| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 2000, | |
| "global_step": 1308, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1530221882172915, | |
| "grad_norm": 0.8040502667427063, | |
| "learning_rate": 0.0002994777318812451, | |
| "loss": 7.6443, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.306044376434583, | |
| "grad_norm": 0.835146427154541, | |
| "learning_rate": 0.0002915914482556251, | |
| "loss": 6.0577, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4590665646518745, | |
| "grad_norm": 0.8971789479255676, | |
| "learning_rate": 0.0002746940863458308, | |
| "loss": 5.6654, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.612088752869166, | |
| "grad_norm": 0.7257961630821228, | |
| "learning_rate": 0.0002498610179546161, | |
| "loss": 5.4399, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7651109410864575, | |
| "grad_norm": 0.7543347477912903, | |
| "learning_rate": 0.00021867265437140772, | |
| "loss": 5.26, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.918133129303749, | |
| "grad_norm": 1.0183438062667847, | |
| "learning_rate": 0.00018311386678204316, | |
| "loss": 5.1171, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.0703902065799542, | |
| "grad_norm": 0.5284886956214905, | |
| "learning_rate": 0.00014544766628363064, | |
| "loss": 4.9976, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.2234123947972455, | |
| "grad_norm": 0.5938099026679993, | |
| "learning_rate": 0.00010807118268549186, | |
| "loss": 4.8596, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.376434583014537, | |
| "grad_norm": 0.6171284317970276, | |
| "learning_rate": 7.336310780721984e-05, | |
| "loss": 4.766, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.5294567712318288, | |
| "grad_norm": 0.6369397640228271, | |
| "learning_rate": 4.353231219625363e-05, | |
| "loss": 4.7103, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.68247895944912, | |
| "grad_norm": 0.5873697996139526, | |
| "learning_rate": 2.047726950930969e-05, | |
| "loss": 4.661, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.8355011476664116, | |
| "grad_norm": 0.5919450521469116, | |
| "learning_rate": 5.665234987127964e-06, | |
| "loss": 4.6367, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.9885233358837031, | |
| "grad_norm": 0.6478385925292969, | |
| "learning_rate": 3.8867273797626995e-08, | |
| "loss": 4.6238, | |
| "step": 1300 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1308, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 2000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4801529605750784e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |