weather-base / trainer_state.json
ChasingMercer's picture
f
2d1218f
{
"best_metric": 0.9358600583090378,
"best_model_checkpoint": "./weather-base/checkpoint-855",
"epoch": 5.995633187772926,
"global_step": 1026,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.06,
"learning_rate": 4.854368932038835e-06,
"loss": 2.5891,
"step": 10
},
{
"epoch": 0.12,
"learning_rate": 9.70873786407767e-06,
"loss": 2.3939,
"step": 20
},
{
"epoch": 0.17,
"learning_rate": 1.4563106796116505e-05,
"loss": 2.0509,
"step": 30
},
{
"epoch": 0.23,
"learning_rate": 1.941747572815534e-05,
"loss": 1.7403,
"step": 40
},
{
"epoch": 0.29,
"learning_rate": 2.4271844660194176e-05,
"loss": 1.3148,
"step": 50
},
{
"epoch": 0.35,
"learning_rate": 2.912621359223301e-05,
"loss": 0.8922,
"step": 60
},
{
"epoch": 0.41,
"learning_rate": 3.398058252427185e-05,
"loss": 0.6958,
"step": 70
},
{
"epoch": 0.47,
"learning_rate": 3.883495145631068e-05,
"loss": 0.5293,
"step": 80
},
{
"epoch": 0.52,
"learning_rate": 4.368932038834951e-05,
"loss": 0.5498,
"step": 90
},
{
"epoch": 0.58,
"learning_rate": 4.854368932038835e-05,
"loss": 0.4659,
"step": 100
},
{
"epoch": 0.64,
"learning_rate": 4.962080173347779e-05,
"loss": 0.4436,
"step": 110
},
{
"epoch": 0.7,
"learning_rate": 4.907908992416035e-05,
"loss": 0.4404,
"step": 120
},
{
"epoch": 0.76,
"learning_rate": 4.853737811484291e-05,
"loss": 0.4192,
"step": 130
},
{
"epoch": 0.82,
"learning_rate": 4.799566630552546e-05,
"loss": 0.3667,
"step": 140
},
{
"epoch": 0.87,
"learning_rate": 4.745395449620802e-05,
"loss": 0.3844,
"step": 150
},
{
"epoch": 0.93,
"learning_rate": 4.691224268689058e-05,
"loss": 0.4201,
"step": 160
},
{
"epoch": 0.99,
"learning_rate": 4.6370530877573135e-05,
"loss": 0.3368,
"step": 170
},
{
"epoch": 1.0,
"eval_accuracy": 0.9008746355685131,
"eval_loss": 0.2779894173145294,
"eval_runtime": 14.9875,
"eval_samples_per_second": 45.771,
"eval_steps_per_second": 5.738,
"step": 171
},
{
"epoch": 1.05,
"learning_rate": 4.582881906825569e-05,
"loss": 0.3262,
"step": 180
},
{
"epoch": 1.11,
"learning_rate": 4.528710725893825e-05,
"loss": 0.2425,
"step": 190
},
{
"epoch": 1.17,
"learning_rate": 4.47453954496208e-05,
"loss": 0.2162,
"step": 200
},
{
"epoch": 1.23,
"learning_rate": 4.420368364030336e-05,
"loss": 0.3276,
"step": 210
},
{
"epoch": 1.29,
"learning_rate": 4.366197183098591e-05,
"loss": 0.3236,
"step": 220
},
{
"epoch": 1.34,
"learning_rate": 4.312026002166848e-05,
"loss": 0.2479,
"step": 230
},
{
"epoch": 1.4,
"learning_rate": 4.2578548212351035e-05,
"loss": 0.3096,
"step": 240
},
{
"epoch": 1.46,
"learning_rate": 4.2036836403033586e-05,
"loss": 0.2766,
"step": 250
},
{
"epoch": 1.52,
"learning_rate": 4.1495124593716144e-05,
"loss": 0.301,
"step": 260
},
{
"epoch": 1.58,
"learning_rate": 4.09534127843987e-05,
"loss": 0.2831,
"step": 270
},
{
"epoch": 1.63,
"learning_rate": 4.0411700975081254e-05,
"loss": 0.2805,
"step": 280
},
{
"epoch": 1.69,
"learning_rate": 3.986998916576382e-05,
"loss": 0.2897,
"step": 290
},
{
"epoch": 1.75,
"learning_rate": 3.932827735644638e-05,
"loss": 0.2581,
"step": 300
},
{
"epoch": 1.81,
"learning_rate": 3.878656554712893e-05,
"loss": 0.2201,
"step": 310
},
{
"epoch": 1.87,
"learning_rate": 3.8244853737811486e-05,
"loss": 0.3577,
"step": 320
},
{
"epoch": 1.93,
"learning_rate": 3.7703141928494044e-05,
"loss": 0.2503,
"step": 330
},
{
"epoch": 1.98,
"learning_rate": 3.71614301191766e-05,
"loss": 0.2129,
"step": 340
},
{
"epoch": 2.0,
"eval_accuracy": 0.9300291545189504,
"eval_loss": 0.23329117894172668,
"eval_runtime": 42.4804,
"eval_samples_per_second": 16.149,
"eval_steps_per_second": 2.024,
"step": 342
},
{
"epoch": 2.05,
"learning_rate": 3.661971830985916e-05,
"loss": 0.1552,
"step": 350
},
{
"epoch": 2.1,
"learning_rate": 3.607800650054171e-05,
"loss": 0.2058,
"step": 360
},
{
"epoch": 2.16,
"learning_rate": 3.553629469122427e-05,
"loss": 0.1833,
"step": 370
},
{
"epoch": 2.22,
"learning_rate": 3.499458288190683e-05,
"loss": 0.1666,
"step": 380
},
{
"epoch": 2.28,
"learning_rate": 3.445287107258938e-05,
"loss": 0.1654,
"step": 390
},
{
"epoch": 2.34,
"learning_rate": 3.3911159263271944e-05,
"loss": 0.229,
"step": 400
},
{
"epoch": 2.4,
"learning_rate": 3.33694474539545e-05,
"loss": 0.1942,
"step": 410
},
{
"epoch": 2.45,
"learning_rate": 3.2827735644637054e-05,
"loss": 0.213,
"step": 420
},
{
"epoch": 2.51,
"learning_rate": 3.228602383531961e-05,
"loss": 0.1931,
"step": 430
},
{
"epoch": 2.57,
"learning_rate": 3.174431202600217e-05,
"loss": 0.1458,
"step": 440
},
{
"epoch": 2.63,
"learning_rate": 3.120260021668472e-05,
"loss": 0.1693,
"step": 450
},
{
"epoch": 2.69,
"learning_rate": 3.0660888407367286e-05,
"loss": 0.2115,
"step": 460
},
{
"epoch": 2.75,
"learning_rate": 3.0119176598049837e-05,
"loss": 0.1264,
"step": 470
},
{
"epoch": 2.8,
"learning_rate": 2.9577464788732395e-05,
"loss": 0.2278,
"step": 480
},
{
"epoch": 2.86,
"learning_rate": 2.9035752979414954e-05,
"loss": 0.1669,
"step": 490
},
{
"epoch": 2.92,
"learning_rate": 2.8494041170097508e-05,
"loss": 0.2084,
"step": 500
},
{
"epoch": 2.98,
"learning_rate": 2.7952329360780066e-05,
"loss": 0.1827,
"step": 510
},
{
"epoch": 3.0,
"eval_accuracy": 0.9212827988338192,
"eval_loss": 0.24402616918087006,
"eval_runtime": 14.6992,
"eval_samples_per_second": 46.669,
"eval_steps_per_second": 5.851,
"step": 513
},
{
"epoch": 3.04,
"learning_rate": 2.7410617551462624e-05,
"loss": 0.1953,
"step": 520
},
{
"epoch": 3.1,
"learning_rate": 2.686890574214518e-05,
"loss": 0.1461,
"step": 530
},
{
"epoch": 3.16,
"learning_rate": 2.6327193932827737e-05,
"loss": 0.2002,
"step": 540
},
{
"epoch": 3.22,
"learning_rate": 2.5785482123510295e-05,
"loss": 0.1134,
"step": 550
},
{
"epoch": 3.27,
"learning_rate": 2.524377031419285e-05,
"loss": 0.1767,
"step": 560
},
{
"epoch": 3.33,
"learning_rate": 2.4702058504875408e-05,
"loss": 0.1726,
"step": 570
},
{
"epoch": 3.39,
"learning_rate": 2.4160346695557963e-05,
"loss": 0.1053,
"step": 580
},
{
"epoch": 3.45,
"learning_rate": 2.361863488624052e-05,
"loss": 0.1547,
"step": 590
},
{
"epoch": 3.51,
"learning_rate": 2.307692307692308e-05,
"loss": 0.1597,
"step": 600
},
{
"epoch": 3.56,
"learning_rate": 2.2535211267605634e-05,
"loss": 0.1319,
"step": 610
},
{
"epoch": 3.62,
"learning_rate": 2.1993499458288192e-05,
"loss": 0.1278,
"step": 620
},
{
"epoch": 3.68,
"learning_rate": 2.1451787648970747e-05,
"loss": 0.1113,
"step": 630
},
{
"epoch": 3.74,
"learning_rate": 2.0910075839653308e-05,
"loss": 0.1664,
"step": 640
},
{
"epoch": 3.8,
"learning_rate": 2.0368364030335863e-05,
"loss": 0.1301,
"step": 650
},
{
"epoch": 3.86,
"learning_rate": 1.9826652221018418e-05,
"loss": 0.0976,
"step": 660
},
{
"epoch": 3.91,
"learning_rate": 1.9284940411700976e-05,
"loss": 0.1927,
"step": 670
},
{
"epoch": 3.97,
"learning_rate": 1.8743228602383534e-05,
"loss": 0.1475,
"step": 680
},
{
"epoch": 4.0,
"eval_accuracy": 0.9314868804664723,
"eval_loss": 0.2305707186460495,
"eval_runtime": 40.2886,
"eval_samples_per_second": 17.027,
"eval_steps_per_second": 2.135,
"step": 684
},
{
"epoch": 4.03,
"learning_rate": 1.820151679306609e-05,
"loss": 0.1206,
"step": 690
},
{
"epoch": 4.09,
"learning_rate": 1.7659804983748647e-05,
"loss": 0.1543,
"step": 700
},
{
"epoch": 4.15,
"learning_rate": 1.7118093174431205e-05,
"loss": 0.0912,
"step": 710
},
{
"epoch": 4.21,
"learning_rate": 1.657638136511376e-05,
"loss": 0.1354,
"step": 720
},
{
"epoch": 4.27,
"learning_rate": 1.6034669555796317e-05,
"loss": 0.0883,
"step": 730
},
{
"epoch": 4.33,
"learning_rate": 1.5492957746478872e-05,
"loss": 0.1252,
"step": 740
},
{
"epoch": 4.38,
"learning_rate": 1.4951245937161432e-05,
"loss": 0.0996,
"step": 750
},
{
"epoch": 4.44,
"learning_rate": 1.4409534127843988e-05,
"loss": 0.0987,
"step": 760
},
{
"epoch": 4.5,
"learning_rate": 1.3867822318526543e-05,
"loss": 0.0881,
"step": 770
},
{
"epoch": 4.56,
"learning_rate": 1.3326110509209103e-05,
"loss": 0.1232,
"step": 780
},
{
"epoch": 4.62,
"learning_rate": 1.278439869989166e-05,
"loss": 0.1109,
"step": 790
},
{
"epoch": 4.68,
"learning_rate": 1.2242686890574214e-05,
"loss": 0.1524,
"step": 800
},
{
"epoch": 4.73,
"learning_rate": 1.1700975081256772e-05,
"loss": 0.0863,
"step": 810
},
{
"epoch": 4.79,
"learning_rate": 1.1159263271939329e-05,
"loss": 0.1184,
"step": 820
},
{
"epoch": 4.85,
"learning_rate": 1.0617551462621887e-05,
"loss": 0.1177,
"step": 830
},
{
"epoch": 4.91,
"learning_rate": 1.0075839653304441e-05,
"loss": 0.1187,
"step": 840
},
{
"epoch": 4.97,
"learning_rate": 9.534127843987e-06,
"loss": 0.1284,
"step": 850
},
{
"epoch": 5.0,
"eval_accuracy": 0.9358600583090378,
"eval_loss": 0.21915613114833832,
"eval_runtime": 14.6548,
"eval_samples_per_second": 46.81,
"eval_steps_per_second": 5.868,
"step": 855
},
{
"epoch": 5.03,
"learning_rate": 8.992416034669558e-06,
"loss": 0.1107,
"step": 860
},
{
"epoch": 5.09,
"learning_rate": 8.450704225352112e-06,
"loss": 0.1019,
"step": 870
},
{
"epoch": 5.15,
"learning_rate": 7.90899241603467e-06,
"loss": 0.0951,
"step": 880
},
{
"epoch": 5.2,
"learning_rate": 7.367280606717227e-06,
"loss": 0.0644,
"step": 890
},
{
"epoch": 5.26,
"learning_rate": 6.825568797399784e-06,
"loss": 0.1038,
"step": 900
},
{
"epoch": 5.32,
"learning_rate": 6.28385698808234e-06,
"loss": 0.0945,
"step": 910
},
{
"epoch": 5.38,
"learning_rate": 5.742145178764898e-06,
"loss": 0.0943,
"step": 920
},
{
"epoch": 5.44,
"learning_rate": 5.200433369447454e-06,
"loss": 0.0832,
"step": 930
},
{
"epoch": 5.49,
"learning_rate": 4.658721560130011e-06,
"loss": 0.0872,
"step": 940
},
{
"epoch": 5.55,
"learning_rate": 4.117009750812568e-06,
"loss": 0.0865,
"step": 950
},
{
"epoch": 5.61,
"learning_rate": 3.5752979414951246e-06,
"loss": 0.1009,
"step": 960
},
{
"epoch": 5.67,
"learning_rate": 3.033586132177682e-06,
"loss": 0.0913,
"step": 970
},
{
"epoch": 5.73,
"learning_rate": 2.4918743228602387e-06,
"loss": 0.0767,
"step": 980
},
{
"epoch": 5.79,
"learning_rate": 1.950162513542795e-06,
"loss": 0.129,
"step": 990
},
{
"epoch": 5.84,
"learning_rate": 1.4084507042253521e-06,
"loss": 0.049,
"step": 1000
},
{
"epoch": 5.9,
"learning_rate": 8.667388949079089e-07,
"loss": 0.062,
"step": 1010
},
{
"epoch": 5.96,
"learning_rate": 3.250270855904659e-07,
"loss": 0.0526,
"step": 1020
},
{
"epoch": 6.0,
"eval_accuracy": 0.9358600583090378,
"eval_loss": 0.2184152901172638,
"eval_runtime": 39.5726,
"eval_samples_per_second": 17.335,
"eval_steps_per_second": 2.173,
"step": 1026
},
{
"epoch": 6.0,
"step": 1026,
"total_flos": 2.549919337377528e+18,
"train_loss": 0.2920494159759834,
"train_runtime": 2402.1234,
"train_samples_per_second": 13.71,
"train_steps_per_second": 0.427
}
],
"max_steps": 1026,
"num_train_epochs": 6,
"total_flos": 2.549919337377528e+18,
"trial_name": null,
"trial_params": null
}