| { | |
| "best_metric": 1.324136734008789, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.005578333751708364, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.7891668758541825e-05, | |
| "eval_loss": 2.138502359390259, | |
| "eval_runtime": 539.9687, | |
| "eval_samples_per_second": 27.959, | |
| "eval_steps_per_second": 6.991, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002789166875854182, | |
| "grad_norm": 3.119084358215332, | |
| "learning_rate": 5.05e-06, | |
| "loss": 2.1448, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005578333751708364, | |
| "grad_norm": 2.9193804264068604, | |
| "learning_rate": 1.01e-05, | |
| "loss": 1.8834, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008367500627562547, | |
| "grad_norm": 3.0759785175323486, | |
| "learning_rate": 9.538888888888889e-06, | |
| "loss": 1.7763, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0011156667503416729, | |
| "grad_norm": 2.9843831062316895, | |
| "learning_rate": 8.977777777777778e-06, | |
| "loss": 1.6058, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.001394583437927091, | |
| "grad_norm": 5.683198928833008, | |
| "learning_rate": 8.416666666666667e-06, | |
| "loss": 1.5341, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.001394583437927091, | |
| "eval_loss": 1.4934452772140503, | |
| "eval_runtime": 540.9009, | |
| "eval_samples_per_second": 27.911, | |
| "eval_steps_per_second": 6.979, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0016735001255125093, | |
| "grad_norm": 2.7144954204559326, | |
| "learning_rate": 7.855555555555556e-06, | |
| "loss": 1.7181, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0019524168130979278, | |
| "grad_norm": 2.7628259658813477, | |
| "learning_rate": 7.294444444444444e-06, | |
| "loss": 1.4813, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0022313335006833458, | |
| "grad_norm": 2.849717140197754, | |
| "learning_rate": 6.733333333333333e-06, | |
| "loss": 1.3881, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.002510250188268764, | |
| "grad_norm": 2.8136160373687744, | |
| "learning_rate": 6.172222222222223e-06, | |
| "loss": 1.3241, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.002789166875854182, | |
| "grad_norm": 4.298107147216797, | |
| "learning_rate": 5.611111111111111e-06, | |
| "loss": 1.3305, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.002789166875854182, | |
| "eval_loss": 1.3773066997528076, | |
| "eval_runtime": 542.8338, | |
| "eval_samples_per_second": 27.811, | |
| "eval_steps_per_second": 6.954, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0030680835634396006, | |
| "grad_norm": 2.741830587387085, | |
| "learning_rate": 5.05e-06, | |
| "loss": 1.6088, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0033470002510250186, | |
| "grad_norm": 2.751880407333374, | |
| "learning_rate": 4.488888888888889e-06, | |
| "loss": 1.2966, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.003625916938610437, | |
| "grad_norm": 3.4367833137512207, | |
| "learning_rate": 3.927777777777778e-06, | |
| "loss": 1.349, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0039048336261958555, | |
| "grad_norm": 3.5134706497192383, | |
| "learning_rate": 3.3666666666666665e-06, | |
| "loss": 1.302, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0041837503137812735, | |
| "grad_norm": 5.4509100914001465, | |
| "learning_rate": 2.8055555555555555e-06, | |
| "loss": 1.2418, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0041837503137812735, | |
| "eval_loss": 1.336289644241333, | |
| "eval_runtime": 539.6746, | |
| "eval_samples_per_second": 27.974, | |
| "eval_steps_per_second": 6.995, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0044626670013666915, | |
| "grad_norm": 2.685837984085083, | |
| "learning_rate": 2.2444444444444445e-06, | |
| "loss": 1.5027, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.00474158368895211, | |
| "grad_norm": 2.422490119934082, | |
| "learning_rate": 1.6833333333333332e-06, | |
| "loss": 1.3534, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.005020500376537528, | |
| "grad_norm": 3.044349193572998, | |
| "learning_rate": 1.1222222222222222e-06, | |
| "loss": 1.2763, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.005299417064122946, | |
| "grad_norm": 3.222191333770752, | |
| "learning_rate": 5.611111111111111e-07, | |
| "loss": 1.2248, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.005578333751708364, | |
| "grad_norm": 7.070194721221924, | |
| "learning_rate": 0.0, | |
| "loss": 1.2512, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.005578333751708364, | |
| "eval_loss": 1.324136734008789, | |
| "eval_runtime": 540.3338, | |
| "eval_samples_per_second": 27.94, | |
| "eval_steps_per_second": 6.986, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.506684316503245e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |