| { | |
| "best_metric": 0.7473347783088684, | |
| "best_model_checkpoint": "/scratch/skscla001/speech/results/xls-r-1b-bigcgen-female-5hrs-model/checkpoint-1200", | |
| "epoch": 6.779661016949152, | |
| "eval_steps": 100, | |
| "global_step": 1600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.423728813559322, | |
| "eval_loss": 3.731572389602661, | |
| "eval_runtime": 24.6238, | |
| "eval_samples_per_second": 13.605, | |
| "eval_steps_per_second": 3.411, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.847457627118644, | |
| "eval_loss": 2.833482027053833, | |
| "eval_runtime": 24.2449, | |
| "eval_samples_per_second": 13.817, | |
| "eval_steps_per_second": 3.465, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.271186440677966, | |
| "eval_loss": 2.0309665203094482, | |
| "eval_runtime": 24.3043, | |
| "eval_samples_per_second": 13.784, | |
| "eval_steps_per_second": 3.456, | |
| "eval_wer": 1.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.694915254237288, | |
| "eval_loss": 1.1695457696914673, | |
| "eval_runtime": 24.5393, | |
| "eval_samples_per_second": 13.652, | |
| "eval_steps_per_second": 3.423, | |
| "eval_wer": 0.9975206611570248, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.1186440677966103, | |
| "grad_norm": 5.734997272491455, | |
| "learning_rate": 3e-05, | |
| "loss": 5.5638, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.1186440677966103, | |
| "eval_loss": 1.157854676246643, | |
| "eval_runtime": 25.7403, | |
| "eval_samples_per_second": 13.015, | |
| "eval_steps_per_second": 3.263, | |
| "eval_wer": 0.9917355371900827, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.542372881355932, | |
| "eval_loss": 1.117336392402649, | |
| "eval_runtime": 24.578, | |
| "eval_samples_per_second": 13.63, | |
| "eval_steps_per_second": 3.418, | |
| "eval_wer": 0.9931129476584022, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.9661016949152543, | |
| "eval_loss": 0.9185360074043274, | |
| "eval_runtime": 24.6366, | |
| "eval_samples_per_second": 13.598, | |
| "eval_steps_per_second": 3.41, | |
| "eval_wer": 0.7611570247933884, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.389830508474576, | |
| "eval_loss": 0.8460559248924255, | |
| "eval_runtime": 24.6486, | |
| "eval_samples_per_second": 13.591, | |
| "eval_steps_per_second": 3.408, | |
| "eval_wer": 0.8633608815426997, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.8135593220338984, | |
| "eval_loss": 0.7551252841949463, | |
| "eval_runtime": 24.7997, | |
| "eval_samples_per_second": 13.508, | |
| "eval_steps_per_second": 3.387, | |
| "eval_wer": 0.7391184573002755, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.237288135593221, | |
| "grad_norm": 2.491547107696533, | |
| "learning_rate": 2.7720364741641338e-05, | |
| "loss": 1.2967, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.237288135593221, | |
| "eval_loss": 0.8461477756500244, | |
| "eval_runtime": 24.6325, | |
| "eval_samples_per_second": 13.6, | |
| "eval_steps_per_second": 3.41, | |
| "eval_wer": 0.8179063360881542, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.661016949152542, | |
| "eval_loss": 1.0125970840454102, | |
| "eval_runtime": 24.7518, | |
| "eval_samples_per_second": 13.534, | |
| "eval_steps_per_second": 3.394, | |
| "eval_wer": 0.931129476584022, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 5.084745762711864, | |
| "eval_loss": 0.7473347783088684, | |
| "eval_runtime": 24.5889, | |
| "eval_samples_per_second": 13.624, | |
| "eval_steps_per_second": 3.416, | |
| "eval_wer": 0.7077134986225895, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5.508474576271187, | |
| "eval_loss": 0.7741428017616272, | |
| "eval_runtime": 24.7431, | |
| "eval_samples_per_second": 13.539, | |
| "eval_steps_per_second": 3.395, | |
| "eval_wer": 0.7567493112947659, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5.932203389830509, | |
| "eval_loss": 0.8527082204818726, | |
| "eval_runtime": 24.6476, | |
| "eval_samples_per_second": 13.592, | |
| "eval_steps_per_second": 3.408, | |
| "eval_wer": 0.7520661157024794, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 6.3559322033898304, | |
| "grad_norm": 7.505873203277588, | |
| "learning_rate": 2.5440729483282676e-05, | |
| "loss": 0.8911, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.3559322033898304, | |
| "eval_loss": 0.9528570771217346, | |
| "eval_runtime": 24.4492, | |
| "eval_samples_per_second": 13.702, | |
| "eval_steps_per_second": 3.436, | |
| "eval_wer": 0.8052341597796143, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.779661016949152, | |
| "eval_loss": 1.0234959125518799, | |
| "eval_runtime": 24.4889, | |
| "eval_samples_per_second": 13.68, | |
| "eval_steps_per_second": 3.43, | |
| "eval_wer": 0.8308539944903581, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6.779661016949152, | |
| "step": 1600, | |
| "total_flos": 9.408039870276794e+18, | |
| "train_loss": 2.461955771446228, | |
| "train_runtime": 2270.622, | |
| "train_samples_per_second": 24.931, | |
| "train_steps_per_second": 3.118 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 7080, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 400, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 4, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 4 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.408039870276794e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |