| { |
| "best_metric": 0.0019476765301078558, |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", |
| "epoch": 0.5979073243647235, |
| "eval_steps": 25, |
| "global_step": 25, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02391629297458894, |
| "grad_norm": 0.8342862725257874, |
| "learning_rate": 5e-05, |
| "loss": 0.151, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.02391629297458894, |
| "eval_loss": 0.3206508159637451, |
| "eval_runtime": 5.0018, |
| "eval_samples_per_second": 9.996, |
| "eval_steps_per_second": 2.599, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.04783258594917788, |
| "grad_norm": 1.0358092784881592, |
| "learning_rate": 0.0001, |
| "loss": 0.1876, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.07174887892376682, |
| "grad_norm": 0.9988421201705933, |
| "learning_rate": 9.990365154573717e-05, |
| "loss": 0.1574, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.09566517189835576, |
| "grad_norm": 0.40356796979904175, |
| "learning_rate": 9.961501876182148e-05, |
| "loss": 0.0344, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.11958146487294469, |
| "grad_norm": 0.4616738557815552, |
| "learning_rate": 9.913533761814537e-05, |
| "loss": 0.0295, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.14349775784753363, |
| "grad_norm": 0.2594583034515381, |
| "learning_rate": 9.846666218300807e-05, |
| "loss": 0.017, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.16741405082212257, |
| "grad_norm": 0.20972101390361786, |
| "learning_rate": 9.761185582727977e-05, |
| "loss": 0.0138, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.19133034379671152, |
| "grad_norm": 0.23585247993469238, |
| "learning_rate": 9.657457896300791e-05, |
| "loss": 0.0162, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.21524663677130046, |
| "grad_norm": 0.2117353081703186, |
| "learning_rate": 9.535927336897098e-05, |
| "loss": 0.0104, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.23916292974588937, |
| "grad_norm": 0.2045036405324936, |
| "learning_rate": 9.397114317029975e-05, |
| "loss": 0.0143, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.26307922272047835, |
| "grad_norm": 0.14103253185749054, |
| "learning_rate": 9.241613255361455e-05, |
| "loss": 0.0282, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.28699551569506726, |
| "grad_norm": 0.11386289447546005, |
| "learning_rate": 9.070090031310558e-05, |
| "loss": 0.0074, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.3109118086696562, |
| "grad_norm": 0.11132951080799103, |
| "learning_rate": 8.883279133655399e-05, |
| "loss": 0.0082, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.33482810164424515, |
| "grad_norm": 0.0779055580496788, |
| "learning_rate": 8.681980515339464e-05, |
| "loss": 0.0056, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.35874439461883406, |
| "grad_norm": 0.08194252848625183, |
| "learning_rate": 8.467056167950311e-05, |
| "loss": 0.0044, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.38266068759342303, |
| "grad_norm": 0.09063728153705597, |
| "learning_rate": 8.239426430539243e-05, |
| "loss": 0.005, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.40657698056801195, |
| "grad_norm": 0.07385275512933731, |
| "learning_rate": 8.000066048588211e-05, |
| "loss": 0.0028, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.4304932735426009, |
| "grad_norm": 0.05866006389260292, |
| "learning_rate": 7.75e-05, |
| "loss": 0.0022, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.45440956651718983, |
| "grad_norm": 0.0739208534359932, |
| "learning_rate": 7.490299105985507e-05, |
| "loss": 0.0016, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.47832585949177875, |
| "grad_norm": 0.09625879675149918, |
| "learning_rate": 7.222075445642904e-05, |
| "loss": 0.0036, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.5022421524663677, |
| "grad_norm": 0.08272045105695724, |
| "learning_rate": 6.946477593864228e-05, |
| "loss": 0.0114, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.5261584454409567, |
| "grad_norm": 0.029296347871422768, |
| "learning_rate": 6.664685702961344e-05, |
| "loss": 0.0017, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.5500747384155455, |
| "grad_norm": 0.04417581856250763, |
| "learning_rate": 6.377906449072578e-05, |
| "loss": 0.0021, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.5739910313901345, |
| "grad_norm": 0.05239644646644592, |
| "learning_rate": 6.087367864990233e-05, |
| "loss": 0.0026, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.5979073243647235, |
| "grad_norm": 0.03702784329652786, |
| "learning_rate": 5.794314081535644e-05, |
| "loss": 0.0013, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.5979073243647235, |
| "eval_loss": 0.0019476765301078558, |
| "eval_runtime": 5.0938, |
| "eval_samples_per_second": 9.816, |
| "eval_steps_per_second": 2.552, |
| "step": 25 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 3.1567025970715034e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
