| { | |
| "best_metric": 0.01786634884774685, | |
| "best_model_checkpoint": "verbnet_train_derived/checkpoint-1318125", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 1318125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.0011935352813452482, | |
| "learning_rate": 1.9600150213371268e-05, | |
| "loss": 0.237, | |
| "step": 263625 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.0812821313738823, | |
| "eval_runtime": 657.1184, | |
| "eval_samples_per_second": 168.919, | |
| "eval_steps_per_second": 21.115, | |
| "step": 263625 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.0008472450426779687, | |
| "learning_rate": 1.9200294357515412e-05, | |
| "loss": 0.0675, | |
| "step": 527250 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.04395299404859543, | |
| "eval_runtime": 635.1223, | |
| "eval_samples_per_second": 174.769, | |
| "eval_steps_per_second": 21.846, | |
| "step": 527250 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.0005161144654266536, | |
| "learning_rate": 1.8800440018966338e-05, | |
| "loss": 0.0402, | |
| "step": 790875 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.03021380864083767, | |
| "eval_runtime": 631.9338, | |
| "eval_samples_per_second": 175.651, | |
| "eval_steps_per_second": 21.956, | |
| "step": 790875 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.3789523109153379e-05, | |
| "learning_rate": 1.8400591749644382e-05, | |
| "loss": 0.0269, | |
| "step": 1054500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.02329804003238678, | |
| "eval_runtime": 635.8959, | |
| "eval_samples_per_second": 174.557, | |
| "eval_steps_per_second": 21.82, | |
| "step": 1054500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 1.8203951185569167e-05, | |
| "learning_rate": 1.8000737411095308e-05, | |
| "loss": 0.019, | |
| "step": 1318125 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.01786634884774685, | |
| "eval_runtime": 635.4082, | |
| "eval_samples_per_second": 174.691, | |
| "eval_steps_per_second": 21.836, | |
| "step": 1318125 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 13181250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.182195585299032e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |