| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1088139281828074, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000544069640914037, | |
| "eval_loss": 0.22625693678855896, | |
| "eval_runtime": 24.4291, | |
| "eval_samples_per_second": 15.842, | |
| "eval_steps_per_second": 7.941, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00544069640914037, | |
| "grad_norm": 0.32291528582572937, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3295, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01088139281828074, | |
| "grad_norm": 0.2552948594093323, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2325, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01632208922742111, | |
| "grad_norm": 0.2857631742954254, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2269, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02176278563656148, | |
| "grad_norm": 0.22182883322238922, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1901, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02720348204570185, | |
| "grad_norm": 0.3137857913970947, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1887, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02720348204570185, | |
| "eval_loss": 0.10863105207681656, | |
| "eval_runtime": 24.3415, | |
| "eval_samples_per_second": 15.899, | |
| "eval_steps_per_second": 7.97, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03264417845484222, | |
| "grad_norm": 0.8275140523910522, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2106, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03808487486398259, | |
| "grad_norm": 0.3336808681488037, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1991, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04352557127312296, | |
| "grad_norm": 0.3360205888748169, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2231, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04896626768226333, | |
| "grad_norm": 0.13263827562332153, | |
| "learning_rate": 0.0002, | |
| "loss": 0.215, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0544069640914037, | |
| "grad_norm": 0.26391035318374634, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1878, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0544069640914037, | |
| "eval_loss": 0.10204492509365082, | |
| "eval_runtime": 24.3432, | |
| "eval_samples_per_second": 15.898, | |
| "eval_steps_per_second": 7.969, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05984766050054407, | |
| "grad_norm": 0.21117790043354034, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2473, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.06528835690968444, | |
| "grad_norm": 0.4645533859729767, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1634, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.07072905331882481, | |
| "grad_norm": 0.18397293984889984, | |
| "learning_rate": 0.0002, | |
| "loss": 0.16, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.07616974972796518, | |
| "grad_norm": 0.3006034195423126, | |
| "learning_rate": 0.0002, | |
| "loss": 0.198, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.08161044613710555, | |
| "grad_norm": 0.32205018401145935, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2153, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.08161044613710555, | |
| "eval_loss": 0.09607148170471191, | |
| "eval_runtime": 24.3523, | |
| "eval_samples_per_second": 15.892, | |
| "eval_steps_per_second": 7.966, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.08705114254624592, | |
| "grad_norm": 0.4278263449668884, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1737, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.09249183895538629, | |
| "grad_norm": 0.9995900988578796, | |
| "learning_rate": 0.0002, | |
| "loss": 0.231, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.09793253536452666, | |
| "grad_norm": 0.1793416291475296, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2015, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.10337323177366703, | |
| "grad_norm": 0.8814968466758728, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1999, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.1088139281828074, | |
| "grad_norm": 0.2865917682647705, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2293, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1088139281828074, | |
| "eval_loss": 0.09589679539203644, | |
| "eval_runtime": 24.4054, | |
| "eval_samples_per_second": 15.857, | |
| "eval_steps_per_second": 7.949, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.044558460734669e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |