visualize-v0-pre1k-preseed1 / trainer_state.json
shengnan's picture
commit from v-shean
ef1bd8e
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.23883448770002388,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1e-05,
"loss": 5.873,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 1e-05,
"loss": 5.4916,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 1e-05,
"loss": 4.8477,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 1e-05,
"loss": 4.5425,
"step": 40
},
{
"epoch": 0.01,
"learning_rate": 1e-05,
"loss": 4.2734,
"step": 50
},
{
"epoch": 0.01,
"learning_rate": 1e-05,
"loss": 3.9337,
"step": 60
},
{
"epoch": 0.02,
"learning_rate": 1e-05,
"loss": 3.9433,
"step": 70
},
{
"epoch": 0.02,
"learning_rate": 1e-05,
"loss": 3.7212,
"step": 80
},
{
"epoch": 0.02,
"learning_rate": 1e-05,
"loss": 3.5957,
"step": 90
},
{
"epoch": 0.02,
"learning_rate": 1e-05,
"loss": 3.436,
"step": 100
},
{
"epoch": 0.03,
"learning_rate": 1e-05,
"loss": 3.387,
"step": 110
},
{
"epoch": 0.03,
"learning_rate": 1e-05,
"loss": 3.4263,
"step": 120
},
{
"epoch": 0.03,
"learning_rate": 1e-05,
"loss": 3.2046,
"step": 130
},
{
"epoch": 0.03,
"learning_rate": 1e-05,
"loss": 3.0605,
"step": 140
},
{
"epoch": 0.04,
"learning_rate": 1e-05,
"loss": 3.1447,
"step": 150
},
{
"epoch": 0.04,
"learning_rate": 1e-05,
"loss": 3.1735,
"step": 160
},
{
"epoch": 0.04,
"learning_rate": 1e-05,
"loss": 2.977,
"step": 170
},
{
"epoch": 0.04,
"learning_rate": 1e-05,
"loss": 3.2005,
"step": 180
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 3.0096,
"step": 190
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 2.8942,
"step": 200
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 2.8821,
"step": 210
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 2.8973,
"step": 220
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 3.0138,
"step": 230
},
{
"epoch": 0.06,
"learning_rate": 1e-05,
"loss": 2.859,
"step": 240
},
{
"epoch": 0.06,
"learning_rate": 1e-05,
"loss": 2.8366,
"step": 250
},
{
"epoch": 0.06,
"learning_rate": 1e-05,
"loss": 2.7728,
"step": 260
},
{
"epoch": 0.06,
"learning_rate": 1e-05,
"loss": 2.8216,
"step": 270
},
{
"epoch": 0.07,
"learning_rate": 1e-05,
"loss": 3.1418,
"step": 280
},
{
"epoch": 0.07,
"learning_rate": 1e-05,
"loss": 2.7978,
"step": 290
},
{
"epoch": 0.07,
"learning_rate": 1e-05,
"loss": 2.7199,
"step": 300
},
{
"epoch": 0.07,
"learning_rate": 1e-05,
"loss": 2.8219,
"step": 310
},
{
"epoch": 0.08,
"learning_rate": 1e-05,
"loss": 2.5467,
"step": 320
},
{
"epoch": 0.08,
"learning_rate": 1e-05,
"loss": 2.7626,
"step": 330
},
{
"epoch": 0.08,
"learning_rate": 1e-05,
"loss": 2.7639,
"step": 340
},
{
"epoch": 0.08,
"learning_rate": 1e-05,
"loss": 2.6535,
"step": 350
},
{
"epoch": 0.09,
"learning_rate": 1e-05,
"loss": 2.582,
"step": 360
},
{
"epoch": 0.09,
"learning_rate": 1e-05,
"loss": 2.5759,
"step": 370
},
{
"epoch": 0.09,
"learning_rate": 1e-05,
"loss": 2.7389,
"step": 380
},
{
"epoch": 0.09,
"learning_rate": 1e-05,
"loss": 2.5658,
"step": 390
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 2.3294,
"step": 400
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 2.6136,
"step": 410
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 2.5115,
"step": 420
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 2.6185,
"step": 430
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 2.7034,
"step": 440
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 2.542,
"step": 450
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 2.4195,
"step": 460
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 2.3935,
"step": 470
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 2.6524,
"step": 480
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 2.5967,
"step": 490
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 2.4715,
"step": 500
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 2.4646,
"step": 510
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 2.51,
"step": 520
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 2.4409,
"step": 530
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 2.3432,
"step": 540
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 2.3886,
"step": 550
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 2.49,
"step": 560
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 2.3519,
"step": 570
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 2.6453,
"step": 580
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 2.5263,
"step": 590
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 2.4042,
"step": 600
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 2.3475,
"step": 610
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 2.3979,
"step": 620
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 2.2499,
"step": 630
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 2.3608,
"step": 640
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 2.3991,
"step": 650
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 2.2029,
"step": 660
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 2.4048,
"step": 670
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 2.3327,
"step": 680
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 2.3633,
"step": 690
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 2.3499,
"step": 700
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 2.4361,
"step": 710
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 2.1677,
"step": 720
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 2.3024,
"step": 730
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 2.2208,
"step": 740
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 2.1665,
"step": 750
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 2.3387,
"step": 760
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 2.2972,
"step": 770
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 2.2578,
"step": 780
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 2.22,
"step": 790
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 2.1765,
"step": 800
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 2.2855,
"step": 810
},
{
"epoch": 0.2,
"learning_rate": 1e-05,
"loss": 2.3016,
"step": 820
},
{
"epoch": 0.2,
"learning_rate": 1e-05,
"loss": 2.3201,
"step": 830
},
{
"epoch": 0.2,
"learning_rate": 1e-05,
"loss": 2.1431,
"step": 840
},
{
"epoch": 0.2,
"learning_rate": 1e-05,
"loss": 2.2683,
"step": 850
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 2.0788,
"step": 860
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 2.1208,
"step": 870
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 2.3935,
"step": 880
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 2.183,
"step": 890
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 2.1116,
"step": 900
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 2.333,
"step": 910
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 2.2625,
"step": 920
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 2.1775,
"step": 930
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 2.1814,
"step": 940
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 2.1495,
"step": 950
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 2.1915,
"step": 960
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 2.1903,
"step": 970
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 2.0176,
"step": 980
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 2.1463,
"step": 990
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 2.1042,
"step": 1000
},
{
"epoch": 0.24,
"eval_accuracy": 0.2134502923976608,
"eval_loss": 1.9532288312911987,
"eval_runtime": 169.591,
"eval_samples_per_second": 4.033,
"step": 1000
}
],
"max_steps": 100000,
"num_train_epochs": 24,
"total_flos": 1177438977523712.0,
"trial_name": null,
"trial_params": null
}