ryusangwon's picture
Model save
2be1f99 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.7446016381236039,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.98758997269794e-05,
"loss": 1.8076,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 4.97517994539588e-05,
"loss": 1.792,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 4.96276991809382e-05,
"loss": 1.7935,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 4.95035989079176e-05,
"loss": 1.7432,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 4.9379498634897e-05,
"loss": 1.7369,
"step": 50
},
{
"epoch": 0.04,
"learning_rate": 4.92553983618764e-05,
"loss": 1.7506,
"step": 60
},
{
"epoch": 0.05,
"learning_rate": 4.91312980888558e-05,
"loss": 1.6795,
"step": 70
},
{
"epoch": 0.06,
"learning_rate": 4.90071978158352e-05,
"loss": 1.721,
"step": 80
},
{
"epoch": 0.07,
"learning_rate": 4.88830975428146e-05,
"loss": 1.6954,
"step": 90
},
{
"epoch": 0.07,
"learning_rate": 4.875899726979399e-05,
"loss": 1.6715,
"step": 100
},
{
"epoch": 0.08,
"learning_rate": 4.86348969967734e-05,
"loss": 1.6799,
"step": 110
},
{
"epoch": 0.09,
"learning_rate": 4.8510796723752796e-05,
"loss": 1.7203,
"step": 120
},
{
"epoch": 0.1,
"learning_rate": 4.8386696450732196e-05,
"loss": 1.6643,
"step": 130
},
{
"epoch": 0.1,
"learning_rate": 4.8262596177711595e-05,
"loss": 1.6655,
"step": 140
},
{
"epoch": 0.11,
"learning_rate": 4.8138495904690995e-05,
"loss": 1.681,
"step": 150
},
{
"epoch": 0.12,
"learning_rate": 4.8014395631670394e-05,
"loss": 1.7232,
"step": 160
},
{
"epoch": 0.13,
"learning_rate": 4.789029535864979e-05,
"loss": 1.6658,
"step": 170
},
{
"epoch": 0.13,
"learning_rate": 4.7766195085629186e-05,
"loss": 1.6965,
"step": 180
},
{
"epoch": 0.14,
"learning_rate": 4.764209481260859e-05,
"loss": 1.6745,
"step": 190
},
{
"epoch": 0.15,
"learning_rate": 4.751799453958799e-05,
"loss": 1.6881,
"step": 200
},
{
"epoch": 0.16,
"learning_rate": 4.739389426656739e-05,
"loss": 1.6899,
"step": 210
},
{
"epoch": 0.16,
"learning_rate": 4.726979399354679e-05,
"loss": 1.6825,
"step": 220
},
{
"epoch": 0.17,
"learning_rate": 4.7145693720526184e-05,
"loss": 1.6894,
"step": 230
},
{
"epoch": 0.18,
"learning_rate": 4.702159344750558e-05,
"loss": 1.7016,
"step": 240
},
{
"epoch": 0.19,
"learning_rate": 4.689749317448498e-05,
"loss": 1.6556,
"step": 250
},
{
"epoch": 0.19,
"learning_rate": 4.677339290146439e-05,
"loss": 1.715,
"step": 260
},
{
"epoch": 0.2,
"learning_rate": 4.664929262844379e-05,
"loss": 1.6415,
"step": 270
},
{
"epoch": 0.21,
"learning_rate": 4.652519235542319e-05,
"loss": 1.6986,
"step": 280
},
{
"epoch": 0.22,
"learning_rate": 4.640109208240258e-05,
"loss": 1.6766,
"step": 290
},
{
"epoch": 0.22,
"learning_rate": 4.627699180938198e-05,
"loss": 1.7016,
"step": 300
},
{
"epoch": 0.23,
"learning_rate": 4.615289153636138e-05,
"loss": 1.698,
"step": 310
},
{
"epoch": 0.24,
"learning_rate": 4.602879126334078e-05,
"loss": 1.6692,
"step": 320
},
{
"epoch": 0.25,
"learning_rate": 4.590469099032018e-05,
"loss": 1.6386,
"step": 330
},
{
"epoch": 0.25,
"learning_rate": 4.5780590717299585e-05,
"loss": 1.7369,
"step": 340
},
{
"epoch": 0.26,
"learning_rate": 4.5656490444278984e-05,
"loss": 1.6997,
"step": 350
},
{
"epoch": 0.27,
"learning_rate": 4.553239017125838e-05,
"loss": 1.6983,
"step": 360
},
{
"epoch": 0.28,
"learning_rate": 4.5408289898237776e-05,
"loss": 1.6702,
"step": 370
},
{
"epoch": 0.28,
"learning_rate": 4.5284189625217176e-05,
"loss": 1.6901,
"step": 380
},
{
"epoch": 0.29,
"learning_rate": 4.5160089352196575e-05,
"loss": 1.6916,
"step": 390
},
{
"epoch": 0.3,
"learning_rate": 4.5035989079175975e-05,
"loss": 1.682,
"step": 400
},
{
"epoch": 0.31,
"learning_rate": 4.491188880615538e-05,
"loss": 1.6756,
"step": 410
},
{
"epoch": 0.31,
"learning_rate": 4.4787788533134774e-05,
"loss": 1.6632,
"step": 420
},
{
"epoch": 0.32,
"learning_rate": 4.466368826011417e-05,
"loss": 1.67,
"step": 430
},
{
"epoch": 0.33,
"learning_rate": 4.453958798709357e-05,
"loss": 1.6581,
"step": 440
},
{
"epoch": 0.34,
"learning_rate": 4.441548771407297e-05,
"loss": 1.7106,
"step": 450
},
{
"epoch": 0.34,
"learning_rate": 4.429138744105237e-05,
"loss": 1.6757,
"step": 460
},
{
"epoch": 0.35,
"learning_rate": 4.416728716803177e-05,
"loss": 1.6315,
"step": 470
},
{
"epoch": 0.36,
"learning_rate": 4.404318689501117e-05,
"loss": 1.66,
"step": 480
},
{
"epoch": 0.36,
"learning_rate": 4.391908662199057e-05,
"loss": 1.6966,
"step": 490
},
{
"epoch": 0.37,
"learning_rate": 4.379498634896997e-05,
"loss": 1.6642,
"step": 500
},
{
"epoch": 0.38,
"learning_rate": 4.367088607594937e-05,
"loss": 1.6882,
"step": 510
},
{
"epoch": 0.39,
"learning_rate": 4.354678580292877e-05,
"loss": 1.6741,
"step": 520
},
{
"epoch": 0.39,
"learning_rate": 4.342268552990817e-05,
"loss": 1.6859,
"step": 530
},
{
"epoch": 0.4,
"learning_rate": 4.329858525688757e-05,
"loss": 1.6925,
"step": 540
},
{
"epoch": 0.41,
"learning_rate": 4.317448498386697e-05,
"loss": 1.6748,
"step": 550
},
{
"epoch": 0.42,
"learning_rate": 4.3050384710846366e-05,
"loss": 1.674,
"step": 560
},
{
"epoch": 0.42,
"learning_rate": 4.2926284437825766e-05,
"loss": 1.6723,
"step": 570
},
{
"epoch": 0.43,
"learning_rate": 4.2802184164805165e-05,
"loss": 1.688,
"step": 580
},
{
"epoch": 0.44,
"learning_rate": 4.2678083891784565e-05,
"loss": 1.6585,
"step": 590
},
{
"epoch": 0.45,
"learning_rate": 4.2553983618763964e-05,
"loss": 1.6902,
"step": 600
},
{
"epoch": 0.45,
"learning_rate": 4.2429883345743364e-05,
"loss": 1.6565,
"step": 610
},
{
"epoch": 0.46,
"learning_rate": 4.2305783072722757e-05,
"loss": 1.6897,
"step": 620
},
{
"epoch": 0.47,
"learning_rate": 4.218168279970216e-05,
"loss": 1.6698,
"step": 630
},
{
"epoch": 0.48,
"learning_rate": 4.205758252668156e-05,
"loss": 1.6712,
"step": 640
},
{
"epoch": 0.48,
"learning_rate": 4.193348225366096e-05,
"loss": 1.6653,
"step": 650
},
{
"epoch": 0.49,
"learning_rate": 4.180938198064036e-05,
"loss": 1.683,
"step": 660
},
{
"epoch": 0.5,
"learning_rate": 4.168528170761976e-05,
"loss": 1.6498,
"step": 670
},
{
"epoch": 0.51,
"learning_rate": 4.1561181434599153e-05,
"loss": 1.6939,
"step": 680
},
{
"epoch": 0.51,
"learning_rate": 4.143708116157855e-05,
"loss": 1.7123,
"step": 690
},
{
"epoch": 0.52,
"learning_rate": 4.131298088855796e-05,
"loss": 1.669,
"step": 700
},
{
"epoch": 0.53,
"learning_rate": 4.118888061553736e-05,
"loss": 1.7012,
"step": 710
},
{
"epoch": 0.54,
"learning_rate": 4.106478034251676e-05,
"loss": 1.668,
"step": 720
},
{
"epoch": 0.54,
"learning_rate": 4.094068006949616e-05,
"loss": 1.6845,
"step": 730
},
{
"epoch": 0.55,
"learning_rate": 4.081657979647556e-05,
"loss": 1.6371,
"step": 740
},
{
"epoch": 0.56,
"learning_rate": 4.069247952345495e-05,
"loss": 1.6871,
"step": 750
},
{
"epoch": 0.57,
"learning_rate": 4.056837925043435e-05,
"loss": 1.6605,
"step": 760
},
{
"epoch": 0.57,
"learning_rate": 4.044427897741375e-05,
"loss": 1.6838,
"step": 770
},
{
"epoch": 0.58,
"learning_rate": 4.0320178704393155e-05,
"loss": 1.6586,
"step": 780
},
{
"epoch": 0.59,
"learning_rate": 4.0196078431372555e-05,
"loss": 1.7265,
"step": 790
},
{
"epoch": 0.6,
"learning_rate": 4.0071978158351954e-05,
"loss": 1.6616,
"step": 800
},
{
"epoch": 0.6,
"learning_rate": 3.994787788533135e-05,
"loss": 1.6445,
"step": 810
},
{
"epoch": 0.61,
"learning_rate": 3.9823777612310746e-05,
"loss": 1.6916,
"step": 820
},
{
"epoch": 0.62,
"learning_rate": 3.9699677339290146e-05,
"loss": 1.6986,
"step": 830
},
{
"epoch": 0.63,
"learning_rate": 3.9575577066269545e-05,
"loss": 1.6776,
"step": 840
},
{
"epoch": 0.63,
"learning_rate": 3.945147679324895e-05,
"loss": 1.6629,
"step": 850
},
{
"epoch": 0.64,
"learning_rate": 3.932737652022835e-05,
"loss": 1.6789,
"step": 860
},
{
"epoch": 0.65,
"learning_rate": 3.9203276247207744e-05,
"loss": 1.6432,
"step": 870
},
{
"epoch": 0.66,
"learning_rate": 3.907917597418714e-05,
"loss": 1.6934,
"step": 880
},
{
"epoch": 0.66,
"learning_rate": 3.895507570116654e-05,
"loss": 1.7064,
"step": 890
},
{
"epoch": 0.67,
"learning_rate": 3.883097542814594e-05,
"loss": 1.6626,
"step": 900
},
{
"epoch": 0.68,
"learning_rate": 3.870687515512534e-05,
"loss": 1.6482,
"step": 910
},
{
"epoch": 0.69,
"learning_rate": 3.858277488210474e-05,
"loss": 1.674,
"step": 920
},
{
"epoch": 0.69,
"learning_rate": 3.845867460908415e-05,
"loss": 1.6474,
"step": 930
},
{
"epoch": 0.7,
"learning_rate": 3.833457433606354e-05,
"loss": 1.6719,
"step": 940
},
{
"epoch": 0.71,
"learning_rate": 3.821047406304294e-05,
"loss": 1.6694,
"step": 950
},
{
"epoch": 0.71,
"learning_rate": 3.808637379002234e-05,
"loss": 1.6876,
"step": 960
},
{
"epoch": 0.72,
"learning_rate": 3.796227351700174e-05,
"loss": 1.6902,
"step": 970
},
{
"epoch": 0.73,
"learning_rate": 3.783817324398114e-05,
"loss": 1.67,
"step": 980
},
{
"epoch": 0.74,
"learning_rate": 3.771407297096054e-05,
"loss": 1.6488,
"step": 990
},
{
"epoch": 0.74,
"learning_rate": 3.758997269793994e-05,
"loss": 1.6153,
"step": 1000
}
],
"logging_steps": 10,
"max_steps": 4029,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 6.3202482192384e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}