| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0440528634361232, | |
| "eval_steps": 25, | |
| "global_step": 43, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07048458149779736, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 904.6357, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07048458149779736, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.7727, | |
| "eval_samples_per_second": 10.476, | |
| "eval_steps_per_second": 2.724, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14096916299559473, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.21145374449339208, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.986796105326832e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.28193832599118945, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.947261907011569e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.3524229074889868, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.881629407450006e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.42290748898678415, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.790283764247188e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4933920704845815, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.673761029959427e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5638766519823789, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.53274500632475e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6343612334801763, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.368063231442406e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7048458149779736, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.18068212345023e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.775330396475771, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.971701309198744e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8458149779735683, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.742347171203542e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9162995594713657, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.493965650745043e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.986784140969163, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.228014349349872e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.0616740088105727, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.946053975005496e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.13215859030837, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.649739183305184e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.2026431718061674, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.34080886727103e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.2731277533039647, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.021075952838262e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.3436123348017621, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.692416759884978e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.4140969162995596, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.356759991241008e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.4845814977973568, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.016075414292803e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.555066079295154, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6723623016051596e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.6255506607929515, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3276376983948415e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.696035242290749, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9839245857071994e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.7665198237885462, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.643240008758992e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.7665198237885462, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.6192, | |
| "eval_samples_per_second": 13.815, | |
| "eval_steps_per_second": 3.592, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8370044052863435, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.307583240115024e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.907488986784141, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9789240471617385e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.9779735682819384, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.659191132728971e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.052863436123348, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.350260816694816e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.1233480176211454, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0539460249945056e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.193832599118943, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7719856506501306e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.26431718061674, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5060343492549566e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.3348017621145374, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.257652828796459e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.405286343612335, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0282986908012567e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.4757709251101323, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.819317876549771e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.5462555066079293, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.631936768557596e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.616740088105727, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4672549936752506e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.6872246696035242, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3262389700405744e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.7577092511013217, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2097162357528127e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.828193832599119, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1183705925499948e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.898678414096916, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0527380929884324e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.9691629955947136, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.013203894673168e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 3.0440528634361232, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 43, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 5.251356976952115e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |