EF-instruments / checkpoint-415 /trainer_state.json
alonb19's picture
Upload folder using huggingface_hub
154f6cb verified
{
"best_metric": 0.9787878787878788,
"best_model_checkpoint": "musical_instrument_detection/checkpoint-415",
"epoch": 5.0,
"global_step": 415,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.12,
"learning_rate": 3.0120481927710846e-06,
"loss": 1.1042,
"step": 10
},
{
"epoch": 0.24,
"learning_rate": 8.433734939759036e-06,
"loss": 1.0962,
"step": 20
},
{
"epoch": 0.36,
"learning_rate": 1.3855421686746989e-05,
"loss": 1.0951,
"step": 30
},
{
"epoch": 0.48,
"learning_rate": 1.9879518072289157e-05,
"loss": 1.0664,
"step": 40
},
{
"epoch": 0.6,
"learning_rate": 2.5903614457831325e-05,
"loss": 1.0012,
"step": 50
},
{
"epoch": 0.72,
"learning_rate": 3.192771084337349e-05,
"loss": 0.8798,
"step": 60
},
{
"epoch": 0.84,
"learning_rate": 3.7951807228915666e-05,
"loss": 0.8234,
"step": 70
},
{
"epoch": 0.96,
"learning_rate": 4.3975903614457834e-05,
"loss": 0.7179,
"step": 80
},
{
"epoch": 1.0,
"eval_accuracy": 0.8757575757575757,
"eval_loss": 0.5570486187934875,
"eval_runtime": 1.3424,
"eval_samples_per_second": 245.837,
"eval_steps_per_second": 15.644,
"step": 83
},
{
"epoch": 1.08,
"learning_rate": 4.9397590361445786e-05,
"loss": 0.5908,
"step": 90
},
{
"epoch": 1.2,
"learning_rate": 4.9397590361445786e-05,
"loss": 0.5123,
"step": 100
},
{
"epoch": 1.33,
"learning_rate": 4.872824631860777e-05,
"loss": 0.4208,
"step": 110
},
{
"epoch": 1.45,
"learning_rate": 4.8058902275769744e-05,
"loss": 0.461,
"step": 120
},
{
"epoch": 1.57,
"learning_rate": 4.738955823293173e-05,
"loss": 0.3973,
"step": 130
},
{
"epoch": 1.69,
"learning_rate": 4.672021419009371e-05,
"loss": 0.2359,
"step": 140
},
{
"epoch": 1.81,
"learning_rate": 4.61178045515395e-05,
"loss": 0.2632,
"step": 150
},
{
"epoch": 1.93,
"learning_rate": 4.5448460508701474e-05,
"loss": 0.2608,
"step": 160
},
{
"epoch": 2.0,
"eval_accuracy": 0.9696969696969697,
"eval_loss": 0.16986176371574402,
"eval_runtime": 1.3339,
"eval_samples_per_second": 247.387,
"eval_steps_per_second": 15.743,
"step": 166
},
{
"epoch": 2.05,
"learning_rate": 4.4779116465863456e-05,
"loss": 0.1711,
"step": 170
},
{
"epoch": 2.17,
"learning_rate": 4.417670682730924e-05,
"loss": 0.3199,
"step": 180
},
{
"epoch": 2.29,
"learning_rate": 4.350736278447122e-05,
"loss": 0.3263,
"step": 190
},
{
"epoch": 2.41,
"learning_rate": 4.2838018741633203e-05,
"loss": 0.161,
"step": 200
},
{
"epoch": 2.53,
"learning_rate": 4.223560910307898e-05,
"loss": 0.2836,
"step": 210
},
{
"epoch": 2.65,
"learning_rate": 4.156626506024097e-05,
"loss": 0.3063,
"step": 220
},
{
"epoch": 2.77,
"learning_rate": 4.0896921017402945e-05,
"loss": 0.2713,
"step": 230
},
{
"epoch": 2.89,
"learning_rate": 4.022757697456493e-05,
"loss": 0.2758,
"step": 240
},
{
"epoch": 3.0,
"eval_accuracy": 0.9636363636363636,
"eval_loss": 0.19073687493801117,
"eval_runtime": 1.2855,
"eval_samples_per_second": 256.705,
"eval_steps_per_second": 16.336,
"step": 249
},
{
"epoch": 3.01,
"learning_rate": 3.955823293172691e-05,
"loss": 0.2528,
"step": 250
},
{
"epoch": 3.13,
"learning_rate": 3.888888888888889e-05,
"loss": 0.236,
"step": 260
},
{
"epoch": 3.25,
"learning_rate": 3.821954484605087e-05,
"loss": 0.2527,
"step": 270
},
{
"epoch": 3.37,
"learning_rate": 3.7550200803212855e-05,
"loss": 0.324,
"step": 280
},
{
"epoch": 3.49,
"learning_rate": 3.688085676037483e-05,
"loss": 0.1528,
"step": 290
},
{
"epoch": 3.61,
"learning_rate": 3.621151271753682e-05,
"loss": 0.2982,
"step": 300
},
{
"epoch": 3.73,
"learning_rate": 3.5542168674698794e-05,
"loss": 0.2162,
"step": 310
},
{
"epoch": 3.86,
"learning_rate": 3.4872824631860776e-05,
"loss": 0.1411,
"step": 320
},
{
"epoch": 3.98,
"learning_rate": 3.420348058902276e-05,
"loss": 0.1493,
"step": 330
},
{
"epoch": 4.0,
"eval_accuracy": 0.9696969696969697,
"eval_loss": 0.16822877526283264,
"eval_runtime": 1.2615,
"eval_samples_per_second": 261.596,
"eval_steps_per_second": 16.647,
"step": 332
},
{
"epoch": 4.1,
"learning_rate": 3.353413654618474e-05,
"loss": 0.0834,
"step": 340
},
{
"epoch": 4.22,
"learning_rate": 3.286479250334672e-05,
"loss": 0.2619,
"step": 350
},
{
"epoch": 4.34,
"learning_rate": 3.2195448460508704e-05,
"loss": 0.1048,
"step": 360
},
{
"epoch": 4.46,
"learning_rate": 3.152610441767068e-05,
"loss": 0.1843,
"step": 370
},
{
"epoch": 4.58,
"learning_rate": 3.085676037483267e-05,
"loss": 0.199,
"step": 380
},
{
"epoch": 4.7,
"learning_rate": 3.0187416331994644e-05,
"loss": 0.2731,
"step": 390
},
{
"epoch": 4.82,
"learning_rate": 2.951807228915663e-05,
"loss": 0.1628,
"step": 400
},
{
"epoch": 4.94,
"learning_rate": 2.8848728246318608e-05,
"loss": 0.1566,
"step": 410
},
{
"epoch": 5.0,
"eval_accuracy": 0.9787878787878788,
"eval_loss": 0.12163327634334564,
"eval_runtime": 1.2638,
"eval_samples_per_second": 261.117,
"eval_steps_per_second": 16.617,
"step": 415
}
],
"max_steps": 830,
"num_train_epochs": 10,
"total_flos": 5.978295839952e+17,
"trial_name": null,
"trial_params": null
}