| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.935672514619883, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03742690058479532, | |
| "grad_norm": 0.3751181662082672, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2768, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03742690058479532, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.0118, | |
| "eval_samples_per_second": 16.601, | |
| "eval_steps_per_second": 4.316, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07485380116959064, | |
| "grad_norm": 0.47280797362327576, | |
| "learning_rate": 0.0001, | |
| "loss": 1.368, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11228070175438597, | |
| "grad_norm": 0.5326794385910034, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 1.4173, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1497076023391813, | |
| "grad_norm": 0.6954847574234009, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 1.311, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1871345029239766, | |
| "grad_norm": 1.2069618701934814, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 1.0481, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22456140350877193, | |
| "grad_norm": 0.36987045407295227, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.261, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.26198830409356727, | |
| "grad_norm": 0.4424230754375458, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 1.1328, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2994152046783626, | |
| "grad_norm": 0.43106013536453247, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 0.9098, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": 0.44935163855552673, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 0.7919, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3742690058479532, | |
| "grad_norm": 0.55058753490448, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.6501, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.41169590643274856, | |
| "grad_norm": 0.6233323812484741, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.4905, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.44912280701754387, | |
| "grad_norm": 0.7761846780776978, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 0.377, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4865497076023392, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5239766081871345, | |
| "grad_norm": 0.578983724117279, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 0.7579, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 0.6018096804618835, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 0.8199, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5988304093567252, | |
| "grad_norm": 0.4542337656021118, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 0.4872, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6362573099415205, | |
| "grad_norm": 0.3547199070453644, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 0.4722, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "grad_norm": 0.4313491880893707, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 0.3292, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.572799563407898, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 0.4275, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7485380116959064, | |
| "grad_norm": 0.5901089310646057, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 0.7894, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7859649122807018, | |
| "grad_norm": 0.4362320601940155, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 0.7968, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8233918128654971, | |
| "grad_norm": 0.3412509262561798, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 0.6955, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8608187134502924, | |
| "grad_norm": 0.3553582429885864, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 0.5357, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8982456140350877, | |
| "grad_norm": 0.4358315169811249, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 0.2451, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.935672514619883, | |
| "grad_norm": 0.8321077227592468, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3221, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.935672514619883, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.0524, | |
| "eval_samples_per_second": 16.38, | |
| "eval_steps_per_second": 4.259, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.642726040455086e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |