| { | |
| "best_metric": 47.521028231962916, | |
| "best_model_checkpoint": "./whisper-small-Persian/checkpoint-1000", | |
| "epoch": 3.1150855365474337, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.4e-08, | |
| "loss": 1.4232, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.4e-08, | |
| "loss": 1.4027, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.44e-07, | |
| "loss": 1.3731, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.94e-07, | |
| "loss": 1.2969, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.4399999999999996e-07, | |
| "loss": 1.1964, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.9399999999999996e-07, | |
| "loss": 1.0995, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 3.4399999999999996e-07, | |
| "loss": 1.0068, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.94e-07, | |
| "loss": 0.8949, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.44e-07, | |
| "loss": 0.8521, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.94e-07, | |
| "loss": 0.7694, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 5.44e-07, | |
| "loss": 0.7196, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 5.939999999999999e-07, | |
| "loss": 0.6902, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 6.44e-07, | |
| "loss": 0.6748, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 6.939999999999999e-07, | |
| "loss": 0.6247, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 7.44e-07, | |
| "loss": 0.63, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 7.94e-07, | |
| "loss": 0.5899, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 8.439999999999999e-07, | |
| "loss": 0.5628, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 8.939999999999999e-07, | |
| "loss": 0.5634, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 9.439999999999999e-07, | |
| "loss": 0.5549, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 9.94e-07, | |
| "loss": 0.5533, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 0.7044046521186829, | |
| "eval_runtime": 1265.1903, | |
| "eval_samples_per_second": 8.132, | |
| "eval_steps_per_second": 0.127, | |
| "eval_wer": 54.54987091580379, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.95111111111111e-07, | |
| "loss": 0.5329, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 9.895555555555554e-07, | |
| "loss": 0.5116, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 9.84e-07, | |
| "loss": 0.511, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 9.784444444444444e-07, | |
| "loss": 0.4963, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 9.728888888888888e-07, | |
| "loss": 0.5177, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.673333333333332e-07, | |
| "loss": 0.4947, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.617777777777776e-07, | |
| "loss": 0.4529, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 9.562222222222223e-07, | |
| "loss": 0.4543, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 9.506666666666667e-07, | |
| "loss": 0.4478, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 9.451111111111111e-07, | |
| "loss": 0.4421, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.395555555555556e-07, | |
| "loss": 0.4465, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 9.34e-07, | |
| "loss": 0.4164, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 9.284444444444444e-07, | |
| "loss": 0.4291, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 9.228888888888888e-07, | |
| "loss": 0.4149, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 9.173333333333333e-07, | |
| "loss": 0.4242, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 9.117777777777778e-07, | |
| "loss": 0.4329, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 9.062222222222222e-07, | |
| "loss": 0.4165, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 9.006666666666666e-07, | |
| "loss": 0.4166, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 8.95111111111111e-07, | |
| "loss": 0.409, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 8.895555555555555e-07, | |
| "loss": 0.3951, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "eval_loss": 0.5893104076385498, | |
| "eval_runtime": 1326.5175, | |
| "eval_samples_per_second": 7.756, | |
| "eval_steps_per_second": 0.121, | |
| "eval_wer": 47.521028231962916, | |
| "step": 1000 | |
| } | |
| ], | |
| "max_steps": 5000, | |
| "num_train_epochs": 16, | |
| "total_flos": 1.849716994470209e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |