| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1593625498007968, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0031872509960159364, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.0945, | |
| "eval_samples_per_second": 32.738, | |
| "eval_steps_per_second": 8.277, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009561752988047808, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01593625498007968, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5519, | |
| "eval_samples_per_second": 35.09, | |
| "eval_steps_per_second": 8.872, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.019123505976095617, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028685258964143426, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03187250996015936, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5738, | |
| "eval_samples_per_second": 34.989, | |
| "eval_steps_per_second": 8.846, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03824701195219123, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04780876494023904, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04780876494023904, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5825, | |
| "eval_samples_per_second": 34.949, | |
| "eval_steps_per_second": 8.836, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05737051792828685, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06374501992031872, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5612, | |
| "eval_samples_per_second": 35.047, | |
| "eval_steps_per_second": 8.861, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06693227091633466, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07649402390438247, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0796812749003984, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5832, | |
| "eval_samples_per_second": 34.946, | |
| "eval_steps_per_second": 8.835, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08605577689243028, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09561752988047809, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09561752988047809, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5712, | |
| "eval_samples_per_second": 35.001, | |
| "eval_steps_per_second": 8.849, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1051792828685259, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11155378486055777, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5795, | |
| "eval_samples_per_second": 34.963, | |
| "eval_steps_per_second": 8.84, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1147410358565737, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12430278884462151, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12749003984063745, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5898, | |
| "eval_samples_per_second": 34.915, | |
| "eval_steps_per_second": 8.828, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13386454183266933, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.14342629482071714, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14342629482071714, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5811, | |
| "eval_samples_per_second": 34.955, | |
| "eval_steps_per_second": 8.838, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.15298804780876493, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1593625498007968, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5814, | |
| "eval_samples_per_second": 34.954, | |
| "eval_steps_per_second": 8.837, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "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": 6622102211788800.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |