| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03040091202736082, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015200456013680411, | |
| "grad_norm": 4.591590404510498, | |
| "learning_rate": 1e-05, | |
| "loss": 177.75, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015200456013680411, | |
| "eval_loss": 11.114282608032227, | |
| "eval_runtime": 19.3598, | |
| "eval_samples_per_second": 57.232, | |
| "eval_steps_per_second": 28.616, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0030400912027360822, | |
| "grad_norm": 4.531345367431641, | |
| "learning_rate": 2e-05, | |
| "loss": 177.8125, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004560136804104123, | |
| "grad_norm": 4.347599983215332, | |
| "learning_rate": 3e-05, | |
| "loss": 177.5625, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0060801824054721645, | |
| "grad_norm": 4.609200477600098, | |
| "learning_rate": 4e-05, | |
| "loss": 177.75, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007600228006840205, | |
| "grad_norm": 4.364078521728516, | |
| "learning_rate": 5e-05, | |
| "loss": 177.875, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007600228006840205, | |
| "eval_loss": 11.11292839050293, | |
| "eval_runtime": 1.42, | |
| "eval_samples_per_second": 780.292, | |
| "eval_steps_per_second": 390.146, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009120273608208246, | |
| "grad_norm": 4.674941539764404, | |
| "learning_rate": 6e-05, | |
| "loss": 177.6875, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010640319209576287, | |
| "grad_norm": 4.507266998291016, | |
| "learning_rate": 7e-05, | |
| "loss": 177.8125, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012160364810944329, | |
| "grad_norm": 4.671020030975342, | |
| "learning_rate": 8e-05, | |
| "loss": 178.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013680410412312369, | |
| "grad_norm": 4.70671272277832, | |
| "learning_rate": 9e-05, | |
| "loss": 177.875, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01520045601368041, | |
| "grad_norm": 4.528318405151367, | |
| "learning_rate": 0.0001, | |
| "loss": 177.8125, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01520045601368041, | |
| "eval_loss": 11.104805946350098, | |
| "eval_runtime": 1.4199, | |
| "eval_samples_per_second": 780.319, | |
| "eval_steps_per_second": 390.159, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016720501615048452, | |
| "grad_norm": 5.062138557434082, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 177.625, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01824054721641649, | |
| "grad_norm": 4.429068565368652, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 177.75, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.019760592817784535, | |
| "grad_norm": 4.724205017089844, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 177.5, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.021280638419152575, | |
| "grad_norm": 5.304701328277588, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 177.4375, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.022800684020520615, | |
| "grad_norm": 5.0064005851745605, | |
| "learning_rate": 5e-05, | |
| "loss": 177.25, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.022800684020520615, | |
| "eval_loss": 11.090591430664062, | |
| "eval_runtime": 1.464, | |
| "eval_samples_per_second": 756.813, | |
| "eval_steps_per_second": 378.406, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.024320729621888658, | |
| "grad_norm": 5.064575672149658, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 177.4375, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.025840775223256698, | |
| "grad_norm": 4.720963478088379, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 177.5625, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.027360820824624738, | |
| "grad_norm": 4.923408031463623, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 177.8125, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02888086642599278, | |
| "grad_norm": 5.069203853607178, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 177.25, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03040091202736082, | |
| "grad_norm": 4.987614631652832, | |
| "learning_rate": 0.0, | |
| "loss": 177.5, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03040091202736082, | |
| "eval_loss": 11.086868286132812, | |
| "eval_runtime": 1.4842, | |
| "eval_samples_per_second": 746.535, | |
| "eval_steps_per_second": 373.267, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 776406564864.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |