whisper-large-v2-sw / trainer_state.json
hedronstone's picture
Upload . with huggingface_hub
c6d929c
raw
history blame
5.3 kB
{
"best_metric": 19.88708733519226,
"best_model_checkpoint": "./whisper-large-v2/checkpoint-1000",
"epoch": 0.25,
"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": 5.5e-07,
"loss": 2.0915,
"step": 25
},
{
"epoch": 0.01,
"learning_rate": 1.175e-06,
"loss": 1.47,
"step": 50
},
{
"epoch": 0.02,
"learning_rate": 1.8000000000000001e-06,
"loss": 1.09,
"step": 75
},
{
"epoch": 0.03,
"learning_rate": 2.425e-06,
"loss": 0.8603,
"step": 100
},
{
"epoch": 0.03,
"learning_rate": 3.0250000000000003e-06,
"loss": 0.5765,
"step": 125
},
{
"epoch": 0.04,
"learning_rate": 3.65e-06,
"loss": 0.4856,
"step": 150
},
{
"epoch": 0.04,
"learning_rate": 4.2750000000000006e-06,
"loss": 0.4594,
"step": 175
},
{
"epoch": 0.05,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.3423,
"step": 200
},
{
"epoch": 0.06,
"learning_rate": 5.5250000000000005e-06,
"loss": 0.2955,
"step": 225
},
{
"epoch": 0.06,
"learning_rate": 6.15e-06,
"loss": 0.2672,
"step": 250
},
{
"epoch": 0.07,
"learning_rate": 6.775e-06,
"loss": 0.2566,
"step": 275
},
{
"epoch": 0.07,
"learning_rate": 7.4e-06,
"loss": 0.2563,
"step": 300
},
{
"epoch": 0.08,
"learning_rate": 8.025e-06,
"loss": 0.2199,
"step": 325
},
{
"epoch": 0.09,
"learning_rate": 8.65e-06,
"loss": 0.1805,
"step": 350
},
{
"epoch": 0.09,
"learning_rate": 9.275e-06,
"loss": 0.1754,
"step": 375
},
{
"epoch": 0.1,
"learning_rate": 9.875000000000001e-06,
"loss": 0.1923,
"step": 400
},
{
"epoch": 0.11,
"learning_rate": 9.944444444444445e-06,
"loss": 0.1952,
"step": 425
},
{
"epoch": 0.11,
"learning_rate": 9.875000000000001e-06,
"loss": 0.1653,
"step": 450
},
{
"epoch": 0.12,
"learning_rate": 9.805555555555556e-06,
"loss": 0.1427,
"step": 475
},
{
"epoch": 0.12,
"learning_rate": 9.736111111111112e-06,
"loss": 0.147,
"step": 500
},
{
"epoch": 0.13,
"learning_rate": 9.666666666666667e-06,
"loss": 0.1091,
"step": 525
},
{
"epoch": 0.14,
"learning_rate": 9.597222222222223e-06,
"loss": 0.107,
"step": 550
},
{
"epoch": 0.14,
"learning_rate": 9.527777777777778e-06,
"loss": 0.1275,
"step": 575
},
{
"epoch": 0.15,
"learning_rate": 9.458333333333334e-06,
"loss": 0.1432,
"step": 600
},
{
"epoch": 0.16,
"learning_rate": 9.38888888888889e-06,
"loss": 0.1279,
"step": 625
},
{
"epoch": 0.16,
"learning_rate": 9.319444444444445e-06,
"loss": 0.1465,
"step": 650
},
{
"epoch": 0.17,
"learning_rate": 9.250000000000001e-06,
"loss": 0.1543,
"step": 675
},
{
"epoch": 0.17,
"learning_rate": 9.180555555555556e-06,
"loss": 0.1415,
"step": 700
},
{
"epoch": 0.18,
"learning_rate": 9.111111111111112e-06,
"loss": 0.1284,
"step": 725
},
{
"epoch": 0.19,
"learning_rate": 9.041666666666667e-06,
"loss": 0.106,
"step": 750
},
{
"epoch": 0.19,
"learning_rate": 8.972222222222223e-06,
"loss": 0.0976,
"step": 775
},
{
"epoch": 0.2,
"learning_rate": 8.902777777777778e-06,
"loss": 0.077,
"step": 800
},
{
"epoch": 0.21,
"learning_rate": 8.833333333333334e-06,
"loss": 0.0941,
"step": 825
},
{
"epoch": 0.21,
"learning_rate": 8.76388888888889e-06,
"loss": 0.0927,
"step": 850
},
{
"epoch": 0.22,
"learning_rate": 8.694444444444445e-06,
"loss": 0.0863,
"step": 875
},
{
"epoch": 0.23,
"learning_rate": 8.625000000000001e-06,
"loss": 0.083,
"step": 900
},
{
"epoch": 0.23,
"learning_rate": 8.555555555555556e-06,
"loss": 0.092,
"step": 925
},
{
"epoch": 0.24,
"learning_rate": 8.486111111111112e-06,
"loss": 0.1108,
"step": 950
},
{
"epoch": 0.24,
"learning_rate": 8.416666666666667e-06,
"loss": 0.1034,
"step": 975
},
{
"epoch": 0.25,
"learning_rate": 8.35e-06,
"loss": 0.082,
"step": 1000
},
{
"epoch": 0.25,
"eval_loss": 0.3526313006877899,
"eval_runtime": 12784.9506,
"eval_samples_per_second": 0.801,
"eval_steps_per_second": 0.1,
"eval_wer": 19.88708733519226,
"step": 1000
}
],
"max_steps": 4000,
"num_train_epochs": 9223372036854775807,
"total_flos": 6.79414726656e+19,
"trial_name": null,
"trial_params": null
}