wav2vec2-large-xlsr-53-sw / trainer_state.json

“Alok”

test

c349099 about 3 years ago

No virus

6.05 kB

	{
	"best_metric": 1.0,
	"best_model_checkpoint": "../wav2vec2-large-xlsr-53-sw/checkpoint-154",
	"epoch": 2.9967637540453076,
	"global_step": 462,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.06,
	"learning_rate": 0.00015,
	"loss": Infinity,
	"step": 10
	},
	{
	"epoch": 0.13,
	"learning_rate": 0.0003,
	"loss": NaN,
	"step": 20
	},
	{
	"epoch": 0.19,
	"learning_rate": 0.000296,
	"loss": NaN,
	"step": 30
	},
	{
	"epoch": 0.26,
	"learning_rate": 0.000292,
	"loss": NaN,
	"step": 40
	},
	{
	"epoch": 0.32,
	"learning_rate": 0.00028799999999999995,
	"loss": NaN,
	"step": 50
	},
	{
	"epoch": 0.39,
	"learning_rate": 0.00028399999999999996,
	"loss": NaN,
	"step": 60
	},
	{
	"epoch": 0.45,
	"learning_rate": 0.00028,
	"loss": NaN,
	"step": 70
	},
	{
	"epoch": 0.52,
	"learning_rate": 0.000276,
	"loss": NaN,
	"step": 80
	},
	{
	"epoch": 0.58,
	"learning_rate": 0.00027199999999999994,
	"loss": NaN,
	"step": 90
	},
	{
	"epoch": 0.65,
	"learning_rate": 0.00026799999999999995,
	"loss": NaN,
	"step": 100
	},
	{
	"epoch": 0.71,
	"learning_rate": 0.00026399999999999997,
	"loss": NaN,
	"step": 110
	},
	{
	"epoch": 0.78,
	"learning_rate": 0.00026,
	"loss": NaN,
	"step": 120
	},
	{
	"epoch": 0.84,
	"learning_rate": 0.000256,
	"loss": NaN,
	"step": 130
	},
	{
	"epoch": 0.91,
	"learning_rate": 0.00025199999999999995,
	"loss": NaN,
	"step": 140
	},
	{
	"epoch": 0.97,
	"learning_rate": 0.00024799999999999996,
	"loss": NaN,
	"step": 150
	},
	{
	"epoch": 1.0,
	"eval_loss": Infinity,
	"eval_runtime": 358.7961,
	"eval_samples_per_second": 5.549,
	"eval_wer": 1.0,
	"step": 154
	},
	{
	"epoch": 1.04,
	"learning_rate": 0.000244,
	"loss": NaN,
	"step": 160
	},
	{
	"epoch": 1.1,
	"learning_rate": 0.00023999999999999998,
	"loss": NaN,
	"step": 170
	},
	{
	"epoch": 1.17,
	"learning_rate": 0.00023599999999999996,
	"loss": NaN,
	"step": 180
	},
	{
	"epoch": 1.23,
	"learning_rate": 0.00023199999999999997,
	"loss": NaN,
	"step": 190
	},
	{
	"epoch": 1.3,
	"learning_rate": 0.00022799999999999999,
	"loss": NaN,
	"step": 200
	},
	{
	"epoch": 1.36,
	"learning_rate": 0.000224,
	"loss": NaN,
	"step": 210
	},
	{
	"epoch": 1.43,
	"learning_rate": 0.00021999999999999995,
	"loss": NaN,
	"step": 220
	},
	{
	"epoch": 1.49,
	"learning_rate": 0.00021599999999999996,
	"loss": NaN,
	"step": 230
	},
	{
	"epoch": 1.56,
	"learning_rate": 0.00021199999999999998,
	"loss": NaN,
	"step": 240
	},
	{
	"epoch": 1.62,
	"learning_rate": 0.000208,
	"loss": NaN,
	"step": 250
	},
	{
	"epoch": 1.69,
	"learning_rate": 0.000204,
	"loss": NaN,
	"step": 260
	},
	{
	"epoch": 1.75,
	"learning_rate": 0.00019999999999999998,
	"loss": NaN,
	"step": 270
	},
	{
	"epoch": 1.82,
	"learning_rate": 0.00019599999999999997,
	"loss": NaN,
	"step": 280
	},
	{
	"epoch": 1.88,
	"learning_rate": 0.00019199999999999998,
	"loss": NaN,
	"step": 290
	},
	{
	"epoch": 1.94,
	"learning_rate": 0.000188,
	"loss": NaN,
	"step": 300
	},
	{
	"epoch": 2.0,
	"eval_loss": Infinity,
	"eval_runtime": 374.8395,
	"eval_samples_per_second": 5.312,
	"eval_wer": 1.0,
	"step": 308
	},
	{
	"epoch": 2.01,
	"learning_rate": 0.00018399999999999997,
	"loss": NaN,
	"step": 310
	},
	{
	"epoch": 2.08,
	"learning_rate": 0.00017999999999999998,
	"loss": NaN,
	"step": 320
	},
	{
	"epoch": 2.14,
	"learning_rate": 0.000176,
	"loss": NaN,
	"step": 330
	},
	{
	"epoch": 2.21,
	"learning_rate": 0.000172,
	"loss": NaN,
	"step": 340
	},
	{
	"epoch": 2.27,
	"learning_rate": 0.000168,
	"loss": NaN,
	"step": 350
	},
	{
	"epoch": 2.34,
	"learning_rate": 0.00016399999999999997,
	"loss": NaN,
	"step": 360
	},
	{
	"epoch": 2.4,
	"learning_rate": 0.00015999999999999999,
	"loss": NaN,
	"step": 370
	},
	{
	"epoch": 2.47,
	"learning_rate": 0.000156,
	"loss": NaN,
	"step": 380
	},
	{
	"epoch": 2.53,
	"learning_rate": 0.000152,
	"loss": NaN,
	"step": 390
	},
	{
	"epoch": 2.6,
	"learning_rate": 0.000148,
	"loss": NaN,
	"step": 400
	},
	{
	"epoch": 2.66,
	"learning_rate": 0.00014399999999999998,
	"loss": NaN,
	"step": 410
	},
	{
	"epoch": 2.72,
	"learning_rate": 0.00014,
	"loss": NaN,
	"step": 420
	},
	{
	"epoch": 2.79,
	"learning_rate": 0.00013599999999999997,
	"loss": NaN,
	"step": 430
	},
	{
	"epoch": 2.85,
	"learning_rate": 0.00013199999999999998,
	"loss": NaN,
	"step": 440
	},
	{
	"epoch": 2.92,
	"learning_rate": 0.000128,
	"loss": NaN,
	"step": 450
	},
	{
	"epoch": 2.98,
	"learning_rate": 0.00012399999999999998,
	"loss": NaN,
	"step": 460
	},
	{
	"epoch": 3.0,
	"eval_loss": Infinity,
	"eval_runtime": 334.0794,
	"eval_samples_per_second": 5.96,
	"eval_wer": 1.0,
	"step": 462
	}
	],
	"max_steps": 770,
	"num_train_epochs": 5,
	"total_flos": 1.7250623020466376e+18,
	"trial_name": null,
	"trial_params": null
	}