| { | |
| "best_metric": 1.7957185506820679, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.050777530942557915, | |
| "eval_steps": 100, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002538876547127896, | |
| "eval_loss": 7.499389171600342, | |
| "eval_runtime": 684.9692, | |
| "eval_samples_per_second": 2.422, | |
| "eval_steps_per_second": 1.212, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025388765471278957, | |
| "grad_norm": 20.01273536682129, | |
| "learning_rate": 1e-05, | |
| "loss": 7.0184, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0050777530942557915, | |
| "grad_norm": 14.389914512634277, | |
| "learning_rate": 2e-05, | |
| "loss": 4.4882, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007616629641383688, | |
| "grad_norm": 9.800585746765137, | |
| "learning_rate": 3e-05, | |
| "loss": 2.4237, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010155506188511583, | |
| "grad_norm": 19.282072067260742, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9135, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.012694382735639479, | |
| "grad_norm": 8.14541244506836, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8893, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.015233259282767376, | |
| "grad_norm": 6.925289154052734, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9096, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.017772135829895272, | |
| "grad_norm": 7.16434907913208, | |
| "learning_rate": 7e-05, | |
| "loss": 1.8435, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.020311012377023166, | |
| "grad_norm": 7.456660270690918, | |
| "learning_rate": 8e-05, | |
| "loss": 1.9227, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.022849888924151063, | |
| "grad_norm": 6.74895715713501, | |
| "learning_rate": 9e-05, | |
| "loss": 1.8224, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.025388765471278957, | |
| "grad_norm": 6.2767510414123535, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7577, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.025388765471278957, | |
| "eval_loss": 1.8877848386764526, | |
| "eval_runtime": 684.2226, | |
| "eval_samples_per_second": 2.425, | |
| "eval_steps_per_second": 1.213, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.027927642018406855, | |
| "grad_norm": 5.097551345825195, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.0565, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.030466518565534752, | |
| "grad_norm": 5.463619709014893, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.8281, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03300539511266265, | |
| "grad_norm": 6.433900356292725, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 1.8498, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.035544271659790544, | |
| "grad_norm": 5.998843193054199, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.0344, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03808314820691844, | |
| "grad_norm": 5.395852088928223, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9115, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.04062202475404633, | |
| "grad_norm": 4.1980390548706055, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.9682, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.04316090130117423, | |
| "grad_norm": 3.98956561088562, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 1.8356, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.04569977784830213, | |
| "grad_norm": 4.076719284057617, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.8401, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.04823865439543002, | |
| "grad_norm": 4.793858051300049, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 1.7489, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.050777530942557915, | |
| "grad_norm": 4.629513740539551, | |
| "learning_rate": 0.0, | |
| "loss": 1.6943, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.050777530942557915, | |
| "eval_loss": 1.7957185506820679, | |
| "eval_runtime": 684.0192, | |
| "eval_samples_per_second": 2.425, | |
| "eval_steps_per_second": 1.213, | |
| "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": 1.541499732885504e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |