| { | |
| "best_metric": 1.5643208026885986, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.00207671380807011, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.30685523228044e-05, | |
| "grad_norm": 0.3230171501636505, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3143, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.30685523228044e-05, | |
| "eval_loss": 2.673133611679077, | |
| "eval_runtime": 697.8923, | |
| "eval_samples_per_second": 7.263, | |
| "eval_steps_per_second": 3.632, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001661371046456088, | |
| "grad_norm": 0.38747304677963257, | |
| "learning_rate": 4e-05, | |
| "loss": 0.9697, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00024920565696841317, | |
| "grad_norm": 0.4644308388233185, | |
| "learning_rate": 6e-05, | |
| "loss": 1.8833, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003322742092912176, | |
| "grad_norm": 0.6362165808677673, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7652, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000415342761614022, | |
| "grad_norm": 0.8625140190124512, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8221, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000415342761614022, | |
| "eval_loss": 2.6570961475372314, | |
| "eval_runtime": 695.9737, | |
| "eval_samples_per_second": 7.283, | |
| "eval_steps_per_second": 3.642, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004984113139368263, | |
| "grad_norm": 0.4483662545681, | |
| "learning_rate": 0.00012, | |
| "loss": 1.5733, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005814798662596307, | |
| "grad_norm": 1.2123891115188599, | |
| "learning_rate": 0.00014, | |
| "loss": 2.1989, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006645484185824351, | |
| "grad_norm": 0.35283467173576355, | |
| "learning_rate": 0.00016, | |
| "loss": 1.1031, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007476169709052396, | |
| "grad_norm": 0.5155271887779236, | |
| "learning_rate": 0.00018, | |
| "loss": 0.8403, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000830685523228044, | |
| "grad_norm": 1.031050205230713, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8104, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000830685523228044, | |
| "eval_loss": 2.4019789695739746, | |
| "eval_runtime": 696.3456, | |
| "eval_samples_per_second": 7.279, | |
| "eval_steps_per_second": 3.64, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009137540755508484, | |
| "grad_norm": 0.4251876771450043, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.3126, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0009968226278736527, | |
| "grad_norm": 0.29052504897117615, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.5978, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001079891180196457, | |
| "grad_norm": 0.6259279251098633, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.9523, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0011629597325192615, | |
| "grad_norm": 0.6137332916259766, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.3758, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0012460282848420659, | |
| "grad_norm": 0.45516347885131836, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.2923, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0012460282848420659, | |
| "eval_loss": 1.8502157926559448, | |
| "eval_runtime": 692.7971, | |
| "eval_samples_per_second": 7.317, | |
| "eval_steps_per_second": 3.659, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013290968371648703, | |
| "grad_norm": 0.4323667287826538, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.1172, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0014121653894876747, | |
| "grad_norm": 0.5879186391830444, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.649, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.001495233941810479, | |
| "grad_norm": 1.1666667461395264, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.4487, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0015783024941332835, | |
| "grad_norm": 0.5356272459030151, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.6611, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.001661371046456088, | |
| "grad_norm": 0.6931415796279907, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.35, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001661371046456088, | |
| "eval_loss": 1.6069304943084717, | |
| "eval_runtime": 690.8101, | |
| "eval_samples_per_second": 7.338, | |
| "eval_steps_per_second": 3.67, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0017444395987788923, | |
| "grad_norm": 0.8257535696029663, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.8202, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0018275081511016967, | |
| "grad_norm": 0.39779406785964966, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.4466, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0019105767034245011, | |
| "grad_norm": 0.5848168134689331, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.4848, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0019936452557473053, | |
| "grad_norm": 0.5994840860366821, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.8308, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00207671380807011, | |
| "grad_norm": 0.39819470047950745, | |
| "learning_rate": 0.0, | |
| "loss": 0.528, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00207671380807011, | |
| "eval_loss": 1.5643208026885986, | |
| "eval_runtime": 692.8523, | |
| "eval_samples_per_second": 7.316, | |
| "eval_steps_per_second": 3.659, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 2808666677575680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |