| { | |
| "best_metric": 0.34694528579711914, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0009974266392706816, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.9897065570827266e-05, | |
| "grad_norm": 34.18605041503906, | |
| "learning_rate": 2e-05, | |
| "loss": 13.0737, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.9897065570827266e-05, | |
| "eval_loss": 13.415596008300781, | |
| "eval_runtime": 1874.0126, | |
| "eval_samples_per_second": 5.632, | |
| "eval_steps_per_second": 2.816, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.979413114165453e-05, | |
| "grad_norm": 28.807968139648438, | |
| "learning_rate": 4e-05, | |
| "loss": 12.9275, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001196911967124818, | |
| "grad_norm": 31.45498275756836, | |
| "learning_rate": 6e-05, | |
| "loss": 13.4907, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00015958826228330906, | |
| "grad_norm": 32.819374084472656, | |
| "learning_rate": 8e-05, | |
| "loss": 12.1004, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00019948532785413634, | |
| "grad_norm": 27.601322174072266, | |
| "learning_rate": 0.0001, | |
| "loss": 13.4579, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00019948532785413634, | |
| "eval_loss": 9.159690856933594, | |
| "eval_runtime": 1772.9234, | |
| "eval_samples_per_second": 5.953, | |
| "eval_steps_per_second": 2.976, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002393823934249636, | |
| "grad_norm": 28.294076919555664, | |
| "learning_rate": 0.00012, | |
| "loss": 9.1527, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00027927945899579087, | |
| "grad_norm": 37.93229293823242, | |
| "learning_rate": 0.00014, | |
| "loss": 5.8707, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003191765245666181, | |
| "grad_norm": 14.759050369262695, | |
| "learning_rate": 0.00016, | |
| "loss": 6.4097, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0003590735901374454, | |
| "grad_norm": 7.974320411682129, | |
| "learning_rate": 0.00018, | |
| "loss": 3.0011, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003989706557082727, | |
| "grad_norm": 12.045090675354004, | |
| "learning_rate": 0.0002, | |
| "loss": 3.9195, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003989706557082727, | |
| "eval_loss": 2.9394724369049072, | |
| "eval_runtime": 1780.2058, | |
| "eval_samples_per_second": 5.929, | |
| "eval_steps_per_second": 2.964, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00043886772127909993, | |
| "grad_norm": 15.616610527038574, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 3.1589, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0004787647868499272, | |
| "grad_norm": 14.602272987365723, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.2852, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005186618524207544, | |
| "grad_norm": 50.422203063964844, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 4.3434, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0005585589179915817, | |
| "grad_norm": 4.45857572555542, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.0479, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0005984559835624089, | |
| "grad_norm": 19.128103256225586, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.7122, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005984559835624089, | |
| "eval_loss": 1.144124984741211, | |
| "eval_runtime": 1799.5762, | |
| "eval_samples_per_second": 5.865, | |
| "eval_steps_per_second": 2.932, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006383530491332362, | |
| "grad_norm": 23.54120445251465, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.604, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0006782501147040636, | |
| "grad_norm": 6.584514617919922, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.788, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0007181471802748908, | |
| "grad_norm": 1.4092001914978027, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.0147, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0007580442458457181, | |
| "grad_norm": 11.170414924621582, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.5299, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0007979413114165454, | |
| "grad_norm": 7.714025020599365, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.0699, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007979413114165454, | |
| "eval_loss": 0.46810051798820496, | |
| "eval_runtime": 1796.8416, | |
| "eval_samples_per_second": 5.874, | |
| "eval_steps_per_second": 2.937, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008378383769873726, | |
| "grad_norm": 26.54975128173828, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.7679, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0008777354425581999, | |
| "grad_norm": 4.3329691886901855, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.2106, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0009176325081290271, | |
| "grad_norm": 0.4202094078063965, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.0065, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0009575295736998544, | |
| "grad_norm": 12.792423248291016, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.7221, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0009974266392706816, | |
| "grad_norm": 12.721324920654297, | |
| "learning_rate": 0.0, | |
| "loss": 0.635, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0009974266392706816, | |
| "eval_loss": 0.34694528579711914, | |
| "eval_runtime": 1795.7899, | |
| "eval_samples_per_second": 5.877, | |
| "eval_steps_per_second": 2.939, | |
| "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": 6889626824343552.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |