| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.038910505836575876, | |
| "eval_steps": 2, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0019455252918287938, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019455252918287938, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.4849, | |
| "eval_samples_per_second": 25.575, | |
| "eval_steps_per_second": 12.846, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0038910505836575876, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0038910505836575876, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.4064, | |
| "eval_samples_per_second": 29.299, | |
| "eval_steps_per_second": 14.717, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005836575875486381, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007782101167315175, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007782101167315175, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.7547, | |
| "eval_samples_per_second": 27.983, | |
| "eval_steps_per_second": 14.056, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009727626459143969, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011673151750972763, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011673151750972763, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.6089, | |
| "eval_samples_per_second": 28.519, | |
| "eval_steps_per_second": 14.325, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013618677042801557, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01556420233463035, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01556420233463035, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.6002, | |
| "eval_samples_per_second": 28.552, | |
| "eval_steps_per_second": 14.342, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.017509727626459144, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.019455252918287938, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.019455252918287938, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5406, | |
| "eval_samples_per_second": 28.778, | |
| "eval_steps_per_second": 14.455, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021400778210116732, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.023346303501945526, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.023346303501945526, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5949, | |
| "eval_samples_per_second": 28.572, | |
| "eval_steps_per_second": 14.352, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02529182879377432, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.027237354085603113, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.027237354085603113, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.555, | |
| "eval_samples_per_second": 28.723, | |
| "eval_steps_per_second": 14.427, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.029182879377431907, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0311284046692607, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0311284046692607, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.491, | |
| "eval_samples_per_second": 28.968, | |
| "eval_steps_per_second": 14.551, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.033073929961089495, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03501945525291829, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03501945525291829, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5868, | |
| "eval_samples_per_second": 28.602, | |
| "eval_steps_per_second": 14.367, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03696498054474708, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.038910505836575876, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.038910505836575876, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5723, | |
| "eval_samples_per_second": 28.657, | |
| "eval_steps_per_second": 14.395, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1029368772034560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |