| { | |
| "best_metric": 0.6607086658477783, | |
| "best_model_checkpoint": "verbnet_train/checkpoint-114510", | |
| "epoch": 15.0, | |
| "eval_steps": 500, | |
| "global_step": 156150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 13.90185260772705, | |
| "learning_rate": 1.960034582132565e-05, | |
| "loss": 1.9688, | |
| "step": 10410 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.0218104124069214, | |
| "eval_runtime": 27.1535, | |
| "eval_samples_per_second": 161.453, | |
| "eval_steps_per_second": 20.182, | |
| "step": 10410 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 35.40193176269531, | |
| "learning_rate": 1.9200499519692607e-05, | |
| "loss": 0.9642, | |
| "step": 20820 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.8278869986534119, | |
| "eval_runtime": 27.1826, | |
| "eval_samples_per_second": 161.28, | |
| "eval_steps_per_second": 20.16, | |
| "step": 20820 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.9018324613571167, | |
| "learning_rate": 1.8800653218059558e-05, | |
| "loss": 0.7979, | |
| "step": 31230 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.7543942928314209, | |
| "eval_runtime": 27.2955, | |
| "eval_samples_per_second": 160.612, | |
| "eval_steps_per_second": 20.077, | |
| "step": 31230 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 10.808300018310547, | |
| "learning_rate": 1.840073006724304e-05, | |
| "loss": 0.7172, | |
| "step": 41640 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.7305750250816345, | |
| "eval_runtime": 27.2998, | |
| "eval_samples_per_second": 160.587, | |
| "eval_steps_per_second": 20.073, | |
| "step": 41640 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 2.197155714035034, | |
| "learning_rate": 1.8000922190201732e-05, | |
| "loss": 0.6632, | |
| "step": 52050 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.7061994671821594, | |
| "eval_runtime": 27.2802, | |
| "eval_samples_per_second": 160.703, | |
| "eval_steps_per_second": 20.088, | |
| "step": 52050 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 6.914452075958252, | |
| "learning_rate": 1.7601075888568687e-05, | |
| "loss": 0.6295, | |
| "step": 62460 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.6925345659255981, | |
| "eval_runtime": 27.2037, | |
| "eval_samples_per_second": 161.154, | |
| "eval_steps_per_second": 20.144, | |
| "step": 62460 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.11944844573736191, | |
| "learning_rate": 1.720126801152738e-05, | |
| "loss": 0.5954, | |
| "step": 72870 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.6798752546310425, | |
| "eval_runtime": 27.2603, | |
| "eval_samples_per_second": 160.82, | |
| "eval_steps_per_second": 20.103, | |
| "step": 72870 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 10.490527153015137, | |
| "learning_rate": 1.6801383285302596e-05, | |
| "loss": 0.5732, | |
| "step": 83280 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.6673381924629211, | |
| "eval_runtime": 27.2557, | |
| "eval_samples_per_second": 160.847, | |
| "eval_steps_per_second": 20.106, | |
| "step": 83280 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 3.331533193588257, | |
| "learning_rate": 1.6401498559077812e-05, | |
| "loss": 0.5513, | |
| "step": 93690 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.6665173172950745, | |
| "eval_runtime": 27.2846, | |
| "eval_samples_per_second": 160.677, | |
| "eval_steps_per_second": 20.085, | |
| "step": 93690 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 10.890799522399902, | |
| "learning_rate": 1.6001613832853028e-05, | |
| "loss": 0.529, | |
| "step": 104100 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.6729404330253601, | |
| "eval_runtime": 27.2246, | |
| "eval_samples_per_second": 161.031, | |
| "eval_steps_per_second": 20.129, | |
| "step": 104100 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 2.3458809852600098, | |
| "learning_rate": 1.5601729106628244e-05, | |
| "loss": 0.5073, | |
| "step": 114510 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.6607086658477783, | |
| "eval_runtime": 27.203, | |
| "eval_samples_per_second": 161.158, | |
| "eval_steps_per_second": 20.145, | |
| "step": 114510 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 0.09025446325540543, | |
| "learning_rate": 1.5201844380403458e-05, | |
| "loss": 0.4939, | |
| "step": 124920 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.6753981113433838, | |
| "eval_runtime": 27.427, | |
| "eval_samples_per_second": 159.842, | |
| "eval_steps_per_second": 19.98, | |
| "step": 124920 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "grad_norm": 8.285615921020508, | |
| "learning_rate": 1.4802036503362153e-05, | |
| "loss": 0.4811, | |
| "step": 135330 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.6707017421722412, | |
| "eval_runtime": 27.4264, | |
| "eval_samples_per_second": 159.846, | |
| "eval_steps_per_second": 19.981, | |
| "step": 135330 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 0.5379312038421631, | |
| "learning_rate": 1.4402190201729108e-05, | |
| "loss": 0.4651, | |
| "step": 145740 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.6765126585960388, | |
| "eval_runtime": 27.3154, | |
| "eval_samples_per_second": 160.495, | |
| "eval_steps_per_second": 20.062, | |
| "step": 145740 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "grad_norm": 7.105310440063477, | |
| "learning_rate": 1.4002343900096062e-05, | |
| "loss": 0.4549, | |
| "step": 156150 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.6791203618049622, | |
| "eval_runtime": 27.2812, | |
| "eval_samples_per_second": 160.697, | |
| "eval_steps_per_second": 20.087, | |
| "step": 156150 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 520500, | |
| "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": 1.386785489977536e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |