 1.02,
"learning_rate": 3.6714022155935386e-05,
"loss": 3.6312,
"step": 811520
},
{
"epoch": 1.02,
"learning_rate": 3.6705636208424866e-05,
"loss": 3.6213,
"step": 812032
},
{
"epoch": 1.02,
"learning_rate": 3.6697266639718075e-05,
"loss": 3.6112,
"step": 812544
},
{
"epoch": 1.02,
"learning_rate": 3.6688880692207555e-05,
"loss": 3.6179,
"step": 813056
},
{
"epoch": 1.02,
"learning_rate": 3.6680494744697035e-05,
"loss": 3.6111,
"step": 813568
},
{
"epoch": 1.02,
"learning_rate": 3.6672108797186515e-05,
"loss": 3.626,
"step": 814080
},
{
"epoch": 1.02,
"learning_rate": 3.6663739228479724e-05,
"loss": 3.6167,
"step": 814592
},
{
"epoch": 1.02,
"learning_rate": 3.6655353280969204e-05,
"loss": 3.6186,
"step": 815104
},
{
"epoch": 1.02,
"learning_rate": 3.664696733345869e-05,
"loss": 3.6142,
"step": 815616
},
{
"epoch": 1.02,
"learning_rate": 3.66385977647519e-05,
"loss": 3.6185,
"step": 816128
},
{
"epoch": 1.02,
"learning_rate": 3.663021181724138e-05,
"loss": 3.6154,
"step": 816640
},
{
"epoch": 1.02,
"learning_rate": 3.662184224853459e-05,
"loss": 3.6165,
"step": 817152
},
{
"epoch": 1.02,
"learning_rate": 3.661345630102407e-05,
"loss": 3.6092,
"step": 817664
},
{
"epoch": 1.02,
"learning_rate": 3.660507035351355e-05,
"loss": 3.6127,
"step": 818176
},
{
"epoch": 1.02,
"learning_rate": 3.659668440600303e-05,
"loss": 3.607,
"step": 818688
},
{
"epoch": 1.02,
"learning_rate": 3.658829845849251e-05,
"loss": 3.6063,
"step": 819200
},
{
"epoch": 1.02,
"learning_rate": 3.657992888978572e-05,
"loss": 3.612,
"step": 819712
},
{
"epoch": 1.02,
"learning_rate": 3.65715429422752e-05,
"loss": 3.6118,
"step": 820224
},
{
"epoch": 1.02,
"learning_rate": 3.656315699476468e-05,
"loss": 3.6161,
"step": 820736
},
{
"epoch": 1.02,
"learning_rate": 3.655477104725416e-05,
"loss": 3.6076,
"step": 821248
},
{
"epoch": 1.02,
"learning_rate": 3.6546385099743644e-05,
"loss": 3.6243,
"step": 821760
},
{
"epoch": 1.02,
"learning_rate": 3.6537999152233124e-05,
"loss": 3.6289,
"step": 822272
},
{
"epoch": 1.02,
"learning_rate": 3.652962958352633e-05,
"loss": 3.6146,
"step": 822784
},
{
"epoch": 1.02,
"learning_rate": 3.652124363601581e-05,
"loss": 3.6237,
"step": 823296
},
{
"epoch": 1.02,
"learning_rate": 3.651285768850529e-05,
"loss": 3.6117,
"step": 823808
},
{
"epoch": 1.02,
"learning_rate": 3.650447174099477e-05,
"loss": 3.6145,
"step": 824320
},
{
"epoch": 1.02,
"learning_rate": 3.649610217228798e-05,
"loss": 3.6117,
"step": 824832
},
{
"epoch": 1.02,
"learning_rate": 3.648771622477746e-05,
"loss": 3.6036,
"step": 825344
},
{
"epoch": 1.02,
"learning_rate": 3.647933027726694e-05,
"loss": 3.6109,
"step": 825856
},
{
"epoch": 1.02,
"learning_rate": 3.647094432975642e-05,
"loss": 3.6169,
"step": 826368
},
{
"epoch": 1.02,
"learning_rate": 3.64625583822459e-05,
"loss": 3.6185,
"step": 826880
},
{
"epoch": 1.02,
"learning_rate": 3.645418881353911e-05,
"loss": 3.614,
"step": 827392
},
{
"epoch": 1.02,
"learning_rate": 3.64458028660286e-05,
"loss": 3.6199,
"step": 827904
},
{
"epoch": 1.02,
"learning_rate": 3.643741691851808e-05,
"loss": 3.6114,
"step": 828416
},
{
"epoch": 1.02,
"learning_rate": 3.642903097100756e-05,
"loss": 3.6115,
"step": 828928
},
{
"epoch": 1.02,
"learning_rate": 3.642064502349704e-05,
"loss": 3.6168,
"step": 829440
},
{
"epoch": 1.02,
"learning_rate": 3.6412275454790247e-05,
"loss": 3.6226,
"step": 829952
},
{
"epoch": 1.02,
"learning_rate": 3.6403889507279727e-05,
"loss": 3.6222,
"step": 830464
},
{
"epoch": 1.02,
"learning_rate": 3.6395503559769207e-05,
"loss": 3.6082,
"step": 830976
},
{
"epoch": 1.02,
"learning_rate": 3.6387117612258686e-05,
"loss": 3.6263,
"step": 831488
},
{
"epoch": 1.02,
"learning_rate": 3.6378731664748166e-05,
"loss": 3.6141,
"step": 832000
},
{
"epoch": 1.02,
"learning_rate": 3.6370362096041376e-05,
"loss": 3.6226,
"step": 832512
},
{
"epoch": 1.02,
"learning_rate": 3.6361976148530855e-05,
"loss": 3.6169,
"step": 833024
},
{
"epoch": 1.02,
"learning_rate": 3.6353590201020335e-05,
"loss": 3.6102,
"step": 833536
},
{
"epoch": 1.02,
"learning_rate": 3.6345204253509815e-05,
"loss": 3.6074,
"step": 834048
},
{
"epoch": 1.02,
"learning_rate": 3.6336818305999295e-05,
"loss": 3.6266,
"step": 834560
},
{
"epoch": 1.02,
"learning_rate": 3.6328432358488775e-05,
"loss": 3.5999,
"step": 835072
},
{
"epoch": 1.02,
"learning_rate": 3.6320046410978255e-05,
"loss": 3.6134,
"step": 835584
},
{
"epoch": 1.02,
"learning_rate": 3.631167684227147e-05,
"loss": 3.6154,
"step": 836096
},
{
"epoch": 1.02,
"learning_rate": 3.6303290894760944e-05,
"loss": 3.6182,
"step": 836608
},
{
"epoch": 1.02,
"learning_rate": 3.6294904947250424e-05,
"loss": 3.6114,
"step": 837120
},
{
"epoch": 1.02,
"learning_rate": 3.6286518999739904e-05,
"loss": 3.6114,
"step": 837632
},
{
"epoch": 1.02,
"learning_rate": 3.6278133052229384e-05,
"loss": 3.614,
"step": 838144
},
{
"epoch": 1.02,
"learning_rate": 3.6269747104718864e-05,
"loss": 3.6211,
"step": 838656
},
{
"epoch": 1.02,
"learning_rate": 3.626137753601207e-05,
"loss": 3.6184,
"step": 839168
},
{
"epoch": 1.03,
"eval_loss": 3.8430676460266113,
"eval_runtime": 307.4904,
"eval_samples_per_second": 1240.985,
"eval_steps_per_second": 38.782,
"step": 839520
},
{
"epoch": 0.0,
"learning_rate": 3.625299158850155e-05,
"loss": 3.5901,
"step": 839680
},
{
"epoch": 0.0,
"learning_rate": 3.624460564099103e-05,
"loss": 3.6052,
"step": 840192
},
{
"epoch": 0.0,
"learning_rate": 3.623621969348051e-05,
"loss": 3.6114,
"step": 840704
},
{
"epoch": 0.0,
"learning_rate": 3.622783374597e-05,
"loss": 3.6157,
"step": 841216
},
{
"epoch": 0.0,
"learning_rate": 3.621946417726321e-05,
"loss": 3.6234,
"step": 841728
},
{
"epoch": 0.0,
"learning_rate": 3.621107822975269e-05,
"loss": 3.6098,
"step": 842240
},
{
"epoch": 0.0,
"learning_rate": 3.620269228224217e-05,
"loss": 3.6118,
"step": 842752
},
{
"epoch": 0.0,
"learning_rate": 3.619430633473165e-05,
"loss": 3.6106,
"step": 843264
},
{
"epoch": 0.0,
"learning_rate": 3.618593676602486e-05,
"loss": 3.6069,
"step": 843776
},
{
"epoch": 0.0,
"learning_rate": 3.617756719731807e-05,
"loss": 3.6019,
"step": 844288
},
{
"epoch": 0.0,
"learning_rate": 3.616918124980755e-05,
"loss": 3.6147,
"step": 844800
},
{
"epoch": 0.0,
"learning_rate": 3.616079530229703e-05,
"loss": 3.6218,
"step": 845312
},
{
"epoch": 0.0,
"learning_rate": 3.615240935478651e-05,
"loss": 3.611,
"step": 845824
},
{
"epoch": 0.0,
"learning_rate": 3.614402340727599e-05,
"loss": 3.5929,
"step": 846336
},
{
"epoch": 0.0,
"learning_rate": 3.613563745976547e-05,
"loss": 3.6139,
"step": 846848
},
{
"epoch": 0.0,
"learning_rate": 3.6127251512254953e-05,
"loss": 3.5933,
"step": 847360
},
{
"epoch": 0.0,
"learning_rate": 3.6118865564744433e-05,
"loss": 3.6084,
"step": 847872
},
{
"epoch": 0.0,
"learning_rate": 3.6110479617233913e-05,
"loss": 3.6049,
"step": 848384
},
{
"epoch": 0.0,
"learning_rate": 3.610209366972339e-05,
"loss": 3.6057,
"step": 848896
},
{
"epoch": 0.0,
"learning_rate": 3.609370772221287e-05,
"loss": 3.6086,
"step": 849408
},
{
"epoch": 0.0,
"learning_rate": 3.608532177470235e-05,
"loss": 3.6185,
"step": 849920
},
{
"epoch": 0.0,
"learning_rate": 3.607696858479929e-05,
"loss": 3.6086,
"step": 850432
},
{
"epoch": 0.0,
"learning_rate": 3.606858263728877e-05,
"loss": 3.6092,
"step": 850944
},
{
"epoch": 0.0,
"learning_rate": 3.606019668977825e-05,
"loss": 3.6048,
"step": 851456
},
{
"epoch": 0.0,
"learning_rate": 3.605181074226773e-05,
"loss": 3.6108,
"step": 851968
},
{
"epoch": 0.0,
"learning_rate": 3.604342479475721e-05,
"loss": 3.6103,
"step": 852480
},
{
"epoch": 0.0,
"learning_rate": 3.603505522605042e-05,
"loss": 3.6036,
"step": 852992
},
{
"epoch": 0.0,
"learning_rate": 3.602666927853991e-05,
"loss": 3.6077,
"step": 853504
},
{
"epoch": 0.0,
"learning_rate": 3.601828333102939e-05,
"loss": 3.6016,
"step": 854016
},
{
"epoch": 0.0,
"learning_rate": 3.600989738351887e-05,
"loss": 3.6051,
"step": 854528
},
{
"epoch": 0.01,
"learning_rate": 3.600151143600835e-05,
"loss": 3.6004,
"step": 855040
},
{
"epoch": 0.01,
"learning_rate": 3.599312548849783e-05,
"loss": 3.6118,
"step": 855552
},
{
"epoch": 0.01,
"learning_rate": 3.5984755919791036e-05,
"loss": 3.6105,
"step": 856064
},
{
"epoch": 0.01,
"learning_rate": 3.5976369972280516e-05,
"loss": 3.6135,
"step": 856576
},
{
"epoch": 0.01,
"learning_rate": 3.5967984024769996e-05,
"loss": 3.6041,
"step": 857088
},
{
"epoch": 0.01,
"learning_rate": 3.5959598077259476e-05,
"loss": 3.6053,
"step": 857600
},
{
"epoch": 0.01,
"learning_rate": 3.595121212974895e-05,
"loss": 3.6117,
"step": 858112
},
{
"epoch": 0.01,
"learning_rate": 3.594282618223843e-05,
"loss": 3.6016,
"step": 858624
},
{
"epoch": 0.01,
"learning_rate": 3.593444023472791e-05,
"loss": 3.5963,
"step": 859136
},
{
"epoch": 0.01,
"learning_rate": 3.5926070666021125e-05,
"loss": 3.6016,
"step": 859648
},
{
"epoch": 0.01,
"learning_rate": 3.5917684718510605e-05,
"loss": 3.5992,
"step": 860160
},
{
"epoch": 0.01,
"learning_rate": 3.5909298771000085e-05,
"loss": 3.6015,
"step": 860672
},
{
"epoch": 0.01,
"learning_rate": 3.5900912823489565e-05,
"loss": 3.5996,
"step": 861184
},
{
"epoch": 0.01,
"learning_rate": 3.589254325478278e-05,
"loss": 3.608,
"step": 861696
},
{
"epoch": 0.01,
"learning_rate": 3.5884157307272254e-05,
"loss": 3.6063,
"step": 862208
},
{
"epoch": 0.01,
"learning_rate": 3.5875771359761734e-05,
"loss": 3.6094,
"step": 862720
},
{
"epoch": 0.01,
"learning_rate": 3.5867385412251214e-05,
"loss": 3.6107,
"step": 863232
},
{
"epoch": 0.01,
"learning_rate": 3.5858999464740694e-05,
"loss": 3.6064,
"step": 863744
},
{
"epoch": 0.01,
"learning_rate": 3.58506298960339e-05,
"loss": 3.5824,
"step": 864256
},
{
"epoch": 0.01,
"learning_rate": 3.584224394852338e-05,
"loss": 3.6121,
"step": 864768
},
{
"epoch": 0.01,
"learning_rate": 3.583385800101286e-05,
"loss": 3.6053,
"step": 865280
},
{
"epoch": 0.01,
"learning_rate": 3.582547205350234e-05,
"loss": 3.6009,
"step": 865792
},
{
"epoch": 0.01,
"learning_rate": 3.581708610599183e-05,
"loss": 3.6051,
"step": 866304
},
{
"epoch": 0.01,
"learning_rate": 3.580870015848131e-05,
"loss": 3.6004,
"step": 866816
},
{
"epoch": 0.01,
"learning_rate": 3.580033058977452e-05,
"loss": 3.5847,
"step": 867328
},
{
"epoch": 0.01,
"learning_rate": 3.5791944642264e-05,
"loss": 3.5948,
"step": 867840
},
{
"epoch": 0.01,
"learning_rate": 3.578355869475348e-05,
"loss": 3.5982,
"step": 868352
},
{
"epoch": 0.01,
"learning_rate": 3.577517274724296e-05,
"loss": 3.5932,
"step": 868864
},
{
"epoch": 0.01,
"learning_rate": 3.576678679973244e-05,
"loss": 3.6123,
"step": 869376
},
{
"epoch": 0.01,
"learning_rate": 3.575841723102565e-05,
"loss": 3.6022,
"step": 869888
},
{
"epoch": 0.01,
"learning_rate": 3.575003128351513e-05,
"loss": 3.5855,
"step": 870400
},
{
"epoch": 0.01,
"learning_rate": 3.574164533600461e-05,
"loss": 3.6128,
"step": 870912
},
{
"epoch": 0.01,
"learning_rate": 3.573325938849409e-05,
"loss": 3.592,
"step": 871424
},
{
"epoch": 0.01,
"learning_rate": 3.572487344098357e-05,
"loss": 3.5853,
"step": 871936
},
{
"epoch": 0.01,
"learning_rate": 3.571650387227678e-05,
"loss": 3.6007,
"step": 872448
},
{
"epoch": 0.01,
"learning_rate": 3.570811792476626e-05,
"loss": 3.5988,
"step": 872960
},
{
"epoch": 0.01,
"learning_rate": 3.569973197725574e-05,
"loss": 3.5898,
"step": 873472
},
{
"epoch": 0.01,
"learning_rate": 3.569134602974522e-05,
"loss": 3.5972,
"step": 873984
},
{
"epoch": 0.01,
"learning_rate": 3.56829600822347e-05,
"loss": 3.5836,
"step": 874496
},
{
"epoch": 0.01,
"learning_rate": 3.567459051352791e-05,
"loss": 3.595,
"step": 875008
},
{
"epoch": 0.01,
"learning_rate": 3.566620456601739e-05,
"loss": 3.6031,
"step": 875520
},
{
"epoch": 0.01,
"learning_rate": 3.565781861850687e-05,
"loss": 3.6008,
"step": 876032
},
{
"epoch": 0.01,
"learning_rate": 3.564943267099635e-05,
"loss": 3.6092,
"step": 876544
},
{
"epoch": 0.01,
"learning_rate": 3.564104672348583e-05,
"loss": 3.5987,
"step": 877056
},
{
"epoch": 0.01,
"learning_rate": 3.563267715477904e-05,
"loss": 3.6164,
"step": 877568
},
{
"epoch": 0.01,
"learning_rate": 3.562429120726852e-05,
"loss": 3.5899,
"step": 878080
},
{
"epoch": 0.01,
"learning_rate": 3.5615905259758e-05,
"loss": 3.6078,
"step": 878592
},
{
"epoch": 0.01,
"learning_rate": 3.560751931224748e-05,
"loss": 3.6013,
"step": 879104
},
{
"epoch": 0.01,
"learning_rate": 3.559913336473696e-05,
"loss": 3.5895,
"step": 879616
},
{
"epoch": 0.01,
"learning_rate": 3.5590763796030177e-05,
"loss": 3.6077,
"step": 880128
},
{
"epoch": 0.01,
"learning_rate": 3.5582377848519657e-05,
"loss": 3.6062,
"step": 880640
},
{
"epoch": 0.01,
"learning_rate": 3.5573991901009137e-05,
"loss": 3.6017,
"step": 881152
},
{
"epoch": 0.01,
"learning_rate": 3.556560595349861e-05,
"loss": 3.6059,
"step": 881664
},
{
"epoch": 0.01,
"learning_rate": 3.5557236384791826e-05,
"loss": 3.5856,
"step": 882176
},
{
"epoch": 0.01,
"learning_rate": 3.5548850437281306e-05,
"loss": 3.5799,
"step": 882688
},
{
"epoch": 0.01,
"learning_rate": 3.5540464489770785e-05,
"loss": 3.5921,
"step": 883200
},
{
"epoch": 0.01,
"learning_rate": 3.553207854226026e-05,
"loss": 3.6064,
"step": 883712
},
{
"epoch": 0.01,
"learning_rate": 3.552369259474974e-05,
"loss": 3.5951,
"step": 884224
},
{
"epoch": 0.01,
"learning_rate": 3.5515323026042954e-05,
"loss": 3.5945,
"step": 884736
},
{
"epoch": 0.01,
"learning_rate": 3.5506937078532434e-05,
"loss": 3.5929,
"step": 885248
},
{
"epoch": 0.02,
"learning_rate": 3.5498551131021914e-05,
"loss": 3.5956,
"step": 885760
},
{
"epoch": 0.02,
"learning_rate": 3.5490165183511394e-05,
"loss": 3.5942,
"step": 886272
},
{
"epoch": 0.02,
"learning_rate": 3.548179561480461e-05,
"loss": 3.5951,
"step": 886784
},
{
"epoch": 0.02,
"learning_rate": 3.5473409667294083e-05,
"loss": 3.6035,
"step": 887296
},
{
"epoch": 0.02,
"learning_rate": 3.546502371978356e-05,
"loss": 3.6137,
"step": 887808
},
{
"epoch": 0.02,
"learning_rate": 3.545663777227304e-05,
"loss": 3.6044,
"step": 888320
},
{
"epoch": 0.02,
"learning_rate": 3.544825182476252e-05,
"loss": 3.591,
"step": 888832
},
{
"epoch": 0.02,
"learning_rate": 3.5439865877252e-05,
"loss": 3.5958,
"step": 889344
},
{
"epoch": 0.02,
"learning_rate": 3.543147992974148e-05,
"loss": 3.5945,
"step": 889856
},
{
"epoch": 0.02,
"learning_rate": 3.542311036103469e-05,
"loss": 3.6065,
"step": 890368
},
{
"epoch": 0.02,
"learning_rate": 3.541472441352417e-05,
"loss": 3.5982,
"step": 890880
},
{
"epoch": 0.02,
"learning_rate": 3.540633846601365e-05,
"loss": 3.5989,
"step": 891392
},
{
"epoch": 0.02,
"learning_rate": 3.539795251850314e-05,
"loss": 3.5991,
"step": 891904
},
{
"epoch": 0.02,
"learning_rate": 3.538956657099262e-05,
"loss": 3.5957,
"step": 892416
},
{
"epoch": 0.02,
"learning_rate": 3.538119700228583e-05,
"loss": 3.6005,
"step": 892928
},
{
"epoch": 0.02,
"learning_rate": 3.537281105477531e-05,
"loss": 3.595,
"step": 893440
},
{
"epoch": 0.02,
"learning_rate": 3.536442510726479e-05,
"loss": 3.5886,
"step": 893952
},
{
"epoch": 0.02,
"learning_rate": 3.535603915975427e-05,
"loss": 3.5896,
"step": 894464
},
{
"epoch": 0.02,
"learning_rate": 3.534766959104748e-05,
"loss": 3.5924,
"step": 894976
},
{
"epoch": 0.02,
"learning_rate": 3.533928364353696e-05,
"loss": 3.5865,
"step": 895488
},
{
"epoch": 0.02,
"learning_rate": 3.533089769602644e-05,
"loss": 3.5928,
"step": 896000
},
{
"epoch": 0.02,
"learning_rate": 3.532251174851592e-05,
"loss": 3.592,
"step": 896512
},
{
"epoch": 0.02,
"learning_rate": 3.53141258010054e-05,
"loss": 3.5948,
"step": 897024
},
{
"epoch": 0.02,
"learning_rate": 3.5305756232298606e-05,
"loss": 3.5867,
"step": 897536
},
{
"epoch": 0.02,
"learning_rate": 3.529737028478809e-05,
"loss": 3.6055,
"step": 898048
},
{
"epoch": 0.02,
"learning_rate": 3.528898433727757e-05,
"loss": 3.61,
"step": 898560
},
{
"epoch": 0.02,
"learning_rate": 3.528059838976705e-05,
"loss": 3.5946,
"step": 899072
},
{
"epoch": 0.02,
"learning_rate": 3.527222882106026e-05,
"loss": 3.6038,
"step": 899584
},
{
"epoch": 0.02,
"learning_rate": 3.526384287354974e-05,
"loss": 3.5932,
"step": 900096
},
{
"epoch": 0.02,
"learning_rate": 3.525545692603922e-05,
"loss": 3.5932,
"step": 900608
},
{
"epoch": 0.02,
"learning_rate": 3.52470709785287e-05,
"loss": 3.5944,
"step": 901120
},
{
"epoch": 0.02,
"learning_rate": 3.523870140982191e-05,
"loss": 3.5806,
"step": 901632
},
{
"epoch": 0.02,
"learning_rate": 3.523031546231139e-05,
"loss": 3.5935,
"step": 902144
},
{
"epoch": 0.02,
"learning_rate": 3.522192951480087e-05,
"loss": 3.5946,
"step": 902656
},
{
"epoch": 0.02,
"learning_rate": 3.521354356729035e-05,
"loss": 3.6018,
"step": 903168
},
{
"epoch": 0.02,
"learning_rate": 3.520517399858356e-05,
"loss": 3.5898,
"step": 903680
},
{
"epoch": 0.02,
"learning_rate": 3.5196788051073046e-05,
"loss": 3.6032,
"step": 904192
},
{
"epoch": 0.02,
"learning_rate": 3.5188402103562526e-05,
"loss": 3.5929,
"step": 904704
},
{
"epoch": 0.02,
"learning_rate": 3.5180016156052006e-05,
"loss": 3.5905,
"step": 905216
},
{
"epoch": 0.02,
"learning_rate": 3.5171630208541486e-05,
"loss": 3.5993,
"step": 905728
},
{
"epoch": 0.02,
"learning_rate": 3.5163260639834695e-05,
"loss": 3.6005,
"step": 906240
},
{
"epoch": 0.02,
"learning_rate": 3.5154874692324175e-05,
"loss": 3.6055,
"step": 906752
},
{
"epoch": 0.02,
"learning_rate": 3.5146488744813655e-05,
"loss": 3.5876,
"step": 907264
},
{
"epoch": 0.02,
"learning_rate": 3.5138102797303135e-05,
"loss": 3.6093,
"step": 907776
},
{
"epoch": 0.02,
"learning_rate": 3.5129733228596344e-05,
"loss": 3.5937,
"step": 908288
},
{
"epoch": 0.02,
"learning_rate": 3.5121347281085824e-05,
"loss": 3.6026,
"step": 908800
},
{
"epoch": 0.02,
"learning_rate": 3.5112961333575304e-05,
"loss": 3.5994,
"step": 909312
},
{
"epoch": 0.02,
"learning_rate": 3.5104575386064784e-05,
"loss": 3.5902,
"step": 909824
},
{
"epoch": 0.02,
"learning_rate": 3.5096205817358e-05,
"loss": 3.59,
"step": 910336
},
{
"epoch": 0.02,
"learning_rate": 3.508781986984748e-05,
"loss": 3.6092,
"step": 910848
},
{
"epoch": 0.02,
"learning_rate": 3.507943392233696e-05,
"loss": 3.5816,
"step": 911360
},
{
"epoch": 0.02,
"learning_rate": 3.507104797482644e-05,
"loss": 3.5944,
"step": 911872
},
{
"epoch": 0.02,
"learning_rate": 3.506267840611965e-05,
"loss": 3.5952,
"step": 912384
},
{
"epoch": 0.02,
"learning_rate": 3.505429245860913e-05,
"loss": 3.5926,
"step": 912896
},
{
"epoch": 0.02,
"learning_rate": 3.504590651109861e-05,
"loss": 3.5965,
"step": 913408
},
{
"epoch": 0.02,
"learning_rate": 3.503752056358809e-05,
"loss": 3.5927,
"step": 913920
},
{
"epoch": 0.02,
"learning_rate": 3.502913461607757e-05,
"loss": 3.5936,
"step": 914432
},
{
"epoch": 0.02,
"learning_rate": 3.502076504737078e-05,
"loss": 3.6019,
"step": 914944
},
{
"epoch": 0.02,
"learning_rate": 3.501237909986026e-05,
"loss": 3.5959,
"step": 915456
},
{
"epoch": 0.03,
"eval_loss": 3.843202590942383,
"eval_runtime": 335.5944,
"eval_samples_per_second": 1137.06,
"eval_steps_per_second": 35.534,
"step": 915840
},
{
"epoch": 1.0,
"learning_rate": 3.500399315234974e-05,
"loss": 3.5899,
"step": 915968
},
{
"epoch": 1.0,
"learning_rate": 3.499560720483922e-05,
"loss": 3.5806,
"step": 916480
},
{
"epoch": 1.0,
"learning_rate": 3.49872212573287e-05,
"loss": 3.5933,
"step": 916992
},
{
"epoch": 1.0,
"learning_rate": 3.497883530981818e-05,
"loss": 3.5992,
"step": 917504
},
{
"epoch": 1.0,
"learning_rate": 3.4970465741111393e-05,
"loss": 3.5981,
"step": 918016
},
{
"epoch": 1.0,
"learning_rate": 3.496207979360087e-05,
"loss": 3.5933,
"step": 918528
},
{
"epoch": 1.0,
"learning_rate": 3.4953693846090347e-05,
"loss": 3.5965,
"step": 919040
},
{
"epoch": 1.0,
"learning_rate": 3.4945307898579827e-05,
"loss": 3.5893,
"step": 919552
},
{
"epoch": 1.0,
"learning_rate": 3.4936921951069306e-05,
"loss": 3.587,
"step": 920064
},
{
"epoch": 1.0,
"learning_rate": 3.492856876116625e-05,
"loss": 3.5814,
"step": 920576
},
{
"epoch": 1.0,
"learning_rate": 3.492018281365573e-05,
"loss": 3.5979,
"step": 921088
},
{
"epoch": 1.0,
"learning_rate": 3.491179686614521e-05,
"loss": 3.6006,
"step": 921600
},
{
"epoch": 1.0,
"learning_rate": 3.490341091863469e-05,
"loss": 3.5944,
"step": 922112
},
{
"epoch": 1.0,
"learning_rate": 3.489502497112417e-05,
"loss": 3.5751,
"step": 922624
},
{
"epoch": 1.0,
"learning_rate": 3.488663902361365e-05,
"loss": 3.5924,
"step": 923136
},
{
"epoch": 1.0,
"learning_rate": 3.487825307610313e-05,
"loss": 3.5746,
"step": 923648
},
{
"epoch": 1.0,
"learning_rate": 3.486986712859261e-05,
"loss": 3.5911,
"step": 924160
},
{
"epoch": 1.0,
"learning_rate": 3.486149755988582e-05,
"loss": 3.5864,
"step": 924672
},
{
"epoch": 1.0,
"learning_rate": 3.48531116123753e-05,
"loss": 3.5853,
"step": 925184
},
{
"epoch": 1.0,
"learning_rate": 3.484472566486478e-05,
"loss": 3.5909,
"step": 925696
},
{
"epoch": 1.0,
"learning_rate": 3.483633971735426e-05,
"loss": 3.6026,
"step": 926208
},
{
"epoch": 1.0,
"learning_rate": 3.482797014864747e-05,
"loss": 3.5887,
"step": 926720
},
{
"epoch": 1.0,
"learning_rate": 3.481958420113695e-05,
"loss": 3.5901,
"step": 927232
},
{
"epoch": 1.0,
"learning_rate": 3.481119825362643e-05,
"loss": 3.5873,
"step": 927744
},
{
"epoch": 1.0,
"learning_rate": 3.480281230611591e-05,
"loss": 3.5928,
"step": 928256
},
{
"epoch": 1.0,
"learning_rate": 3.4794442737409125e-05,
"loss": 3.5926,
"step": 928768
},
{
"epoch": 1.0,
"learning_rate": 3.4786056789898605e-05,
"loss": 3.5854,
"step": 929280
},
{
"epoch": 1.0,
"learning_rate": 3.4777670842388085e-05,
"loss": 3.5874,
"step": 929792
},
{
"epoch": 1.0,
"learning_rate": 3.4769284894877565e-05,
"loss": 3.5824,
"step": 930304
},
{
"epoch": 1.0,
"learning_rate": 3.4760898947367045e-05,
"loss": 3.5848,
"step": 930816
},
{
"epoch": 1.01,
"learning_rate": 3.4752512999856525e-05,
"loss": 3.5844,
"step": 931328
},
{
"epoch": 1.01,
"learning_rate": 3.4744127052346005e-05,
"loss": 3.5911,
"step": 931840
},
{
"epoch": 1.01,
"learning_rate": 3.4735741104835485e-05,
"loss": 3.5884,
"step": 932352
},
{
"epoch": 1.01,
"learning_rate": 3.4727371536128694e-05,
"loss": 3.5962,
"step": 932864
},
{
"epoch": 1.01,
"learning_rate": 3.4718985588618174e-05,
"loss": 3.5863,
"step": 933376
},
{
"epoch": 1.01,
"learning_rate": 3.4710599641107654e-05,
"loss": 3.5838,
"step": 933888
},
{
"epoch": 1.01,
"learning_rate": 3.4702213693597134e-05,
"loss": 3.595,
"step": 934400
},
{
"epoch": 1.01,
"learning_rate": 3.469384412489034e-05,
"loss": 3.5795,
"step": 934912
},
{
"epoch": 1.01,
"learning_rate": 3.468545817737982e-05,
"loss": 3.576,
"step": 935424
},
{
"epoch": 1.01,
"learning_rate": 3.467707222986931e-05,
"loss": 3.5838,
"step": 935936
},
{
"epoch": 1.01,
"learning_rate": 3.466868628235879e-05,
"loss": 3.5819,
"step": 936448
},
{
"epoch": 1.01,
"learning_rate": 3.4660316713652e-05,
"loss": 3.5804,
"step": 936960
},
{
"epoch": 1.01,
"learning_rate": 3.465193076614148e-05,
"loss": 3.5823,
"step": 937472
},
{
"epoch": 1.01,
"learning_rate": 3.464354481863096e-05,
"loss": 3.5871,
"step": 937984
},
{
"epoch": 1.01,
"learning_rate": 3.463515887112044e-05,
"loss": 3.5876,
"step": 938496
},
{
"epoch": 1.01,
"learning_rate": 3.462677292360992e-05,
"loss": 3.5904,
"step": 939008
},
{
"epoch": 1.01,
"learning_rate": 3.461840335490313e-05,
"loss": 3.592,
"step": 939520
},
{
"epoch": 1.01,
"learning_rate": 3.461001740739261e-05,
"loss": 3.5871,
"step": 940032
},
{
"epoch": 1.01,
"learning_rate": 3.460163145988209e-05,
"loss": 3.5677,
"step": 940544
},
{
"epoch": 1.01,
"learning_rate": 3.459324551237157e-05,
"loss": 3.5908,
"step": 941056
},
{
"epoch": 1.01,
"learning_rate": 3.458485956486105e-05,
"loss": 3.5837,
"step": 941568
},
{
"epoch": 1.01,
"learning_rate": 3.457648999615426e-05,
"loss": 3.5859,
"step": 942080
},
{
"epoch": 1.01,
"learning_rate": 3.456810404864374e-05,
"loss": 3.5816,
"step": 942592
},
{
"epoch": 1.01,
"learning_rate": 3.455971810113322e-05,
"loss": 3.5805,
"step": 943104
},
{
"epoch": 1.01,
"learning_rate": 3.45513321536227e-05,
"loss": 3.5712,
"step": 943616
},
{
"epoch": 1.01,
"learning_rate": 3.454296258491591e-05,
"loss": 3.5772,
"step": 944128
},
{
"epoch": 1.01,
"learning_rate": 3.453457663740539e-05,
"loss": 3.5827,
"step": 944640
},
{
"epoch": 1.01,
"learning_rate": 3.452619068989487e-05,
"loss": 3.5723,
"step": 945152
},
{
"epoch": 1.01,
"learning_rate": 3.451780474238435e-05,
"loss": 3.5934,
"step": 945664
},
{
"epoch": 1.01,
"learning_rate": 3.450943517367756e-05,
"loss": 3.5873,
"step": 946176
},
{
"epoch": 1.01,
"learning_rate": 3.450104922616704e-05,
"loss": 3.5656,
"step": 946688
},
{
"epoch": 1.01,
"learning_rate": 3.449266327865652e-05,
"loss": 3.597,
"step": 947200
},
{
"epoch": 1.01,
"learning_rate": 3.4484277331146e-05,
"loss": 3.5724,
"step": 947712
},
{
"epoch": 1.01,
"learning_rate": 3.447589138363548e-05,
"loss": 3.5685,
"step": 948224
},
{
"epoch": 1.01,
"learning_rate": 3.44675218149287e-05,
"loss": 3.5807,
"step": 948736
},
{
"epoch": 1.01,
"learning_rate": 3.445913586741818e-05,
"loss": 3.5813,
"step": 949248
},
{
"epoch": 1.01,
"learning_rate": 3.445074991990765e-05,
"loss": 3.5685,
"step": 949760
},
{
"epoch": 1.01,
"learning_rate": 3.444236397239713e-05,
"loss": 3.5816,
"step": 950272
},
{
"epoch": 1.01,
"learning_rate": 3.4433994403690346e-05,
"loss": 3.5674,
"step": 950784
},
{
"epoch": 1.01,
"learning_rate": 3.4425608456179826e-05,
"loss": 3.572,
"step": 951296
},
{
"epoch": 1.01,
"learning_rate": 3.44172225086693e-05,
"loss": 3.5879,
"step": 951808
},
{
"epoch": 1.01,
"learning_rate": 3.440883656115878e-05,
"loss": 3.5828,
"step": 952320
},
{
"epoch": 1.01,
"learning_rate": 3.4400466992451995e-05,
"loss": 3.5891,
"step": 952832
},
{
"epoch": 1.01,
"learning_rate": 3.439208104494147e-05,
"loss": 3.5817,
"step": 953344
},
{
"epoch": 1.01,
"learning_rate": 3.4383695097430955e-05,
"loss": 3.5992,
"step": 953856
},
{
"epoch": 1.01,
"learning_rate": 3.4375309149920435e-05,
"loss": 3.5732,
"step": 954368
},
{
"epoch": 1.01,
"learning_rate": 3.436693958121365e-05,
"loss": 3.5903,
"step": 954880
},
{
"epoch": 1.01,
"learning_rate": 3.4358553633703124e-05,
"loss": 3.5807,
"step": 955392
},
{
"epoch": 1.01,
"learning_rate": 3.4350167686192604e-05,
"loss": 3.5744,
"step": 955904
},
{
"epoch": 1.01,
"learning_rate": 3.4341781738682083e-05,
"loss": 3.5834,
"step": 956416
},
{
"epoch": 1.01,
"learning_rate": 3.4333395791171563e-05,
"loss": 3.5943,
"step": 956928
},
{
"epoch": 1.01,
"learning_rate": 3.432502622246477e-05,
"loss": 3.5796,
"step": 957440
},
{
"epoch": 1.01,
"learning_rate": 3.431664027495425e-05,
"loss": 3.59,
"step": 957952
},
{
"epoch": 1.01,
"learning_rate": 3.430825432744373e-05,
"loss": 3.5675,
"step": 958464
},
{
"epoch": 1.01,
"learning_rate": 3.429986837993321e-05,
"loss": 3.5614,
"step": 958976
},
{
"epoch": 1.01,
"learning_rate": 3.429149881122642e-05,
"loss": 3.5745,
"step": 959488
},
{
"epoch": 1.01,
"learning_rate": 3.428311286371591e-05,
"loss": 3.5859,
"step": 960000
},
{
"epoch": 1.01,
"learning_rate": 3.427472691620539e-05,
"loss": 3.58,
"step": 960512
},
{
"epoch": 1.01,
"learning_rate": 3.426634096869487e-05,
"loss": 3.5763,
"step": 961024
},
{
"epoch": 1.01,
"learning_rate": 3.425795502118435e-05,
"loss": 3.5728,
"step": 961536
},
{
"epoch": 1.02,
"learning_rate": 3.424958545247756e-05,
"loss": 3.5784,
"step": 962048
},
{
"epoch": 1.02,
"learning_rate": 3.424119950496704e-05,
"loss": 3.5765,
"step": 962560
},
{
"epoch": 1.02,
"learning_rate": 3.423281355745652e-05,
"loss": 3.5735,
"step": 963072
},
{
"epoch": 1.02,
"learning_rate": 3.4224427609946e-05,
"loss": 3.5867,
"step": 963584
},
{
"epoch": 1.02,
"learning_rate": 3.4216058041239206e-05,
"loss": 3.5923,
"step": 964096
},
{
"epoch": 1.02,
"learning_rate": 3.4207672093728686e-05,
"loss": 3.5906,
"step": 964608
},
{
"epoch": 1.02,
"learning_rate": 3.4199286146218166e-05,
"loss": 3.5692,
"step": 965120
},
{
"epoch": 1.02,
"learning_rate": 3.4190900198707646e-05,
"loss": 3.5788,
"step": 965632
},
{
"epoch": 1.02,
"learning_rate": 3.418253063000086e-05,
"loss": 3.5762,
"step": 966144
},
{
"epoch": 1.02,
"learning_rate": 3.417414468249034e-05,
"loss": 3.587,
"step": 966656
},
{
"epoch": 1.02,
"learning_rate": 3.416575873497982e-05,
"loss": 3.5835,
"step": 967168
},
{
"epoch": 1.02,
"learning_rate": 3.41573727874693e-05,
"loss": 3.5804,
"step": 967680
},
{
"epoch": 1.02,
"learning_rate": 3.414900321876251e-05,
"loss": 3.5783,
"step": 968192
},
{
"epoch": 1.02,
"learning_rate": 3.414061727125199e-05,
"loss": 3.5794,
"step": 968704
},
{
"epoch": 1.02,
"learning_rate": 3.413223132374147e-05,
"loss": 3.5809,
"step": 969216
},
{
"epoch": 1.02,
"learning_rate": 3.412384537623095e-05,
"loss": 3.5764,
"step": 969728
},
{
"epoch": 1.02,
"learning_rate": 3.411547580752416e-05,
"loss": 3.5742,
"step": 970240
},
{
"epoch": 1.02,
"learning_rate": 3.410708986001364e-05,
"loss": 3.5703,
"step": 970752
},
{
"epoch": 1.02,
"learning_rate": 3.409870391250312e-05,
"loss": 3.5711,
"step": 971264
},
{
"epoch": 1.02,
"learning_rate": 3.40903179649926e-05,
"loss": 3.5715,
"step": 971776
},
{
"epoch": 1.02,
"learning_rate": 3.408194839628581e-05,
"loss": 3.5704,
"step": 972288
},
{
"epoch": 1.02,
"learning_rate": 3.4073562448775296e-05,
"loss": 3.5738,
"step": 972800
},
{
"epoch": 1.02,
"learning_rate": 3.4065176501264775e-05,
"loss": 3.5795,
"step": 973312
},
{
"epoch": 1.02,
"learning_rate": 3.4056790553754255e-05,
"loss": 3.5665,
"step": 973824
},
{
"epoch": 1.02,
"learning_rate": 3.4048420985047465e-05,
"loss": 3.5859,
"step": 974336
},
{
"epoch": 1.02,
"learning_rate": 3.4040035037536944e-05,
"loss": 3.5912,
"step": 974848
},
{
"epoch": 1.02,
"learning_rate": 3.4031649090026424e-05,
"loss": 3.5792,
"step": 975360
},
{
"epoch": 1.02,
"learning_rate": 3.4023263142515904e-05,
"loss": 3.5834,
"step": 975872
},
{
"epoch": 1.02,
"learning_rate": 3.4014877195005384e-05,
"loss": 3.5809,
"step": 976384
},
{
"epoch": 1.02,
"learning_rate": 3.4006507626298593e-05,
"loss": 3.5712,
"step": 976896
},
{
"epoch": 1.02,
"learning_rate": 3.3998121678788073e-05,
"loss": 3.5831,
"step": 977408
},
{
"epoch": 1.02,
"learning_rate": 3.398973573127755e-05,
"loss": 3.5598,
"step": 977920
},
{
"epoch": 1.02,
"learning_rate": 3.398134978376703e-05,
"loss": 3.5782,
"step": 978432
},
{
"epoch": 1.02,
"learning_rate": 3.397298021506025e-05,
"loss": 3.5759,
"step": 978944
},
{
"epoch": 1.02,
"learning_rate": 3.396459426754973e-05,
"loss": 3.5823,
"step": 979456
},
{
"epoch": 1.02,
"learning_rate": 3.395620832003921e-05,
"loss": 3.5755,
"step": 979968
},
{
"epoch": 1.02,
"learning_rate": 3.394782237252869e-05,
"loss": 3.5845,
"step": 980480
},
{
"epoch": 1.02,
"learning_rate": 3.39394528038219e-05,
"loss": 3.5721,
"step": 980992
},
{
"epoch": 1.02,
"learning_rate": 3.393106685631138e-05,
"loss": 3.571,
"step": 981504
},
{
"epoch": 1.02,
"learning_rate": 3.392268090880086e-05,
"loss": 3.584,
"step": 982016
},
{
"epoch": 1.02,
"learning_rate": 3.391429496129034e-05,
"loss": 3.5796,
"step": 982528
},
{
"epoch": 1.02,
"learning_rate": 3.390592539258355e-05,
"loss": 3.5879,
"step": 983040
},
{
"epoch": 1.02,
"learning_rate": 3.389753944507303e-05,
"loss": 3.5721,
"step": 983552
},
{
"epoch": 1.02,
"learning_rate": 3.388915349756251e-05,
"loss": 3.5873,
"step": 984064
},
{
"epoch": 1.02,
"learning_rate": 3.388076755005199e-05,
"loss": 3.5771,
"step": 984576
},
{
"epoch": 1.02,
"learning_rate": 3.38723979813452e-05,
"loss": 3.5811,
"step": 985088
},
{
"epoch": 1.02,
"learning_rate": 3.386401203383468e-05,
"loss": 3.5825,
"step": 985600
},
{
"epoch": 1.02,
"learning_rate": 3.385562608632416e-05,
"loss": 3.5755,
"step": 986112
},
{
"epoch": 1.02,
"learning_rate": 3.384724013881364e-05,
"loss": 3.5735,
"step": 986624
},
{
"epoch": 1.02,
"learning_rate": 3.383885419130312e-05,
"loss": 3.5875,
"step": 987136
},
{
"epoch": 1.02,
"learning_rate": 3.38304682437926e-05,
"loss": 3.565,
"step": 987648
},
{
"epoch": 1.02,
"learning_rate": 3.382209867508581e-05,
"loss": 3.5736,
"step": 988160
},
{
"epoch": 1.02,
"learning_rate": 3.381371272757529e-05,
"loss": 3.58,
"step": 988672
},
{
"epoch": 1.02,
"learning_rate": 3.380532678006477e-05,
"loss": 3.5768,
"step": 989184
},
{
"epoch": 1.02,
"learning_rate": 3.379694083255425e-05,
"loss": 3.5783,
"step": 989696
},
{
"epoch": 1.02,
"learning_rate": 3.378857126384746e-05,
"loss": 3.5763,
"step": 990208
},
{
"epoch": 1.02,
"learning_rate": 3.378018531633694e-05,
"loss": 3.5761,
"step": 990720
},
{
"epoch": 1.02,
"learning_rate": 3.377179936882642e-05,
"loss": 3.5823,
"step": 991232
},
{
"epoch": 1.02,
"learning_rate": 3.37634134213159e-05,
"loss": 3.5817,
"step": 991744
},
{
"epoch": 1.03,
"eval_loss": 3.8422842025756836,
"eval_runtime": 333.4719,
"eval_samples_per_second": 1144.297,
"eval_steps_per_second": 35.76,
"step": 992160
},
{
"epoch": 0.0,
"learning_rate": 3.375502747380538e-05,
"loss": 3.5694,
"step": 992256
},
{
"epoch": 0.0,
"learning_rate": 3.374664152629486e-05,
"loss": 3.5628,
"step": 992768
},
{
"epoch": 0.0,
"learning_rate": 3.373825557878434e-05,
"loss": 3.573,
"step": 993280
},
{
"epoch": 0.0,
"learning_rate": 3.372986963127382e-05,
"loss": 3.5862,
"step": 993792
},
{
"epoch": 0.0,
"learning_rate": 3.372150006256703e-05,
"loss": 3.5776,
"step": 994304
},
{
"epoch": 0.0,
"learning_rate": 3.371311411505651e-05,
"loss": 3.5759,
"step": 994816
},
{
"epoch": 0.0,
"learning_rate": 3.370472816754599e-05,
"loss": 3.5789,
"step": 995328
},
{
"epoch": 0.0,
"learning_rate": 3.369634222003547e-05,
"loss": 3.5733,
"step": 995840
},
{
"epoch": 0.0,
"learning_rate": 3.368795627252495e-05,
"loss": 3.5659,
"step": 996352
},
{
"epoch": 0.0,
"learning_rate": 3.367958670381816e-05,
"loss": 3.5704,
"step": 996864
},
{
"epoch": 0.0,
"learning_rate": 3.367120075630764e-05,
"loss": 3.5777,
"step": 997376
},
{
"epoch": 0.0,
"learning_rate": 3.3662814808797125e-05,
"loss": 3.5828,
"step": 997888
},
{
"epoch": 0.0,
"learning_rate": 3.3654428861286605e-05,
"loss": 3.5808,
"step": 998400
},
{
"epoch": 0.0,
"learning_rate": 3.3646059292579814e-05,
"loss": 3.5521,
"step": 998912
},
{
"epoch": 0.0,
"learning_rate": 3.3637673345069294e-05,
"loss": 3.5702,
"step": 999424
},
{
"epoch": 0.0,
"learning_rate": 3.3629287397558774e-05,
"loss": 3.5596,
"step": 999936
},
{
"epoch": 0.0,
"learning_rate": 3.3620901450048254e-05,
"loss": 3.5744,
"step": 1000448
},
{
"epoch": 0.0,
"learning_rate": 3.3612515502537734e-05,
"loss": 3.5688,
"step": 1000960
},
{
"epoch": 0.0,
"learning_rate": 3.360414593383094e-05,
"loss": 3.5695,
"step": 1001472
},
{
"epoch": 0.0,
"learning_rate": 3.359575998632042e-05,
"loss": 3.5678,
"step": 1001984
},
{
"epoch": 0.0,
"learning_rate": 3.35873740388099e-05,
"loss": 3.5905,
"step": 1002496
},
{
"epoch": 0.0,
"learning_rate": 3.357898809129938e-05,
"loss": 3.5687,
"step": 1003008
},
{
"epoch": 0.0,
"learning_rate": 3.357061852259259e-05,
"loss": 3.5735,
"step": 1003520
},
{
"epoch": 0.0,
"learning_rate": 3.356223257508208e-05,
"loss": 3.5684,
"step": 1004032
},
{
"epoch": 0.0,
"learning_rate": 3.355384662757156e-05,
"loss": 3.5761,
"step": 1004544
},
{
"epoch": 0.0,
"learning_rate": 3.354546068006104e-05,
"loss": 3.5733,
"step": 1005056
},
{
"epoch": 0.0,
"learning_rate": 3.353709111135425e-05,
"loss": 3.5661,
"step": 1005568
},
{
"epoch": 0.0,
"learning_rate": 3.352870516384373e-05,
"loss": 3.5725,
"step": 1006080
},
{
"epoch": 0.0,
"learning_rate": 3.352031921633321e-05,
"loss": 3.5646,
"step": 1006592
},
{
"epoch": 0.0,
"learning_rate": 3.351193326882269e-05,
"loss": 3.5644,
"step": 1007104
},
{
"epoch": 0.01,
"learning_rate": 3.35035637001159e-05,
"loss": 3.5701,
"step": 1007616
},
{
"epoch": 0.01,
"learning_rate": 3.349517775260538e-05,
"loss": 3.5694,
"step": 1008128
},
{
"epoch": 0.01,
"learning_rate": 3.348679180509486e-05,
"loss": 3.5741,
"step": 1008640
},
{
"epoch": 0.01,
"learning_rate": 3.3478405857584337e-05,
"loss": 3.5776,
"step": 1009152
},
{
"epoch": 0.01,
"learning_rate": 3.3470019910073817e-05,
"loss": 3.571,
"step": 1009664
},
{
"epoch": 0.01,
"learning_rate": 3.346165034136703e-05,
"loss": 3.5701,
"step": 1010176
},
{
"epoch": 0.01,
"learning_rate": 3.345326439385651e-05,
"loss": 3.5786,
"step": 1010688
},
{
"epoch": 0.01,
"learning_rate": 3.344487844634599e-05,
"loss": 3.5578,
"step": 1011200
},
{
"epoch": 0.01,
"learning_rate": 3.343649249883547e-05,
"loss": 3.562,
"step": 1011712
},
{
"epoch": 0.01,
"learning_rate": 3.342812293012868e-05,
"loss": 3.5676,
"step": 1012224
},
{
"epoch": 0.01,
"learning_rate": 3.341973698261816e-05,
"loss": 3.5604,
"step": 1012736
},
{
"epoch": 0.01,
"learning_rate": 3.341135103510764e-05,
"loss": 3.566,
"step": 1013248
},
{
"epoch": 0.01,
"learning_rate": 3.340296508759712e-05,
"loss": 3.5697,
"step": 1013760
},
{
"epoch": 0.01,
"learning_rate": 3.339459551889033e-05,
"loss": 3.5671,
"step": 1014272
},
{
"epoch": 0.01,
"learning_rate": 3.338620957137981e-05,
"loss": 3.5703,
"step": 1014784
},
{
"epoch": 0.01,
"learning_rate": 3.337782362386929e-05,
"loss": 3.5723,
"step": 1015296
},
{
"epoch": 0.01,
"learning_rate": 3.336943767635877e-05,
"loss": 3.5778,
"step": 1015808
},
{
"epoch": 0.01,
"learning_rate": 3.336105172884825e-05,
"loss": 3.5688,
"step": 1016320
},
{
"epoch": 0.01,
"learning_rate": 3.3352682160141466e-05,
"loss": 3.5522,
"step": 1016832
},
{
"epoch": 0.01,
"learning_rate": 3.3344296212630946e-05,
"loss": 3.5699,
"step": 1017344
},
{
"epoch": 0.01,
"learning_rate": 3.3335910265120426e-05,
"loss": 3.5683,
"step": 1017856
},
{
"epoch": 0.01,
"learning_rate": 3.3327524317609906e-05,
"loss": 3.5707,
"step": 1018368
},
{
"epoch": 0.01,
"learning_rate": 3.3319138370099386e-05,
"loss": 3.5653,
"step": 1018880
},
{
"epoch": 0.01,
"learning_rate": 3.3310768801392595e-05,
"loss": 3.5604,
"step": 1019392
},
{
"epoch": 0.01,
"learning_rate": 3.3302382853882075e-05,
"loss": 3.5559,
"step": 1019904
},
{
"epoch": 0.01,
"learning_rate": 3.3293996906371555e-05,
"loss": 3.5579,
"step": 1020416
},
{
"epoch": 0.01,
"learning_rate": 3.3285610958861035e-05,
"loss": 3.5667,
"step": 1020928
},
{
"epoch": 0.01,
"learning_rate": 3.3277241390154244e-05,
"loss": 3.5534,
"step": 1021440
},
{
"epoch": 0.01,
"learning_rate": 3.3268855442643724e-05,
"loss": 3.5763,
"step": 1021952
},
{
"epoch": 0.01,
"learning_rate": 3.3260469495133204e-05,
"loss": 3.5709,
"step": 1022464
},
{
"epoch": 0.01,
"learning_rate": 3.325209992642642e-05,
"loss": 3.5469,
"step": 1022976
},
{
"epoch": 0.01,
"learning_rate": 3.32437139789159e-05,
"loss": 3.5763,
"step": 1023488
},
{
"epoch": 0.01,
"learning_rate": 3.323532803140538e-05,
"loss": 3.553,
"step": 1024000
},
{
"epoch": 0.01,
"learning_rate": 3.322694208389486e-05,
"loss": 3.5568,
"step": 1024512
},
{
"epoch": 0.01,
"learning_rate": 3.321855613638433e-05,
"loss": 3.5556,
"step": 1025024
},
{
"epoch": 0.01,
"learning_rate": 3.321018656767755e-05,
"loss": 3.5686,
"step": 1025536
},
{
"epoch": 0.01,
"learning_rate": 3.320180062016703e-05,
"loss": 3.5512,
"step": 1026048
},
{
"epoch": 0.01,
"learning_rate": 3.319341467265651e-05,
"loss": 3.5686,
"step": 1026560
},
{
"epoch": 0.01,
"learning_rate": 3.318502872514598e-05,
"loss": 3.548,
"step": 1027072
},
{
"epoch": 0.01,
"learning_rate": 3.31766591564392e-05,
"loss": 3.5565,
"step": 1027584
},
{
"epoch": 0.01,
"learning_rate": 3.316827320892868e-05,
"loss": 3.573,
"step": 1028096
},
{
"epoch": 0.01,
"learning_rate": 3.315988726141816e-05,
"loss": 3.5614,
"step": 1028608
},
{
"epoch": 0.01,
"learning_rate": 3.315150131390764e-05,
"loss": 3.573,
"step": 1029120
},
{
"epoch": 0.01,
"learning_rate": 3.314313174520085e-05,
"loss": 3.5631,
"step": 1029632
},
{
"epoch": 0.01,
"learning_rate": 3.313474579769033e-05,
"loss": 3.5816,
"step": 1030144
},
{
"epoch": 0.01,
"learning_rate": 3.3126359850179806e-05,
"loss": 3.5576,
"step": 1030656
},
{
"epoch": 0.01,
"learning_rate": 3.3117973902669286e-05,
"loss": 3.5759,
"step": 1031168
},
{
"epoch": 0.01,
"learning_rate": 3.3109587955158766e-05,
"loss": 3.5599,
"step": 1031680
},
{
"epoch": 0.01,
"learning_rate": 3.310121838645198e-05,
"loss": 3.5585,
"step": 1032192
},
{
"epoch": 0.01,
"learning_rate": 3.3092832438941455e-05,
"loss": 3.566,
"step": 1032704
},
{
"epoch": 0.01,
"learning_rate": 3.3084446491430935e-05,
"loss": 3.5774,
"step": 1033216
},
{
"epoch": 0.01,
"learning_rate": 3.3076060543920415e-05,
"loss": 3.5656,
"step": 1033728
},
{
"epoch": 0.01,
"learning_rate": 3.3067690975213624e-05,
"loss": 3.57,
"step": 1034240
},
{
"epoch": 0.01,
"learning_rate": 3.305930502770311e-05,
"loss": 3.5498,
"step": 1034752
},
{
"epoch": 0.01,
"learning_rate": 3.305091908019259e-05,
"loss": 3.5474,
"step": 1035264
},
{
"epoch": 0.01,
"learning_rate": 3.304253313268207e-05,
"loss": 3.559,
"step": 1035776
},
{
"epoch": 0.01,
"learning_rate": 3.303414718517155e-05,
"loss": 3.5659,
"step": 1036288
},
{
"epoch": 0.01,
"learning_rate": 3.302577761646476e-05,
"loss": 3.5622,
"step": 1036800
},
{
"epoch": 0.01,
"learning_rate": 3.301739166895424e-05,
"loss": 3.5585,
"step": 1037312
},
{
"epoch": 0.01,
"learning_rate": 3.300900572144372e-05,
"loss": 3.5614,
"step": 1037824
},
{
"epoch": 0.02,
"learning_rate": 3.30006197739332e-05,
"loss": 3.5584,
"step": 1038336
},
{
"epoch": 0.02,
"learning_rate": 3.299225020522641e-05,
"loss": 3.5626,
"step": 1038848
},
{
"epoch": 0.02,
"learning_rate": 3.298386425771589e-05,
"loss": 3.5558,
"step": 1039360
},
{
"epoch": 0.02,
"learning_rate": 3.297547831020537e-05,
"loss": 3.5671,
"step": 1039872
},
{
"epoch": 0.02,
"learning_rate": 3.296709236269485e-05,
"loss": 3.5758,
"step": 1040384
},
{
"epoch": 0.02,
"learning_rate": 3.2958722793988065e-05,
"loss": 3.5728,
"step": 1040896
},
{
"epoch": 0.02,
"learning_rate": 3.2950336846477545e-05,
"loss": 3.554,
"step": 1041408
},
{
"epoch": 0.02,
"learning_rate": 3.2941950898967025e-05,
"loss": 3.5588,
"step": 1041920
},
{
"epoch": 0.02,
"learning_rate": 3.2933564951456505e-05,
"loss": 3.561,
"step": 1042432
},
{
"epoch": 0.02,
"learning_rate": 3.2925195382749714e-05,
"loss": 3.5703,
"step": 1042944
},
{
"epoch": 0.02,
"learning_rate": 3.2916809435239194e-05,
"loss": 3.5636,
"step": 1043456
},
{
"epoch": 0.02,
"learning_rate": 3.2908423487728674e-05,
"loss": 3.5619,
"step": 1043968
},
{
"epoch": 0.02,
"learning_rate": 3.2900037540218154e-05,
"loss": 3.5635,
"step": 1044480
},
{
"epoch": 0.02,
"learning_rate": 3.2891651592707634e-05,
"loss": 3.5669,
"step": 1044992
},
{
"epoch": 0.02,
"learning_rate": 3.288328202400084e-05,
"loss": 3.5619,
"step": 1045504
},
{
"epoch": 0.02,
"learning_rate": 3.287489607649032e-05,
"loss": 3.5605,
"step": 1046016
},
{
"epoch": 0.02,
"learning_rate": 3.28665101289798e-05,
"loss": 3.5566,
"step": 1046528
},
{
"epoch": 0.02,
"learning_rate": 3.285812418146928e-05,
"loss": 3.5533,
"step": 1047040
},
{
"epoch": 0.02,
"learning_rate": 3.28497546127625e-05,
"loss": 3.5602,
"step": 1047552
},
{
"epoch": 0.02,
"learning_rate": 3.284136866525198e-05,
"loss": 3.5516,
"step": 1048064
},
{
"epoch": 0.02,
"learning_rate": 3.283298271774146e-05,
"loss": 3.5541,
"step": 1048576
},
{
"epoch": 0.02,
"learning_rate": 3.282459677023094e-05,
"loss": 3.5558,
"step": 1049088
},
{
"epoch": 0.02,
"learning_rate": 3.281622720152415e-05,
"loss": 3.5604,
"step": 1049600
},
{
"epoch": 0.02,
"learning_rate": 3.280784125401363e-05,
"loss": 3.5563,
"step": 1050112
},
{
"epoch": 0.02,
"learning_rate": 3.279945530650311e-05,
"loss": 3.5643,
"step": 1050624
},
{
"epoch": 0.02,
"learning_rate": 3.279106935899259e-05,
"loss": 3.5725,
"step": 1051136
},
{
"epoch": 0.02,
"learning_rate": 3.2782699790285796e-05,
"loss": 3.5661,
"step": 1051648
},
{
"epoch": 0.02,
"learning_rate": 3.2774313842775276e-05,
"loss": 3.5692,
"step": 1052160
},
{
"epoch": 0.02,
"learning_rate": 3.2765927895264756e-05,
"loss": 3.5588,
"step": 1052672
},
{
"epoch": 0.02,
"learning_rate": 3.2757541947754236e-05,
"loss": 3.5619,
"step": 1053184
},
{
"epoch": 0.02,
"learning_rate": 3.2749156000243716e-05,
"loss": 3.5621,
"step": 1053696
},
{
"epoch": 0.02,
"learning_rate": 3.274078643153693e-05,
"loss": 3.5466,
"step": 1054208
},
{
"epoch": 0.02,
"learning_rate": 3.273240048402641e-05,
"loss": 3.5618,
"step": 1054720
},
{
"epoch": 0.02,
"learning_rate": 3.272401453651589e-05,
"loss": 3.5536,
"step": 1055232
},
{
"epoch": 0.02,
"learning_rate": 3.271562858900537e-05,
"loss": 3.5668,
"step": 1055744
},
{
"epoch": 0.02,
"learning_rate": 3.270725902029858e-05,
"loss": 3.5629,
"step": 1056256
},
{
"epoch": 0.02,
"learning_rate": 3.269887307278806e-05,
"loss": 3.5635,
"step": 1056768
},
{
"epoch": 0.02,
"learning_rate": 3.269048712527754e-05,
"loss": 3.5531,
"step": 1057280
},
{
"epoch": 0.02,
"learning_rate": 3.268210117776702e-05,
"loss": 3.5562,
"step": 1057792
},
{
"epoch": 0.02,
"learning_rate": 3.267373160906023e-05,
"loss": 3.5671,
"step": 1058304
},
{
"epoch": 0.02,
"learning_rate": 3.266534566154971e-05,
"loss": 3.5632,
"step": 1058816
},
{
"epoch": 0.02,
"learning_rate": 3.265695971403919e-05,
"loss": 3.5716,
"step": 1059328
},
{
"epoch": 0.02,
"learning_rate": 3.264857376652867e-05,
"loss": 3.5537,
"step": 1059840
},
{
"epoch": 0.02,
"learning_rate": 3.2640204197821886e-05,
"loss": 3.568,
"step": 1060352
},
{
"epoch": 0.02,
"learning_rate": 3.2631818250311366e-05,
"loss": 3.5622,
"step": 1060864
},
{
"epoch": 0.02,
"learning_rate": 3.2623432302800846e-05,
"loss": 3.5642,
"step": 1061376
},
{
"epoch": 0.02,
"learning_rate": 3.2615046355290326e-05,
"loss": 3.5664,
"step": 1061888
},
{
"epoch": 0.02,
"learning_rate": 3.2606676786583535e-05,
"loss": 3.5599,
"step": 1062400
},
{
"epoch": 0.02,
"learning_rate": 3.2598290839073015e-05,
"loss": 3.5587,
"step": 1062912
},
{
"epoch": 0.02,
"learning_rate": 3.2589904891562495e-05,
"loss": 3.5689,
"step": 1063424
},
{
"epoch": 0.02,
"learning_rate": 3.2581518944051975e-05,
"loss": 3.5547,
"step": 1063936
},
{
"epoch": 0.02,
"learning_rate": 3.2573132996541455e-05,
"loss": 3.553,
"step": 1064448
},
{
"epoch": 0.02,
"learning_rate": 3.2564763427834664e-05,
"loss": 3.5667,
"step": 1064960
},
{
"epoch": 0.02,
"learning_rate": 3.2556377480324144e-05,
"loss": 3.5637,
"step": 1065472
},
{
"epoch": 0.02,
"learning_rate": 3.2547991532813624e-05,
"loss": 3.5594,
"step": 1065984
},
{
"epoch": 0.02,
"learning_rate": 3.2539605585303103e-05,
"loss": 3.5624,
"step": 1066496
},
{
"epoch": 0.02,
"learning_rate": 3.253123601659632e-05,
"loss": 3.5558,
"step": 1067008
},
{
"epoch": 0.02,
"learning_rate": 3.25228500690858e-05,
"loss": 3.5689,
"step": 1067520
},
{
"epoch": 0.02,
"learning_rate": 3.251446412157528e-05,
"loss": 3.5621,
"step": 1068032
},
{
"epoch": 0.03,
"eval_loss": 3.8428895473480225,
"eval_runtime": 312.5757,
"eval_samples_per_second": 1220.796,
"eval_steps_per_second": 38.151,
"step": 1068480
},
{
"epoch": 1.0,
"learning_rate": 3.250607817406476e-05,
"loss": 3.557,
"step": 1068544
},
{
"epoch": 1.0,
"learning_rate": 3.249770860535797e-05,
"loss": 3.5477,
"step": 1069056
},
{
"epoch": 1.0,
"learning_rate": 3.248932265784745e-05,
"loss": 3.5552,
"step": 1069568
},
{
"epoch": 1.0,
"learning_rate": 3.248093671033693e-05,
"loss": 3.5707,
"step": 1070080
},
{
"epoch": 1.0,
"learning_rate": 3.247255076282641e-05,
"loss": 3.5637,
"step": 1070592
},
{
"epoch": 1.0,
"learning_rate": 3.246418119411962e-05,
"loss": 3.5608,
"step": 1071104
},
{
"epoch": 1.0,
"learning_rate": 3.24557952466091e-05,
"loss": 3.5575,
"step": 1071616
},
{
"epoch": 1.0,
"learning_rate": 3.244740929909858e-05,
"loss": 3.5573,
"step": 1072128
},
{
"epoch": 1.0,
"learning_rate": 3.243902335158806e-05,
"loss": 3.5463,
"step": 1072640
},
{
"epoch": 1.0,
"learning_rate": 3.243063740407754e-05,
"loss": 3.5594,
"step": 1073152
},
{
"epoch": 1.0,
"learning_rate": 3.242226783537075e-05,
"loss": 3.5574,
"step": 1073664
},
{
"epoch": 1.0,
"learning_rate": 3.241388188786023e-05,
"loss": 3.571,
"step": 1074176
},
{
"epoch": 1.0,
"learning_rate": 3.2405495940349706e-05,
"loss": 3.5634,
"step": 1074688
},
{
"epoch": 1.0,
"learning_rate": 3.2397109992839186e-05,
"loss": 3.5366,
"step": 1075200
},
{
"epoch": 1.0,
"learning_rate": 3.23887404241324e-05,
"loss": 3.5572,
"step": 1075712
},
{
"epoch": 1.0,
"learning_rate": 3.238035447662188e-05,
"loss": 3.542,
"step": 1076224
},
{
"epoch": 1.0,
"learning_rate": 3.2371968529111355e-05,
"loss": 3.558,
"step": 1076736
},
{
"epoch": 1.0,
"learning_rate": 3.2363582581600835e-05,
"loss": 3.5502,
"step": 1077248
},
{
"epoch": 1.0,
"learning_rate": 3.235521301289405e-05,
"loss": 3.557,
"step": 1077760
},
{
"epoch": 1.0,
"learning_rate": 3.234682706538353e-05,
"loss": 3.5485,
"step": 1078272
},
{
"epoch": 1.0,
"learning_rate": 3.233844111787301e-05,
"loss": 3.5734,
"step": 1078784
},
{
"epoch": 1.0,
"learning_rate": 3.233005517036249e-05,
"loss": 3.5544,
"step": 1079296
},
{
"epoch": 1.0,
"learning_rate": 3.232168560165571e-05,
"loss": 3.5557,
"step": 1079808
},
{
"epoch": 1.0,
"learning_rate": 3.231329965414518e-05,
"loss": 3.5506,
"step": 1080320
},
{
"epoch": 1.0,
"learning_rate": 3.230491370663466e-05,
"loss": 3.5684,
"step": 1080832
},
{
"epoch": 1.0,
"learning_rate": 3.229652775912414e-05,
"loss": 3.5517,
"step": 1081344
},
{
"epoch": 1.0,
"learning_rate": 3.2288158190417356e-05,
"loss": 3.5501,
"step": 1081856
},
{
"epoch": 1.0,
"learning_rate": 3.227977224290683e-05,
"loss": 3.5548,
"step": 1082368
},
{
"epoch": 1.0,
"learning_rate": 3.227138629539631e-05,
"loss": 3.5541,
"step": 1082880
},
{
"epoch": 1.0,
"learning_rate": 3.226300034788579e-05,
"loss": 3.5478,
"step": 1083392
},
{
"epoch": 1.01,
"learning_rate": 3.2254630779179005e-05,
"loss": 3.5545,
"step": 1083904
},
{
"epoch": 1.01,
"learning_rate": 3.2246244831668485e-05,
"loss": 3.5512,
"step": 1084416
},
{
"epoch": 1.01,
"learning_rate": 3.2237858884157964e-05,
"loss": 3.558,
"step": 1084928
},
{
"epoch": 1.01,
"learning_rate": 3.2229472936647444e-05,
"loss": 3.5587,
"step": 1085440
},
{
"epoch": 1.01,
"learning_rate": 3.2221086989136924e-05,
"loss": 3.5554,
"step": 1085952
},
{
"epoch": 1.01,
"learning_rate": 3.2212717420430134e-05,
"loss": 3.5576,
"step": 1086464
},
{
"epoch": 1.01,
"learning_rate": 3.2204331472919613e-05,
"loss": 3.5578,
"step": 1086976
},
{
"epoch": 1.01,
"learning_rate": 3.2195945525409093e-05,
"loss": 3.5443,
"step": 1087488
},
{
"epoch": 1.01,
"learning_rate": 3.218755957789857e-05,
"loss": 3.5505,
"step": 1088000
},
{
"epoch": 1.01,
"learning_rate": 3.217919000919178e-05,
"loss": 3.5502,
"step": 1088512
},
{
"epoch": 1.01,
"learning_rate": 3.217080406168126e-05,
"loss": 3.542,
"step": 1089024
},
{
"epoch": 1.01,
"learning_rate": 3.216241811417074e-05,
"loss": 3.551,
"step": 1089536
},
{
"epoch": 1.01,
"learning_rate": 3.215403216666022e-05,
"loss": 3.5548,
"step": 1090048
},
{
"epoch": 1.01,
"learning_rate": 3.214566259795344e-05,
"loss": 3.549,
"step": 1090560
},
{
"epoch": 1.01,
"learning_rate": 3.213727665044292e-05,
"loss": 3.5557,
"step": 1091072
},
{
"epoch": 1.01,
"learning_rate": 3.21288907029324e-05,
"loss": 3.5563,
"step": 1091584
},
{
"epoch": 1.01,
"learning_rate": 3.212050475542188e-05,
"loss": 3.5594,
"step": 1092096
},
{
"epoch": 1.01,
"learning_rate": 3.211213518671509e-05,
"loss": 3.554,
"step": 1092608
},
{
"epoch": 1.01,
"learning_rate": 3.210374923920457e-05,
"loss": 3.5376,
"step": 1093120
},
{
"epoch": 1.01,
"learning_rate": 3.209536329169405e-05,
"loss": 3.555,
"step": 1093632
},
{
"epoch": 1.01,
"learning_rate": 3.208697734418353e-05,
"loss": 3.5557,
"step": 1094144
},
{
"epoch": 1.01,
"learning_rate": 3.207859139667301e-05,
"loss": 3.557,
"step": 1094656
},
{
"epoch": 1.01,
"learning_rate": 3.2070221827966216e-05,
"loss": 3.5469,
"step": 1095168
},
{
"epoch": 1.01,
"learning_rate": 3.2061835880455696e-05,
"loss": 3.546,
"step": 1095680
},
{
"epoch": 1.01,
"learning_rate": 3.2053449932945176e-05,
"loss": 3.538,
"step": 1096192
},
{
"epoch": 1.01,
"learning_rate": 3.2045063985434656e-05,
"loss": 3.5427,
"step": 1096704
},
{
"epoch": 1.01,
"learning_rate": 3.203669441672787e-05,
"loss": 3.5513,
"step": 1097216
},
{
"epoch": 1.01,
"learning_rate": 3.202830846921735e-05,
"loss": 3.5353,
"step": 1097728
},
{
"epoch": 1.01,
"learning_rate": 3.201992252170683e-05,
"loss": 3.5625,
"step": 1098240
},
{
"epoch": 1.01,
"learning_rate": 3.201153657419631e-05,
"loss": 3.5559,
"step": 1098752
},
{
"epoch": 1.01,
"learning_rate": 3.200316700548952e-05,
"loss": 3.533,
"step": 1099264
},
{
"epoch": 1.01,
"learning_rate": 3.1994781057979e-05,
"loss": 3.5621,
"step": 1099776
},
{
"epoch": 1.01,
"learning_rate": 3.198639511046848e-05,
"loss": 3.5375,
"step": 1100288
},
{
"epoch": 1.01,
"learning_rate": 3.197800916295796e-05,
"loss": 3.5439,
"step": 1100800
},
{
"epoch": 1.01,
"learning_rate": 3.196963959425117e-05,
"loss": 3.5389,
"step": 1101312
},
{
"epoch": 1.01,
"learning_rate": 3.196125364674065e-05,
"loss": 3.5521,
"step": 1101824
},
{
"epoch": 1.01,
"learning_rate": 3.195286769923013e-05,
"loss": 3.5366,
"step": 1102336
},
{
"epoch": 1.01,
"learning_rate": 3.194448175171961e-05,
"loss": 3.5511,
"step": 1102848
},
{
"epoch": 1.01,
"learning_rate": 3.1936112183012825e-05,
"loss": 3.5291,
"step": 1103360
},
{
"epoch": 1.01,
"learning_rate": 3.1927726235502305e-05,
"loss": 3.5425,
"step": 1103872
},
{
"epoch": 1.01,
"learning_rate": 3.1919340287991785e-05,
"loss": 3.5551,
"step": 1104384
},
{
"epoch": 1.01,
"learning_rate": 3.1910954340481265e-05,
"loss": 3.5477,
"step": 1104896
},
{
"epoch": 1.01,
"learning_rate": 3.1902584771774474e-05,
"loss": 3.5566,
"step": 1105408
},
{
"epoch": 1.01,
"learning_rate": 3.1894198824263954e-05,
"loss": 3.55,
"step": 1105920
},
{
"epoch": 1.01,
"learning_rate": 3.1885812876753434e-05,
"loss": 3.5655,
"step": 1106432
},
{
"epoch": 1.01,
"learning_rate": 3.1877426929242914e-05,
"loss": 3.5412,
"step": 1106944
},
{
"epoch": 1.01,
"learning_rate": 3.1869057360536123e-05,
"loss": 3.5614,
"step": 1107456
},
{
"epoch": 1.01,
"learning_rate": 3.18606714130256e-05,
"loss": 3.5417,
"step": 1107968
},
{
"epoch": 1.01,
"learning_rate": 3.185228546551508e-05,
"loss": 3.5425,
"step": 1108480
},
{
"epoch": 1.01,
"learning_rate": 3.184389951800456e-05,
"loss": 3.5504,
"step": 1108992
},
{
"epoch": 1.01,
"learning_rate": 3.183552994929778e-05,
"loss": 3.5575,
"step": 1109504
},
{
"epoch": 1.01,
"learning_rate": 3.182714400178726e-05,
"loss": 3.5523,
"step": 1110016
},
{
"epoch": 1.01,
"learning_rate": 3.181875805427674e-05,
"loss": 3.5536,
"step": 1110528
},
{
"epoch": 1.01,
"learning_rate": 3.181037210676622e-05,
"loss": 3.5354,
"step": 1111040
},
{
"epoch": 1.01,
"learning_rate": 3.180200253805943e-05,
"loss": 3.5294,
"step": 1111552
},
{
"epoch": 1.01,
"learning_rate": 3.179361659054891e-05,
"loss": 3.5436,
"step": 1112064
},
{
"epoch": 1.01,
"learning_rate": 3.178523064303839e-05,
"loss": 3.5508,
"step": 1112576
},
{
"epoch": 1.01,
"learning_rate": 3.177684469552787e-05,
"loss": 3.5458,
"step": 1113088
},
{
"epoch": 1.01,
"learning_rate": 3.176847512682108e-05,
"loss": 3.5414,
"step": 1113600
},
{
"epoch": 1.01,
"learning_rate": 3.176008917931056e-05,
"loss": 3.5476,
"step": 1114112
},
{
"epoch": 1.02,
"learning_rate": 3.175170323180004e-05,
"loss": 3.5413,
"step": 1114624
},
{
"epoch": 1.02,
"learning_rate": 3.174331728428952e-05,
"loss": 3.5468,
"step": 1115136
},
{
"epoch": 1.02,
"learning_rate": 3.1734931336779e-05,
"loss": 3.5422,
"step": 1115648
},
{
"epoch": 1.02,
"learning_rate": 3.172656176807221e-05,
"loss": 3.5541,
"step": 1116160
},
{
"epoch": 1.02,
"learning_rate": 3.171817582056169e-05,
"loss": 3.5589,
"step": 1116672
},
{
"epoch": 1.02,
"learning_rate": 3.170978987305117e-05,
"loss": 3.5588,
"step": 1117184
},
{
"epoch": 1.02,
"learning_rate": 3.170140392554065e-05,
"loss": 3.5361,
"step": 1117696
},
{
"epoch": 1.02,
"learning_rate": 3.169303435683386e-05,
"loss": 3.5461,
"step": 1118208
},
{
"epoch": 1.02,
"learning_rate": 3.168464840932334e-05,
"loss": 3.5445,
"step": 1118720
},
{
"epoch": 1.02,
"learning_rate": 3.167626246181282e-05,
"loss": 3.5524,
"step": 1119232
},
{
"epoch": 1.02,
"learning_rate": 3.16678765143023e-05,
"loss": 3.5505,
"step": 1119744
},
{
"epoch": 1.02,
"learning_rate": 3.165950694559551e-05,
"loss": 3.5455,
"step": 1120256
},
{
"epoch": 1.02,
"learning_rate": 3.165112099808499e-05,
"loss": 3.5467,
"step": 1120768
},
{
"epoch": 1.02,
"learning_rate": 3.164273505057447e-05,
"loss": 3.5466,
"step": 1121280
},
{
"epoch": 1.02,
"learning_rate": 3.163434910306395e-05,
"loss": 3.5493,
"step": 1121792
},
{
"epoch": 1.02,
"learning_rate": 3.1625979534357166e-05,
"loss": 3.5423,
"step": 1122304
},
{
"epoch": 1.02,
"learning_rate": 3.1617593586846646e-05,
"loss": 3.5472,
"step": 1122816
},
{
"epoch": 1.02,
"learning_rate": 3.1609207639336126e-05,
"loss": 3.5352,
"step": 1123328
},
{
"epoch": 1.02,
"learning_rate": 3.1600821691825606e-05,
"loss": 3.5447,
"step": 1123840
},
{
"epoch": 1.02,
"learning_rate": 3.1592452123118815e-05,
"loss": 3.5353,
"step": 1124352
},
{
"epoch": 1.02,
"learning_rate": 3.1584066175608295e-05,
"loss": 3.5389,
"step": 1124864
},
{
"epoch": 1.02,
"learning_rate": 3.1575680228097775e-05,
"loss": 3.5384,
"step": 1125376
},
{
"epoch": 1.02,
"learning_rate": 3.1567294280587255e-05,
"loss": 3.5464,
"step": 1125888
},
{
"epoch": 1.02,
"learning_rate": 3.1558924711880464e-05,
"loss": 3.5414,
"step": 1126400
},
{
"epoch": 1.02,
"learning_rate": 3.1550538764369944e-05,
"loss": 3.5462,
"step": 1126912
},
{
"epoch": 1.02,
"learning_rate": 3.1542152816859424e-05,
"loss": 3.5561,
"step": 1127424
},
{
"epoch": 1.02,
"learning_rate": 3.1533766869348904e-05,
"loss": 3.5538,
"step": 1127936
},
{
"epoch": 1.02,
"learning_rate": 3.152539730064212e-05,
"loss": 3.553,
"step": 1128448
},
{
"epoch": 1.02,
"learning_rate": 3.15170113531316e-05,
"loss": 3.5441,
"step": 1128960
},
{
"epoch": 1.02,
"learning_rate": 3.150862540562108e-05,
"loss": 3.5466,
"step": 1129472
},
{
"epoch": 1.02,
"learning_rate": 3.150023945811055e-05,
"loss": 3.5449,
"step": 1129984
},
{
"epoch": 1.02,
"learning_rate": 3.149186988940377e-05,
"loss": 3.5308,
"step": 1130496
},
{
"epoch": 1.02,
"learning_rate": 3.148348394189325e-05,
"loss": 3.5457,
"step": 1131008
},
{
"epoch": 1.02,
"learning_rate": 3.147509799438273e-05,
"loss": 3.5393,
"step": 1131520
},
{
"epoch": 1.02,
"learning_rate": 3.14667120468722e-05,
"loss": 3.5533,
"step": 1132032
},
{
"epoch": 1.02,
"learning_rate": 3.145834247816542e-05,
"loss": 3.5437,
"step": 1132544
},
{
"epoch": 1.02,
"learning_rate": 3.14499565306549e-05,
"loss": 3.5478,
"step": 1133056
},
{
"epoch": 1.02,
"learning_rate": 3.144157058314438e-05,
"loss": 3.5405,
"step": 1133568
},
{
"epoch": 1.02,
"learning_rate": 3.143318463563386e-05,
"loss": 3.5404,
"step": 1134080
},
{
"epoch": 1.02,
"learning_rate": 3.1424815066927074e-05,
"loss": 3.5534,
"step": 1134592
},
{
"epoch": 1.02,
"learning_rate": 3.1416429119416554e-05,
"loss": 3.5462,
"step": 1135104
},
{
"epoch": 1.02,
"learning_rate": 3.140804317190603e-05,
"loss": 3.56,
"step": 1135616
},
{
"epoch": 1.02,
"learning_rate": 3.139965722439551e-05,
"loss": 3.542,
"step": 1136128
},
{
"epoch": 1.02,
"learning_rate": 3.139128765568872e-05,
"loss": 3.5519,
"step": 1136640
},
{
"epoch": 1.02,
"learning_rate": 3.13829017081782e-05,
"loss": 3.5495,
"step": 1137152
},
{
"epoch": 1.02,
"learning_rate": 3.1374515760667676e-05,
"loss": 3.5496,
"step": 1137664
},
{
"epoch": 1.02,
"learning_rate": 3.1366129813157156e-05,
"loss": 3.5458,
"step": 1138176
},
{
"epoch": 1.02,
"learning_rate": 3.135776024445037e-05,
"loss": 3.5417,
"step": 1138688
},
{
"epoch": 1.02,
"learning_rate": 3.134937429693985e-05,
"loss": 3.5482,
"step": 1139200
},
{
"epoch": 1.02,
"learning_rate": 3.134098834942933e-05,
"loss": 3.554,
"step": 1139712
},
{
"epoch": 1.02,
"learning_rate": 3.133260240191881e-05,
"loss": 3.5403,
"step": 1140224
},
{
"epoch": 1.02,
"learning_rate": 3.132423283321203e-05,
"loss": 3.5391,
"step": 1140736
},
{
"epoch": 1.02,
"learning_rate": 3.13158468857015e-05,
"loss": 3.5458,
"step": 1141248
},
{
"epoch": 1.02,
"learning_rate": 3.130746093819098e-05,
"loss": 3.5466,
"step": 1141760
},
{
"epoch": 1.02,
"learning_rate": 3.129907499068046e-05,
"loss": 3.5426,
"step": 1142272
},
{
"epoch": 1.02,
"learning_rate": 3.1290705421973676e-05,
"loss": 3.5485,
"step": 1142784
},
{
"epoch": 1.02,
"learning_rate": 3.128231947446315e-05,
"loss": 3.5396,
"step": 1143296
},
{
"epoch": 1.02,
"learning_rate": 3.127393352695263e-05,
"loss": 3.559,
"step": 1143808
},
{
"epoch": 1.02,
"learning_rate": 3.126554757944211e-05,
"loss": 3.5438,
"step": 1144320
},
{
"epoch": 1.03,
"eval_loss": 3.8439462184906006,
"eval_runtime": 324.8967,
"eval_samples_per_second": 1174.5,
"eval_steps_per_second": 36.704,
"step": 1144800
},
{
"epoch": 0.0,
"learning_rate": 3.1257178010735325e-05,
"loss": 3.5054,
"step": 1144832
},
{
"epoch": 0.0,
"learning_rate": 3.1248792063224805e-05,
"loss": 3.5343,
"step": 1145344
},
{
"epoch": 0.0,
"learning_rate": 3.1240406115714285e-05,
"loss": 3.5373,
"step": 1145856
},
{
"epoch": 0.0,
"learning_rate": 3.1232020168203765e-05,
"loss": 3.5541,
"step": 1146368
},
{
"epoch": 0.0,
"learning_rate": 3.1223650599496974e-05,
"loss": 3.5475,
"step": 1146880
},
{
"epoch": 0.0,
"learning_rate": 3.1215264651986454e-05,
"loss": 3.5474,
"step": 1147392
},
{
"epoch": 0.0,
"learning_rate": 3.1206878704475934e-05,
"loss": 3.5414,
"step": 1147904
},
{
"epoch": 0.0,
"learning_rate": 3.1198492756965414e-05,
"loss": 3.5434,
"step": 1148416
},
{
"epoch": 0.0,
"learning_rate": 3.119012318825862e-05,
"loss": 3.5354,
"step": 1148928
},
{
"epoch": 0.0,
"learning_rate": 3.11817372407481e-05,
"loss": 3.5437,
"step": 1149440
},
{
"epoch": 0.0,
"learning_rate": 3.117335129323758e-05,
"loss": 3.5412,
"step": 1149952
},
{
"epoch": 0.0,
"learning_rate": 3.116496534572706e-05,
"loss": 3.5563,
"step": 1150464
},
{
"epoch": 0.0,
"learning_rate": 3.115659577702027e-05,
"loss": 3.5479,
"step": 1150976
},
{
"epoch": 0.0,
"learning_rate": 3.114820982950976e-05,
"loss": 3.5241,
"step": 1151488
},
{
"epoch": 0.0,
"learning_rate": 3.113982388199924e-05,
"loss": 3.5397,
"step": 1152000
},
{
"epoch": 0.0,
"learning_rate": 3.113143793448872e-05,
"loss": 3.5296,
"step": 1152512
},
{
"epoch": 0.0,
"learning_rate": 3.112306836578193e-05,
"loss": 3.5415,
"step": 1153024
},
{
"epoch": 0.0,
"learning_rate": 3.111468241827141e-05,
"loss": 3.5357,
"step": 1153536
},
{
"epoch": 0.0,
"learning_rate": 3.110629647076089e-05,
"loss": 3.5412,
"step": 1154048
},
{
"epoch": 0.0,
"learning_rate": 3.109791052325037e-05,
"loss": 3.5325,
"step": 1154560
},
{
"epoch": 0.0,
"learning_rate": 3.108952457573985e-05,
"loss": 3.5575,
"step": 1155072
},
{
"epoch": 0.0,
"learning_rate": 3.108115500703306e-05,
"loss": 3.5424,
"step": 1155584
},
{
"epoch": 0.0,
"learning_rate": 3.107276905952254e-05,
"loss": 3.538,
"step": 1156096
},
{
"epoch": 0.0,
"learning_rate": 3.106438311201202e-05,
"loss": 3.5368,
"step": 1156608
},
{
"epoch": 0.0,
"learning_rate": 3.10559971645015e-05,
"loss": 3.5543,
"step": 1157120
},
{
"epoch": 0.0,
"learning_rate": 3.104762759579471e-05,
"loss": 3.5379,
"step": 1157632
},
{
"epoch": 0.0,
"learning_rate": 3.103924164828419e-05,
"loss": 3.5338,
"step": 1158144
},
{
"epoch": 0.0,
"learning_rate": 3.103085570077367e-05,
"loss": 3.5431,
"step": 1158656
},
{
"epoch": 0.0,
"learning_rate": 3.102246975326315e-05,
"loss": 3.534,
"step": 1159168
},
{
"epoch": 0.0,
"learning_rate": 3.101410018455636e-05,
"loss": 3.5329,
"step": 1159680
},
{
"epoch": 0.01,
"learning_rate": 3.100571423704584e-05,
"loss": 3.5386,
"step": 1160192
},
{
"epoch": 0.01,
"learning_rate": 3.099732828953532e-05,
"loss": 3.5377,
"step": 1160704
},
{
"epoch": 0.01,
"learning_rate": 3.09889423420248e-05,
"loss": 3.5406,
"step": 1161216
},
{
"epoch": 0.01,
"learning_rate": 3.098057277331801e-05,
"loss": 3.5444,
"step": 1161728
},
{
"epoch": 0.01,
"learning_rate": 3.097218682580749e-05,
"loss": 3.5451,
"step": 1162240
},
{
"epoch": 0.01,
"learning_rate": 3.096380087829697e-05,
"loss": 3.5396,
"step": 1162752
},
{
"epoch": 0.01,
"learning_rate": 3.095543130959018e-05,
"loss": 3.5426,
"step": 1163264
},
{
"epoch": 0.01,
"learning_rate": 3.0947045362079666e-05,
"loss": 3.5301,
"step": 1163776
},
{
"epoch": 0.01,
"learning_rate": 3.0938659414569146e-05,
"loss": 3.5371,
"step": 1164288
},
{
"epoch": 0.01,
"learning_rate": 3.0930273467058626e-05,
"loss": 3.5329,
"step": 1164800
},
{
"epoch": 0.01,
"learning_rate": 3.0921903898351835e-05,
"loss": 3.5331,
"step": 1165312
},
{
"epoch": 0.01,
"learning_rate": 3.0913517950841315e-05,
"loss": 3.5325,
"step": 1165824
},
{
"epoch": 0.01,
"learning_rate": 3.0905132003330795e-05,
"loss": 3.5424,
"step": 1166336
},
{
"epoch": 0.01,
"learning_rate": 3.0896746055820275e-05,
"loss": 3.5338,
"step": 1166848
},
{
"epoch": 0.01,
"learning_rate": 3.0888376487113484e-05,
"loss": 3.54,
"step": 1167360
},
{
"epoch": 0.01,
"learning_rate": 3.0879990539602964e-05,
"loss": 3.544,
"step": 1167872
},
{
"epoch": 0.01,
"learning_rate": 3.0871604592092444e-05,
"loss": 3.5444,
"step": 1168384
},
{
"epoch": 0.01,
"learning_rate": 3.0863218644581924e-05,
"loss": 3.5383,
"step": 1168896
},
{
"epoch": 0.01,
"learning_rate": 3.085484907587513e-05,
"loss": 3.5214,
"step": 1169408
},
{
"epoch": 0.01,
"learning_rate": 3.084646312836461e-05,
"loss": 3.5366,
"step": 1169920
},
{
"epoch": 0.01,
"learning_rate": 3.08380771808541e-05,
"loss": 3.5415,
"step": 1170432
},
{
"epoch": 0.01,
"learning_rate": 3.082969123334358e-05,
"loss": 3.5411,
"step": 1170944
},
{
"epoch": 0.01,
"learning_rate": 3.082132166463679e-05,
"loss": 3.5298,
"step": 1171456
},
{
"epoch": 0.01,
"learning_rate": 3.081293571712627e-05,
"loss": 3.5319,
"step": 1171968
},
{
"epoch": 0.01,
"learning_rate": 3.080454976961575e-05,
"loss": 3.5241,
"step": 1172480
},
{
"epoch": 0.01,
"learning_rate": 3.079616382210523e-05,
"loss": 3.5237,
"step": 1172992
},
{
"epoch": 0.01,
"learning_rate": 3.078779425339844e-05,
"loss": 3.5395,
"step": 1173504
},
{
"epoch": 0.01,
"learning_rate": 3.077940830588792e-05,
"loss": 3.5245,
"step": 1174016
},
{
"epoch": 0.01,
"learning_rate": 3.07710223583774e-05,
"loss": 3.5438,
"step": 1174528
},
{
"epoch": 0.01,
"learning_rate": 3.076263641086688e-05,
"loss": 3.537,
"step": 1175040
},
{
"epoch": 0.01,
"learning_rate": 3.075425046335636e-05,
"loss": 3.525,
"step": 1175552
},
{
"epoch": 0.01,
"learning_rate": 3.074588089464957e-05,
"loss": 3.5451,
"step": 1176064
},
{
"epoch": 0.01,
"learning_rate": 3.0737494947139054e-05,
"loss": 3.5222,
"step": 1176576
},
{
"epoch": 0.01,
"learning_rate": 3.0729108999628534e-05,
"loss": 3.5286,
"step": 1177088
},
{
"epoch": 0.01,
"learning_rate": 3.0720723052118014e-05,
"loss": 3.5235,
"step": 1177600
},
{
"epoch": 0.01,
"learning_rate": 3.071235348341122e-05,
"loss": 3.539,
"step": 1178112
},
{
"epoch": 0.01,
"learning_rate": 3.07039675359007e-05,
"loss": 3.5203,
"step": 1178624
},
{
"epoch": 0.01,
"learning_rate": 3.069558158839018e-05,
"loss": 3.5354,
"step": 1179136
},
{
"epoch": 0.01,
"learning_rate": 3.068719564087966e-05,
"loss": 3.5122,
"step": 1179648
},
{
"epoch": 0.01,
"learning_rate": 3.067882607217287e-05,
"loss": 3.5257,
"step": 1180160
},
{
"epoch": 0.01,
"learning_rate": 3.067044012466235e-05,
"loss": 3.5396,
"step": 1180672
},
{
"epoch": 0.01,
"learning_rate": 3.066205417715183e-05,
"loss": 3.5356,
"step": 1181184
},
{
"epoch": 0.01,
"learning_rate": 3.065366822964131e-05,
"loss": 3.5375,
"step": 1181696
},
{
"epoch": 0.01,
"learning_rate": 3.064529866093452e-05,
"loss": 3.5373,
"step": 1182208
},
{
"epoch": 0.01,
"learning_rate": 3.063691271342401e-05,
"loss": 3.5491,
"step": 1182720
},
{
"epoch": 0.01,
"learning_rate": 3.062852676591349e-05,
"loss": 3.53,
"step": 1183232
},
{
"epoch": 0.01,
"learning_rate": 3.062014081840297e-05,
"loss": 3.5456,
"step": 1183744
},
{
"epoch": 0.01,
"learning_rate": 3.0611771249696176e-05,
"loss": 3.5236,
"step": 1184256
},
{
"epoch": 0.01,
"learning_rate": 3.0603385302185656e-05,
"loss": 3.5301,
"step": 1184768
},
{
"epoch": 0.01,
"learning_rate": 3.0594999354675136e-05,
"loss": 3.5357,
"step": 1185280
},
{
"epoch": 0.01,
"learning_rate": 3.0586613407164616e-05,
"loss": 3.5422,
"step": 1185792
},
{
"epoch": 0.01,
"learning_rate": 3.0578243838457825e-05,
"loss": 3.5354,
"step": 1186304
},
{
"epoch": 0.01,
"learning_rate": 3.0569857890947305e-05,
"loss": 3.5421,
"step": 1186816
},
{
"epoch": 0.01,
"learning_rate": 3.0561471943436785e-05,
"loss": 3.5253,
"step": 1187328
},
{
"epoch": 0.01,
"learning_rate": 3.0553085995926265e-05,
"loss": 3.5146,
"step": 1187840
},
{
"epoch": 0.01,
"learning_rate": 3.0544716427219474e-05,
"loss": 3.5259,
"step": 1188352
},
{
"epoch": 0.01,
"learning_rate": 3.053633047970896e-05,
"loss": 3.5361,
"step": 1188864
},
{
"epoch": 0.01,
"learning_rate": 3.052794453219844e-05,
"loss": 3.5288,
"step": 1189376
},
{
"epoch": 0.01,
"learning_rate": 3.051955858468792e-05,
"loss": 3.5281,
"step": 1189888
},
{
"epoch": 0.01,
"learning_rate": 3.051118901598113e-05,
"loss": 3.5355,
"step": 1190400
},
{
"epoch": 0.02,
"learning_rate": 3.050280306847061e-05,
"loss": 3.5265,
"step": 1190912
},
{
"epoch": 0.02,
"learning_rate": 3.049441712096009e-05,
"loss": 3.5294,
"step": 1191424
},
{
"epoch": 0.02,
"learning_rate": 3.048603117344957e-05,
"loss": 3.5272,
"step": 1191936
},
{
"epoch": 0.02,
"learning_rate": 3.047766160474278e-05,
"loss": 3.5398,
"step": 1192448
},
{
"epoch": 0.02,
"learning_rate": 3.046927565723226e-05,
"loss": 3.5452,
"step": 1192960
},
{
"epoch": 0.02,
"learning_rate": 3.046088970972174e-05,
"loss": 3.5415,
"step": 1193472
},
{
"epoch": 0.02,
"learning_rate": 3.0452503762211222e-05,
"loss": 3.5231,
"step": 1193984
},
{
"epoch": 0.02,
"learning_rate": 3.044413419350443e-05,
"loss": 3.5344,
"step": 1194496
},
{
"epoch": 0.02,
"learning_rate": 3.043574824599391e-05,
"loss": 3.5292,
"step": 1195008
},
{
"epoch": 0.02,
"learning_rate": 3.042736229848339e-05,
"loss": 3.5387,
"step": 1195520
},
{
"epoch": 0.02,
"learning_rate": 3.041897635097287e-05,
"loss": 3.5371,
"step": 1196032
},
{
"epoch": 0.02,
"learning_rate": 3.0410606782266084e-05,
"loss": 3.5299,
"step": 1196544
},
{
"epoch": 0.02,
"learning_rate": 3.0402220834755564e-05,
"loss": 3.5312,
"step": 1197056
},
{
"epoch": 0.02,
"learning_rate": 3.0393834887245044e-05,
"loss": 3.5358,
"step": 1197568
},
{
"epoch": 0.02,
"learning_rate": 3.0385448939734524e-05,
"loss": 3.5331,
"step": 1198080
},
{
"epoch": 0.02,
"learning_rate": 3.0377079371027733e-05,
"loss": 3.5281,
"step": 1198592
},
{
"epoch": 0.02,
"learning_rate": 3.0368693423517213e-05,
"loss": 3.5305,
"step": 1199104
},
{
"epoch": 0.02,
"learning_rate": 3.0360307476006693e-05,
"loss": 3.5221,
"step": 1199616
},
{
"epoch": 0.02,
"learning_rate": 3.0351921528496176e-05,
"loss": 3.529,
"step": 1200128
},
{
"epoch": 0.02,
"learning_rate": 3.0343551959789385e-05,
"loss": 3.5213,
"step": 1200640
},
{
"epoch": 0.02,
"learning_rate": 3.0335166012278865e-05,
"loss": 3.5269,
"step": 1201152
},
{
"epoch": 0.02,
"learning_rate": 3.0326780064768345e-05,
"loss": 3.5218,
"step": 1201664
},
{
"epoch": 0.02,
"learning_rate": 3.031839411725782e-05,
"loss": 3.5336,
"step": 1202176
},
{
"epoch": 0.02,
"learning_rate": 3.0310024548551037e-05,
"loss": 3.5303,
"step": 1202688
},
{
"epoch": 0.02,
"learning_rate": 3.0301638601040517e-05,
"loss": 3.5277,
"step": 1203200
},
{
"epoch": 0.02,
"learning_rate": 3.0293252653529997e-05,
"loss": 3.5422,
"step": 1203712
},
{
"epoch": 0.02,
"learning_rate": 3.028486670601947e-05,
"loss": 3.5399,
"step": 1204224
},
{
"epoch": 0.02,
"learning_rate": 3.027648075850895e-05,
"loss": 3.5369,
"step": 1204736
},
{
"epoch": 0.02,
"learning_rate": 3.0268111189802166e-05,
"loss": 3.5296,
"step": 1205248
},
{
"epoch": 0.02,
"learning_rate": 3.0259725242291646e-05,
"loss": 3.5314,
"step": 1205760
},
{
"epoch": 0.02,
"learning_rate": 3.0251339294781123e-05,
"loss": 3.5277,
"step": 1206272
},
{
"epoch": 0.02,
"learning_rate": 3.0242953347270603e-05,
"loss": 3.5198,
"step": 1206784
},
{
"epoch": 0.02,
"learning_rate": 3.023458377856382e-05,
"loss": 3.5303,
"step": 1207296
},
{
"epoch": 0.02,
"learning_rate": 3.0226197831053292e-05,
"loss": 3.5252,
"step": 1207808
},
{
"epoch": 0.02,
"learning_rate": 3.0217811883542775e-05,
"loss": 3.5347,
"step": 1208320
},
{
"epoch": 0.02,
"learning_rate": 3.020944231483599e-05,
"loss": 3.5289,
"step": 1208832
},
{
"epoch": 0.02,
"learning_rate": 3.020105636732547e-05,
"loss": 3.5362,
"step": 1209344
},
{
"epoch": 0.02,
"learning_rate": 3.0192670419814944e-05,
"loss": 3.5299,
"step": 1209856
},
{
"epoch": 0.02,
"learning_rate": 3.0184284472304424e-05,
"loss": 3.5257,
"step": 1210368
},
{
"epoch": 0.02,
"learning_rate": 3.0175898524793904e-05,
"loss": 3.5332,
"step": 1210880
},
{
"epoch": 0.02,
"learning_rate": 3.016752895608712e-05,
"loss": 3.5364,
"step": 1211392
},
{
"epoch": 0.02,
"learning_rate": 3.0159143008576596e-05,
"loss": 3.5425,
"step": 1211904
},
{
"epoch": 0.02,
"learning_rate": 3.0150757061066076e-05,
"loss": 3.5307,
"step": 1212416
},
{
"epoch": 0.02,
"learning_rate": 3.0142371113555556e-05,
"loss": 3.5354,
"step": 1212928
},
{
"epoch": 0.02,
"learning_rate": 3.0134001544848765e-05,
"loss": 3.5351,
"step": 1213440
},
{
"epoch": 0.02,
"learning_rate": 3.0125615597338245e-05,
"loss": 3.5349,
"step": 1213952
},
{
"epoch": 0.02,
"learning_rate": 3.011722964982773e-05,
"loss": 3.5307,
"step": 1214464
},
{
"epoch": 0.02,
"learning_rate": 3.010884370231721e-05,
"loss": 3.5303,
"step": 1214976
},
{
"epoch": 0.02,
"learning_rate": 3.0100474133610418e-05,
"loss": 3.5361,
"step": 1215488
},
{
"epoch": 0.02,
"learning_rate": 3.0092088186099898e-05,
"loss": 3.5367,
"step": 1216000
},
{
"epoch": 0.02,
"learning_rate": 3.0083702238589378e-05,
"loss": 3.529,
"step": 1216512
},
{
"epoch": 0.02,
"learning_rate": 3.0075332669882594e-05,
"loss": 3.5242,
"step": 1217024
},
{
"epoch": 0.02,
"learning_rate": 3.006694672237207e-05,
"loss": 3.5305,
"step": 1217536
},
{
"epoch": 0.02,
"learning_rate": 3.005856077486155e-05,
"loss": 3.5314,
"step": 1218048
},
{
"epoch": 0.02,
"learning_rate": 3.005017482735103e-05,
"loss": 3.5269,
"step": 1218560
},
{
"epoch": 0.02,
"learning_rate": 3.004180525864424e-05,
"loss": 3.5374,
"step": 1219072
},
{
"epoch": 0.02,
"learning_rate": 3.003341931113372e-05,
"loss": 3.5249,
"step": 1219584
},
{
"epoch": 0.02,
"learning_rate": 3.00250333636232e-05,
"loss": 3.5415,
"step": 1220096
},
{
"epoch": 0.02,
"learning_rate": 3.0016647416112682e-05,
"loss": 3.5324,
"step": 1220608
},
{
"epoch": 0.03,
"learning_rate": 3.000827784740589e-05,
"loss": 3.5273,
"step": 1221120
},
{
"epoch": 0.03,
"eval_loss": 3.844001054763794,
"eval_runtime": 314.9677,
"eval_samples_per_second": 1211.524,
"eval_steps_per_second": 37.861,
"step": 1221120
},
{
"epoch": 1.0,
"learning_rate": 2.999989189989537e-05,
"loss": 3.5206,
"step": 1221632
},
{
"epoch": 1.0,
"learning_rate": 2.999150595238485e-05,
"loss": 3.5205,
"step": 1222144
},
{
"epoch": 1.0,
"learning_rate": 2.998312000487433e-05,
"loss": 3.5384,
"step": 1222656
},
{
"epoch": 1.0,
"learning_rate": 2.997473405736381e-05,
"loss": 3.5354,
"step": 1223168
},
{
"epoch": 1.0,
"learning_rate": 2.9966364488657024e-05,
"loss": 3.5346,
"step": 1223680
},
{
"epoch": 1.0,
"learning_rate": 2.9957978541146504e-05,
"loss": 3.5275,
"step": 1224192
},
{
"epoch": 1.0,
"learning_rate": 2.9949592593635984e-05,
"loss": 3.5278,
"step": 1224704
},
{
"epoch": 1.0,
"learning_rate": 2.9941206646125464e-05,
"loss": 3.5147,
"step": 1225216
},
{
"epoch": 1.0,
"learning_rate": 2.9932837077418673e-05,
"loss": 3.5346,
"step": 1225728
},
{
"epoch": 1.0,
"learning_rate": 2.9924451129908153e-05,
"loss": 3.5225,
"step": 1226240
},
{
"epoch": 1.0,
"learning_rate": 2.9916065182397636e-05,
"loss": 3.5464,
"step": 1226752
},
{
"epoch": 1.0,
"learning_rate": 2.9907679234887116e-05,
"loss": 3.5341,
"step": 1227264
},
{
"epoch": 1.0,
"learning_rate": 2.9899309666180325e-05,
"loss": 3.5102,
"step": 1227776
},
{
"epoch": 1.0,
"learning_rate": 2.9890923718669805e-05,
"loss": 3.5219,
"step": 1228288
},
{
"epoch": 1.0,
"learning_rate": 2.9882537771159285e-05,
"loss": 3.5217,
"step": 1228800
},
{
"epoch": 1.0,
"learning_rate": 2.9874151823648765e-05,
"loss": 3.5216,
"step": 1229312
},
{
"epoch": 1.0,
"learning_rate": 2.9865782254941978e-05,
"loss": 3.5274,
"step": 1229824
},
{
"epoch": 1.0,
"learning_rate": 2.9857396307431457e-05,
"loss": 3.5276,
"step": 1230336
},
{
"epoch": 1.0,
"learning_rate": 2.9849010359920937e-05,
"loss": 3.5185,
"step": 1230848
},
{
"epoch": 1.0,
"learning_rate": 2.9840624412410417e-05,
"loss": 3.5441,
"step": 1231360
},
{
"epoch": 1.0,
"learning_rate": 2.9832254843703626e-05,
"loss": 3.5245,
"step": 1231872
},
{
"epoch": 1.0,
"learning_rate": 2.9823868896193106e-05,
"loss": 3.5258,
"step": 1232384
},
{
"epoch": 1.0,
"learning_rate": 2.981548294868259e-05,
"loss": 3.5225,
"step": 1232896
},
{
"epoch": 1.0,
"learning_rate": 2.980709700117207e-05,
"loss": 3.5392,
"step": 1233408
},
{
"epoch": 1.0,
"learning_rate": 2.979872743246528e-05,
"loss": 3.5234,
"step": 1233920
},
{
"epoch": 1.0,
"learning_rate": 2.979034148495476e-05,
"loss": 3.5207,
"step": 1234432
},
{
"epoch": 1.0,
"learning_rate": 2.978195553744424e-05,
"loss": 3.5272,
"step": 1234944
},
{
"epoch": 1.0,
"learning_rate": 2.977356958993372e-05,
"loss": 3.5209,
"step": 1235456
},
{
"epoch": 1.0,
"learning_rate": 2.976520002122693e-05,
"loss": 3.5221,
"step": 1235968
},
{
"epoch": 1.01,
"learning_rate": 2.975681407371641e-05,
"loss": 3.5217,
"step": 1236480
},
{
"epoch": 1.01,
"learning_rate": 2.974842812620589e-05,
"loss": 3.5239,
"step": 1236992
},
{
"epoch": 1.01,
"learning_rate": 2.974004217869537e-05,
"loss": 3.5269,
"step": 1237504
},
{
"epoch": 1.01,
"learning_rate": 2.973167260998858e-05,
"loss": 3.5261,
"step": 1238016
},
{
"epoch": 1.01,
"learning_rate": 2.972328666247806e-05,
"loss": 3.5262,
"step": 1238528
},
{
"epoch": 1.01,
"learning_rate": 2.9714900714967543e-05,
"loss": 3.5264,
"step": 1239040
},
{
"epoch": 1.01,
"learning_rate": 2.9706514767457023e-05,
"loss": 3.5296,
"step": 1239552
},
{
"epoch": 1.01,
"learning_rate": 2.9698145198750232e-05,
"loss": 3.5164,
"step": 1240064
},
{
"epoch": 1.01,
"learning_rate": 2.9689759251239712e-05,
"loss": 3.5233,
"step": 1240576
},
{
"epoch": 1.01,
"learning_rate": 2.9681373303729192e-05,
"loss": 3.5146,
"step": 1241088
},
{
"epoch": 1.01,
"learning_rate": 2.9672987356218672e-05,
"loss": 3.5216,
"step": 1241600
},
{
"epoch": 1.01,
"learning_rate": 2.9664617787511885e-05,
"loss": 3.5171,
"step": 1242112
},
{
"epoch": 1.01,
"learning_rate": 2.9656231840001365e-05,
"loss": 3.5285,
"step": 1242624
},
{
"epoch": 1.01,
"learning_rate": 2.9647845892490845e-05,
"loss": 3.5218,
"step": 1243136
},
{
"epoch": 1.01,
"learning_rate": 2.9639459944980325e-05,
"loss": 3.5251,
"step": 1243648
},
{
"epoch": 1.01,
"learning_rate": 2.9631073997469805e-05,
"loss": 3.5269,
"step": 1244160
},
{
"epoch": 1.01,
"learning_rate": 2.9622704428763014e-05,
"loss": 3.5314,
"step": 1244672
},
{
"epoch": 1.01,
"learning_rate": 2.9614318481252497e-05,
"loss": 3.5239,
"step": 1245184
},
{
"epoch": 1.01,
"learning_rate": 2.9605932533741977e-05,
"loss": 3.509,
"step": 1245696
},
{
"epoch": 1.01,
"learning_rate": 2.9597546586231457e-05,
"loss": 3.5175,
"step": 1246208
},
{
"epoch": 1.01,
"learning_rate": 2.9589177017524666e-05,
"loss": 3.536,
"step": 1246720
},
{
"epoch": 1.01,
"learning_rate": 2.9580791070014146e-05,
"loss": 3.5252,
"step": 1247232
},
{
"epoch": 1.01,
"learning_rate": 2.9572405122503626e-05,
"loss": 3.5155,
"step": 1247744
},
{
"epoch": 1.01,
"learning_rate": 2.9564019174993106e-05,
"loss": 3.5136,
"step": 1248256
},
{
"epoch": 1.01,
"learning_rate": 2.955564960628632e-05,
"loss": 3.5173,
"step": 1248768
},
{
"epoch": 1.01,
"learning_rate": 2.95472636587758e-05,
"loss": 3.5067,
"step": 1249280
},
{
"epoch": 1.01,
"learning_rate": 2.953887771126528e-05,
"loss": 3.5279,
"step": 1249792
},
{
"epoch": 1.01,
"learning_rate": 2.953049176375476e-05,
"loss": 3.5114,
"step": 1250304
},
{
"epoch": 1.01,
"learning_rate": 2.9522122195047967e-05,
"loss": 3.5216,
"step": 1250816
},
{
"epoch": 1.01,
"learning_rate": 2.9513736247537447e-05,
"loss": 3.5246,
"step": 1251328
},
{
"epoch": 1.01,
"learning_rate": 2.950535030002693e-05,
"loss": 3.5091,
"step": 1251840
},
{
"epoch": 1.01,
"learning_rate": 2.949696435251641e-05,
"loss": 3.5294,
"step": 1252352
},
{
"epoch": 1.01,
"learning_rate": 2.948859478380962e-05,
"loss": 3.5092,
"step": 1252864
},
{
"epoch": 1.01,
"learning_rate": 2.94802088362991e-05,
"loss": 3.5168,
"step": 1253376
},
{
"epoch": 1.01,
"learning_rate": 2.947182288878858e-05,
"loss": 3.5047,
"step": 1253888
},
{
"epoch": 1.01,
"learning_rate": 2.946343694127806e-05,
"loss": 3.528,
"step": 1254400
},
{
"epoch": 1.01,
"learning_rate": 2.9455067372571272e-05,
"loss": 3.51,
"step": 1254912
},
{
"epoch": 1.01,
"learning_rate": 2.9446681425060752e-05,
"loss": 3.515,
"step": 1255424
},
{
"epoch": 1.01,
"learning_rate": 2.9438295477550232e-05,
"loss": 3.5047,
"step": 1255936
},
{
"epoch": 1.01,
"learning_rate": 2.9429909530039712e-05,
"loss": 3.5103,
"step": 1256448
},
{
"epoch": 1.01,
"learning_rate": 2.942153996133292e-05,
"loss": 3.5233,
"step": 1256960
},
{
"epoch": 1.01,
"learning_rate": 2.94131540138224e-05,
"loss": 3.5272,
"step": 1257472
},
{
"epoch": 1.01,
"learning_rate": 2.9404768066311884e-05,
"loss": 3.5224,
"step": 1257984
},
{
"epoch": 1.01,
"learning_rate": 2.9396382118801364e-05,
"loss": 3.5227,
"step": 1258496
},
{
"epoch": 1.01,
"learning_rate": 2.9388012550094573e-05,
"loss": 3.5324,
"step": 1259008
},
{
"epoch": 1.01,
"learning_rate": 2.9379626602584053e-05,
"loss": 3.5155,
"step": 1259520
},
{
"epoch": 1.01,
"learning_rate": 2.9371240655073533e-05,
"loss": 3.5339,
"step": 1260032
},
{
"epoch": 1.01,
"learning_rate": 2.9362854707563013e-05,
"loss": 3.5136,
"step": 1260544
},
{
"epoch": 1.01,
"learning_rate": 2.9354485138856226e-05,
"loss": 3.5141,
"step": 1261056
},
{
"epoch": 1.01,
"learning_rate": 2.9346099191345706e-05,
"loss": 3.5216,
"step": 1261568
},
{
"epoch": 1.01,
"learning_rate": 2.9337713243835186e-05,
"loss": 3.5274,
"step": 1262080
},
{
"epoch": 1.01,
"learning_rate": 2.9329327296324666e-05,
"loss": 3.5216,
"step": 1262592
},
{
"epoch": 1.01,
"learning_rate": 2.9320957727617875e-05,
"loss": 3.529,
"step": 1263104
},
{
"epoch": 1.01,
"learning_rate": 2.9312571780107355e-05,
"loss": 3.5147,
"step": 1263616
},
{
"epoch": 1.01,
"learning_rate": 2.9304185832596838e-05,
"loss": 3.4968,
"step": 1264128
},
{
"epoch": 1.01,
"learning_rate": 2.9295799885086318e-05,
"loss": 3.5131,
"step": 1264640
},
{
"epoch": 1.01,
"learning_rate": 2.9287430316379527e-05,
"loss": 3.5203,
"step": 1265152
},
{
"epoch": 1.01,
"learning_rate": 2.9279044368869007e-05,
"loss": 3.5168,
"step": 1265664
},
{
"epoch": 1.01,
"learning_rate": 2.9270658421358487e-05,
"loss": 3.5153,
"step": 1266176
},
{
"epoch": 1.01,
"learning_rate": 2.9262272473847967e-05,
"loss": 3.5235,
"step": 1266688
},
{
"epoch": 1.02,
"learning_rate": 2.925390290514118e-05,
"loss": 3.5106,
"step": 1267200
},
{
"epoch": 1.02,
"learning_rate": 2.924551695763066e-05,
"loss": 3.5164,
"step": 1267712
},
{
"epoch": 1.02,
"learning_rate": 2.923713101012014e-05,
"loss": 3.515,
"step": 1268224
},
{
"epoch": 1.02,
"learning_rate": 2.922874506260962e-05,
"loss": 3.5245,
"step": 1268736
},
{
"epoch": 1.02,
"learning_rate": 2.922037549390283e-05,
"loss": 3.5278,
"step": 1269248
},
{
"epoch": 1.02,
"learning_rate": 2.921198954639231e-05,
"loss": 3.5328,
"step": 1269760
},
{
"epoch": 1.02,
"learning_rate": 2.9203603598881792e-05,
"loss": 3.5053,
"step": 1270272
},
{
"epoch": 1.02,
"learning_rate": 2.9195217651371265e-05,
"loss": 3.5186,
"step": 1270784
},
{
"epoch": 1.02,
"learning_rate": 2.918684808266448e-05,
"loss": 3.5166,
"step": 1271296
},
{
"epoch": 1.02,
"learning_rate": 2.917846213515396e-05,
"loss": 3.5224,
"step": 1271808
},
{
"epoch": 1.02,
"learning_rate": 2.917007618764344e-05,
"loss": 3.5253,
"step": 1272320
},
{
"epoch": 1.02,
"learning_rate": 2.9161690240132917e-05,
"loss": 3.5147,
"step": 1272832
},
{
"epoch": 1.02,
"learning_rate": 2.9153320671426133e-05,
"loss": 3.5162,
"step": 1273344
},
{
"epoch": 1.02,
"learning_rate": 2.9144934723915613e-05,
"loss": 3.5237,
"step": 1273856
},
{
"epoch": 1.02,
"learning_rate": 2.9136548776405086e-05,
"loss": 3.5202,
"step": 1274368
},
{
"epoch": 1.02,
"learning_rate": 2.9128162828894566e-05,
"loss": 3.5143,
"step": 1274880
},
{
"epoch": 1.02,
"learning_rate": 2.9119776881384046e-05,
"loss": 3.5187,
"step": 1275392
},
{
"epoch": 1.02,
"learning_rate": 2.9111407312677262e-05,
"loss": 3.5137,
"step": 1275904
},
{
"epoch": 1.02,
"learning_rate": 2.910302136516674e-05,
"loss": 3.513,
"step": 1276416
},
{
"epoch": 1.02,
"learning_rate": 2.909463541765622e-05,
"loss": 3.5094,
"step": 1276928
},
{
"epoch": 1.02,
"learning_rate": 2.90862494701457e-05,
"loss": 3.5113,
"step": 1277440
},
{
"epoch": 1.02,
"learning_rate": 2.9077879901438914e-05,
"loss": 3.5086,
"step": 1277952
},
{
"epoch": 1.02,
"learning_rate": 2.906949395392839e-05,
"loss": 3.5204,
"step": 1278464
},
{
"epoch": 1.02,
"learning_rate": 2.906110800641787e-05,
"loss": 3.5138,
"step": 1278976
},
{
"epoch": 1.02,
"learning_rate": 2.905272205890735e-05,
"loss": 3.5157,
"step": 1279488
},
{
"epoch": 1.02,
"learning_rate": 2.904435249020056e-05,
"loss": 3.529,
"step": 1280000
},
{
"epoch": 1.02,
"learning_rate": 2.903596654269004e-05,
"loss": 3.527,
"step": 1280512
},
{
"epoch": 1.02,
"learning_rate": 2.902758059517952e-05,
"loss": 3.5171,
"step": 1281024
},
{
"epoch": 1.02,
"learning_rate": 2.9019194647669e-05,
"loss": 3.5215,
"step": 1281536
},
{
"epoch": 1.02,
"learning_rate": 2.9010825078962212e-05,
"loss": 3.5167,
"step": 1282048
},
{
"epoch": 1.02,
"learning_rate": 2.9002439131451692e-05,
"loss": 3.5143,
"step": 1282560
},
{
"epoch": 1.02,
"learning_rate": 2.8994053183941172e-05,
"loss": 3.5079,
"step": 1283072
},
{
"epoch": 1.02,
"learning_rate": 2.8985667236430652e-05,
"loss": 3.513,
"step": 1283584
},
{
"epoch": 1.02,
"learning_rate": 2.897729766772386e-05,
"loss": 3.5146,
"step": 1284096
},
{
"epoch": 1.02,
"learning_rate": 2.8968911720213345e-05,
"loss": 3.5226,
"step": 1284608
},
{
"epoch": 1.02,
"learning_rate": 2.8960525772702825e-05,
"loss": 3.5164,
"step": 1285120
},
{
"epoch": 1.02,
"learning_rate": 2.8952139825192305e-05,
"loss": 3.5218,
"step": 1285632
},
{
"epoch": 1.02,
"learning_rate": 2.8943770256485514e-05,
"loss": 3.5152,
"step": 1286144
},
{
"epoch": 1.02,
"learning_rate": 2.8935384308974994e-05,
"loss": 3.5119,
"step": 1286656
},
{
"epoch": 1.02,
"learning_rate": 2.8926998361464474e-05,
"loss": 3.5147,
"step": 1287168
},
{
"epoch": 1.02,
"learning_rate": 2.8918612413953954e-05,
"loss": 3.5277,
"step": 1287680
},
{
"epoch": 1.02,
"learning_rate": 2.8910242845247166e-05,
"loss": 3.5276,
"step": 1288192
},
{
"epoch": 1.02,
"learning_rate": 2.8901856897736646e-05,
"loss": 3.5145,
"step": 1288704
},
{
"epoch": 1.02,
"learning_rate": 2.8893470950226126e-05,
"loss": 3.5192,
"step": 1289216
},
{
"epoch": 1.02,
"learning_rate": 2.8885085002715606e-05,
"loss": 3.5238,
"step": 1289728
},
{
"epoch": 1.02,
"learning_rate": 2.8876715434008815e-05,
"loss": 3.5209,
"step": 1290240
},
{
"epoch": 1.02,
"learning_rate": 2.8868329486498298e-05,
"loss": 3.522,
"step": 1290752
},
{
"epoch": 1.02,
"learning_rate": 2.8859943538987778e-05,
"loss": 3.5138,
"step": 1291264
},
{
"epoch": 1.02,
"learning_rate": 2.8851557591477258e-05,
"loss": 3.5225,
"step": 1291776
},
{
"epoch": 1.02,
"learning_rate": 2.8843188022770467e-05,
"loss": 3.5188,
"step": 1292288
},
{
"epoch": 1.02,
"learning_rate": 2.8834802075259947e-05,
"loss": 3.516,
"step": 1292800
},
{
"epoch": 1.02,
"learning_rate": 2.8826416127749427e-05,
"loss": 3.512,
"step": 1293312
},
{
"epoch": 1.02,
"learning_rate": 2.8818030180238907e-05,
"loss": 3.5149,
"step": 1293824
},
{
"epoch": 1.02,
"learning_rate": 2.880966061153212e-05,
"loss": 3.5185,
"step": 1294336
},
{
"epoch": 1.02,
"learning_rate": 2.88012746640216e-05,
"loss": 3.5133,
"step": 1294848
},
{
"epoch": 1.02,
"learning_rate": 2.879288871651108e-05,
"loss": 3.5257,
"step": 1295360
},
{
"epoch": 1.02,
"learning_rate": 2.878450276900056e-05,
"loss": 3.5151,
"step": 1295872
},
{
"epoch": 1.02,
"learning_rate": 2.877613320029377e-05,
"loss": 3.5221,
"step": 1296384
},
{
"epoch": 1.02,
"learning_rate": 2.8767747252783252e-05,
"loss": 3.5238,
"step": 1296896
},
{
"epoch": 1.02,
"learning_rate": 2.8759361305272732e-05,
"loss": 3.5096,
"step": 1297408
},
{
"epoch": 1.03,
"eval_loss": 3.8457820415496826,
"eval_runtime": 310.9329,
"eval_samples_per_second": 1227.245,
"eval_steps_per_second": 38.352,
"step": 1297440
},
{
"epoch": 0.0,
"learning_rate": 2.8750975357762212e-05,
"loss": 3.5045,
"step": 1297920
},
{
"epoch": 0.0,
"learning_rate": 2.8742589410251692e-05,
"loss": 3.5066,
"step": 1298432
},
{
"epoch": 0.0,
"learning_rate": 2.8734203462741172e-05,
"loss": 3.5276,
"step": 1298944
},
{
"epoch": 0.0,
"learning_rate": 2.872583389403438e-05,
"loss": 3.5148,
"step": 1299456
},
{
"epoch": 0.0,
"learning_rate": 2.871744794652386e-05,
"loss": 3.524,
"step": 1299968
},
{
"epoch": 0.0,
"learning_rate": 2.870906199901334e-05,
"loss": 3.515,
"step": 1300480
},
{
"epoch": 0.0,
"learning_rate": 2.8700676051502824e-05,
"loss": 3.5113,
"step": 1300992
},
{
"epoch": 0.0,
"learning_rate": 2.8692306482796033e-05,
"loss": 3.5042,
"step": 1301504
},
{
"epoch": 0.0,
"learning_rate": 2.8683920535285513e-05,
"loss": 3.5188,
"step": 1302016
},
{
"epoch": 0.0,
"learning_rate": 2.8675534587774993e-05,
"loss": 3.5098,
"step": 1302528
},
{
"epoch": 0.0,
"learning_rate": 2.8667148640264473e-05,
"loss": 3.5321,
"step": 1303040
},
{
"epoch": 0.0,
"learning_rate": 2.8658762692753953e-05,
"loss": 3.5176,
"step": 1303552
},
{
"epoch": 0.0,
"learning_rate": 2.8650393124047166e-05,
"loss": 3.5024,
"step": 1304064
},
{
"epoch": 0.0,
"learning_rate": 2.8642007176536645e-05,
"loss": 3.5071,
"step": 1304576
},
{
"epoch": 0.0,
"learning_rate": 2.8633621229026125e-05,
"loss": 3.5108,
"step": 1305088
},
{
"epoch": 0.0,
"learning_rate": 2.8625251660319335e-05,
"loss": 3.5025,
"step": 1305600
},
{
"epoch": 0.0,
"learning_rate": 2.8616865712808815e-05,
"loss": 3.5139,
"step": 1306112
},
{
"epoch": 0.0,
"learning_rate": 2.8608479765298294e-05,
"loss": 3.5133,
"step": 1306624
},
{
"epoch": 0.0,
"learning_rate": 2.8600093817787778e-05,
"loss": 3.5036,
"step": 1307136
},
{
"epoch": 0.0,
"learning_rate": 2.8591724249080987e-05,
"loss": 3.5308,
"step": 1307648
},
{
"epoch": 0.0,
"learning_rate": 2.8583338301570467e-05,
"loss": 3.5121,
"step": 1308160
},
{
"epoch": 0.0,
"learning_rate": 2.8574952354059947e-05,
"loss": 3.5119,
"step": 1308672
},
{
"epoch": 0.0,
"learning_rate": 2.8566566406549427e-05,
"loss": 3.5099,
"step": 1309184
},
{
"epoch": 0.0,
"learning_rate": 2.855819683784264e-05,
"loss": 3.5281,
"step": 1309696
},
{
"epoch": 0.0,
"learning_rate": 2.854981089033212e-05,
"loss": 3.5043,
"step": 1310208
},
{
"epoch": 0.0,
"learning_rate": 2.85414249428216e-05,
"loss": 3.512,
"step": 1310720
},
{
"epoch": 0.0,
"learning_rate": 2.853303899531108e-05,
"loss": 3.5096,
"step": 1311232
},
{
"epoch": 0.0,
"learning_rate": 2.8524669426604288e-05,
"loss": 3.5106,
"step": 1311744
},
{
"epoch": 0.0,
"learning_rate": 2.8516283479093768e-05,
"loss": 3.5052,
"step": 1312256
},
{
"epoch": 0.01,
"learning_rate": 2.8507897531583248e-05,
"loss": 3.5104,
"step": 1312768
},
{
"epoch": 0.01,
"learning_rate": 2.849951158407273e-05,
"loss": 3.5129,
"step": 1313280
},
{
"epoch": 0.01,
"learning_rate": 2.849114201536594e-05,
"loss": 3.5126,
"step": 1313792
},
{
"epoch": 0.01,
"learning_rate": 2.848275606785542e-05,
"loss": 3.5133,
"step": 1314304
},
{
"epoch": 0.01,
"learning_rate": 2.84743701203449e-05,
"loss": 3.5176,
"step": 1314816
},
{
"epoch": 0.01,
"learning_rate": 2.846598417283438e-05,
"loss": 3.5114,
"step": 1315328
},
{
"epoch": 0.01,
"learning_rate": 2.8457614604127593e-05,
"loss": 3.5144,
"step": 1315840
},
{
"epoch": 0.01,
"learning_rate": 2.8449228656617073e-05,
"loss": 3.5041,
"step": 1316352
},
{
"epoch": 0.01,
"learning_rate": 2.8440842709106553e-05,
"loss": 3.5102,
"step": 1316864
},
{
"epoch": 0.01,
"learning_rate": 2.8432456761596033e-05,
"loss": 3.5019,
"step": 1317376
},
{
"epoch": 0.01,
"learning_rate": 2.8424087192889242e-05,
"loss": 3.5093,
"step": 1317888
},
{
"epoch": 0.01,
"learning_rate": 2.8415701245378722e-05,
"loss": 3.5039,
"step": 1318400
},
{
"epoch": 0.01,
"learning_rate": 2.8407315297868202e-05,
"loss": 3.5177,
"step": 1318912
},
{
"epoch": 0.01,
"learning_rate": 2.8398929350357685e-05,
"loss": 3.5013,
"step": 1319424
},
{
"epoch": 0.01,
"learning_rate": 2.8390559781650894e-05,
"loss": 3.5158,
"step": 1319936
},
{
"epoch": 0.01,
"learning_rate": 2.8382173834140374e-05,
"loss": 3.5132,
"step": 1320448
},
{
"epoch": 0.01,
"learning_rate": 2.8373787886629854e-05,
"loss": 3.5166,
"step": 1320960
},
{
"epoch": 0.01,
"learning_rate": 2.8365401939119334e-05,
"loss": 3.5108,
"step": 1321472
},
{
"epoch": 0.01,
"learning_rate": 2.8357032370412547e-05,
"loss": 3.4981,
"step": 1321984
},
{
"epoch": 0.01,
"learning_rate": 2.8348646422902027e-05,
"loss": 3.5065,
"step": 1322496
},
{
"epoch": 0.01,
"learning_rate": 2.8340260475391506e-05,
"loss": 3.5171,
"step": 1323008
},
{
"epoch": 0.01,
"learning_rate": 2.8331874527880986e-05,
"loss": 3.5106,
"step": 1323520
},
{
"epoch": 0.01,
"learning_rate": 2.8323504959174196e-05,
"loss": 3.5028,
"step": 1324032
},
{
"epoch": 0.01,
"learning_rate": 2.8315119011663676e-05,
"loss": 3.4989,
"step": 1324544
},
{
"epoch": 0.01,
"learning_rate": 2.8306733064153155e-05,
"loss": 3.5074,
"step": 1325056
},
{
"epoch": 0.01,
"learning_rate": 2.829834711664264e-05,
"loss": 3.4903,
"step": 1325568
},
{
"epoch": 0.01,
"learning_rate": 2.8289977547935848e-05,
"loss": 3.5184,
"step": 1326080
},
{
"epoch": 0.01,
"learning_rate": 2.8281591600425328e-05,
"loss": 3.4954,
"step": 1326592
},
{
"epoch": 0.01,
"learning_rate": 2.8273205652914808e-05,
"loss": 3.511,
"step": 1327104
},
{
"epoch": 0.01,
"learning_rate": 2.8264819705404288e-05,
"loss": 3.5095,
"step": 1327616
},
{
"epoch": 0.01,
"learning_rate": 2.82564501366975e-05,
"loss": 3.4974,
"step": 1328128
},
{
"epoch": 0.01,
"learning_rate": 2.824806418918698e-05,
"loss": 3.5126,
"step": 1328640
},
{
"epoch": 0.01,
"learning_rate": 2.823967824167646e-05,
"loss": 3.5,
"step": 1329152
},
{
"epoch": 0.01,
"learning_rate": 2.823129229416594e-05,
"loss": 3.5025,
"step": 1329664
},
{
"epoch": 0.01,
"learning_rate": 2.822292272545915e-05,
"loss": 3.4931,
"step": 1330176
},
{
"epoch": 0.01,
"learning_rate": 2.821453677794863e-05,
"loss": 3.5187,
"step": 1330688
},
{
"epoch": 0.01,
"learning_rate": 2.820615083043811e-05,
"loss": 3.4964,
"step": 1331200
},
{
"epoch": 0.01,
"learning_rate": 2.8197764882927586e-05,
"loss": 3.5041,
"step": 1331712
},
{
"epoch": 0.01,
"learning_rate": 2.8189378935417066e-05,
"loss": 3.4879,
"step": 1332224
},
{
"epoch": 0.01,
"learning_rate": 2.818100936671028e-05,
"loss": 3.5009,
"step": 1332736
},
{
"epoch": 0.01,
"learning_rate": 2.817262341919976e-05,
"loss": 3.5075,
"step": 1333248
},
{
"epoch": 0.01,
"learning_rate": 2.8164237471689238e-05,
"loss": 3.5129,
"step": 1333760
},
{
"epoch": 0.01,
"learning_rate": 2.8155851524178718e-05,
"loss": 3.5081,
"step": 1334272
},
{
"epoch": 0.01,
"learning_rate": 2.8147481955471934e-05,
"loss": 3.5103,
"step": 1334784
},
{
"epoch": 0.01,
"learning_rate": 2.8139096007961414e-05,
"loss": 3.5183,
"step": 1335296
},
{
"epoch": 0.01,
"learning_rate": 2.8130710060450887e-05,
"loss": 3.5048,
"step": 1335808
},
{
"epoch": 0.01,
"learning_rate": 2.8122324112940367e-05,
"loss": 3.5171,
"step": 1336320
},
{
"epoch": 0.01,
"learning_rate": 2.8113954544233583e-05,
"loss": 3.5027,
"step": 1336832
},
{
"epoch": 0.01,
"learning_rate": 2.810556859672306e-05,
"loss": 3.5027,
"step": 1337344
},
{
"epoch": 0.01,
"learning_rate": 2.809718264921254e-05,
"loss": 3.5047,
"step": 1337856
},
{
"epoch": 0.01,
"learning_rate": 2.8088813080505755e-05,
"loss": 3.5113,
"step": 1338368
},
{
"epoch": 0.01,
"learning_rate": 2.8080427132995235e-05,
"loss": 3.5089,
"step": 1338880
},
{
"epoch": 0.01,
"learning_rate": 2.807204118548471e-05,
"loss": 3.5149,
"step": 1339392
},
{
"epoch": 0.01,
"learning_rate": 2.8063655237974192e-05,
"loss": 3.5049,
"step": 1339904
},
{
"epoch": 0.01,
"learning_rate": 2.8055285669267408e-05,
"loss": 3.4844,
"step": 1340416
},
{
"epoch": 0.01,
"learning_rate": 2.8046899721756888e-05,
"loss": 3.4991,
"step": 1340928
},
{
"epoch": 0.01,
"learning_rate": 2.803851377424636e-05,
"loss": 3.5063,
"step": 1341440
},
{
"epoch": 0.01,
"learning_rate": 2.803012782673584e-05,
"loss": 3.5048,
"step": 1341952
},
{
"epoch": 0.01,
"learning_rate": 2.8021758258029057e-05,
"loss": 3.501,
"step": 1342464
},
{
"epoch": 0.01,
"learning_rate": 2.8013372310518533e-05,
"loss": 3.5121,
"step": 1342976
},
{
"epoch": 0.02,
"learning_rate": 2.8004986363008013e-05,
"loss": 3.4965,
"step": 1343488
},
{
"epoch": 0.02,
"learning_rate": 2.7996600415497493e-05,
"loss": 3.4982,
"step": 1344000
},
{
"epoch": 0.02,
"learning_rate": 2.7988214467986973e-05,
"loss": 3.5032,
"step": 1344512
},
{
"epoch": 0.02,
"learning_rate": 2.7979844899280182e-05,
"loss": 3.5105,
"step": 1345024
},
{
"epoch": 0.02,
"learning_rate": 2.7971458951769662e-05,
"loss": 3.5139,
"step": 1345536
},
{
"epoch": 0.02,
"learning_rate": 2.7963073004259145e-05,
"loss": 3.5211,
"step": 1346048
},
{
"epoch": 0.02,
"learning_rate": 2.7954687056748625e-05,
"loss": 3.4924,
"step": 1346560
},
{
"epoch": 0.02,
"learning_rate": 2.7946317488041834e-05,
"loss": 3.5051,
"step": 1347072
},
{
"epoch": 0.02,
"learning_rate": 2.7937931540531314e-05,
"loss": 3.5058,
"step": 1347584
},
{
"epoch": 0.02,
"learning_rate": 2.7929545593020794e-05,
"loss": 3.5066,
"step": 1348096
},
{
"epoch": 0.02,
"learning_rate": 2.7921159645510274e-05,
"loss": 3.5126,
"step": 1348608
},
{
"epoch": 0.02,
"learning_rate": 2.7912790076803487e-05,
"loss": 3.5014,
"step": 1349120
},
{
"epoch": 0.02,
"learning_rate": 2.7904404129292967e-05,
"loss": 3.5022,
"step": 1349632
},
{
"epoch": 0.02,
"learning_rate": 2.7896018181782447e-05,
"loss": 3.5115,
"step": 1350144
},
{
"epoch": 0.02,
"learning_rate": 2.7887632234271927e-05,
"loss": 3.5091,
"step": 1350656
},
{
"epoch": 0.02,
"learning_rate": 2.7879262665565136e-05,
"loss": 3.4959,
"step": 1351168
},
{
"epoch": 0.02,
"learning_rate": 2.7870876718054616e-05,
"loss": 3.5075,
"step": 1351680
},
{
"epoch": 0.02,
"learning_rate": 2.78624907705441e-05,
"loss": 3.5011,
"step": 1352192
},
{
"epoch": 0.02,
"learning_rate": 2.785410482303358e-05,
"loss": 3.4986,
"step": 1352704
},
{
"epoch": 0.02,
"learning_rate": 2.7845735254326788e-05,
"loss": 3.4947,
"step": 1353216
},
{
"epoch": 0.02,
"learning_rate": 2.7837349306816268e-05,
"loss": 3.4997,
"step": 1353728
},
{
"epoch": 0.02,
"learning_rate": 2.7828963359305748e-05,
"loss": 3.4944,
"step": 1354240
},
{
"epoch": 0.02,
"learning_rate": 2.7820577411795228e-05,
"loss": 3.5092,
"step": 1354752
},
{
"epoch": 0.02,
"learning_rate": 2.781220784308844e-05,
"loss": 3.4987,
"step": 1355264
},
{
"epoch": 0.02,
"learning_rate": 2.780382189557792e-05,
"loss": 3.505,
"step": 1355776
},
{
"epoch": 0.02,
"learning_rate": 2.77954359480674e-05,
"loss": 3.516,
"step": 1356288
},
{
"epoch": 0.02,
"learning_rate": 2.778705000055688e-05,
"loss": 3.5119,
"step": 1356800
},
{
"epoch": 0.02,
"learning_rate": 2.777868043185009e-05,
"loss": 3.5051,
"step": 1357312
},
{
"epoch": 0.02,
"learning_rate": 2.777029448433957e-05,
"loss": 3.5091,
"step": 1357824
},
{
"epoch": 0.02,
"learning_rate": 2.776190853682905e-05,
"loss": 3.5025,
"step": 1358336
},
{
"epoch": 0.02,
"learning_rate": 2.7753522589318533e-05,
"loss": 3.5012,
"step": 1358848
},
{
"epoch": 0.02,
"learning_rate": 2.7745153020611742e-05,
"loss": 3.4957,
"step": 1359360
},
{
"epoch": 0.02,
"learning_rate": 2.7736767073101222e-05,
"loss": 3.4958,
"step": 1359872
},
{
"epoch": 0.02,
"learning_rate": 2.77283811255907e-05,
"loss": 3.5026,
"step": 1360384
},
{
"epoch": 0.02,
"learning_rate": 2.771999517808018e-05,
"loss": 3.5104,
"step": 1360896
},
{
"epoch": 0.02,
"learning_rate": 2.7711625609373394e-05,
"loss": 3.5058,
"step": 1361408
},
{
"epoch": 0.02,
"learning_rate": 2.7703239661862874e-05,
"loss": 3.5052,
"step": 1361920
},
{
"epoch": 0.02,
"learning_rate": 2.7694853714352354e-05,
"loss": 3.5046,
"step": 1362432
},
{
"epoch": 0.02,
"learning_rate": 2.7686467766841834e-05,
"loss": 3.4979,
"step": 1362944
},
{
"epoch": 0.02,
"learning_rate": 2.7678098198135043e-05,
"loss": 3.5002,
"step": 1363456
},
{
"epoch": 0.02,
"learning_rate": 2.7669712250624523e-05,
"loss": 3.5156,
"step": 1363968
},
{
"epoch": 0.02,
"learning_rate": 2.7661326303114003e-05,
"loss": 3.5145,
"step": 1364480
},
{
"epoch": 0.02,
"learning_rate": 2.7652940355603486e-05,
"loss": 3.5072,
"step": 1364992
},
{
"epoch": 0.02,
"learning_rate": 2.7644570786896695e-05,
"loss": 3.5017,
"step": 1365504
},
{
"epoch": 0.02,
"learning_rate": 2.7636184839386175e-05,
"loss": 3.5082,
"step": 1366016
},
{
"epoch": 0.02,
"learning_rate": 2.7627798891875655e-05,
"loss": 3.5057,
"step": 1366528
},
{
"epoch": 0.02,
"learning_rate": 2.7619412944365135e-05,
"loss": 3.512,
"step": 1367040
},
{
"epoch": 0.02,
"learning_rate": 2.7611043375658348e-05,
"loss": 3.5053,
"step": 1367552
},
{
"epoch": 0.02,
"learning_rate": 2.7602657428147828e-05,
"loss": 3.5054,
"step": 1368064
},
{
"epoch": 0.02,
"learning_rate": 2.7594271480637308e-05,
"loss": 3.504,
"step": 1368576
},
{
"epoch": 0.02,
"learning_rate": 2.7585885533126788e-05,
"loss": 3.5047,
"step": 1369088
},
{
"epoch": 0.02,
"learning_rate": 2.7577515964419997e-05,
"loss": 3.4976,
"step": 1369600
},
{
"epoch": 0.02,
"learning_rate": 2.7569130016909477e-05,
"loss": 3.5048,
"step": 1370112
},
{
"epoch": 0.02,
"learning_rate": 2.7560744069398957e-05,
"loss": 3.5085,
"step": 1370624
},
{
"epoch": 0.02,
"learning_rate": 2.755235812188844e-05,
"loss": 3.4964,
"step": 1371136
},
{
"epoch": 0.02,
"learning_rate": 2.754398855318165e-05,
"loss": 3.5142,
"step": 1371648
},
{
"epoch": 0.02,
"learning_rate": 2.753560260567113e-05,
"loss": 3.5039,
"step": 1372160
},
{
"epoch": 0.02,
"learning_rate": 2.752721665816061e-05,
"loss": 3.504,
"step": 1372672
},
{
"epoch": 0.02,
"learning_rate": 2.751883071065009e-05,
"loss": 3.5081,
"step": 1373184
},
{
"epoch": 0.02,
"learning_rate": 2.75104611419433e-05,
"loss": 3.4966,
"step": 1373696
},
{
"epoch": 0.03,
"eval_loss": 3.846426486968994,
"eval_runtime": 303.3495,
"eval_samples_per_second": 1257.925,
"eval_steps_per_second": 39.311,
"step": 1373760
},
{
"epoch": 1.0,
"learning_rate": 2.750207519443278e-05,
"loss": 3.4975,
"step": 1374208
},
{
"epoch": 1.0,
"learning_rate": 2.749368924692226e-05,
"loss": 3.4945,
"step": 1374720
},
{
"epoch": 1.0,
"learning_rate": 2.748530329941174e-05,
"loss": 3.5153,
"step": 1375232
},
{
"epoch": 1.0,
"learning_rate": 2.747691735190122e-05,
"loss": 3.5025,
"step": 1375744
},
{
"epoch": 1.0,
"learning_rate": 2.746854778319443e-05,
"loss": 3.5153,
"step": 1376256
},
{
"epoch": 1.0,
"learning_rate": 2.746016183568391e-05,
"loss": 3.4986,
"step": 1376768
},
{
"epoch": 1.0,
"learning_rate": 2.7451775888173394e-05,
"loss": 3.5011,
"step": 1377280
},
{
"epoch": 1.0,
"learning_rate": 2.7443406319466603e-05,
"loss": 3.4885,
"step": 1377792
},
{
"epoch": 1.0,
"learning_rate": 2.7435020371956083e-05,
"loss": 3.5041,
"step": 1378304
},
{
"epoch": 1.0,
"learning_rate": 2.7426634424445563e-05,
"loss": 3.4991,
"step": 1378816
},
{
"epoch": 1.0,
"learning_rate": 2.7418248476935043e-05,
"loss": 3.5148,
"step": 1379328
},
{
"epoch": 1.0,
"learning_rate": 2.7409878908228255e-05,
"loss": 3.5042,
"step": 1379840
},
{
"epoch": 1.0,
"learning_rate": 2.7401492960717735e-05,
"loss": 3.4904,
"step": 1380352
},
{
"epoch": 1.0,
"learning_rate": 2.7393107013207215e-05,
"loss": 3.4925,
"step": 1380864
},
{
"epoch": 1.0,
"learning_rate": 2.7384721065696695e-05,
"loss": 3.5006,
"step": 1381376
},
{
"epoch": 1.0,
"learning_rate": 2.7376351496989904e-05,
"loss": 3.4863,
"step": 1381888
},
{
"epoch": 1.0,
"learning_rate": 2.7367965549479384e-05,
"loss": 3.4988,
"step": 1382400
},
{
"epoch": 1.0,
"learning_rate": 2.7359579601968864e-05,
"loss": 3.5012,
"step": 1382912
},
{
"epoch": 1.0,
"learning_rate": 2.7351193654458347e-05,
"loss": 3.4922,
"step": 1383424
},
{
"epoch": 1.0,
"learning_rate": 2.7342824085751556e-05,
"loss": 3.5194,
"step": 1383936
},
{
"epoch": 1.0,
"learning_rate": 2.7334438138241036e-05,
"loss": 3.4968,
"step": 1384448
},
{
"epoch": 1.0,
"learning_rate": 2.7326052190730516e-05,
"loss": 3.5019,
"step": 1384960
},
{
"epoch": 1.0,
"learning_rate": 2.7317666243219996e-05,
"loss": 3.4982,
"step": 1385472
},
{
"epoch": 1.0,
"learning_rate": 2.730929667451321e-05,
"loss": 3.5123,
"step": 1385984
},
{
"epoch": 1.0,
"learning_rate": 2.730091072700269e-05,
"loss": 3.4893,
"step": 1386496
},
{
"epoch": 1.0,
"learning_rate": 2.729252477949217e-05,
"loss": 3.499,
"step": 1387008
},
{
"epoch": 1.0,
"learning_rate": 2.728413883198165e-05,
"loss": 3.4937,
"step": 1387520
},
{
"epoch": 1.0,
"learning_rate": 2.7275769263274858e-05,
"loss": 3.5009,
"step": 1388032
},
{
"epoch": 1.0,
"learning_rate": 2.7267383315764338e-05,
"loss": 3.4953,
"step": 1388544
},
{
"epoch": 1.01,
"learning_rate": 2.7258997368253818e-05,
"loss": 3.4954,
"step": 1389056
},
{
"epoch": 1.01,
"learning_rate": 2.72506114207433e-05,
"loss": 3.5016,
"step": 1389568
},
{
"epoch": 1.01,
"learning_rate": 2.724224185203651e-05,
"loss": 3.5027,
"step": 1390080
},
{
"epoch": 1.01,
"learning_rate": 2.723385590452599e-05,
"loss": 3.4988,
"step": 1390592
},
{
"epoch": 1.01,
"learning_rate": 2.722546995701547e-05,
"loss": 3.5073,
"step": 1391104
},
{
"epoch": 1.01,
"learning_rate": 2.721708400950495e-05,
"loss": 3.4928,
"step": 1391616
},
{
"epoch": 1.01,
"learning_rate": 2.7208714440798162e-05,
"loss": 3.5026,
"step": 1392128
},
{
"epoch": 1.01,
"learning_rate": 2.7200328493287642e-05,
"loss": 3.4933,
"step": 1392640
},
{
"epoch": 1.01,
"learning_rate": 2.7191942545777122e-05,
"loss": 3.4973,
"step": 1393152
},
{
"epoch": 1.01,
"learning_rate": 2.7183556598266602e-05,
"loss": 3.4865,
"step": 1393664
},
{
"epoch": 1.01,
"learning_rate": 2.717518702955981e-05,
"loss": 3.4993,
"step": 1394176
},
{
"epoch": 1.01,
"learning_rate": 2.716680108204929e-05,
"loss": 3.4909,
"step": 1394688
},
{
"epoch": 1.01,
"learning_rate": 2.715841513453877e-05,
"loss": 3.5045,
"step": 1395200
},
{
"epoch": 1.01,
"learning_rate": 2.7150029187028255e-05,
"loss": 3.4905,
"step": 1395712
},
{
"epoch": 1.01,
"learning_rate": 2.7141659618321464e-05,
"loss": 3.499,
"step": 1396224
},
{
"epoch": 1.01,
"learning_rate": 2.7133273670810944e-05,
"loss": 3.5045,
"step": 1396736
},
{
"epoch": 1.01,
"learning_rate": 2.7124887723300424e-05,
"loss": 3.5019,
"step": 1397248
},
{
"epoch": 1.01,
"learning_rate": 2.7116501775789904e-05,
"loss": 3.5003,
"step": 1397760
},
{
"epoch": 1.01,
"learning_rate": 2.7108132207083116e-05,
"loss": 3.4859,
"step": 1398272
},
{
"epoch": 1.01,
"learning_rate": 2.7099746259572596e-05,
"loss": 3.4927,
"step": 1398784
},
{
"epoch": 1.01,
"learning_rate": 2.7091360312062076e-05,
"loss": 3.5058,
"step": 1399296
},
{
"epoch": 1.01,
"learning_rate": 2.7082974364551556e-05,
"loss": 3.4964,
"step": 1399808
},
{
"epoch": 1.01,
"learning_rate": 2.7074604795844765e-05,
"loss": 3.4925,
"step": 1400320
},
{
"epoch": 1.01,
"learning_rate": 2.7066218848334245e-05,
"loss": 3.4856,
"step": 1400832
},
{
"epoch": 1.01,
"learning_rate": 2.7057832900823725e-05,
"loss": 3.4948,
"step": 1401344
},
{
"epoch": 1.01,
"learning_rate": 2.704944695331321e-05,
"loss": 3.4745,
"step": 1401856
},
{
"epoch": 1.01,
"learning_rate": 2.7041077384606417e-05,
"loss": 3.5097,
"step": 1402368
},
{
"epoch": 1.01,
"learning_rate": 2.7032691437095897e-05,
"loss": 3.4814,
"step": 1402880
},
{
"epoch": 1.01,
"learning_rate": 2.7024305489585377e-05,
"loss": 3.4997,
"step": 1403392
},
{
"epoch": 1.01,
"learning_rate": 2.7015919542074854e-05,
"loss": 3.4982,
"step": 1403904
},
{
"epoch": 1.01,
"learning_rate": 2.700754997336807e-05,
"loss": 3.4838,
"step": 1404416
},
{
"epoch": 1.01,
"learning_rate": 2.699916402585755e-05,
"loss": 3.5029,
"step": 1404928
},
{
"epoch": 1.01,
"learning_rate": 2.699077807834703e-05,
"loss": 3.4871,
"step": 1405440
},
{
"epoch": 1.01,
"learning_rate": 2.6982392130836503e-05,
"loss": 3.4879,
"step": 1405952
},
{
"epoch": 1.01,
"learning_rate": 2.697402256212972e-05,
"loss": 3.4763,
"step": 1406464
},
{
"epoch": 1.01,
"learning_rate": 2.69656366146192e-05,
"loss": 3.5043,
"step": 1406976
},
{
"epoch": 1.01,
"learning_rate": 2.695725066710868e-05,
"loss": 3.485,
"step": 1407488
},
{
"epoch": 1.01,
"learning_rate": 2.6948864719598155e-05,
"loss": 3.4905,
"step": 1408000
},
{
"epoch": 1.01,
"learning_rate": 2.694049515089137e-05,
"loss": 3.4767,
"step": 1408512
},
{
"epoch": 1.01,
"learning_rate": 2.693210920338085e-05,
"loss": 3.4866,
"step": 1409024
},
{
"epoch": 1.01,
"learning_rate": 2.6923723255870324e-05,
"loss": 3.4958,
"step": 1409536
},
{
"epoch": 1.01,
"learning_rate": 2.6915337308359808e-05,
"loss": 3.5009,
"step": 1410048
},
{
"epoch": 1.01,
"learning_rate": 2.690696773965302e-05,
"loss": 3.4908,
"step": 1410560
},
{
"epoch": 1.01,
"learning_rate": 2.6898581792142503e-05,
"loss": 3.5021,
"step": 1411072
},
{
"epoch": 1.01,
"learning_rate": 2.6890195844631977e-05,
"loss": 3.5039,
"step": 1411584
},
{
"epoch": 1.01,
"learning_rate": 2.6881809897121457e-05,
"loss": 3.4941,
"step": 1412096
},
{
"epoch": 1.01,
"learning_rate": 2.6873440328414672e-05,
"loss": 3.4989,
"step": 1412608
},
{
"epoch": 1.01,
"learning_rate": 2.6865054380904152e-05,
"loss": 3.4972,
"step": 1413120
},
{
"epoch": 1.01,
"learning_rate": 2.685666843339363e-05,
"loss": 3.4883,
"step": 1413632
},
{
"epoch": 1.01,
"learning_rate": 2.684828248588311e-05,
"loss": 3.4924,
"step": 1414144
},
{
"epoch": 1.01,
"learning_rate": 2.6839912917176325e-05,
"loss": 3.498,
"step": 1414656
},
{
"epoch": 1.01,
"learning_rate": 2.6831526969665798e-05,
"loss": 3.4999,
"step": 1415168
},
{
"epoch": 1.01,
"learning_rate": 2.6823141022155278e-05,
"loss": 3.5043,
"step": 1415680
},
{
"epoch": 1.01,
"learning_rate": 2.6814755074644758e-05,
"loss": 3.4902,
"step": 1416192
},
{
"epoch": 1.01,
"learning_rate": 2.6806385505937974e-05,
"loss": 3.4718,
"step": 1416704
},
{
"epoch": 1.01,
"learning_rate": 2.679799955842745e-05,
"loss": 3.4829,
"step": 1417216
},
{
"epoch": 1.01,
"learning_rate": 2.678961361091693e-05,
"loss": 3.4958,
"step": 1417728
},
{
"epoch": 1.01,
"learning_rate": 2.678122766340641e-05,
"loss": 3.4921,
"step": 1418240
},
{
"epoch": 1.01,
"learning_rate": 2.6772858094699626e-05,
"loss": 3.4877,
"step": 1418752
},
{
"epoch": 1.01,
"learning_rate": 2.6764472147189103e-05,
"loss": 3.4975,
"step": 1419264
},
{
"epoch": 1.02,
"learning_rate": 2.6756086199678583e-05,
"loss": 3.4899,
"step": 1419776
},
{
"epoch": 1.02,
"learning_rate": 2.6747700252168063e-05,
"loss": 3.4811,
"step": 1420288
},
{
"epoch": 1.02,
"learning_rate": 2.673933068346127e-05,
"loss": 3.4914,
"step": 1420800
},
{
"epoch": 1.02,
"learning_rate": 2.673094473595075e-05,
"loss": 3.4996,
"step": 1421312
},
{
"epoch": 1.02,
"learning_rate": 2.672255878844023e-05,
"loss": 3.4983,
"step": 1421824
},
{
"epoch": 1.02,
"learning_rate": 2.671417284092971e-05,
"loss": 3.5061,
"step": 1422336
},
{
"epoch": 1.02,
"learning_rate": 2.6705803272222924e-05,
"loss": 3.4872,
"step": 1422848
},
{
"epoch": 1.02,
"learning_rate": 2.6697417324712404e-05,
"loss": 3.4937,
"step": 1423360
},
{
"epoch": 1.02,
"learning_rate": 2.6689031377201884e-05,
"loss": 3.492,
"step": 1423872
},
{
"epoch": 1.02,
"learning_rate": 2.6680645429691364e-05,
"loss": 3.4954,
"step": 1424384
},
{
"epoch": 1.02,
"learning_rate": 2.6672275860984573e-05,
"loss": 3.4989,
"step": 1424896
},
{
"epoch": 1.02,
"learning_rate": 2.6663889913474056e-05,
"loss": 3.4897,
"step": 1425408
},
{
"epoch": 1.02,
"learning_rate": 2.6655503965963536e-05,
"loss": 3.4892,
"step": 1425920
},
{
"epoch": 1.02,
"learning_rate": 2.6647118018453016e-05,
"loss": 3.4964,
"step": 1426432
},
{
"epoch": 1.02,
"learning_rate": 2.6638748449746225e-05,
"loss": 3.4977,
"step": 1426944
},
{
"epoch": 1.02,
"learning_rate": 2.6630362502235705e-05,
"loss": 3.4832,
"step": 1427456
},
{
"epoch": 1.02,
"learning_rate": 2.6621976554725185e-05,
"loss": 3.4918,
"step": 1427968
},
{
"epoch": 1.02,
"learning_rate": 2.6613590607214665e-05,
"loss": 3.4932,
"step": 1428480
},
{
"epoch": 1.02,
"learning_rate": 2.6605221038507878e-05,
"loss": 3.4858,
"step": 1428992
},
{
"epoch": 1.02,
"learning_rate": 2.6596835090997358e-05,
"loss": 3.4806,
"step": 1429504
},
{
"epoch": 1.02,
"learning_rate": 2.6588449143486838e-05,
"loss": 3.4857,
"step": 1430016
},
{
"epoch": 1.02,
"learning_rate": 2.6580063195976318e-05,
"loss": 3.4871,
"step": 1430528
},
{
"epoch": 1.02,
"learning_rate": 2.6571693627269527e-05,
"loss": 3.4922,
"step": 1431040
},
{
"epoch": 1.02,
"learning_rate": 2.656330767975901e-05,
"loss": 3.4856,
"step": 1431552
},
{
"epoch": 1.02,
"learning_rate": 2.655492173224849e-05,
"loss": 3.49,
"step": 1432064
},
{
"epoch": 1.02,
"learning_rate": 2.654653578473797e-05,
"loss": 3.5025,
"step": 1432576
},
{
"epoch": 1.02,
"learning_rate": 2.653816621603118e-05,
"loss": 3.5054,
"step": 1433088
},
{
"epoch": 1.02,
"learning_rate": 2.652978026852066e-05,
"loss": 3.4927,
"step": 1433600
},
{
"epoch": 1.02,
"learning_rate": 2.652139432101014e-05,
"loss": 3.4974,
"step": 1434112
},
{
"epoch": 1.02,
"learning_rate": 2.651300837349962e-05,
"loss": 3.4895,
"step": 1434624
},
{
"epoch": 1.02,
"learning_rate": 2.650463880479283e-05,
"loss": 3.4882,
"step": 1435136
},
{
"epoch": 1.02,
"learning_rate": 2.649625285728231e-05,
"loss": 3.4827,
"step": 1435648
},
{
"epoch": 1.02,
"learning_rate": 2.648786690977179e-05,
"loss": 3.4826,
"step": 1436160
},
{
"epoch": 1.02,
"learning_rate": 2.647948096226127e-05,
"loss": 3.4896,
"step": 1436672
},
{
"epoch": 1.02,
"learning_rate": 2.647111139355448e-05,
"loss": 3.4989,
"step": 1437184
},
{
"epoch": 1.02,
"learning_rate": 2.6462725446043964e-05,
"loss": 3.4913,
"step": 1437696
},
{
"epoch": 1.02,
"learning_rate": 2.6454339498533444e-05,
"loss": 3.4936,
"step": 1438208
},
{
"epoch": 1.02,
"learning_rate": 2.6445953551022924e-05,
"loss": 3.4919,
"step": 1438720
},
{
"epoch": 1.02,
"learning_rate": 2.6437583982316133e-05,
"loss": 3.485,
"step": 1439232
},
{
"epoch": 1.02,
"learning_rate": 2.6429198034805613e-05,
"loss": 3.4877,
"step": 1439744
},
{
"epoch": 1.02,
"learning_rate": 2.6420812087295093e-05,
"loss": 3.5025,
"step": 1440256
},
{
"epoch": 1.02,
"learning_rate": 2.6412426139784573e-05,
"loss": 3.5037,
"step": 1440768
},
{
"epoch": 1.02,
"learning_rate": 2.6404056571077785e-05,
"loss": 3.4934,
"step": 1441280
},
{
"epoch": 1.02,
"learning_rate": 2.6395670623567265e-05,
"loss": 3.4891,
"step": 1441792
},
{
"epoch": 1.02,
"learning_rate": 2.6387284676056745e-05,
"loss": 3.4927,
"step": 1442304
},
{
"epoch": 1.02,
"learning_rate": 2.6378898728546225e-05,
"loss": 3.4941,
"step": 1442816
},
{
"epoch": 1.02,
"learning_rate": 2.6370529159839434e-05,
"loss": 3.5041,
"step": 1443328
},
{
"epoch": 1.02,
"learning_rate": 2.6362143212328917e-05,
"loss": 3.4931,
"step": 1443840
},
{
"epoch": 1.02,
"learning_rate": 2.6353757264818397e-05,
"loss": 3.4928,
"step": 1444352
},
{
"epoch": 1.02,
"learning_rate": 2.6345371317307877e-05,
"loss": 3.4895,
"step": 1444864
},
{
"epoch": 1.02,
"learning_rate": 2.6337001748601086e-05,
"loss": 3.4913,
"step": 1445376
},
{
"epoch": 1.02,
"learning_rate": 2.6328615801090566e-05,
"loss": 3.4887,
"step": 1445888
},
{
"epoch": 1.02,
"learning_rate": 2.6320229853580046e-05,
"loss": 3.4896,
"step": 1446400
},
{
"epoch": 1.02,
"learning_rate": 2.6311843906069526e-05,
"loss": 3.4961,
"step": 1446912
},
{
"epoch": 1.02,
"learning_rate": 2.630347433736274e-05,
"loss": 3.4852,
"step": 1447424
},
{
"epoch": 1.02,
"learning_rate": 2.629508838985222e-05,
"loss": 3.5,
"step": 1447936
},
{
"epoch": 1.02,
"learning_rate": 2.62867024423417e-05,
"loss": 3.4961,
"step": 1448448
},
{
"epoch": 1.02,
"learning_rate": 2.627831649483118e-05,
"loss": 3.4925,
"step": 1448960
},
{
"epoch": 1.02,
"learning_rate": 2.626993054732066e-05,
"loss": 3.4956,
"step": 1449472
},
{
"epoch": 1.02,
"learning_rate": 2.626156097861387e-05,
"loss": 3.4822,
"step": 1449984
},
{
"epoch": 1.03,
"eval_loss": 3.8478291034698486,
"eval_runtime": 303.5766,
"eval_samples_per_second": 1256.984,
"eval_steps_per_second": 39.282,
"step": 1450080
},
{
"epoch": 0.0,
"learning_rate": 2.625317503110335e-05,
"loss": 3.4819,
"step": 1450496
},
{
"epoch": 0.0,
"learning_rate": 2.624478908359283e-05,
"loss": 3.4806,
"step": 1451008
},
{
"epoch": 0.0,
"learning_rate": 2.623640313608231e-05,
"loss": 3.501,
"step": 1451520
},
{
"epoch": 0.0,
"learning_rate": 2.622801718857179e-05,
"loss": 3.4883,
"step": 1452032
},
{
"epoch": 0.0,
"learning_rate": 2.6219647619865e-05,
"loss": 3.5057,
"step": 1452544
},
{
"epoch": 0.0,
"learning_rate": 2.621126167235448e-05,
"loss": 3.485,
"step": 1453056
},
{
"epoch": 0.0,
"learning_rate": 2.6202875724843963e-05,
"loss": 3.4914,
"step": 1453568
},
{
"epoch": 0.0,
"learning_rate": 2.6194489777333443e-05,
"loss": 3.4756,
"step": 1454080
},
{
"epoch": 0.0,
"learning_rate": 2.6186120208626652e-05,
"loss": 3.4929,
"step": 1454592
},
{
"epoch": 0.0,
"learning_rate": 2.6177734261116132e-05,
"loss": 3.4823,
"step": 1455104
},
{
"epoch": 0.0,
"learning_rate": 2.6169348313605612e-05,
"loss": 3.5017,
"step": 1455616
},
{
"epoch": 0.0,
"learning_rate": 2.6160962366095092e-05,
"loss": 3.4921,
"step": 1456128
},
{
"epoch": 0.0,
"learning_rate": 2.6152592797388305e-05,
"loss": 3.4762,
"step": 1456640
},
{
"epoch": 0.0,
"learning_rate": 2.6144206849877785e-05,
"loss": 3.4806,
"step": 1457152
},
{
"epoch": 0.0,
"learning_rate": 2.6135820902367265e-05,
"loss": 3.4889,
"step": 1457664
},
{
"epoch": 0.0,
"learning_rate": 2.6127434954856744e-05,
"loss": 3.4772,
"step": 1458176
},
{
"epoch": 0.0,
"learning_rate": 2.6119065386149954e-05,
"loss": 3.4867,
"step": 1458688
},
{
"epoch": 0.0,
"learning_rate": 2.6110679438639434e-05,
"loss": 3.4876,
"step": 1459200
},
{
"epoch": 0.0,
"learning_rate": 2.6102293491128917e-05,
"loss": 3.4794,
"step": 1459712
},
{
"epoch": 0.0,
"learning_rate": 2.6093923922422126e-05,
"loss": 3.509,
"step": 1460224
},
{
"epoch": 0.0,
"learning_rate": 2.6085537974911606e-05,
"loss": 3.4866,
"step": 1460736
},
{
"epoch": 0.0,
"learning_rate": 2.6077152027401086e-05,
"loss": 3.4873,
"step": 1461248
},
{
"epoch": 0.0,
"learning_rate": 2.6068766079890566e-05,
"loss": 3.4889,
"step": 1461760
},
{
"epoch": 0.0,
"learning_rate": 2.606039651118378e-05,
"loss": 3.4945,
"step": 1462272
},
{
"epoch": 0.0,
"learning_rate": 2.6052010563673258e-05,
"loss": 3.4799,
"step": 1462784
},
{
"epoch": 0.0,
"learning_rate": 2.6043624616162738e-05,
"loss": 3.4878,
"step": 1463296
},
{
"epoch": 0.0,
"learning_rate": 2.6035238668652218e-05,
"loss": 3.4816,
"step": 1463808
},
{
"epoch": 0.0,
"learning_rate": 2.6026869099945427e-05,
"loss": 3.4875,
"step": 1464320
},
{
"epoch": 0.0,
"learning_rate": 2.6018483152434907e-05,
"loss": 3.4815,
"step": 1464832
},
{
"epoch": 0.01,
"learning_rate": 2.6010097204924387e-05,
"loss": 3.4831,
"step": 1465344
},
{
"epoch": 0.01,
"learning_rate": 2.6001711257413867e-05,
"loss": 3.4855,
"step": 1465856
},
{
"epoch": 0.01,
"learning_rate": 2.599334168870708e-05,
"loss": 3.4913,
"step": 1466368
},
{
"epoch": 0.01,
"learning_rate": 2.598495574119656e-05,
"loss": 3.4902,
"step": 1466880
},
{
"epoch": 0.01,
"learning_rate": 2.597656979368604e-05,
"loss": 3.4933,
"step": 1467392
},
{
"epoch": 0.01,
"learning_rate": 2.596818384617552e-05,
"loss": 3.4824,
"step": 1467904
},
{
"epoch": 0.01,
"learning_rate": 2.595981427746873e-05,
"loss": 3.49,
"step": 1468416
},
{
"epoch": 0.01,
"learning_rate": 2.5951428329958212e-05,
"loss": 3.4775,
"step": 1468928
},
{
"epoch": 0.01,
"learning_rate": 2.5943042382447692e-05,
"loss": 3.4914,
"step": 1469440
},
{
"epoch": 0.01,
"learning_rate": 2.5934656434937172e-05,
"loss": 3.4745,
"step": 1469952
},
{
"epoch": 0.01,
"learning_rate": 2.592628686623038e-05,
"loss": 3.4853,
"step": 1470464
},
{
"epoch": 0.01,
"learning_rate": 2.591790091871986e-05,
"loss": 3.4778,
"step": 1470976
},
{
"epoch": 0.01,
"learning_rate": 2.590951497120934e-05,
"loss": 3.4938,
"step": 1471488
},
{
"epoch": 0.01,
"learning_rate": 2.590112902369882e-05,
"loss": 3.4784,
"step": 1472000
},
{
"epoch": 0.01,
"learning_rate": 2.5892759454992033e-05,
"loss": 3.4831,
"step": 1472512
},
{
"epoch": 0.01,
"learning_rate": 2.5884373507481513e-05,
"loss": 3.4956,
"step": 1473024
},
{
"epoch": 0.01,
"learning_rate": 2.5875987559970993e-05,
"loss": 3.4906,
"step": 1473536
},
{
"epoch": 0.01,
"learning_rate": 2.5867601612460473e-05,
"loss": 3.4919,
"step": 1474048
},
{
"epoch": 0.01,
"learning_rate": 2.5859232043753682e-05,
"loss": 3.4732,
"step": 1474560
},
{
"epoch": 0.01,
"learning_rate": 2.5850846096243166e-05,
"loss": 3.4769,
"step": 1475072
},
{
"epoch": 0.01,
"learning_rate": 2.5842460148732646e-05,
"loss": 3.4906,
"step": 1475584
},
{
"epoch": 0.01,
"learning_rate": 2.583407420122212e-05,
"loss": 3.4855,
"step": 1476096
},
{
"epoch": 0.01,
"learning_rate": 2.5825704632515335e-05,
"loss": 3.4796,
"step": 1476608
},
{
"epoch": 0.01,
"learning_rate": 2.5817318685004815e-05,
"loss": 3.476,
"step": 1477120
},
{
"epoch": 0.01,
"learning_rate": 2.5808932737494295e-05,
"loss": 3.4821,
"step": 1477632
},
{
"epoch": 0.01,
"learning_rate": 2.580054678998377e-05,
"loss": 3.4666,
"step": 1478144
},
{
"epoch": 0.01,
"learning_rate": 2.5792177221276987e-05,
"loss": 3.4877,
"step": 1478656
},
{
"epoch": 0.01,
"learning_rate": 2.5783791273766467e-05,
"loss": 3.4748,
"step": 1479168
},
{
"epoch": 0.01,
"learning_rate": 2.5775405326255947e-05,
"loss": 3.4838,
"step": 1479680
},
{
"epoch": 0.01,
"learning_rate": 2.576701937874542e-05,
"loss": 3.4895,
"step": 1480192
},
{
"epoch": 0.01,
"learning_rate": 2.5758649810038636e-05,
"loss": 3.473,
"step": 1480704
},
{
"epoch": 0.01,
"learning_rate": 2.575026386252812e-05,
"loss": 3.4873,
"step": 1481216
},
{
"epoch": 0.01,
"learning_rate": 2.5741877915017592e-05,
"loss": 3.4774,
"step": 1481728
},
{
"epoch": 0.01,
"learning_rate": 2.5733491967507072e-05,
"loss": 3.473,
"step": 1482240
},
{
"epoch": 0.01,
"learning_rate": 2.5725122398800288e-05,
"loss": 3.4723,
"step": 1482752
},
{
"epoch": 0.01,
"learning_rate": 2.5716736451289768e-05,
"loss": 3.4864,
"step": 1483264
},
{
"epoch": 0.01,
"learning_rate": 2.5708350503779245e-05,
"loss": 3.4749,
"step": 1483776
},
{
"epoch": 0.01,
"learning_rate": 2.5699964556268725e-05,
"loss": 3.4777,
"step": 1484288
},
{
"epoch": 0.01,
"learning_rate": 2.5691578608758205e-05,
"loss": 3.4668,
"step": 1484800
},
{
"epoch": 0.01,
"learning_rate": 2.568320904005142e-05,
"loss": 3.4739,
"step": 1485312
},
{
"epoch": 0.01,
"learning_rate": 2.5674823092540894e-05,
"loss": 3.4822,
"step": 1485824
},
{
"epoch": 0.01,
"learning_rate": 2.5666437145030374e-05,
"loss": 3.4895,
"step": 1486336
},
{
"epoch": 0.01,
"learning_rate": 2.5658051197519857e-05,
"loss": 3.479,
"step": 1486848
},
{
"epoch": 0.01,
"learning_rate": 2.5649681628813066e-05,
"loss": 3.4878,
"step": 1487360
},
{
"epoch": 0.01,
"learning_rate": 2.5641295681302546e-05,
"loss": 3.4891,
"step": 1487872
},
{
"epoch": 0.01,
"learning_rate": 2.5632909733792026e-05,
"loss": 3.4811,
"step": 1488384
},
{
"epoch": 0.01,
"learning_rate": 2.5624523786281506e-05,
"loss": 3.4876,
"step": 1488896
},
{
"epoch": 0.01,
"learning_rate": 2.561615421757472e-05,
"loss": 3.483,
"step": 1489408
},
{
"epoch": 0.01,
"learning_rate": 2.56077682700642e-05,
"loss": 3.4793,
"step": 1489920
},
{
"epoch": 0.01,
"learning_rate": 2.559938232255368e-05,
"loss": 3.4785,
"step": 1490432
},
{
"epoch": 0.01,
"learning_rate": 2.559099637504316e-05,
"loss": 3.486,
"step": 1490944
},
{
"epoch": 0.01,
"learning_rate": 2.5582626806336367e-05,
"loss": 3.4895,
"step": 1491456
},
{
"epoch": 0.01,
"learning_rate": 2.5574240858825847e-05,
"loss": 3.4841,
"step": 1491968
},
{
"epoch": 0.01,
"learning_rate": 2.5565854911315327e-05,
"loss": 3.481,
"step": 1492480
},
{
"epoch": 0.01,
"learning_rate": 2.555746896380481e-05,
"loss": 3.4634,
"step": 1492992
},
{
"epoch": 0.01,
"learning_rate": 2.554909939509802e-05,
"loss": 3.4703,
"step": 1493504
},
{
"epoch": 0.01,
"learning_rate": 2.55407134475875e-05,
"loss": 3.481,
"step": 1494016
},
{
"epoch": 0.01,
"learning_rate": 2.553232750007698e-05,
"loss": 3.4807,
"step": 1494528
},
{
"epoch": 0.01,
"learning_rate": 2.552394155256646e-05,
"loss": 3.476,
"step": 1495040
},
{
"epoch": 0.01,
"learning_rate": 2.5515571983859672e-05,
"loss": 3.4838,
"step": 1495552
},
{
"epoch": 0.02,
"learning_rate": 2.5507186036349152e-05,
"loss": 3.4769,
"step": 1496064
},
{
"epoch": 0.02,
"learning_rate": 2.5498800088838632e-05,
"loss": 3.4718,
"step": 1496576
},
{
"epoch": 0.02,
"learning_rate": 2.5490414141328112e-05,
"loss": 3.4772,
"step": 1497088
},
{
"epoch": 0.02,
"learning_rate": 2.548204457262132e-05,
"loss": 3.4849,
"step": 1497600
},
{
"epoch": 0.02,
"learning_rate": 2.54736586251108e-05,
"loss": 3.4856,
"step": 1498112
},
{
"epoch": 0.02,
"learning_rate": 2.546527267760028e-05,
"loss": 3.4946,
"step": 1498624
},
{
"epoch": 0.02,
"learning_rate": 2.5456886730089764e-05,
"loss": 3.4767,
"step": 1499136
},
{
"epoch": 0.02,
"learning_rate": 2.5448517161382974e-05,
"loss": 3.4766,
"step": 1499648
},
{
"epoch": 0.02,
"learning_rate": 2.5440131213872453e-05,
"loss": 3.4823,
"step": 1500160
},
{
"epoch": 0.02,
"learning_rate": 2.5431745266361933e-05,
"loss": 3.4822,
"step": 1500672
},
{
"epoch": 0.02,
"learning_rate": 2.5423375697655143e-05,
"loss": 3.4878,
"step": 1501184
},
{
"epoch": 0.02,
"learning_rate": 2.5414989750144626e-05,
"loss": 3.4763,
"step": 1501696
},
{
"epoch": 0.02,
"learning_rate": 2.5406603802634106e-05,
"loss": 3.4767,
"step": 1502208
},
{
"epoch": 0.02,
"learning_rate": 2.5398217855123586e-05,
"loss": 3.4821,
"step": 1502720
},
{
"epoch": 0.02,
"learning_rate": 2.5389848286416795e-05,
"loss": 3.4865,
"step": 1503232
},
{
"epoch": 0.02,
"learning_rate": 2.5381462338906275e-05,
"loss": 3.4714,
"step": 1503744
},
{
"epoch": 0.02,
"learning_rate": 2.5373076391395755e-05,
"loss": 3.4819,
"step": 1504256
},
{
"epoch": 0.02,
"learning_rate": 2.5364690443885235e-05,
"loss": 3.48,
"step": 1504768
},
{
"epoch": 0.02,
"learning_rate": 2.5356320875178447e-05,
"loss": 3.4723,
"step": 1505280
},
{
"epoch": 0.02,
"learning_rate": 2.5347934927667927e-05,
"loss": 3.4657,
"step": 1505792
},
{
"epoch": 0.02,
"learning_rate": 2.5339548980157407e-05,
"loss": 3.4786,
"step": 1506304
},
{
"epoch": 0.02,
"learning_rate": 2.5331163032646887e-05,
"loss": 3.4765,
"step": 1506816
},
{
"epoch": 0.02,
"learning_rate": 2.5322793463940096e-05,
"loss": 3.4774,
"step": 1507328
},
{
"epoch": 0.02,
"learning_rate": 2.531440751642958e-05,
"loss": 3.4749,
"step": 1507840
},
{
"epoch": 0.02,
"learning_rate": 2.530602156891906e-05,
"loss": 3.4745,
"step": 1508352
},
{
"epoch": 0.02,
"learning_rate": 2.529763562140854e-05,
"loss": 3.4911,
"step": 1508864
},
{
"epoch": 0.02,
"learning_rate": 2.528926605270175e-05,
"loss": 3.4898,
"step": 1509376
},
{
"epoch": 0.02,
"learning_rate": 2.528088010519123e-05,
"loss": 3.4817,
"step": 1509888
},
{
"epoch": 0.02,
"learning_rate": 2.527249415768071e-05,
"loss": 3.4856,
"step": 1510400
},
{
"epoch": 0.02,
"learning_rate": 2.526410821017019e-05,
"loss": 3.4788,
"step": 1510912
},
{
"epoch": 0.02,
"learning_rate": 2.52557386414634e-05,
"loss": 3.4766,
"step": 1511424
},
{
"epoch": 0.02,
"learning_rate": 2.524735269395288e-05,
"loss": 3.4727,
"step": 1511936
},
{
"epoch": 0.02,
"learning_rate": 2.523896674644236e-05,
"loss": 3.4711,
"step": 1512448
},
{
"epoch": 0.02,
"learning_rate": 2.523058079893184e-05,
"loss": 3.4782,
"step": 1512960
},
{
"epoch": 0.02,
"learning_rate": 2.522221123022505e-05,
"loss": 3.4877,
"step": 1513472
},
{
"epoch": 0.02,
"learning_rate": 2.5213825282714533e-05,
"loss": 3.4762,
"step": 1513984
},
{
"epoch": 0.02,
"learning_rate": 2.5205439335204013e-05,
"loss": 3.4858,
"step": 1514496
},
{
"epoch": 0.02,
"learning_rate": 2.5197053387693493e-05,
"loss": 3.478,
"step": 1515008
},
{
"epoch": 0.02,
"learning_rate": 2.5188683818986702e-05,
"loss": 3.4745,
"step": 1515520
},
{
"epoch": 0.02,
"learning_rate": 2.5180297871476182e-05,
"loss": 3.473,
"step": 1516032
},
{
"epoch": 0.02,
"learning_rate": 2.5171911923965662e-05,
"loss": 3.4903,
"step": 1516544
},
{
"epoch": 0.02,
"learning_rate": 2.5163525976455142e-05,
"loss": 3.4946,
"step": 1517056
},
{
"epoch": 0.02,
"learning_rate": 2.5155156407748355e-05,
"loss": 3.483,
"step": 1517568
},
{
"epoch": 0.02,
"learning_rate": 2.5146770460237835e-05,
"loss": 3.4782,
"step": 1518080
},
{
"epoch": 0.02,
"learning_rate": 2.5138384512727314e-05,
"loss": 3.4836,
"step": 1518592
},
{
"epoch": 0.02,
"learning_rate": 2.5129998565216794e-05,
"loss": 3.4799,
"step": 1519104
},
{
"epoch": 0.02,
"learning_rate": 2.5121628996510004e-05,
"loss": 3.4892,
"step": 1519616
},
{
"epoch": 0.02,
"learning_rate": 2.5113243048999487e-05,
"loss": 3.4774,
"step": 1520128
},
{
"epoch": 0.02,
"learning_rate": 2.5104857101488967e-05,
"loss": 3.4843,
"step": 1520640
},
{
"epoch": 0.02,
"learning_rate": 2.5096471153978447e-05,
"loss": 3.476,
"step": 1521152
},
{
"epoch": 0.02,
"learning_rate": 2.5088101585271656e-05,
"loss": 3.4849,
"step": 1521664
},
{
"epoch": 0.02,
"learning_rate": 2.5079715637761136e-05,
"loss": 3.4753,
"step": 1522176
},
{
"epoch": 0.02,
"learning_rate": 2.5071329690250616e-05,
"loss": 3.4757,
"step": 1522688
},
{
"epoch": 0.02,
"learning_rate": 2.5062943742740096e-05,
"loss": 3.4821,
"step": 1523200
},
{
"epoch": 0.02,
"learning_rate": 2.5054557795229576e-05,
"loss": 3.4753,
"step": 1523712
},
{
"epoch": 0.02,
"learning_rate": 2.5046188226522788e-05,
"loss": 3.4827,
"step": 1524224
},
{
"epoch": 0.02,
"learning_rate": 2.5037802279012268e-05,
"loss": 3.489,
"step": 1524736
},
{
"epoch": 0.02,
"learning_rate": 2.5029416331501748e-05,
"loss": 3.4785,
"step": 1525248
},
{
"epoch": 0.02,
"learning_rate": 2.5021046762794957e-05,
"loss": 3.4828,
"step": 1525760
},
{
"epoch": 0.02,
"learning_rate": 2.5012660815284437e-05,
"loss": 3.4746,
"step": 1526272
},
{
"epoch": 0.03,
"eval_loss": 3.849086046218872,
"eval_runtime": 303.7233,
"eval_samples_per_second": 1256.377,
"eval_steps_per_second": 39.263,
"step": 1526400
},
{
"epoch": 1.0,
"learning_rate": 2.500427486777392e-05,
"loss": 3.4765,
"step": 1526784
},
{
"epoch": 1.0,
"learning_rate": 2.49958889202634e-05,
"loss": 3.4712,
"step": 1527296
},
{
"epoch": 1.0,
"learning_rate": 2.498750297275288e-05,
"loss": 3.4849,
"step": 1527808
},
{
"epoch": 1.0,
"learning_rate": 2.497913340404609e-05,
"loss": 3.4811,
"step": 1528320
},
{
"epoch": 1.0,
"learning_rate": 2.497074745653557e-05,
"loss": 3.4942,
"step": 1528832
},
{
"epoch": 1.0,
"learning_rate": 2.496236150902505e-05,
"loss": 3.472,
"step": 1529344
},
{
"epoch": 1.0,
"learning_rate": 2.495397556151453e-05,
"loss": 3.4825,
"step": 1529856
},
{
"epoch": 1.0,
"learning_rate": 2.4945605992807742e-05,
"loss": 3.4622,
"step": 1530368
},
{
"epoch": 1.0,
"learning_rate": 2.4937220045297222e-05,
"loss": 3.4861,
"step": 1530880
},
{
"epoch": 1.0,
"learning_rate": 2.4928834097786702e-05,
"loss": 3.471,
"step": 1531392
},
{
"epoch": 1.0,
"learning_rate": 2.492044815027618e-05,
"loss": 3.4862,
"step": 1531904
},
{
"epoch": 1.0,
"learning_rate": 2.491207858156939e-05,
"loss": 3.4823,
"step": 1532416
},
{
"epoch": 1.0,
"learning_rate": 2.4903692634058874e-05,
"loss": 3.4616,
"step": 1532928
},
{
"epoch": 1.0,
"learning_rate": 2.4895306686548354e-05,
"loss": 3.4735,
"step": 1533440
},
{
"epoch": 1.0,
"learning_rate": 2.488692073903783e-05,
"loss": 3.4756,
"step": 1533952
},
{
"epoch": 1.0,
"learning_rate": 2.4878551170331043e-05,
"loss": 3.4658,
"step": 1534464
},
{
"epoch": 1.0,
"learning_rate": 2.4870165222820523e-05,
"loss": 3.4746,
"step": 1534976
},
{
"epoch": 1.0,
"learning_rate": 2.4861779275310003e-05,
"loss": 3.4759,
"step": 1535488
},
{
"epoch": 1.0,
"learning_rate": 2.4853393327799483e-05,
"loss": 3.473,
"step": 1536000
},
{
"epoch": 1.0,
"learning_rate": 2.4845023759092696e-05,
"loss": 3.4933,
"step": 1536512
},
{
"epoch": 1.0,
"learning_rate": 2.4836637811582175e-05,
"loss": 3.4719,
"step": 1537024
},
{
"epoch": 1.0,
"learning_rate": 2.4828251864071652e-05,
"loss": 3.4755,
"step": 1537536
},
{
"epoch": 1.0,
"learning_rate": 2.4819865916561132e-05,
"loss": 3.4782,
"step": 1538048
},
{
"epoch": 1.0,
"learning_rate": 2.4811496347854344e-05,
"loss": 3.4805,
"step": 1538560
},
{
"epoch": 1.0,
"learning_rate": 2.4803110400343828e-05,
"loss": 3.47,
"step": 1539072
},
{
"epoch": 1.0,
"learning_rate": 2.4794724452833304e-05,
"loss": 3.4798,
"step": 1539584
},
{
"epoch": 1.0,
"learning_rate": 2.4786338505322784e-05,
"loss": 3.4653,
"step": 1540096
},
{
"epoch": 1.0,
"learning_rate": 2.4777968936615997e-05,
"loss": 3.4744,
"step": 1540608
},
{
"epoch": 1.0,
"learning_rate": 2.4769582989105473e-05,
"loss": 3.4679,
"step": 1541120
},
{
"epoch": 1.0,
"learning_rate": 2.4761197041594957e-05,
"loss": 3.4738,
"step": 1541632
},
{
"epoch": 1.01,
"learning_rate": 2.4752811094084437e-05,
"loss": 3.4728,
"step": 1542144
},
{
"epoch": 1.01,
"learning_rate": 2.474444152537765e-05,
"loss": 3.4785,
"step": 1542656
},
{
"epoch": 1.01,
"learning_rate": 2.4736055577867126e-05,
"loss": 3.4781,
"step": 1543168
},
{
"epoch": 1.01,
"learning_rate": 2.4727669630356606e-05,
"loss": 3.4808,
"step": 1543680
},
{
"epoch": 1.01,
"learning_rate": 2.4719283682846086e-05,
"loss": 3.4674,
"step": 1544192
},
{
"epoch": 1.01,
"learning_rate": 2.4710914114139298e-05,
"loss": 3.4792,
"step": 1544704
},
{
"epoch": 1.01,
"learning_rate": 2.4702528166628778e-05,
"loss": 3.4698,
"step": 1545216
},
{
"epoch": 1.01,
"learning_rate": 2.4694142219118258e-05,
"loss": 3.4715,
"step": 1545728
},
{
"epoch": 1.01,
"learning_rate": 2.4685756271607738e-05,
"loss": 3.4641,
"step": 1546240
},
{
"epoch": 1.01,
"learning_rate": 2.4677386702900947e-05,
"loss": 3.471,
"step": 1546752
},
{
"epoch": 1.01,
"learning_rate": 2.4669000755390427e-05,
"loss": 3.4689,
"step": 1547264
},
{
"epoch": 1.01,
"learning_rate": 2.466061480787991e-05,
"loss": 3.4814,
"step": 1547776
},
{
"epoch": 1.01,
"learning_rate": 2.465222886036939e-05,
"loss": 3.4659,
"step": 1548288
},
{
"epoch": 1.01,
"learning_rate": 2.46438592916626e-05,
"loss": 3.4712,
"step": 1548800
},
{
"epoch": 1.01,
"learning_rate": 2.463547334415208e-05,
"loss": 3.4864,
"step": 1549312
},
{
"epoch": 1.01,
"learning_rate": 2.462708739664156e-05,
"loss": 3.4776,
"step": 1549824
},
{
"epoch": 1.01,
"learning_rate": 2.4618717827934772e-05,
"loss": 3.4766,
"step": 1550336
},
{
"epoch": 1.01,
"learning_rate": 2.4610331880424252e-05,
"loss": 3.467,
"step": 1550848
},
{
"epoch": 1.01,
"learning_rate": 2.4601945932913732e-05,
"loss": 3.4593,
"step": 1551360
},
{
"epoch": 1.01,
"learning_rate": 2.4593559985403212e-05,
"loss": 3.4798,
"step": 1551872
},
{
"epoch": 1.01,
"learning_rate": 2.458519041669642e-05,
"loss": 3.4734,
"step": 1552384
},
{
"epoch": 1.01,
"learning_rate": 2.45768044691859e-05,
"loss": 3.4667,
"step": 1552896
},
{
"epoch": 1.01,
"learning_rate": 2.456841852167538e-05,
"loss": 3.4653,
"step": 1553408
},
{
"epoch": 1.01,
"learning_rate": 2.456003257416486e-05,
"loss": 3.4741,
"step": 1553920
},
{
"epoch": 1.01,
"learning_rate": 2.4551646626654344e-05,
"loss": 3.4557,
"step": 1554432
},
{
"epoch": 1.01,
"learning_rate": 2.4543277057947553e-05,
"loss": 3.4756,
"step": 1554944
},
{
"epoch": 1.01,
"learning_rate": 2.4534891110437033e-05,
"loss": 3.4614,
"step": 1555456
},
{
"epoch": 1.01,
"learning_rate": 2.4526505162926513e-05,
"loss": 3.4748,
"step": 1555968
},
{
"epoch": 1.01,
"learning_rate": 2.4518119215415993e-05,
"loss": 3.4748,
"step": 1556480
},
{
"epoch": 1.01,
"learning_rate": 2.4509749646709205e-05,
"loss": 3.4655,
"step": 1556992
},
{
"epoch": 1.01,
"learning_rate": 2.4501363699198685e-05,
"loss": 3.4709,
"step": 1557504
},
{
"epoch": 1.01,
"learning_rate": 2.4492977751688165e-05,
"loss": 3.4663,
"step": 1558016
},
{
"epoch": 1.01,
"learning_rate": 2.4484591804177645e-05,
"loss": 3.4606,
"step": 1558528
},
{
"epoch": 1.01,
"learning_rate": 2.4476222235470854e-05,
"loss": 3.4655,
"step": 1559040
},
{
"epoch": 1.01,
"learning_rate": 2.4467836287960334e-05,
"loss": 3.4681,
"step": 1559552
},
{
"epoch": 1.01,
"learning_rate": 2.4459450340449814e-05,
"loss": 3.4664,
"step": 1560064
},
{
"epoch": 1.01,
"learning_rate": 2.4451064392939298e-05,
"loss": 3.4672,
"step": 1560576
},
{
"epoch": 1.01,
"learning_rate": 2.4442694824232507e-05,
"loss": 3.4559,
"step": 1561088
},
{
"epoch": 1.01,
"learning_rate": 2.4434308876721987e-05,
"loss": 3.4587,
"step": 1561600
},
{
"epoch": 1.01,
"learning_rate": 2.4425922929211467e-05,
"loss": 3.4695,
"step": 1562112
},
{
"epoch": 1.01,
"learning_rate": 2.4417536981700947e-05,
"loss": 3.48,
"step": 1562624
},
{
"epoch": 1.01,
"learning_rate": 2.440916741299416e-05,
"loss": 3.4667,
"step": 1563136
},
{
"epoch": 1.01,
"learning_rate": 2.440078146548364e-05,
"loss": 3.4795,
"step": 1563648
},
{
"epoch": 1.01,
"learning_rate": 2.439239551797312e-05,
"loss": 3.4776,
"step": 1564160
},
{
"epoch": 1.01,
"learning_rate": 2.43840095704626e-05,
"loss": 3.468,
"step": 1564672
},
{
"epoch": 1.01,
"learning_rate": 2.4375640001755808e-05,
"loss": 3.4711,
"step": 1565184
},
{
"epoch": 1.01,
"learning_rate": 2.4367254054245288e-05,
"loss": 3.4774,
"step": 1565696
},
{
"epoch": 1.01,
"learning_rate": 2.4358868106734768e-05,
"loss": 3.4675,
"step": 1566208
},
{
"epoch": 1.01,
"learning_rate": 2.435049853802798e-05,
"loss": 3.467,
"step": 1566720
},
{
"epoch": 1.01,
"learning_rate": 2.434211259051746e-05,
"loss": 3.4762,
"step": 1567232
},
{
"epoch": 1.01,
"learning_rate": 2.433372664300694e-05,
"loss": 3.4741,
"step": 1567744
},
{
"epoch": 1.01,
"learning_rate": 2.432534069549642e-05,
"loss": 3.4736,
"step": 1568256
},
{
"epoch": 1.01,
"learning_rate": 2.431697112678963e-05,
"loss": 3.469,
"step": 1568768
},
{
"epoch": 1.01,
"learning_rate": 2.4308585179279113e-05,
"loss": 3.454,
"step": 1569280
},
{
"epoch": 1.01,
"learning_rate": 2.4300199231768593e-05,
"loss": 3.456,
"step": 1569792
},
{
"epoch": 1.01,
"learning_rate": 2.4291813284258073e-05,
"loss": 3.4704,
"step": 1570304
},
{
"epoch": 1.01,
"learning_rate": 2.4283443715551282e-05,
"loss": 3.4703,
"step": 1570816
},
{
"epoch": 1.01,
"learning_rate": 2.4275057768040762e-05,
"loss": 3.4649,
"step": 1571328
},
{
"epoch": 1.01,
"learning_rate": 2.4266671820530242e-05,
"loss": 3.4704,
"step": 1571840
},
{
"epoch": 1.02,
"learning_rate": 2.425828587301972e-05,
"loss": 3.4624,
"step": 1572352
},
{
"epoch": 1.02,
"learning_rate": 2.42498999255092e-05,
"loss": 3.4633,
"step": 1572864
},
{
"epoch": 1.02,
"learning_rate": 2.4241530356802414e-05,
"loss": 3.4677,
"step": 1573376
},
{
"epoch": 1.02,
"learning_rate": 2.4233144409291894e-05,
"loss": 3.4691,
"step": 1573888
},
{
"epoch": 1.02,
"learning_rate": 2.422475846178137e-05,
"loss": 3.4759,
"step": 1574400
},
{
"epoch": 1.02,
"learning_rate": 2.421637251427085e-05,
"loss": 3.4791,
"step": 1574912
},
{
"epoch": 1.02,
"learning_rate": 2.4208002945564066e-05,
"loss": 3.4734,
"step": 1575424
},
{
"epoch": 1.02,
"learning_rate": 2.4199616998053546e-05,
"loss": 3.4603,
"step": 1575936
},
{
"epoch": 1.02,
"learning_rate": 2.4191231050543023e-05,
"loss": 3.4746,
"step": 1576448
},
{
"epoch": 1.02,
"learning_rate": 2.4182845103032503e-05,
"loss": 3.4682,
"step": 1576960
},
{
"epoch": 1.02,
"learning_rate": 2.4174475534325715e-05,
"loss": 3.4763,
"step": 1577472
},
{
"epoch": 1.02,
"learning_rate": 2.4166089586815195e-05,
"loss": 3.4664,
"step": 1577984
},
{
"epoch": 1.02,
"learning_rate": 2.4157703639304675e-05,
"loss": 3.4612,
"step": 1578496
},
{
"epoch": 1.02,
"learning_rate": 2.4149317691794155e-05,
"loss": 3.4755,
"step": 1579008
},
{
"epoch": 1.02,
"learning_rate": 2.4140948123087368e-05,
"loss": 3.4705,
"step": 1579520
},
{
"epoch": 1.02,
"learning_rate": 2.4132562175576844e-05,
"loss": 3.4643,
"step": 1580032
},
{
"epoch": 1.02,
"learning_rate": 2.4124176228066324e-05,
"loss": 3.4698,
"step": 1580544
},
{
"epoch": 1.02,
"learning_rate": 2.4115790280555804e-05,
"loss": 3.4682,
"step": 1581056
},
{
"epoch": 1.02,
"learning_rate": 2.410742071184902e-05,
"loss": 3.4521,
"step": 1581568
},
{
"epoch": 1.02,
"learning_rate": 2.4099034764338497e-05,
"loss": 3.4574,
"step": 1582080
},
{
"epoch": 1.02,
"learning_rate": 2.4090648816827977e-05,
"loss": 3.4696,
"step": 1582592
},
{
"epoch": 1.02,
"learning_rate": 2.4082262869317457e-05,
"loss": 3.4623,
"step": 1583104
},
{
"epoch": 1.02,
"learning_rate": 2.407389330061067e-05,
"loss": 3.4631,
"step": 1583616
},
{
"epoch": 1.02,
"learning_rate": 2.406550735310015e-05,
"loss": 3.4631,
"step": 1584128
},
{
"epoch": 1.02,
"learning_rate": 2.405712140558963e-05,
"loss": 3.4608,
"step": 1584640
},
{
"epoch": 1.02,
"learning_rate": 2.404873545807911e-05,
"loss": 3.4806,
"step": 1585152
},
{
"epoch": 1.02,
"learning_rate": 2.4040365889372318e-05,
"loss": 3.4819,
"step": 1585664
},
{
"epoch": 1.02,
"learning_rate": 2.4031979941861798e-05,
"loss": 3.4686,
"step": 1586176
},
{
"epoch": 1.02,
"learning_rate": 2.4023593994351278e-05,
"loss": 3.472,
"step": 1586688
},
{
"epoch": 1.02,
"learning_rate": 2.4015208046840758e-05,
"loss": 3.463,
"step": 1587200
},
{
"epoch": 1.02,
"learning_rate": 2.400683847813397e-05,
"loss": 3.4635,
"step": 1587712
},
{
"epoch": 1.02,
"learning_rate": 2.399845253062345e-05,
"loss": 3.4611,
"step": 1588224
},
{
"epoch": 1.02,
"learning_rate": 2.399006658311293e-05,
"loss": 3.4636,
"step": 1588736
},
{
"epoch": 1.02,
"learning_rate": 2.398168063560241e-05,
"loss": 3.4635,
"step": 1589248
},
{
"epoch": 1.02,
"learning_rate": 2.397331106689562e-05,
"loss": 3.474,
"step": 1589760
},
{
"epoch": 1.02,
"learning_rate": 2.39649251193851e-05,
"loss": 3.4667,
"step": 1590272
},
{
"epoch": 1.02,
"learning_rate": 2.3956539171874583e-05,
"loss": 3.4711,
"step": 1590784
},
{
"epoch": 1.02,
"learning_rate": 2.3948153224364063e-05,
"loss": 3.4682,
"step": 1591296
},
{
"epoch": 1.02,
"learning_rate": 2.3939783655657272e-05,
"loss": 3.4614,
"step": 1591808
},
{
"epoch": 1.02,
"learning_rate": 2.393139770814675e-05,
"loss": 3.4648,
"step": 1592320
},
{
"epoch": 1.02,
"learning_rate": 2.392301176063623e-05,
"loss": 3.4737,
"step": 1592832
},
{
"epoch": 1.02,
"learning_rate": 2.391462581312571e-05,
"loss": 3.4829,
"step": 1593344
},
{
"epoch": 1.02,
"learning_rate": 2.3906256244418924e-05,
"loss": 3.4728,
"step": 1593856
},
{
"epoch": 1.02,
"learning_rate": 2.3897870296908404e-05,
"loss": 3.4652,
"step": 1594368
},
{
"epoch": 1.02,
"learning_rate": 2.3889484349397884e-05,
"loss": 3.4753,
"step": 1594880
},
{
"epoch": 1.02,
"learning_rate": 2.3881098401887364e-05,
"loss": 3.4674,
"step": 1595392
},
{
"epoch": 1.02,
"learning_rate": 2.3872728833180573e-05,
"loss": 3.4766,
"step": 1595904
},
{
"epoch": 1.02,
"learning_rate": 2.3864342885670053e-05,
"loss": 3.4671,
"step": 1596416
},
{
"epoch": 1.02,
"learning_rate": 2.3855956938159536e-05,
"loss": 3.471,
"step": 1596928
},
{
"epoch": 1.02,
"learning_rate": 2.3847570990649016e-05,
"loss": 3.4661,
"step": 1597440
},
{
"epoch": 1.02,
"learning_rate": 2.3839201421942225e-05,
"loss": 3.4758,
"step": 1597952
},
{
"epoch": 1.02,
"learning_rate": 2.3830815474431705e-05,
"loss": 3.4611,
"step": 1598464
},
{
"epoch": 1.02,
"learning_rate": 2.3822429526921185e-05,
"loss": 3.4655,
"step": 1598976
},
{
"epoch": 1.02,
"learning_rate": 2.3814043579410665e-05,
"loss": 3.4694,
"step": 1599488
},
{
"epoch": 1.02,
"learning_rate": 2.3805674010703878e-05,
"loss": 3.466,
"step": 1600000
},
{
"epoch": 1.02,
"learning_rate": 2.3797288063193358e-05,
"loss": 3.4701,
"step": 1600512
},
{
"epoch": 1.02,
"learning_rate": 2.3788902115682838e-05,
"loss": 3.4742,
"step": 1601024
},
{
"epoch": 1.02,
"learning_rate": 2.3780516168172318e-05,
"loss": 3.47,
"step": 1601536
},
{
"epoch": 1.02,
"learning_rate": 2.3772146599465527e-05,
"loss": 3.4659,
"step": 1602048
},
{
"epoch": 1.02,
"learning_rate": 2.3763760651955007e-05,
"loss": 3.4649,
"step": 1602560
},
{
"epoch": 1.03,
"eval_loss": 3.850848436355591,
"eval_runtime": 303.7567,
"eval_samples_per_second": 1256.239,
"eval_steps_per_second": 39.258,
"step": 1602720
},
{
"epoch": 0.0,
"learning_rate": 2.375537470444449e-05,
"loss": 3.4599,
"step": 1603072
},
{
"epoch": 0.0,
"learning_rate": 2.374698875693397e-05,
"loss": 3.4558,
"step": 1603584
},
{
"epoch": 0.0,
"learning_rate": 2.3738602809423447e-05,
"loss": 3.4756,
"step": 1604096
},
{
"epoch": 0.0,
"learning_rate": 2.3730216861912926e-05,
"loss": 3.4708,
"step": 1604608
},
{
"epoch": 0.0,
"learning_rate": 2.372184729320614e-05,
"loss": 3.4792,
"step": 1605120
},
{
"epoch": 0.0,
"learning_rate": 2.371346134569562e-05,
"loss": 3.4651,
"step": 1605632
},
{
"epoch": 0.0,
"learning_rate": 2.37050753981851e-05,
"loss": 3.4663,
"step": 1606144
},
{
"epoch": 0.0,
"learning_rate": 2.369668945067458e-05,
"loss": 3.4547,
"step": 1606656
},
{
"epoch": 0.0,
"learning_rate": 2.368831988196779e-05,
"loss": 3.467,
"step": 1607168
},
{
"epoch": 0.0,
"learning_rate": 2.3679933934457268e-05,
"loss": 3.4631,
"step": 1607680
},
{
"epoch": 0.0,
"learning_rate": 2.3671547986946748e-05,
"loss": 3.4715,
"step": 1608192
},
{
"epoch": 0.0,
"learning_rate": 2.3663162039436228e-05,
"loss": 3.4729,
"step": 1608704
},
{
"epoch": 0.0,
"learning_rate": 2.3654792470729444e-05,
"loss": 3.4487,
"step": 1609216
},
{
"epoch": 0.0,
"learning_rate": 2.364640652321892e-05,
"loss": 3.4624,
"step": 1609728
},
{
"epoch": 0.0,
"learning_rate": 2.36380205757084e-05,
"loss": 3.4665,
"step": 1610240
},
{
"epoch": 0.0,
"learning_rate": 2.362963462819788e-05,
"loss": 3.4565,
"step": 1610752
},
{
"epoch": 0.0,
"learning_rate": 2.3621265059491093e-05,
"loss": 3.4618,
"step": 1611264
},
{
"epoch": 0.0,
"learning_rate": 2.361287911198057e-05,
"loss": 3.4632,
"step": 1611776
},
{
"epoch": 0.0,
"learning_rate": 2.3604493164470053e-05,
"loss": 3.4613,
"step": 1612288
},
{
"epoch": 0.0,
"learning_rate": 2.3596107216959533e-05,
"loss": 3.4777,
"step": 1612800
},
{
"epoch": 0.0,
"learning_rate": 2.358773764825274e-05,
"loss": 3.4625,
"step": 1613312
},
{
"epoch": 0.0,
"learning_rate": 2.357935170074222e-05,
"loss": 3.4671,
"step": 1613824
},
{
"epoch": 0.0,
"learning_rate": 2.35709657532317e-05,
"loss": 3.4656,
"step": 1614336
},
{
"epoch": 0.0,
"learning_rate": 2.356257980572118e-05,
"loss": 3.4697,
"step": 1614848
},
{
"epoch": 0.0,
"learning_rate": 2.3554210237014394e-05,
"loss": 3.4607,
"step": 1615360
},
{
"epoch": 0.0,
"learning_rate": 2.3545824289503874e-05,
"loss": 3.4665,
"step": 1615872
},
{
"epoch": 0.0,
"learning_rate": 2.3537438341993354e-05,
"loss": 3.4595,
"step": 1616384
},
{
"epoch": 0.0,
"learning_rate": 2.3529052394482834e-05,
"loss": 3.4588,
"step": 1616896
},
{
"epoch": 0.0,
"learning_rate": 2.3520682825776043e-05,
"loss": 3.4583,
"step": 1617408
},
{
"epoch": 0.0,
"learning_rate": 2.3512296878265523e-05,
"loss": 3.461,
"step": 1617920
},
{
"epoch": 0.01,
"learning_rate": 2.3503910930755006e-05,
"loss": 3.4608,
"step": 1618432
},
{
"epoch": 0.01,
"learning_rate": 2.3495541362048215e-05,
"loss": 3.4676,
"step": 1618944
},
{
"epoch": 0.01,
"learning_rate": 2.3487155414537695e-05,
"loss": 3.4678,
"step": 1619456
},
{
"epoch": 0.01,
"learning_rate": 2.3478769467027175e-05,
"loss": 3.4697,
"step": 1619968
},
{
"epoch": 0.01,
"learning_rate": 2.3470383519516655e-05,
"loss": 3.4564,
"step": 1620480
},
{
"epoch": 0.01,
"learning_rate": 2.3462013950809868e-05,
"loss": 3.4661,
"step": 1620992
},
{
"epoch": 0.01,
"learning_rate": 2.3453628003299348e-05,
"loss": 3.4612,
"step": 1621504
},
{
"epoch": 0.01,
"learning_rate": 2.3445242055788828e-05,
"loss": 3.4631,
"step": 1622016
},
{
"epoch": 0.01,
"learning_rate": 2.3436856108278308e-05,
"loss": 3.4497,
"step": 1622528
},
{
"epoch": 0.01,
"learning_rate": 2.3428486539571517e-05,
"loss": 3.4565,
"step": 1623040
},
{
"epoch": 0.01,
"learning_rate": 2.3420100592060997e-05,
"loss": 3.4607,
"step": 1623552
},
{
"epoch": 0.01,
"learning_rate": 2.3411714644550477e-05,
"loss": 3.4648,
"step": 1624064
},
{
"epoch": 0.01,
"learning_rate": 2.340332869703996e-05,
"loss": 3.4563,
"step": 1624576
},
{
"epoch": 0.01,
"learning_rate": 2.339495912833317e-05,
"loss": 3.4582,
"step": 1625088
},
{
"epoch": 0.01,
"learning_rate": 2.338657318082265e-05,
"loss": 3.4756,
"step": 1625600
},
{
"epoch": 0.01,
"learning_rate": 2.337818723331213e-05,
"loss": 3.4667,
"step": 1626112
},
{
"epoch": 0.01,
"learning_rate": 2.336980128580161e-05,
"loss": 3.466,
"step": 1626624
},
{
"epoch": 0.01,
"learning_rate": 2.336143171709482e-05,
"loss": 3.4554,
"step": 1627136
},
{
"epoch": 0.01,
"learning_rate": 2.33530457695843e-05,
"loss": 3.445,
"step": 1627648
},
{
"epoch": 0.01,
"learning_rate": 2.334465982207378e-05,
"loss": 3.4667,
"step": 1628160
},
{
"epoch": 0.01,
"learning_rate": 2.333627387456326e-05,
"loss": 3.4631,
"step": 1628672
},
{
"epoch": 0.01,
"learning_rate": 2.332790430585647e-05,
"loss": 3.4557,
"step": 1629184
},
{
"epoch": 0.01,
"learning_rate": 2.331951835834595e-05,
"loss": 3.4565,
"step": 1629696
},
{
"epoch": 0.01,
"learning_rate": 2.331113241083543e-05,
"loss": 3.4651,
"step": 1630208
},
{
"epoch": 0.01,
"learning_rate": 2.3302746463324914e-05,
"loss": 3.4374,
"step": 1630720
},
{
"epoch": 0.01,
"learning_rate": 2.3294376894618123e-05,
"loss": 3.4661,
"step": 1631232
},
{
"epoch": 0.01,
"learning_rate": 2.3285990947107603e-05,
"loss": 3.4515,
"step": 1631744
},
{
"epoch": 0.01,
"learning_rate": 2.3277604999597083e-05,
"loss": 3.4568,
"step": 1632256
},
{
"epoch": 0.01,
"learning_rate": 2.3269219052086563e-05,
"loss": 3.4647,
"step": 1632768
},
{
"epoch": 0.01,
"learning_rate": 2.3260849483379775e-05,
"loss": 3.4561,
"step": 1633280
},
{
"epoch": 0.01,
"learning_rate": 2.3252463535869255e-05,
"loss": 3.4567,
"step": 1633792
},
{
"epoch": 0.01,
"learning_rate": 2.3244077588358735e-05,
"loss": 3.459,
"step": 1634304
},
{
"epoch": 0.01,
"learning_rate": 2.3235691640848215e-05,
"loss": 3.4488,
"step": 1634816
},
{
"epoch": 0.01,
"learning_rate": 2.3227322072141424e-05,
"loss": 3.4495,
"step": 1635328
},
{
"epoch": 0.01,
"learning_rate": 2.3218936124630904e-05,
"loss": 3.4585,
"step": 1635840
},
{
"epoch": 0.01,
"learning_rate": 2.3210550177120384e-05,
"loss": 3.4569,
"step": 1636352
},
{
"epoch": 0.01,
"learning_rate": 2.3202164229609867e-05,
"loss": 3.452,
"step": 1636864
},
{
"epoch": 0.01,
"learning_rate": 2.3193794660903076e-05,
"loss": 3.4479,
"step": 1637376
},
{
"epoch": 0.01,
"learning_rate": 2.3185408713392556e-05,
"loss": 3.4479,
"step": 1637888
},
{
"epoch": 0.01,
"learning_rate": 2.3177022765882036e-05,
"loss": 3.4551,
"step": 1638400
},
{
"epoch": 0.01,
"learning_rate": 2.3168636818371516e-05,
"loss": 3.4657,
"step": 1638912
},
{
"epoch": 0.01,
"learning_rate": 2.316026724966473e-05,
"loss": 3.4559,
"step": 1639424
},
{
"epoch": 0.01,
"learning_rate": 2.315188130215421e-05,
"loss": 3.469,
"step": 1639936
},
{
"epoch": 0.01,
"learning_rate": 2.314349535464369e-05,
"loss": 3.4681,
"step": 1640448
},
{
"epoch": 0.01,
"learning_rate": 2.3135109407133165e-05,
"loss": 3.4609,
"step": 1640960
},
{
"epoch": 0.01,
"learning_rate": 2.3126739838426378e-05,
"loss": 3.4554,
"step": 1641472
},
{
"epoch": 0.01,
"learning_rate": 2.3118353890915858e-05,
"loss": 3.4666,
"step": 1641984
},
{
"epoch": 0.01,
"learning_rate": 2.3109967943405338e-05,
"loss": 3.4576,
"step": 1642496
},
{
"epoch": 0.01,
"learning_rate": 2.3101581995894818e-05,
"loss": 3.4517,
"step": 1643008
},
{
"epoch": 0.01,
"learning_rate": 2.309321242718803e-05,
"loss": 3.4653,
"step": 1643520
},
{
"epoch": 0.01,
"learning_rate": 2.308482647967751e-05,
"loss": 3.4608,
"step": 1644032
},
{
"epoch": 0.01,
"learning_rate": 2.307644053216699e-05,
"loss": 3.4639,
"step": 1644544
},
{
"epoch": 0.01,
"learning_rate": 2.3068054584656466e-05,
"loss": 3.4581,
"step": 1645056
},
{
"epoch": 0.01,
"learning_rate": 2.3059685015949682e-05,
"loss": 3.4433,
"step": 1645568
},
{
"epoch": 0.01,
"learning_rate": 2.3051299068439162e-05,
"loss": 3.4421,
"step": 1646080
},
{
"epoch": 0.01,
"learning_rate": 2.304291312092864e-05,
"loss": 3.4568,
"step": 1646592
},
{
"epoch": 0.01,
"learning_rate": 2.303452717341812e-05,
"loss": 3.4608,
"step": 1647104
},
{
"epoch": 0.01,
"learning_rate": 2.302615760471133e-05,
"loss": 3.455,
"step": 1647616
},
{
"epoch": 0.01,
"learning_rate": 2.301777165720081e-05,
"loss": 3.4578,
"step": 1648128
},
{
"epoch": 0.02,
"learning_rate": 2.300938570969029e-05,
"loss": 3.454,
"step": 1648640
},
{
"epoch": 0.02,
"learning_rate": 2.300099976217977e-05,
"loss": 3.447,
"step": 1649152
},
{
"epoch": 0.02,
"learning_rate": 2.2992630193472984e-05,
"loss": 3.457,
"step": 1649664
},
{
"epoch": 0.02,
"learning_rate": 2.2984244245962464e-05,
"loss": 3.4527,
"step": 1650176
},
{
"epoch": 0.02,
"learning_rate": 2.297585829845194e-05,
"loss": 3.4668,
"step": 1650688
},
{
"epoch": 0.02,
"learning_rate": 2.296747235094142e-05,
"loss": 3.4683,
"step": 1651200
},
{
"epoch": 0.02,
"learning_rate": 2.2959102782234636e-05,
"loss": 3.4636,
"step": 1651712
},
{
"epoch": 0.02,
"learning_rate": 2.2950716834724113e-05,
"loss": 3.4531,
"step": 1652224
},
{
"epoch": 0.02,
"learning_rate": 2.2942330887213593e-05,
"loss": 3.459,
"step": 1652736
},
{
"epoch": 0.02,
"learning_rate": 2.2933944939703072e-05,
"loss": 3.457,
"step": 1653248
},
{
"epoch": 0.02,
"learning_rate": 2.2925575370996285e-05,
"loss": 3.4681,
"step": 1653760
},
{
"epoch": 0.02,
"learning_rate": 2.291718942348576e-05,
"loss": 3.4548,
"step": 1654272
},
{
"epoch": 0.02,
"learning_rate": 2.2908803475975245e-05,
"loss": 3.4528,
"step": 1654784
},
{
"epoch": 0.02,
"learning_rate": 2.2900417528464725e-05,
"loss": 3.4632,
"step": 1655296
},
{
"epoch": 0.02,
"learning_rate": 2.2892047959757937e-05,
"loss": 3.4581,
"step": 1655808
},
{
"epoch": 0.02,
"learning_rate": 2.2883662012247414e-05,
"loss": 3.4541,
"step": 1656320
},
{
"epoch": 0.02,
"learning_rate": 2.2875276064736894e-05,
"loss": 3.4607,
"step": 1656832
},
{
"epoch": 0.02,
"learning_rate": 2.2866890117226374e-05,
"loss": 3.4517,
"step": 1657344
},
{
"epoch": 0.02,
"learning_rate": 2.2858520548519586e-05,
"loss": 3.4501,
"step": 1657856
},
{
"epoch": 0.02,
"learning_rate": 2.2850134601009066e-05,
"loss": 3.4395,
"step": 1658368
},
{
"epoch": 0.02,
"learning_rate": 2.2841748653498546e-05,
"loss": 3.4579,
"step": 1658880
},
{
"epoch": 0.02,
"learning_rate": 2.2833362705988026e-05,
"loss": 3.4549,
"step": 1659392
},
{
"epoch": 0.02,
"learning_rate": 2.2824993137281235e-05,
"loss": 3.4522,
"step": 1659904
},
{
"epoch": 0.02,
"learning_rate": 2.2816607189770715e-05,
"loss": 3.4519,
"step": 1660416
},
{
"epoch": 0.02,
"learning_rate": 2.28082212422602e-05,
"loss": 3.4468,
"step": 1660928
},
{
"epoch": 0.02,
"learning_rate": 2.279983529474968e-05,
"loss": 3.4684,
"step": 1661440
},
{
"epoch": 0.02,
"learning_rate": 2.2791465726042888e-05,
"loss": 3.469,
"step": 1661952
},
{
"epoch": 0.02,
"learning_rate": 2.2783079778532368e-05,
"loss": 3.46,
"step": 1662464
},
{
"epoch": 0.02,
"learning_rate": 2.2774693831021848e-05,
"loss": 3.4597,
"step": 1662976
},
{
"epoch": 0.02,
"learning_rate": 2.276632426231506e-05,
"loss": 3.4529,
"step": 1663488
},
{
"epoch": 0.02,
"learning_rate": 2.275793831480454e-05,
"loss": 3.4527,
"step": 1664000
},
{
"epoch": 0.02,
"learning_rate": 2.274955236729402e-05,
"loss": 3.4498,
"step": 1664512
},
{
"epoch": 0.02,
"learning_rate": 2.27411664197835e-05,
"loss": 3.451,
"step": 1665024
},
{
"epoch": 0.02,
"learning_rate": 2.273279685107671e-05,
"loss": 3.4561,
"step": 1665536
},
{
"epoch": 0.02,
"learning_rate": 2.272441090356619e-05,
"loss": 3.4582,
"step": 1666048
},
{
"epoch": 0.02,
"learning_rate": 2.271602495605567e-05,
"loss": 3.4574,
"step": 1666560
},
{
"epoch": 0.02,
"learning_rate": 2.2707639008545152e-05,
"loss": 3.4557,
"step": 1667072
},
{
"epoch": 0.02,
"learning_rate": 2.269926943983836e-05,
"loss": 3.4586,
"step": 1667584
},
{
"epoch": 0.02,
"learning_rate": 2.269088349232784e-05,
"loss": 3.451,
"step": 1668096
},
{
"epoch": 0.02,
"learning_rate": 2.268249754481732e-05,
"loss": 3.4544,
"step": 1668608
},
{
"epoch": 0.02,
"learning_rate": 2.26741115973068e-05,
"loss": 3.4561,
"step": 1669120
},
{
"epoch": 0.02,
"learning_rate": 2.2665742028600014e-05,
"loss": 3.4685,
"step": 1669632
},
{
"epoch": 0.02,
"learning_rate": 2.2657356081089494e-05,
"loss": 3.4677,
"step": 1670144
},
{
"epoch": 0.02,
"learning_rate": 2.2648970133578974e-05,
"loss": 3.4524,
"step": 1670656
},
{
"epoch": 0.02,
"learning_rate": 2.2640584186068454e-05,
"loss": 3.4643,
"step": 1671168
},
{
"epoch": 0.02,
"learning_rate": 2.2632214617361663e-05,
"loss": 3.4594,
"step": 1671680
},
{
"epoch": 0.02,
"learning_rate": 2.2623828669851143e-05,
"loss": 3.4617,
"step": 1672192
},
{
"epoch": 0.02,
"learning_rate": 2.2615442722340623e-05,
"loss": 3.4573,
"step": 1672704
},
{
"epoch": 0.02,
"learning_rate": 2.2607056774830106e-05,
"loss": 3.4603,
"step": 1673216
},
{
"epoch": 0.02,
"learning_rate": 2.2598687206123315e-05,
"loss": 3.4555,
"step": 1673728
},
{
"epoch": 0.02,
"learning_rate": 2.2590301258612795e-05,
"loss": 3.4621,
"step": 1674240
},
{
"epoch": 0.02,
"learning_rate": 2.2581915311102275e-05,
"loss": 3.448,
"step": 1674752
},
{
"epoch": 0.02,
"learning_rate": 2.2573529363591755e-05,
"loss": 3.4542,
"step": 1675264
},
{
"epoch": 0.02,
"learning_rate": 2.2565159794884967e-05,
"loss": 3.4551,
"step": 1675776
},
{
"epoch": 0.02,
"learning_rate": 2.2556773847374447e-05,
"loss": 3.461,
"step": 1676288
},
{
"epoch": 0.02,
"learning_rate": 2.2548387899863927e-05,
"loss": 3.4591,
"step": 1676800
},
{
"epoch": 0.02,
"learning_rate": 2.2540001952353407e-05,
"loss": 3.4566,
"step": 1677312
},
{
"epoch": 0.02,
"learning_rate": 2.2531632383646616e-05,
"loss": 3.4647,
"step": 1677824
},
{
"epoch": 0.02,
"learning_rate": 2.2523246436136096e-05,
"loss": 3.4508,
"step": 1678336
},
{
"epoch": 0.02,
"learning_rate": 2.2514860488625576e-05,
"loss": 3.4573,
"step": 1678848
},
{
"epoch": 0.03,
"eval_loss": 3.852997303009033,
"eval_runtime": 303.0539,
"eval_samples_per_second": 1259.152,
"eval_steps_per_second": 39.349,
"step": 1679040
},
{
"epoch": 1.0,
"learning_rate": 2.250647454111506e-05,
"loss": 3.4552,
"step": 1679360
},
{
"epoch": 1.0,
"learning_rate": 2.249810497240827e-05,
"loss": 3.4424,
"step": 1679872
},
{
"epoch": 1.0,
"learning_rate": 2.248971902489775e-05,
"loss": 3.4642,
"step": 1680384
},
{
"epoch": 1.0,
"learning_rate": 2.248133307738723e-05,
"loss": 3.458,
"step": 1680896
},
{
"epoch": 1.0,
"learning_rate": 2.247294712987671e-05,
"loss": 3.4697,
"step": 1681408
},
{
"epoch": 1.0,
"learning_rate": 2.246457756116992e-05,
"loss": 3.4548,
"step": 1681920
},
{
"epoch": 1.0,
"learning_rate": 2.24561916136594e-05,
"loss": 3.4509,
"step": 1682432
},
{
"epoch": 1.0,
"learning_rate": 2.244780566614888e-05,
"loss": 3.4471,
"step": 1682944
},
{
"epoch": 1.0,
"learning_rate": 2.243941971863836e-05,
"loss": 3.4537,
"step": 1683456
},
{
"epoch": 1.0,
"learning_rate": 2.243105014993157e-05,
"loss": 3.4517,
"step": 1683968
},
{
"epoch": 1.0,
"learning_rate": 2.242266420242105e-05,
"loss": 3.4589,
"step": 1684480
},
{
"epoch": 1.0,
"learning_rate": 2.241427825491053e-05,
"loss": 3.4638,
"step": 1684992
},
{
"epoch": 1.0,
"learning_rate": 2.240589230740001e-05,
"loss": 3.4395,
"step": 1685504
},
{
"epoch": 1.0,
"learning_rate": 2.2397522738693222e-05,
"loss": 3.4474,
"step": 1686016
},
{
"epoch": 1.0,
"learning_rate": 2.2389136791182702e-05,
"loss": 3.4576,
"step": 1686528
},
{
"epoch": 1.0,
"learning_rate": 2.2380750843672182e-05,
"loss": 3.4441,
"step": 1687040
},
{
"epoch": 1.0,
"learning_rate": 2.237236489616166e-05,
"loss": 3.4489,
"step": 1687552
},
{
"epoch": 1.0,
"learning_rate": 2.2363995327454875e-05,
"loss": 3.4507,
"step": 1688064
},
{
"epoch": 1.0,
"learning_rate": 2.2355609379944355e-05,
"loss": 3.4497,
"step": 1688576
},
{
"epoch": 1.0,
"learning_rate": 2.2347223432433835e-05,
"loss": 3.4658,
"step": 1689088
},
{
"epoch": 1.0,
"learning_rate": 2.233883748492331e-05,
"loss": 3.4538,
"step": 1689600
},
{
"epoch": 1.0,
"learning_rate": 2.2330467916216524e-05,
"loss": 3.4521,
"step": 1690112
},
{
"epoch": 1.0,
"learning_rate": 2.2322081968706004e-05,
"loss": 3.4539,
"step": 1690624
},
{
"epoch": 1.0,
"learning_rate": 2.2313696021195484e-05,
"loss": 3.4554,
"step": 1691136
},
{
"epoch": 1.0,
"learning_rate": 2.2305310073684963e-05,
"loss": 3.4496,
"step": 1691648
},
{
"epoch": 1.0,
"learning_rate": 2.2296940504978176e-05,
"loss": 3.4555,
"step": 1692160
},
{
"epoch": 1.0,
"learning_rate": 2.2288554557467656e-05,
"loss": 3.4471,
"step": 1692672
},
{
"epoch": 1.0,
"learning_rate": 2.2280168609957133e-05,
"loss": 3.4471,
"step": 1693184
},
{
"epoch": 1.0,
"learning_rate": 2.2271782662446612e-05,
"loss": 3.4493,
"step": 1693696
},
{
"epoch": 1.0,
"learning_rate": 2.226341309373983e-05,
"loss": 3.4516,
"step": 1694208
},
{
"epoch": 1.01,
"learning_rate": 2.2255027146229308e-05,
"loss": 3.4508,
"step": 1694720
},
{
"epoch": 1.01,
"learning_rate": 2.2246641198718785e-05,
"loss": 3.453,
"step": 1695232
},
{
"epoch": 1.01,
"learning_rate": 2.2238255251208265e-05,
"loss": 3.4582,
"step": 1695744
},
{
"epoch": 1.01,
"learning_rate": 2.2229885682501477e-05,
"loss": 3.4608,
"step": 1696256
},
{
"epoch": 1.01,
"learning_rate": 2.2221499734990954e-05,
"loss": 3.4473,
"step": 1696768
},
{
"epoch": 1.01,
"learning_rate": 2.2213113787480437e-05,
"loss": 3.4525,
"step": 1697280
},
{
"epoch": 1.01,
"learning_rate": 2.2204727839969917e-05,
"loss": 3.4526,
"step": 1697792
},
{
"epoch": 1.01,
"learning_rate": 2.219635827126313e-05,
"loss": 3.4504,
"step": 1698304
},
{
"epoch": 1.01,
"learning_rate": 2.2187972323752606e-05,
"loss": 3.4389,
"step": 1698816
},
{
"epoch": 1.01,
"learning_rate": 2.2179586376242086e-05,
"loss": 3.4463,
"step": 1699328
},
{
"epoch": 1.01,
"learning_rate": 2.2171200428731566e-05,
"loss": 3.448,
"step": 1699840
},
{
"epoch": 1.01,
"learning_rate": 2.216283086002478e-05,
"loss": 3.4515,
"step": 1700352
},
{
"epoch": 1.01,
"learning_rate": 2.215444491251426e-05,
"loss": 3.448,
"step": 1700864
},
{
"epoch": 1.01,
"learning_rate": 2.214605896500374e-05,
"loss": 3.4464,
"step": 1701376
},
{
"epoch": 1.01,
"learning_rate": 2.213768939629695e-05,
"loss": 3.466,
"step": 1701888
},
{
"epoch": 1.01,
"learning_rate": 2.2129303448786428e-05,
"loss": 3.4522,
"step": 1702400
},
{
"epoch": 1.01,
"learning_rate": 2.2120917501275908e-05,
"loss": 3.4557,
"step": 1702912
},
{
"epoch": 1.01,
"learning_rate": 2.211253155376539e-05,
"loss": 3.4438,
"step": 1703424
},
{
"epoch": 1.01,
"learning_rate": 2.2104161985058603e-05,
"loss": 3.4347,
"step": 1703936
},
{
"epoch": 1.01,
"learning_rate": 2.209577603754808e-05,
"loss": 3.4595,
"step": 1704448
},
{
"epoch": 1.01,
"learning_rate": 2.208739009003756e-05,
"loss": 3.4491,
"step": 1704960
},
{
"epoch": 1.01,
"learning_rate": 2.207900414252704e-05,
"loss": 3.4445,
"step": 1705472
},
{
"epoch": 1.01,
"learning_rate": 2.2070634573820252e-05,
"loss": 3.4471,
"step": 1705984
},
{
"epoch": 1.01,
"learning_rate": 2.2062248626309732e-05,
"loss": 3.4514,
"step": 1706496
},
{
"epoch": 1.01,
"learning_rate": 2.2053862678799212e-05,
"loss": 3.428,
"step": 1707008
},
{
"epoch": 1.01,
"learning_rate": 2.2045476731288692e-05,
"loss": 3.4501,
"step": 1707520
},
{
"epoch": 1.01,
"learning_rate": 2.20371071625819e-05,
"loss": 3.4424,
"step": 1708032
},
{
"epoch": 1.01,
"learning_rate": 2.202872121507138e-05,
"loss": 3.442,
"step": 1708544
},
{
"epoch": 1.01,
"learning_rate": 2.202033526756086e-05,
"loss": 3.4588,
"step": 1709056
},
{
"epoch": 1.01,
"learning_rate": 2.2011949320050345e-05,
"loss": 3.4465,
"step": 1709568
},
{
"epoch": 1.01,
"learning_rate": 2.2003579751343554e-05,
"loss": 3.4437,
"step": 1710080
},
{
"epoch": 1.01,
"learning_rate": 2.1995193803833034e-05,
"loss": 3.4511,
"step": 1710592
},
{
"epoch": 1.01,
"learning_rate": 2.1986807856322514e-05,
"loss": 3.4361,
"step": 1711104
},
{
"epoch": 1.01,
"learning_rate": 2.1978421908811994e-05,
"loss": 3.4403,
"step": 1711616
},
{
"epoch": 1.01,
"learning_rate": 2.1970052340105206e-05,
"loss": 3.4438,
"step": 1712128
},
{
"epoch": 1.01,
"learning_rate": 2.1961666392594686e-05,
"loss": 3.4462,
"step": 1712640
},
{
"epoch": 1.01,
"learning_rate": 2.1953280445084166e-05,
"loss": 3.4448,
"step": 1713152
},
{
"epoch": 1.01,
"learning_rate": 2.1944894497573646e-05,
"loss": 3.4385,
"step": 1713664
},
{
"epoch": 1.01,
"learning_rate": 2.1936524928866855e-05,
"loss": 3.4289,
"step": 1714176
},
{
"epoch": 1.01,
"learning_rate": 2.1928138981356335e-05,
"loss": 3.4433,
"step": 1714688
},
{
"epoch": 1.01,
"learning_rate": 2.1919753033845815e-05,
"loss": 3.4545,
"step": 1715200
},
{
"epoch": 1.01,
"learning_rate": 2.1911367086335298e-05,
"loss": 3.4429,
"step": 1715712
},
{
"epoch": 1.01,
"learning_rate": 2.1902997517628507e-05,
"loss": 3.4605,
"step": 1716224
},
{
"epoch": 1.01,
"learning_rate": 2.1894611570117987e-05,
"loss": 3.4556,
"step": 1716736
},
{
"epoch": 1.01,
"learning_rate": 2.1886225622607467e-05,
"loss": 3.4547,
"step": 1717248
},
{
"epoch": 1.01,
"learning_rate": 2.1877839675096947e-05,
"loss": 3.4404,
"step": 1717760
},
{
"epoch": 1.01,
"learning_rate": 2.186947010639016e-05,
"loss": 3.4565,
"step": 1718272
},
{
"epoch": 1.01,
"learning_rate": 2.186108415887964e-05,
"loss": 3.4473,
"step": 1718784
},
{
"epoch": 1.01,
"learning_rate": 2.185269821136912e-05,
"loss": 3.4409,
"step": 1719296
},
{
"epoch": 1.01,
"learning_rate": 2.18443122638586e-05,
"loss": 3.4576,
"step": 1719808
},
{
"epoch": 1.01,
"learning_rate": 2.183594269515181e-05,
"loss": 3.4494,
"step": 1720320
},
{
"epoch": 1.01,
"learning_rate": 2.182755674764129e-05,
"loss": 3.452,
"step": 1720832
},
{
"epoch": 1.01,
"learning_rate": 2.181917080013077e-05,
"loss": 3.4471,
"step": 1721344
},
{
"epoch": 1.01,
"learning_rate": 2.181078485262025e-05,
"loss": 3.4299,
"step": 1721856
},
{
"epoch": 1.01,
"learning_rate": 2.180241528391346e-05,
"loss": 3.4319,
"step": 1722368
},
{
"epoch": 1.01,
"learning_rate": 2.179402933640294e-05,
"loss": 3.4423,
"step": 1722880
},
{
"epoch": 1.01,
"learning_rate": 2.178564338889242e-05,
"loss": 3.4532,
"step": 1723392
},
{
"epoch": 1.01,
"learning_rate": 2.17772574413819e-05,
"loss": 3.4477,
"step": 1723904
},
{
"epoch": 1.01,
"learning_rate": 2.1768887872675113e-05,
"loss": 3.4415,
"step": 1724416
},
{
"epoch": 1.02,
"learning_rate": 2.1760501925164593e-05,
"loss": 3.4457,
"step": 1724928
},
{
"epoch": 1.02,
"learning_rate": 2.1752115977654073e-05,
"loss": 3.4365,
"step": 1725440
},
{
"epoch": 1.02,
"learning_rate": 2.1743730030143553e-05,
"loss": 3.4453,
"step": 1725952
},
{
"epoch": 1.02,
"learning_rate": 2.1735360461436762e-05,
"loss": 3.4407,
"step": 1726464
},
{
"epoch": 1.02,
"learning_rate": 2.1726974513926242e-05,
"loss": 3.4597,
"step": 1726976
},
{
"epoch": 1.02,
"learning_rate": 2.1718588566415722e-05,
"loss": 3.4575,
"step": 1727488
},
{
"epoch": 1.02,
"learning_rate": 2.1710202618905202e-05,
"loss": 3.4498,
"step": 1728000
},
{
"epoch": 1.02,
"learning_rate": 2.1701833050198415e-05,
"loss": 3.4417,
"step": 1728512
},
{
"epoch": 1.02,
"learning_rate": 2.1693447102687895e-05,
"loss": 3.4502,
"step": 1729024
},
{
"epoch": 1.02,
"learning_rate": 2.1685061155177375e-05,
"loss": 3.4389,
"step": 1729536
},
{
"epoch": 1.02,
"learning_rate": 2.167667520766685e-05,
"loss": 3.4596,
"step": 1730048
},
{
"epoch": 1.02,
"learning_rate": 2.1668305638960064e-05,
"loss": 3.4407,
"step": 1730560
},
{
"epoch": 1.02,
"learning_rate": 2.1659919691449547e-05,
"loss": 3.4427,
"step": 1731072
},
{
"epoch": 1.02,
"learning_rate": 2.1651533743939027e-05,
"loss": 3.4502,
"step": 1731584
},
{
"epoch": 1.02,
"learning_rate": 2.1643147796428503e-05,
"loss": 3.4492,
"step": 1732096
},
{
"epoch": 1.02,
"learning_rate": 2.1634778227721716e-05,
"loss": 3.4395,
"step": 1732608
},
{
"epoch": 1.02,
"learning_rate": 2.1626392280211196e-05,
"loss": 3.4515,
"step": 1733120
},
{
"epoch": 1.02,
"learning_rate": 2.1618006332700676e-05,
"loss": 3.4408,
"step": 1733632
},
{
"epoch": 1.02,
"learning_rate": 2.1609620385190156e-05,
"loss": 3.4361,
"step": 1734144
},
{
"epoch": 1.02,
"learning_rate": 2.160125081648337e-05,
"loss": 3.4313,
"step": 1734656
},
{
"epoch": 1.02,
"learning_rate": 2.1592864868972848e-05,
"loss": 3.4467,
"step": 1735168
},
{
"epoch": 1.02,
"learning_rate": 2.1584478921462325e-05,
"loss": 3.4458,
"step": 1735680
},
{
"epoch": 1.02,
"learning_rate": 2.1576092973951805e-05,
"loss": 3.4403,
"step": 1736192
},
{
"epoch": 1.02,
"learning_rate": 2.1567723405245017e-05,
"loss": 3.4424,
"step": 1736704
},
{
"epoch": 1.02,
"learning_rate": 2.15593374577345e-05,
"loss": 3.438,
"step": 1737216
},
{
"epoch": 1.02,
"learning_rate": 2.1550951510223977e-05,
"loss": 3.4528,
"step": 1737728
},
{
"epoch": 1.02,
"learning_rate": 2.1542565562713457e-05,
"loss": 3.4586,
"step": 1738240
},
{
"epoch": 1.02,
"learning_rate": 2.153419599400667e-05,
"loss": 3.4489,
"step": 1738752
},
{
"epoch": 1.02,
"learning_rate": 2.152581004649615e-05,
"loss": 3.4488,
"step": 1739264
},
{
"epoch": 1.02,
"learning_rate": 2.151742409898563e-05,
"loss": 3.441,
"step": 1739776
},
{
"epoch": 1.02,
"learning_rate": 2.150903815147511e-05,
"loss": 3.4423,
"step": 1740288
},
{
"epoch": 1.02,
"learning_rate": 2.1500668582768322e-05,
"loss": 3.4336,
"step": 1740800
},
{
"epoch": 1.02,
"learning_rate": 2.14922826352578e-05,
"loss": 3.4404,
"step": 1741312
},
{
"epoch": 1.02,
"learning_rate": 2.148389668774728e-05,
"loss": 3.4452,
"step": 1741824
},
{
"epoch": 1.02,
"learning_rate": 2.147551074023676e-05,
"loss": 3.4454,
"step": 1742336
},
{
"epoch": 1.02,
"learning_rate": 2.146714117152997e-05,
"loss": 3.4483,
"step": 1742848
},
{
"epoch": 1.02,
"learning_rate": 2.145875522401945e-05,
"loss": 3.447,
"step": 1743360
},
{
"epoch": 1.02,
"learning_rate": 2.145036927650893e-05,
"loss": 3.452,
"step": 1743872
},
{
"epoch": 1.02,
"learning_rate": 2.144198332899841e-05,
"loss": 3.4397,
"step": 1744384
},
{
"epoch": 1.02,
"learning_rate": 2.1433613760291623e-05,
"loss": 3.4473,
"step": 1744896
},
{
"epoch": 1.02,
"learning_rate": 2.14252278127811e-05,
"loss": 3.4447,
"step": 1745408
},
{
"epoch": 1.02,
"learning_rate": 2.1416841865270583e-05,
"loss": 3.4539,
"step": 1745920
},
{
"epoch": 1.02,
"learning_rate": 2.1408472296563796e-05,
"loss": 3.4586,
"step": 1746432
},
{
"epoch": 1.02,
"learning_rate": 2.1400086349053272e-05,
"loss": 3.4413,
"step": 1746944
},
{
"epoch": 1.02,
"learning_rate": 2.1391700401542752e-05,
"loss": 3.4534,
"step": 1747456
},
{
"epoch": 1.02,
"learning_rate": 2.1383314454032232e-05,
"loss": 3.4467,
"step": 1747968
},
{
"epoch": 1.02,
"learning_rate": 2.1374944885325445e-05,
"loss": 3.4513,
"step": 1748480
},
{
"epoch": 1.02,
"learning_rate": 2.1366558937814925e-05,
"loss": 3.4447,
"step": 1748992
},
{
"epoch": 1.02,
"learning_rate": 2.1358172990304405e-05,
"loss": 3.4527,
"step": 1749504
},
{
"epoch": 1.02,
"learning_rate": 2.1349787042793885e-05,
"loss": 3.4402,
"step": 1750016
},
{
"epoch": 1.02,
"learning_rate": 2.1341417474087097e-05,
"loss": 3.4531,
"step": 1750528
},
{
"epoch": 1.02,
"learning_rate": 2.1333031526576574e-05,
"loss": 3.4344,
"step": 1751040
},
{
"epoch": 1.02,
"learning_rate": 2.1324645579066054e-05,
"loss": 3.4437,
"step": 1751552
},
{
"epoch": 1.02,
"learning_rate": 2.1316259631555537e-05,
"loss": 3.4447,
"step": 1752064
},
{
"epoch": 1.02,
"learning_rate": 2.1307890062848746e-05,
"loss": 3.4498,
"step": 1752576
},
{
"epoch": 1.02,
"learning_rate": 2.1299504115338226e-05,
"loss": 3.4453,
"step": 1753088
},
{
"epoch": 1.02,
"learning_rate": 2.1291118167827706e-05,
"loss": 3.4465,
"step": 1753600
},
{
"epoch": 1.02,
"learning_rate": 2.1282732220317186e-05,
"loss": 3.4527,
"step": 1754112
},
{
"epoch": 1.02,
"learning_rate": 2.12743626516104e-05,
"loss": 3.4369,
"step": 1754624
},
{
"epoch": 1.02,
"learning_rate": 2.1265976704099878e-05,
"loss": 3.4517,
"step": 1755136
},
{
"epoch": 1.03,
"eval_loss": 3.853703737258911,
"eval_runtime": 302.8951,
"eval_samples_per_second": 1259.813,
"eval_steps_per_second": 39.37,
"step": 1755360
},
{
"epoch": 0.0,
"learning_rate": 2.1257590756589358e-05,
"loss": 3.4409,
"step": 1755648
},
{
"epoch": 0.0,
"learning_rate": 2.1249204809078838e-05,
"loss": 3.4349,
"step": 1756160
},
{
"epoch": 0.0,
"learning_rate": 2.1240818861568318e-05,
"loss": 3.4483,
"step": 1756672
},
{
"epoch": 0.0,
"learning_rate": 2.1232432914057798e-05,
"loss": 3.4475,
"step": 1757184
},
{
"epoch": 0.0,
"learning_rate": 2.1224063345351007e-05,
"loss": 3.4555,
"step": 1757696
},
{
"epoch": 0.0,
"learning_rate": 2.1215677397840487e-05,
"loss": 3.4432,
"step": 1758208
},
{
"epoch": 0.0,
"learning_rate": 2.120729145032997e-05,
"loss": 3.4409,
"step": 1758720
},
{
"epoch": 0.0,
"learning_rate": 2.119890550281945e-05,
"loss": 3.4384,
"step": 1759232
},
{
"epoch": 0.0,
"learning_rate": 2.119053593411266e-05,
"loss": 3.443,
"step": 1759744
},
{
"epoch": 0.0,
"learning_rate": 2.118214998660214e-05,
"loss": 3.4386,
"step": 1760256
},
{
"epoch": 0.0,
"learning_rate": 2.117376403909162e-05,
"loss": 3.448,
"step": 1760768
},
{
"epoch": 0.0,
"learning_rate": 2.11653780915811e-05,
"loss": 3.4494,
"step": 1761280
},
{
"epoch": 0.0,
"learning_rate": 2.1157008522874312e-05,
"loss": 3.4351,
"step": 1761792
},
{
"epoch": 0.0,
"learning_rate": 2.114863895416752e-05,
"loss": 3.434,
"step": 1762304
},
{
"epoch": 0.0,
"learning_rate": 2.1140253006657e-05,
"loss": 3.4451,
"step": 1762816
},
{
"epoch": 0.0,
"learning_rate": 2.113186705914648e-05,
"loss": 3.4289,
"step": 1763328
},
{
"epoch": 0.0,
"learning_rate": 2.112348111163596e-05,
"loss": 3.4399,
"step": 1763840
},
{
"epoch": 0.0,
"learning_rate": 2.111509516412544e-05,
"loss": 3.4402,
"step": 1764352
},
{
"epoch": 0.0,
"learning_rate": 2.1106709216614924e-05,
"loss": 3.4395,
"step": 1764864
},
{
"epoch": 0.0,
"learning_rate": 2.10983232691044e-05,
"loss": 3.4502,
"step": 1765376
},
{
"epoch": 0.0,
"learning_rate": 2.108993732159388e-05,
"loss": 3.4452,
"step": 1765888
},
{
"epoch": 0.0,
"learning_rate": 2.1081567752887093e-05,
"loss": 3.4415,
"step": 1766400
},
{
"epoch": 0.0,
"learning_rate": 2.1073181805376573e-05,
"loss": 3.4441,
"step": 1766912
},
{
"epoch": 0.0,
"learning_rate": 2.1064812236669786e-05,
"loss": 3.4419,
"step": 1767424
},
{
"epoch": 0.0,
"learning_rate": 2.1056426289159266e-05,
"loss": 3.4394,
"step": 1767936
},
{
"epoch": 0.0,
"learning_rate": 2.1048040341648746e-05,
"loss": 3.4461,
"step": 1768448
},
{
"epoch": 0.0,
"learning_rate": 2.1039654394138222e-05,
"loss": 3.4389,
"step": 1768960
},
{
"epoch": 0.0,
"learning_rate": 2.1031268446627702e-05,
"loss": 3.4344,
"step": 1769472
},
{
"epoch": 0.0,
"learning_rate": 2.1022882499117182e-05,
"loss": 3.4357,
"step": 1769984
},
{
"epoch": 0.0,
"learning_rate": 2.1014496551606662e-05,
"loss": 3.4441,
"step": 1770496
},
{
"epoch": 0.01,
"learning_rate": 2.1006110604096145e-05,
"loss": 3.4361,
"step": 1771008
},
{
"epoch": 0.01,
"learning_rate": 2.0997741035389354e-05,
"loss": 3.4444,
"step": 1771520
},
{
"epoch": 0.01,
"learning_rate": 2.0989355087878834e-05,
"loss": 3.449,
"step": 1772032
},
{
"epoch": 0.01,
"learning_rate": 2.0980969140368314e-05,
"loss": 3.4458,
"step": 1772544
},
{
"epoch": 0.01,
"learning_rate": 2.0972583192857794e-05,
"loss": 3.4321,
"step": 1773056
},
{
"epoch": 0.01,
"learning_rate": 2.0964213624151007e-05,
"loss": 3.4433,
"step": 1773568
},
{
"epoch": 0.01,
"learning_rate": 2.0955827676640487e-05,
"loss": 3.4413,
"step": 1774080
},
{
"epoch": 0.01,
"learning_rate": 2.0947441729129967e-05,
"loss": 3.4369,
"step": 1774592
},
{
"epoch": 0.01,
"learning_rate": 2.0939055781619447e-05,
"loss": 3.4301,
"step": 1775104
},
{
"epoch": 0.01,
"learning_rate": 2.0930686212912656e-05,
"loss": 3.4327,
"step": 1775616
},
{
"epoch": 0.01,
"learning_rate": 2.0922300265402136e-05,
"loss": 3.4399,
"step": 1776128
},
{
"epoch": 0.01,
"learning_rate": 2.0913914317891616e-05,
"loss": 3.4418,
"step": 1776640
},
{
"epoch": 0.01,
"learning_rate": 2.0905528370381096e-05,
"loss": 3.4358,
"step": 1777152
},
{
"epoch": 0.01,
"learning_rate": 2.0897158801674308e-05,
"loss": 3.4355,
"step": 1777664
},
{
"epoch": 0.01,
"learning_rate": 2.0888772854163788e-05,
"loss": 3.4523,
"step": 1778176
},
{
"epoch": 0.01,
"learning_rate": 2.0880386906653268e-05,
"loss": 3.4419,
"step": 1778688
},
{
"epoch": 0.01,
"learning_rate": 2.0872000959142748e-05,
"loss": 3.4473,
"step": 1779200
},
{
"epoch": 0.01,
"learning_rate": 2.0863631390435957e-05,
"loss": 3.4335,
"step": 1779712
},
{
"epoch": 0.01,
"learning_rate": 2.085524544292544e-05,
"loss": 3.4218,
"step": 1780224
},
{
"epoch": 0.01,
"learning_rate": 2.084685949541492e-05,
"loss": 3.4506,
"step": 1780736
},
{
"epoch": 0.01,
"learning_rate": 2.08384735479044e-05,
"loss": 3.4392,
"step": 1781248
},
{
"epoch": 0.01,
"learning_rate": 2.083010397919761e-05,
"loss": 3.4338,
"step": 1781760
},
{
"epoch": 0.01,
"learning_rate": 2.082171803168709e-05,
"loss": 3.4404,
"step": 1782272
},
{
"epoch": 0.01,
"learning_rate": 2.081333208417657e-05,
"loss": 3.4345,
"step": 1782784
},
{
"epoch": 0.01,
"learning_rate": 2.080494613666605e-05,
"loss": 3.4255,
"step": 1783296
},
{
"epoch": 0.01,
"learning_rate": 2.0796576567959262e-05,
"loss": 3.4332,
"step": 1783808
},
{
"epoch": 0.01,
"learning_rate": 2.078819062044874e-05,
"loss": 3.4326,
"step": 1784320
},
{
"epoch": 0.01,
"learning_rate": 2.077980467293822e-05,
"loss": 3.4349,
"step": 1784832
},
{
"epoch": 0.01,
"learning_rate": 2.07714187254277e-05,
"loss": 3.443,
"step": 1785344
},
{
"epoch": 0.01,
"learning_rate": 2.076304915672091e-05,
"loss": 3.4369,
"step": 1785856
},
{
"epoch": 0.01,
"learning_rate": 2.0754663209210394e-05,
"loss": 3.4334,
"step": 1786368
},
{
"epoch": 0.01,
"learning_rate": 2.0746277261699874e-05,
"loss": 3.4419,
"step": 1786880
},
{
"epoch": 0.01,
"learning_rate": 2.073789131418935e-05,
"loss": 3.4237,
"step": 1787392
},
{
"epoch": 0.01,
"learning_rate": 2.0729521745482563e-05,
"loss": 3.4297,
"step": 1787904
},
{
"epoch": 0.01,
"learning_rate": 2.0721135797972043e-05,
"loss": 3.4323,
"step": 1788416
},
{
"epoch": 0.01,
"learning_rate": 2.0712749850461523e-05,
"loss": 3.4353,
"step": 1788928
},
{
"epoch": 0.01,
"learning_rate": 2.0704363902951003e-05,
"loss": 3.4302,
"step": 1789440
},
{
"epoch": 0.01,
"learning_rate": 2.0695994334244215e-05,
"loss": 3.4337,
"step": 1789952
},
{
"epoch": 0.01,
"learning_rate": 2.0687608386733695e-05,
"loss": 3.4154,
"step": 1790464
},
{
"epoch": 0.01,
"learning_rate": 2.0679222439223175e-05,
"loss": 3.4311,
"step": 1790976
},
{
"epoch": 0.01,
"learning_rate": 2.0670852870516384e-05,
"loss": 3.4462,
"step": 1791488
},
{
"epoch": 0.01,
"learning_rate": 2.0662466923005864e-05,
"loss": 3.4302,
"step": 1792000
},
{
"epoch": 0.01,
"learning_rate": 2.0654080975495348e-05,
"loss": 3.4506,
"step": 1792512
},
{
"epoch": 0.01,
"learning_rate": 2.0645695027984824e-05,
"loss": 3.4421,
"step": 1793024
},
{
"epoch": 0.01,
"learning_rate": 2.0637325459278037e-05,
"loss": 3.4476,
"step": 1793536
},
{
"epoch": 0.01,
"learning_rate": 2.0628939511767517e-05,
"loss": 3.4319,
"step": 1794048
},
{
"epoch": 0.01,
"learning_rate": 2.0620553564256997e-05,
"loss": 3.4444,
"step": 1794560
},
{
"epoch": 0.01,
"learning_rate": 2.0612167616746477e-05,
"loss": 3.435,
"step": 1795072
},
{
"epoch": 0.01,
"learning_rate": 2.060379804803969e-05,
"loss": 3.4309,
"step": 1795584
},
{
"epoch": 0.01,
"learning_rate": 2.059541210052917e-05,
"loss": 3.4466,
"step": 1796096
},
{
"epoch": 0.01,
"learning_rate": 2.0587026153018646e-05,
"loss": 3.4356,
"step": 1796608
},
{
"epoch": 0.01,
"learning_rate": 2.0578640205508126e-05,
"loss": 3.4411,
"step": 1797120
},
{
"epoch": 0.01,
"learning_rate": 2.0570270636801338e-05,
"loss": 3.4388,
"step": 1797632
},
{
"epoch": 0.01,
"learning_rate": 2.0561884689290818e-05,
"loss": 3.4164,
"step": 1798144
},
{
"epoch": 0.01,
"learning_rate": 2.0553498741780298e-05,
"loss": 3.4251,
"step": 1798656
},
{
"epoch": 0.01,
"learning_rate": 2.0545112794269778e-05,
"loss": 3.4285,
"step": 1799168
},
{
"epoch": 0.01,
"learning_rate": 2.053674322556299e-05,
"loss": 3.4407,
"step": 1799680
},
{
"epoch": 0.01,
"learning_rate": 2.052835727805247e-05,
"loss": 3.4392,
"step": 1800192
},
{
"epoch": 0.01,
"learning_rate": 2.0519971330541947e-05,
"loss": 3.4296,
"step": 1800704
},
{
"epoch": 0.02,
"learning_rate": 2.051158538303143e-05,
"loss": 3.4331,
"step": 1801216
},
{
"epoch": 0.02,
"learning_rate": 2.0503215814324643e-05,
"loss": 3.4273,
"step": 1801728
},
{
"epoch": 0.02,
"learning_rate": 2.049482986681412e-05,
"loss": 3.4309,
"step": 1802240
},
{
"epoch": 0.02,
"learning_rate": 2.04864439193036e-05,
"loss": 3.429,
"step": 1802752
},
{
"epoch": 0.02,
"learning_rate": 2.047805797179308e-05,
"loss": 3.4468,
"step": 1803264
},
{
"epoch": 0.02,
"learning_rate": 2.0469688403086292e-05,
"loss": 3.4531,
"step": 1803776
},
{
"epoch": 0.02,
"learning_rate": 2.046130245557577e-05,
"loss": 3.4327,
"step": 1804288
},
{
"epoch": 0.02,
"learning_rate": 2.045291650806525e-05,
"loss": 3.4315,
"step": 1804800
},
{
"epoch": 0.02,
"learning_rate": 2.044453056055473e-05,
"loss": 3.4393,
"step": 1805312
},
{
"epoch": 0.02,
"learning_rate": 2.0436160991847944e-05,
"loss": 3.4302,
"step": 1805824
},
{
"epoch": 0.02,
"learning_rate": 2.042777504433742e-05,
"loss": 3.4482,
"step": 1806336
},
{
"epoch": 0.02,
"learning_rate": 2.04193890968269e-05,
"loss": 3.4329,
"step": 1806848
},
{
"epoch": 0.02,
"learning_rate": 2.041100314931638e-05,
"loss": 3.4345,
"step": 1807360
},
{
"epoch": 0.02,
"learning_rate": 2.0402633580609593e-05,
"loss": 3.4386,
"step": 1807872
},
{
"epoch": 0.02,
"learning_rate": 2.0394247633099073e-05,
"loss": 3.4399,
"step": 1808384
},
{
"epoch": 0.02,
"learning_rate": 2.0385861685588553e-05,
"loss": 3.4289,
"step": 1808896
},
{
"epoch": 0.02,
"learning_rate": 2.0377475738078033e-05,
"loss": 3.437,
"step": 1809408
},
{
"epoch": 0.02,
"learning_rate": 2.0369106169371245e-05,
"loss": 3.4322,
"step": 1809920
},
{
"epoch": 0.02,
"learning_rate": 2.0360720221860725e-05,
"loss": 3.4248,
"step": 1810432
},
{
"epoch": 0.02,
"learning_rate": 2.0352334274350205e-05,
"loss": 3.4234,
"step": 1810944
},
{
"epoch": 0.02,
"learning_rate": 2.0343948326839685e-05,
"loss": 3.4336,
"step": 1811456
},
{
"epoch": 0.02,
"learning_rate": 2.0335578758132894e-05,
"loss": 3.4364,
"step": 1811968
},
{
"epoch": 0.02,
"learning_rate": 2.0327192810622374e-05,
"loss": 3.4291,
"step": 1812480
},
{
"epoch": 0.02,
"learning_rate": 2.0318806863111854e-05,
"loss": 3.4328,
"step": 1812992
},
{
"epoch": 0.02,
"learning_rate": 2.0310420915601334e-05,
"loss": 3.4286,
"step": 1813504
},
{
"epoch": 0.02,
"learning_rate": 2.0302051346894547e-05,
"loss": 3.4432,
"step": 1814016
},
{
"epoch": 0.02,
"learning_rate": 2.0293665399384027e-05,
"loss": 3.4464,
"step": 1814528
},
{
"epoch": 0.02,
"learning_rate": 2.0285279451873507e-05,
"loss": 3.4401,
"step": 1815040
},
{
"epoch": 0.02,
"learning_rate": 2.0276893504362987e-05,
"loss": 3.4371,
"step": 1815552
},
{
"epoch": 0.02,
"learning_rate": 2.0268523935656196e-05,
"loss": 3.4272,
"step": 1816064
},
{
"epoch": 0.02,
"learning_rate": 2.026013798814568e-05,
"loss": 3.4356,
"step": 1816576
},
{
"epoch": 0.02,
"learning_rate": 2.025175204063516e-05,
"loss": 3.4252,
"step": 1817088
},
{
"epoch": 0.02,
"learning_rate": 2.024336609312464e-05,
"loss": 3.4316,
"step": 1817600
},
{
"epoch": 0.02,
"learning_rate": 2.0234996524417848e-05,
"loss": 3.4294,
"step": 1818112
},
{
"epoch": 0.02,
"learning_rate": 2.0226610576907328e-05,
"loss": 3.4368,
"step": 1818624
},
{
"epoch": 0.02,
"learning_rate": 2.0218224629396808e-05,
"loss": 3.4348,
"step": 1819136
},
{
"epoch": 0.02,
"learning_rate": 2.0209838681886288e-05,
"loss": 3.4345,
"step": 1819648
},
{
"epoch": 0.02,
"learning_rate": 2.02014691131795e-05,
"loss": 3.4415,
"step": 1820160
},
{
"epoch": 0.02,
"learning_rate": 2.019308316566898e-05,
"loss": 3.4288,
"step": 1820672
},
{
"epoch": 0.02,
"learning_rate": 2.018471359696219e-05,
"loss": 3.437,
"step": 1821184
},
{
"epoch": 0.02,
"learning_rate": 2.017632764945167e-05,
"loss": 3.4362,
"step": 1821696
},
{
"epoch": 0.02,
"learning_rate": 2.016794170194115e-05,
"loss": 3.4396,
"step": 1822208
},
{
"epoch": 0.02,
"learning_rate": 2.0159555754430633e-05,
"loss": 3.4493,
"step": 1822720
},
{
"epoch": 0.02,
"learning_rate": 2.0151169806920113e-05,
"loss": 3.4298,
"step": 1823232
},
{
"epoch": 0.02,
"learning_rate": 2.0142783859409593e-05,
"loss": 3.4432,
"step": 1823744
},
{
"epoch": 0.02,
"learning_rate": 2.0134397911899073e-05,
"loss": 3.4364,
"step": 1824256
},
{
"epoch": 0.02,
"learning_rate": 2.012601196438855e-05,
"loss": 3.4396,
"step": 1824768
},
{
"epoch": 0.02,
"learning_rate": 2.011764239568176e-05,
"loss": 3.4331,
"step": 1825280
},
{
"epoch": 0.02,
"learning_rate": 2.010925644817124e-05,
"loss": 3.4419,
"step": 1825792
},
{
"epoch": 0.02,
"learning_rate": 2.010087050066072e-05,
"loss": 3.4299,
"step": 1826304
},
{
"epoch": 0.02,
"learning_rate": 2.00924845531502e-05,
"loss": 3.444,
"step": 1826816
},
{
"epoch": 0.02,
"learning_rate": 2.0084114984443414e-05,
"loss": 3.422,
"step": 1827328
},
{
"epoch": 0.02,
"learning_rate": 2.0075729036932894e-05,
"loss": 3.4317,
"step": 1827840
},
{
"epoch": 0.02,
"learning_rate": 2.006734308942237e-05,
"loss": 3.4373,
"step": 1828352
},
{
"epoch": 0.02,
"learning_rate": 2.0058957141911854e-05,
"loss": 3.4387,
"step": 1828864
},
{
"epoch": 0.02,
"learning_rate": 2.0050587573205066e-05,
"loss": 3.4318,
"step": 1829376
},
{
"epoch": 0.02,
"learning_rate": 2.0042201625694546e-05,
"loss": 3.4341,
"step": 1829888
},
{
"epoch": 0.02,
"learning_rate": 2.0033815678184023e-05,
"loss": 3.4435,
"step": 1830400
},
{
"epoch": 0.02,
"learning_rate": 2.0025429730673503e-05,
"loss": 3.4266,
"step": 1830912
},
{
"epoch": 0.02,
"learning_rate": 2.0017060161966715e-05,
"loss": 3.4416,
"step": 1831424
},
{
"epoch": 0.03,
"eval_loss": 3.854403018951416,
"eval_runtime": 304.4984,
"eval_samples_per_second": 1253.179,
"eval_steps_per_second": 39.163,
"step": 1831680
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.2748030266272072e+18,
"trial_name": null,
"trial_params": null
}