| { | |
| "best_metric": 0.005579269025474787, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.042180744490140254, | |
| "eval_steps": 100, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00021090372245070126, | |
| "eval_loss": 0.9089367985725403, | |
| "eval_runtime": 708.2475, | |
| "eval_samples_per_second": 2.82, | |
| "eval_steps_per_second": 1.411, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021090372245070126, | |
| "grad_norm": 14.0634126663208, | |
| "learning_rate": 1e-05, | |
| "loss": 1.7235, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004218074449014025, | |
| "grad_norm": 26.957786560058594, | |
| "learning_rate": 2e-05, | |
| "loss": 0.059, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006327111673521037, | |
| "grad_norm": 0.11090046167373657, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0071, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00843614889802805, | |
| "grad_norm": 0.15285538136959076, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0386, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010545186122535063, | |
| "grad_norm": 0.04513653367757797, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0078, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012654223347042075, | |
| "grad_norm": 42.402244567871094, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0887, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.014763260571549088, | |
| "grad_norm": 68.10028839111328, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0061, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0168722977960561, | |
| "grad_norm": 5.722660541534424, | |
| "learning_rate": 8e-05, | |
| "loss": 0.1373, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.018981335020563112, | |
| "grad_norm": 17.748676300048828, | |
| "learning_rate": 9e-05, | |
| "loss": 0.3995, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.021090372245070127, | |
| "grad_norm": 5.94190788269043, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1634, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.021090372245070127, | |
| "eval_loss": 0.035220917314291, | |
| "eval_runtime": 707.5102, | |
| "eval_samples_per_second": 2.823, | |
| "eval_steps_per_second": 1.412, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02319940946957714, | |
| "grad_norm": 62.70212173461914, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0896, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02530844669408415, | |
| "grad_norm": 0.842799723148346, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.1349, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.027417483918591164, | |
| "grad_norm": 166.96304321289062, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.2701, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.029526521143098176, | |
| "grad_norm": 17.788463592529297, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.1667, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03163555836760519, | |
| "grad_norm": 1.1575299501419067, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1699, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0337445955921122, | |
| "grad_norm": 12.75675106048584, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0575, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03585363281661921, | |
| "grad_norm": 0.6250290870666504, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0638, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.037962670041126224, | |
| "grad_norm": 0.22166423499584198, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0095, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.040071707265633236, | |
| "grad_norm": 0.012423542328178883, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.013, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.042180744490140254, | |
| "grad_norm": 0.02760171703994274, | |
| "learning_rate": 0.0, | |
| "loss": 0.063, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.042180744490140254, | |
| "eval_loss": 0.005579269025474787, | |
| "eval_runtime": 707.9758, | |
| "eval_samples_per_second": 2.821, | |
| "eval_steps_per_second": 1.411, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "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": 1.463984163127296e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |