| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0049584727903805624, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004958472790380563, | |
| "grad_norm": 1.354319453239441, | |
| "learning_rate": 2e-05, | |
| "loss": 44.5007, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004958472790380563, | |
| "eval_loss": 11.119476318359375, | |
| "eval_runtime": 13.8265, | |
| "eval_samples_per_second": 61.476, | |
| "eval_steps_per_second": 30.738, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009916945580761127, | |
| "grad_norm": 1.1608377695083618, | |
| "learning_rate": 4e-05, | |
| "loss": 44.4894, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014875418371141688, | |
| "grad_norm": 1.5842955112457275, | |
| "learning_rate": 6e-05, | |
| "loss": 44.5914, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014875418371141688, | |
| "eval_loss": 11.118513107299805, | |
| "eval_runtime": 14.5565, | |
| "eval_samples_per_second": 58.393, | |
| "eval_steps_per_second": 29.197, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019833891161522253, | |
| "grad_norm": 1.3338695764541626, | |
| "learning_rate": 8e-05, | |
| "loss": 44.5022, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0024792363951902812, | |
| "grad_norm": 1.641688585281372, | |
| "learning_rate": 0.0001, | |
| "loss": 44.3975, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029750836742283376, | |
| "grad_norm": 1.0880950689315796, | |
| "learning_rate": 0.00012, | |
| "loss": 44.4181, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029750836742283376, | |
| "eval_loss": 11.114364624023438, | |
| "eval_runtime": 14.1842, | |
| "eval_samples_per_second": 59.926, | |
| "eval_steps_per_second": 29.963, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003470930953266394, | |
| "grad_norm": 1.3382055759429932, | |
| "learning_rate": 0.00014, | |
| "loss": 44.4795, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003966778232304451, | |
| "grad_norm": 1.4787648916244507, | |
| "learning_rate": 0.00016, | |
| "loss": 44.4646, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004462625511342506, | |
| "grad_norm": 1.4588122367858887, | |
| "learning_rate": 0.00018, | |
| "loss": 44.4685, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004462625511342506, | |
| "eval_loss": 11.106067657470703, | |
| "eval_runtime": 14.2521, | |
| "eval_samples_per_second": 59.641, | |
| "eval_steps_per_second": 29.82, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0049584727903805624, | |
| "grad_norm": 1.0532503128051758, | |
| "learning_rate": 0.0002, | |
| "loss": 44.438, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 831982141440.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |