| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.014842300556586271, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002968460111317254, | |
| "eval_loss": NaN, | |
| "eval_runtime": 423.8224, | |
| "eval_samples_per_second": 13.388, | |
| "eval_steps_per_second": 1.675, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008905380333951762, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001484230055658627, | |
| "eval_loss": NaN, | |
| "eval_runtime": 424.3722, | |
| "eval_samples_per_second": 13.37, | |
| "eval_steps_per_second": 1.673, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017810760667903525, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002671614100185529, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002968460111317254, | |
| "eval_loss": NaN, | |
| "eval_runtime": 424.248, | |
| "eval_samples_per_second": 13.374, | |
| "eval_steps_per_second": 1.674, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003562152133580705, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0044526901669758815, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0044526901669758815, | |
| "eval_loss": NaN, | |
| "eval_runtime": 424.023, | |
| "eval_samples_per_second": 13.381, | |
| "eval_steps_per_second": 1.674, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005343228200371058, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005936920222634508, | |
| "eval_loss": NaN, | |
| "eval_runtime": 423.9902, | |
| "eval_samples_per_second": 13.382, | |
| "eval_steps_per_second": 1.675, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006233766233766234, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00712430426716141, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0074211502782931356, | |
| "eval_loss": NaN, | |
| "eval_runtime": 424.5104, | |
| "eval_samples_per_second": 13.366, | |
| "eval_steps_per_second": 1.673, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008014842300556586, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.008905380333951763, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008905380333951763, | |
| "eval_loss": NaN, | |
| "eval_runtime": 424.4669, | |
| "eval_samples_per_second": 13.367, | |
| "eval_steps_per_second": 1.673, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009795918367346938, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01038961038961039, | |
| "eval_loss": NaN, | |
| "eval_runtime": 424.4339, | |
| "eval_samples_per_second": 13.368, | |
| "eval_steps_per_second": 1.673, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010686456400742115, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01157699443413729, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.011873840445269016, | |
| "eval_loss": NaN, | |
| "eval_runtime": 424.5651, | |
| "eval_samples_per_second": 13.364, | |
| "eval_steps_per_second": 1.672, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.012467532467532468, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.013358070500927645, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.013358070500927645, | |
| "eval_loss": NaN, | |
| "eval_runtime": 424.6214, | |
| "eval_samples_per_second": 13.362, | |
| "eval_steps_per_second": 1.672, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01424860853432282, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.014842300556586271, | |
| "eval_loss": NaN, | |
| "eval_runtime": 424.649, | |
| "eval_samples_per_second": 13.362, | |
| "eval_steps_per_second": 1.672, | |
| "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": 7.351060341876326e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |