| { | |
| "best_metric": 1.4964512586593628, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.039647140449995046, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015858856179998017, | |
| "grad_norm": 17.070512771606445, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6777, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015858856179998017, | |
| "eval_loss": 5.90218448638916, | |
| "eval_runtime": 3.3307, | |
| "eval_samples_per_second": 15.012, | |
| "eval_steps_per_second": 3.903, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031717712359996034, | |
| "grad_norm": 19.348953247070312, | |
| "learning_rate": 0.0001, | |
| "loss": 4.7538, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004757656853999405, | |
| "grad_norm": 13.42625617980957, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.2714, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006343542471999207, | |
| "grad_norm": 2.2228305339813232, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.0772, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007929428089999009, | |
| "grad_norm": 1.0048638582229614, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.954, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00951531370799881, | |
| "grad_norm": 1.0425435304641724, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.876, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011101199325998613, | |
| "grad_norm": 1.0215988159179688, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.8797, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012687084943998414, | |
| "grad_norm": 0.8580153584480286, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.8136, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014272970561998216, | |
| "grad_norm": 0.6667729616165161, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.7673, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015858856179998018, | |
| "grad_norm": 0.701425313949585, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.7358, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01744474179799782, | |
| "grad_norm": 0.7387133836746216, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.6905, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01903062741599762, | |
| "grad_norm": 1.0632332563400269, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.7093, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.020616513033997422, | |
| "grad_norm": 0.7202914953231812, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.6132, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.022202398651997225, | |
| "grad_norm": 0.7657666206359863, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.6596, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.023788284269997028, | |
| "grad_norm": 0.6034996509552002, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.668, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.025374169887996827, | |
| "grad_norm": 0.5026582479476929, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.7384, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02696005550599663, | |
| "grad_norm": 0.42584991455078125, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.6253, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.028545941123996433, | |
| "grad_norm": 0.4252493381500244, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.6889, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.030131826741996232, | |
| "grad_norm": 0.4458921551704407, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.6895, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.031717712359996035, | |
| "grad_norm": 0.4872418940067291, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.6197, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.033303597977995834, | |
| "grad_norm": 0.4587940573692322, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.622, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03488948359599564, | |
| "grad_norm": 0.48748770356178284, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.6673, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03647536921399544, | |
| "grad_norm": 0.5389514565467834, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.6634, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03806125483199524, | |
| "grad_norm": 0.6838032603263855, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.6041, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.039647140449995046, | |
| "grad_norm": 1.1133662462234497, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.5255, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.039647140449995046, | |
| "eval_loss": 1.4964512586593628, | |
| "eval_runtime": 3.4121, | |
| "eval_samples_per_second": 14.654, | |
| "eval_steps_per_second": 3.81, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.315690861756416e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |