{
"best_metric": 0.06379657983779907,
"best_model_checkpoint": "/home/cloudwalker/ASVmodel/wavlm-base_4/checkpoint-200",
"epoch": 9.98109640831758,
"eval_steps": 100,
"global_step": 3960,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.25,
"learning_rate": 7.575757575757576e-05,
"loss": 0.3784,
"step": 100
},
{
"epoch": 0.25,
"eval_f1": 0.9905683736634776,
"eval_loss": 0.07838701456785202,
"eval_runtime": 494.4493,
"eval_samples_per_second": 50.246,
"eval_steps_per_second": 25.123,
"step": 100
},
{
"epoch": 0.5,
"learning_rate": 0.00015151515151515152,
"loss": 0.1125,
"step": 200
},
{
"epoch": 0.5,
"eval_f1": 0.9925361354770335,
"eval_loss": 0.06379657983779907,
"eval_runtime": 495.4697,
"eval_samples_per_second": 50.142,
"eval_steps_per_second": 25.071,
"step": 200
},
{
"epoch": 0.76,
"learning_rate": 0.00022727272727272725,
"loss": 0.1158,
"step": 300
},
{
"epoch": 0.76,
"eval_f1": 0.9773465624725612,
"eval_loss": 0.1715879738330841,
"eval_runtime": 495.6685,
"eval_samples_per_second": 50.122,
"eval_steps_per_second": 25.061,
"step": 300
},
{
"epoch": 1.01,
"learning_rate": 0.00029966329966329963,
"loss": 0.327,
"step": 400
},
{
"epoch": 1.01,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3308480978012085,
"eval_runtime": 495.7404,
"eval_samples_per_second": 50.115,
"eval_steps_per_second": 25.057,
"step": 400
},
{
"epoch": 1.26,
"learning_rate": 0.00029124579124579125,
"loss": 0.3346,
"step": 500
},
{
"epoch": 1.26,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.34493646025657654,
"eval_runtime": 495.7377,
"eval_samples_per_second": 50.115,
"eval_steps_per_second": 25.058,
"step": 500
},
{
"epoch": 1.51,
"learning_rate": 0.0002828282828282828,
"loss": 0.3345,
"step": 600
},
{
"epoch": 1.51,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3316415250301361,
"eval_runtime": 495.8008,
"eval_samples_per_second": 50.109,
"eval_steps_per_second": 25.054,
"step": 600
},
{
"epoch": 1.76,
"learning_rate": 0.0002744107744107744,
"loss": 0.3313,
"step": 700
},
{
"epoch": 1.76,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3320470452308655,
"eval_runtime": 495.8537,
"eval_samples_per_second": 50.103,
"eval_steps_per_second": 25.052,
"step": 700
},
{
"epoch": 2.02,
"learning_rate": 0.00026599326599326595,
"loss": 0.3249,
"step": 800
},
{
"epoch": 2.02,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.33273717761039734,
"eval_runtime": 496.067,
"eval_samples_per_second": 50.082,
"eval_steps_per_second": 25.041,
"step": 800
},
{
"epoch": 2.27,
"learning_rate": 0.00025757575757575756,
"loss": 0.3403,
"step": 900
},
{
"epoch": 2.27,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3314824402332306,
"eval_runtime": 496.0647,
"eval_samples_per_second": 50.082,
"eval_steps_per_second": 25.041,
"step": 900
},
{
"epoch": 2.52,
"learning_rate": 0.00024915824915824913,
"loss": 0.3345,
"step": 1000
},
{
"epoch": 2.52,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3381609320640564,
"eval_runtime": 496.3675,
"eval_samples_per_second": 50.052,
"eval_steps_per_second": 25.026,
"step": 1000
},
{
"epoch": 2.77,
"learning_rate": 0.00024074074074074072,
"loss": 0.3174,
"step": 1100
},
{
"epoch": 2.77,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.33755871653556824,
"eval_runtime": 496.1396,
"eval_samples_per_second": 50.075,
"eval_steps_per_second": 25.037,
"step": 1100
},
{
"epoch": 3.02,
"learning_rate": 0.0002323232323232323,
"loss": 0.3274,
"step": 1200
},
{
"epoch": 3.02,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3353538513183594,
"eval_runtime": 496.3912,
"eval_samples_per_second": 50.049,
"eval_steps_per_second": 25.025,
"step": 1200
},
{
"epoch": 3.28,
"learning_rate": 0.0002239057239057239,
"loss": 0.3296,
"step": 1300
},
{
"epoch": 3.28,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.33069172501564026,
"eval_runtime": 496.1466,
"eval_samples_per_second": 50.074,
"eval_steps_per_second": 25.037,
"step": 1300
},
{
"epoch": 3.53,
"learning_rate": 0.00021548821548821544,
"loss": 0.3175,
"step": 1400
},
{
"epoch": 3.53,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3341147303581238,
"eval_runtime": 496.5334,
"eval_samples_per_second": 50.035,
"eval_steps_per_second": 25.017,
"step": 1400
},
{
"epoch": 3.78,
"learning_rate": 0.00020707070707070703,
"loss": 0.3416,
"step": 1500
},
{
"epoch": 3.78,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3344402611255646,
"eval_runtime": 496.2158,
"eval_samples_per_second": 50.067,
"eval_steps_per_second": 25.033,
"step": 1500
},
{
"epoch": 4.03,
"learning_rate": 0.00019865319865319862,
"loss": 0.3412,
"step": 1600
},
{
"epoch": 4.03,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3307790160179138,
"eval_runtime": 496.5097,
"eval_samples_per_second": 50.037,
"eval_steps_per_second": 25.019,
"step": 1600
},
{
"epoch": 4.28,
"learning_rate": 0.00019023569023569022,
"loss": 0.3293,
"step": 1700
},
{
"epoch": 4.28,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3313847482204437,
"eval_runtime": 496.395,
"eval_samples_per_second": 50.049,
"eval_steps_per_second": 25.024,
"step": 1700
},
{
"epoch": 4.54,
"learning_rate": 0.0001818181818181818,
"loss": 0.3346,
"step": 1800
},
{
"epoch": 4.54,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.33080053329467773,
"eval_runtime": 496.4252,
"eval_samples_per_second": 50.046,
"eval_steps_per_second": 25.023,
"step": 1800
},
{
"epoch": 4.79,
"learning_rate": 0.0001734006734006734,
"loss": 0.3279,
"step": 1900
},
{
"epoch": 4.79,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3317018449306488,
"eval_runtime": 496.5163,
"eval_samples_per_second": 50.037,
"eval_steps_per_second": 25.018,
"step": 1900
},
{
"epoch": 5.04,
"learning_rate": 0.000164983164983165,
"loss": 0.3246,
"step": 2000
},
{
"epoch": 5.04,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.33184757828712463,
"eval_runtime": 496.5592,
"eval_samples_per_second": 50.032,
"eval_steps_per_second": 25.016,
"step": 2000
},
{
"epoch": 5.29,
"learning_rate": 0.00015656565656565653,
"loss": 0.3373,
"step": 2100
},
{
"epoch": 5.29,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.33109256625175476,
"eval_runtime": 496.5149,
"eval_samples_per_second": 50.037,
"eval_steps_per_second": 25.018,
"step": 2100
},
{
"epoch": 5.55,
"learning_rate": 0.00014814814814814812,
"loss": 0.3262,
"step": 2200
},
{
"epoch": 5.55,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.33351102471351624,
"eval_runtime": 496.6308,
"eval_samples_per_second": 50.025,
"eval_steps_per_second": 25.013,
"step": 2200
},
{
"epoch": 5.8,
"learning_rate": 0.0001397306397306397,
"loss": 0.3279,
"step": 2300
},
{
"epoch": 5.8,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3326103985309601,
"eval_runtime": 496.8717,
"eval_samples_per_second": 50.001,
"eval_steps_per_second": 25.0,
"step": 2300
},
{
"epoch": 6.05,
"learning_rate": 0.0001313131313131313,
"loss": 0.3298,
"step": 2400
},
{
"epoch": 6.05,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3322770297527313,
"eval_runtime": 496.7239,
"eval_samples_per_second": 50.016,
"eval_steps_per_second": 25.008,
"step": 2400
},
{
"epoch": 6.3,
"learning_rate": 0.0001228956228956229,
"loss": 0.3397,
"step": 2500
},
{
"epoch": 6.3,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3311246633529663,
"eval_runtime": 496.772,
"eval_samples_per_second": 50.011,
"eval_steps_per_second": 25.005,
"step": 2500
},
{
"epoch": 6.55,
"learning_rate": 0.00011447811447811446,
"loss": 0.3312,
"step": 2600
},
{
"epoch": 6.55,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.33860132098197937,
"eval_runtime": 496.8085,
"eval_samples_per_second": 50.007,
"eval_steps_per_second": 25.004,
"step": 2600
},
{
"epoch": 6.81,
"learning_rate": 0.00010606060606060605,
"loss": 0.3291,
"step": 2700
},
{
"epoch": 6.81,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3316628634929657,
"eval_runtime": 496.6873,
"eval_samples_per_second": 50.019,
"eval_steps_per_second": 25.01,
"step": 2700
},
{
"epoch": 7.06,
"learning_rate": 9.764309764309764e-05,
"loss": 0.3146,
"step": 2800
},
{
"epoch": 7.06,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.33230647444725037,
"eval_runtime": 496.6634,
"eval_samples_per_second": 50.022,
"eval_steps_per_second": 25.011,
"step": 2800
},
{
"epoch": 7.31,
"learning_rate": 8.92255892255892e-05,
"loss": 0.3296,
"step": 2900
},
{
"epoch": 7.31,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3313485085964203,
"eval_runtime": 496.6247,
"eval_samples_per_second": 50.026,
"eval_steps_per_second": 25.013,
"step": 2900
},
{
"epoch": 7.56,
"learning_rate": 8.08080808080808e-05,
"loss": 0.3367,
"step": 3000
},
{
"epoch": 7.56,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.33174964785575867,
"eval_runtime": 496.735,
"eval_samples_per_second": 50.015,
"eval_steps_per_second": 25.007,
"step": 3000
},
{
"epoch": 7.81,
"learning_rate": 7.239057239057239e-05,
"loss": 0.3232,
"step": 3100
},
{
"epoch": 7.81,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3318324387073517,
"eval_runtime": 496.5843,
"eval_samples_per_second": 50.03,
"eval_steps_per_second": 25.015,
"step": 3100
},
{
"epoch": 8.07,
"learning_rate": 6.397306397306397e-05,
"loss": 0.3314,
"step": 3200
},
{
"epoch": 8.07,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3325050175189972,
"eval_runtime": 496.7125,
"eval_samples_per_second": 50.017,
"eval_steps_per_second": 25.008,
"step": 3200
},
{
"epoch": 8.32,
"learning_rate": 5.5555555555555545e-05,
"loss": 0.3201,
"step": 3300
},
{
"epoch": 8.32,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.33225715160369873,
"eval_runtime": 496.6425,
"eval_samples_per_second": 50.024,
"eval_steps_per_second": 25.012,
"step": 3300
},
{
"epoch": 8.57,
"learning_rate": 4.7138047138047136e-05,
"loss": 0.3301,
"step": 3400
},
{
"epoch": 8.57,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3346656262874603,
"eval_runtime": 496.595,
"eval_samples_per_second": 50.029,
"eval_steps_per_second": 25.014,
"step": 3400
},
{
"epoch": 8.82,
"learning_rate": 3.8720538720538714e-05,
"loss": 0.3268,
"step": 3500
},
{
"epoch": 8.82,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.33254188299179077,
"eval_runtime": 496.5109,
"eval_samples_per_second": 50.037,
"eval_steps_per_second": 25.019,
"step": 3500
},
{
"epoch": 9.07,
"learning_rate": 3.03030303030303e-05,
"loss": 0.3361,
"step": 3600
},
{
"epoch": 9.07,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.33214762806892395,
"eval_runtime": 496.8406,
"eval_samples_per_second": 50.004,
"eval_steps_per_second": 25.002,
"step": 3600
},
{
"epoch": 9.33,
"learning_rate": 2.1885521885521884e-05,
"loss": 0.3395,
"step": 3700
},
{
"epoch": 9.33,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3312663733959198,
"eval_runtime": 496.7467,
"eval_samples_per_second": 50.013,
"eval_steps_per_second": 25.007,
"step": 3700
},
{
"epoch": 9.58,
"learning_rate": 1.3468013468013465e-05,
"loss": 0.3231,
"step": 3800
},
{
"epoch": 9.58,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3319169878959656,
"eval_runtime": 496.7702,
"eval_samples_per_second": 50.011,
"eval_steps_per_second": 25.006,
"step": 3800
},
{
"epoch": 9.83,
"learning_rate": 5.05050505050505e-06,
"loss": 0.3197,
"step": 3900
},
{
"epoch": 9.83,
"eval_f1": 0.9459482392872296,
"eval_loss": 0.3325766921043396,
"eval_runtime": 496.6934,
"eval_samples_per_second": 50.019,
"eval_steps_per_second": 25.009,
"step": 3900
},
{
"epoch": 9.98,
"step": 3960,
"total_flos": 1.506420070651024e+19,
"train_loss": 0.32019265878080116,
"train_runtime": 22716.823,
"train_samples_per_second": 11.172,
"train_steps_per_second": 0.174
}
],
"logging_steps": 100,
"max_steps": 3960,
"num_train_epochs": 10,
"save_steps": 100,
"total_flos": 1.506420070651024e+19,
"trial_name": null,
"trial_params": null
}