| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.7084282460136673, | |
| "eval_steps": 200, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11389521640091116, | |
| "eval_loss": 0.7147656679153442, | |
| "eval_runtime": 189.2611, | |
| "eval_samples_per_second": 37.102, | |
| "eval_steps_per_second": 0.581, | |
| "eval_wer": 0.46031703849373495, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.22779043280182232, | |
| "eval_loss": 0.6810471415519714, | |
| "eval_runtime": 189.9773, | |
| "eval_samples_per_second": 36.962, | |
| "eval_steps_per_second": 0.579, | |
| "eval_wer": 0.4794509626755604, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2847380410022779, | |
| "grad_norm": 3.062281370162964, | |
| "learning_rate": 0.0002781111111111111, | |
| "loss": 1.4735, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3416856492027335, | |
| "eval_loss": 0.6035017371177673, | |
| "eval_runtime": 190.2908, | |
| "eval_samples_per_second": 36.901, | |
| "eval_steps_per_second": 0.578, | |
| "eval_wer": 0.4485975099323669, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.45558086560364464, | |
| "eval_loss": 0.6222513914108276, | |
| "eval_runtime": 191.1122, | |
| "eval_samples_per_second": 36.743, | |
| "eval_steps_per_second": 0.576, | |
| "eval_wer": 0.5104638647869357, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5694760820045558, | |
| "grad_norm": 3.101222515106201, | |
| "learning_rate": 0.00022266666666666664, | |
| "loss": 0.7681, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5694760820045558, | |
| "eval_loss": 0.5656484365463257, | |
| "eval_runtime": 192.373, | |
| "eval_samples_per_second": 36.502, | |
| "eval_steps_per_second": 0.572, | |
| "eval_wer": 0.4336225567706188, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.683371298405467, | |
| "eval_loss": 0.5275253057479858, | |
| "eval_runtime": 193.09, | |
| "eval_samples_per_second": 36.366, | |
| "eval_steps_per_second": 0.57, | |
| "eval_wer": 0.4008291367145458, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.7972665148063781, | |
| "eval_loss": 0.5284231305122375, | |
| "eval_runtime": 193.9644, | |
| "eval_samples_per_second": 36.203, | |
| "eval_steps_per_second": 0.567, | |
| "eval_wer": 0.40279567892212226, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.8542141230068337, | |
| "grad_norm": 6.068333148956299, | |
| "learning_rate": 0.00016744444444444443, | |
| "loss": 0.7159, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.9111617312072893, | |
| "eval_loss": 0.4989575147628784, | |
| "eval_runtime": 194.0102, | |
| "eval_samples_per_second": 36.194, | |
| "eval_steps_per_second": 0.567, | |
| "eval_wer": 0.39135518675507247, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.0250569476082005, | |
| "eval_loss": 0.4855109453201294, | |
| "eval_runtime": 193.5264, | |
| "eval_samples_per_second": 36.284, | |
| "eval_steps_per_second": 0.568, | |
| "eval_wer": 0.37300522196680796, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.1389521640091116, | |
| "grad_norm": 2.826504707336426, | |
| "learning_rate": 0.0001121111111111111, | |
| "loss": 0.6203, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.1389521640091116, | |
| "eval_loss": 0.47395312786102295, | |
| "eval_runtime": 193.5198, | |
| "eval_samples_per_second": 36.286, | |
| "eval_steps_per_second": 0.568, | |
| "eval_wer": 0.3622822519565766, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.2528473804100229, | |
| "eval_loss": 0.45885559916496277, | |
| "eval_runtime": 194.4002, | |
| "eval_samples_per_second": 36.121, | |
| "eval_steps_per_second": 0.566, | |
| "eval_wer": 0.3536454111800582, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.366742596810934, | |
| "eval_loss": 0.4538777470588684, | |
| "eval_runtime": 194.3098, | |
| "eval_samples_per_second": 36.138, | |
| "eval_steps_per_second": 0.566, | |
| "eval_wer": 0.34074329980467455, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.4236902050113895, | |
| "grad_norm": 1.8585691452026367, | |
| "learning_rate": 5.666666666666666e-05, | |
| "loss": 0.5447, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.4806378132118452, | |
| "eval_loss": 0.4409582316875458, | |
| "eval_runtime": 193.3591, | |
| "eval_samples_per_second": 36.316, | |
| "eval_steps_per_second": 0.569, | |
| "eval_wer": 0.3357339321542938, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.5945330296127562, | |
| "eval_loss": 0.43471136689186096, | |
| "eval_runtime": 193.3767, | |
| "eval_samples_per_second": 36.313, | |
| "eval_steps_per_second": 0.569, | |
| "eval_wer": 0.3293426699796702, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.7084282460136673, | |
| "grad_norm": 1.961743712425232, | |
| "learning_rate": 1.222222222222222e-06, | |
| "loss": 0.5392, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.7084282460136673, | |
| "eval_loss": 0.4313787817955017, | |
| "eval_runtime": 192.9526, | |
| "eval_samples_per_second": 36.392, | |
| "eval_steps_per_second": 0.57, | |
| "eval_wer": 0.3285321356914123, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.7084282460136673, | |
| "step": 3000, | |
| "total_flos": 5.591115044514249e+18, | |
| "train_loss": 0.7769642333984375, | |
| "train_runtime": 4540.3637, | |
| "train_samples_per_second": 10.572, | |
| "train_steps_per_second": 0.661 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.591115044514249e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |