| { | |
| "best_metric": 2.0811705589294434, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.004537205081669692, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00018148820326678765, | |
| "grad_norm": 1.800824522972107, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8611, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00018148820326678765, | |
| "eval_loss": 3.4104740619659424, | |
| "eval_runtime": 292.4283, | |
| "eval_samples_per_second": 126.937, | |
| "eval_steps_per_second": 15.867, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003629764065335753, | |
| "grad_norm": 1.8991063833236694, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9253, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000544464609800363, | |
| "grad_norm": 1.764054298400879, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.8722, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007259528130671506, | |
| "grad_norm": 1.9196327924728394, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.6705, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009074410163339383, | |
| "grad_norm": 2.1063144207000732, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.5424, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001088929219600726, | |
| "grad_norm": 1.8720324039459229, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.4721, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0012704174228675136, | |
| "grad_norm": 1.2982118129730225, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.423, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0014519056261343012, | |
| "grad_norm": 1.6299554109573364, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3525, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001633393829401089, | |
| "grad_norm": 2.0756640434265137, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.2914, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0018148820326678765, | |
| "grad_norm": 1.3040707111358643, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.232, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001996370235934664, | |
| "grad_norm": 1.9184094667434692, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.1852, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002177858439201452, | |
| "grad_norm": 4.158185958862305, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.2036, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0023593466424682396, | |
| "grad_norm": 7.172682285308838, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.4279, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002540834845735027, | |
| "grad_norm": 7.375123500823975, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.2959, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0027223230490018148, | |
| "grad_norm": 2.036797046661377, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.1958, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0029038112522686023, | |
| "grad_norm": 1.9762221574783325, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.1766, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0030852994555353903, | |
| "grad_norm": 1.3871911764144897, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.1618, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003266787658802178, | |
| "grad_norm": 1.7979756593704224, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.1442, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0034482758620689655, | |
| "grad_norm": 1.3586605787277222, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.1036, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003629764065335753, | |
| "grad_norm": 1.0065734386444092, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.1057, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003811252268602541, | |
| "grad_norm": 1.2989829778671265, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.1006, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003992740471869328, | |
| "grad_norm": 0.970647394657135, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.0562, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004174228675136116, | |
| "grad_norm": 1.3675737380981445, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.9966, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004355716878402904, | |
| "grad_norm": 2.907510995864868, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.9918, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004537205081669692, | |
| "grad_norm": 1.8407702445983887, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.83, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004537205081669692, | |
| "eval_loss": 2.0811705589294434, | |
| "eval_runtime": 292.655, | |
| "eval_samples_per_second": 126.839, | |
| "eval_steps_per_second": 15.855, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.91521434075136e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |