| { |
| "best_global_step": 600, |
| "best_metric": 0.45842912793159485, |
| "best_model_checkpoint": "./speecht5_finetuned_Darija/checkpoint-600", |
| "epoch": 1.6724799441925358, |
| "eval_steps": 100, |
| "global_step": 600, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.06975933031042902, |
| "grad_norm": 4.014983654022217, |
| "learning_rate": 2.4e-05, |
| "loss": 1.2037, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.13951866062085805, |
| "grad_norm": 4.588967800140381, |
| "learning_rate": 4.8e-05, |
| "loss": 0.8946, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.20927799093128707, |
| "grad_norm": 4.026744842529297, |
| "learning_rate": 7.3e-05, |
| "loss": 0.6685, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.2790373212417161, |
| "grad_norm": 3.659444808959961, |
| "learning_rate": 9.8e-05, |
| "loss": 0.6168, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.2790373212417161, |
| "eval_loss": 0.5272690057754517, |
| "eval_runtime": 41.6965, |
| "eval_samples_per_second": 30.578, |
| "eval_steps_per_second": 15.301, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.3487966515521451, |
| "grad_norm": 6.453115940093994, |
| "learning_rate": 9.878947368421053e-05, |
| "loss": 0.5847, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.41855598186257414, |
| "grad_norm": 3.9114222526550293, |
| "learning_rate": 9.747368421052632e-05, |
| "loss": 0.5667, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.4883153121730031, |
| "grad_norm": 5.056523323059082, |
| "learning_rate": 9.615789473684212e-05, |
| "loss": 0.5662, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.5580746424834322, |
| "grad_norm": 5.494399070739746, |
| "learning_rate": 9.48421052631579e-05, |
| "loss": 0.5699, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5580746424834322, |
| "eval_loss": 0.5231854915618896, |
| "eval_runtime": 37.0744, |
| "eval_samples_per_second": 34.39, |
| "eval_steps_per_second": 17.209, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.6278339727938612, |
| "grad_norm": 2.748530864715576, |
| "learning_rate": 9.352631578947368e-05, |
| "loss": 0.5448, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.6975933031042902, |
| "grad_norm": 3.9691007137298584, |
| "learning_rate": 9.221052631578948e-05, |
| "loss": 0.5358, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.7673526334147193, |
| "grad_norm": 3.5358879566192627, |
| "learning_rate": 9.089473684210526e-05, |
| "loss": 0.5245, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.8371119637251483, |
| "grad_norm": 2.21895432472229, |
| "learning_rate": 8.957894736842106e-05, |
| "loss": 0.5231, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.8371119637251483, |
| "eval_loss": 0.47762706875801086, |
| "eval_runtime": 36.3582, |
| "eval_samples_per_second": 35.068, |
| "eval_steps_per_second": 17.548, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.9068712940355773, |
| "grad_norm": 3.315195322036743, |
| "learning_rate": 8.826315789473684e-05, |
| "loss": 0.5349, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.9766306243460062, |
| "grad_norm": 2.936798572540283, |
| "learning_rate": 8.694736842105264e-05, |
| "loss": 0.5248, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.0446459713986747, |
| "grad_norm": 2.950599431991577, |
| "learning_rate": 8.563157894736843e-05, |
| "loss": 0.5101, |
| "step": 375 |
| }, |
| { |
| "epoch": 1.1144053017091036, |
| "grad_norm": 4.972070693969727, |
| "learning_rate": 8.431578947368422e-05, |
| "loss": 0.515, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.1144053017091036, |
| "eval_loss": 0.49294987320899963, |
| "eval_runtime": 35.8818, |
| "eval_samples_per_second": 35.533, |
| "eval_steps_per_second": 17.781, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.1841646320195327, |
| "grad_norm": 2.6673648357391357, |
| "learning_rate": 8.3e-05, |
| "loss": 0.5115, |
| "step": 425 |
| }, |
| { |
| "epoch": 1.2539239623299616, |
| "grad_norm": 3.388873338699341, |
| "learning_rate": 8.16842105263158e-05, |
| "loss": 0.5064, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.3236832926403905, |
| "grad_norm": 2.4961979389190674, |
| "learning_rate": 8.036842105263158e-05, |
| "loss": 0.5028, |
| "step": 475 |
| }, |
| { |
| "epoch": 1.3934426229508197, |
| "grad_norm": 2.7970707416534424, |
| "learning_rate": 7.905263157894737e-05, |
| "loss": 0.4975, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.3934426229508197, |
| "eval_loss": 0.4633351266384125, |
| "eval_runtime": 36.5245, |
| "eval_samples_per_second": 34.908, |
| "eval_steps_per_second": 17.468, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.4632019532612488, |
| "grad_norm": 2.774756908416748, |
| "learning_rate": 7.773684210526317e-05, |
| "loss": 0.498, |
| "step": 525 |
| }, |
| { |
| "epoch": 1.5329612835716777, |
| "grad_norm": 5.114898204803467, |
| "learning_rate": 7.642105263157895e-05, |
| "loss": 0.4974, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.6027206138821066, |
| "grad_norm": 3.1757712364196777, |
| "learning_rate": 7.510526315789475e-05, |
| "loss": 0.5068, |
| "step": 575 |
| }, |
| { |
| "epoch": 1.6724799441925358, |
| "grad_norm": 2.1318249702453613, |
| "learning_rate": 7.378947368421053e-05, |
| "loss": 0.5003, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.6724799441925358, |
| "eval_loss": 0.45842912793159485, |
| "eval_runtime": 36.8677, |
| "eval_samples_per_second": 34.583, |
| "eval_steps_per_second": 17.305, |
| "step": 600 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 2000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 739768973036544.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
