| { | |
| "best_metric": 3.0633466243743896, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.033909149072297, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.020473448496481125, | |
| "grad_norm": 60.07720947265625, | |
| "learning_rate": 5e-05, | |
| "loss": 7.1087, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.020473448496481125, | |
| "eval_loss": 8.921172142028809, | |
| "eval_runtime": 1.7057, | |
| "eval_samples_per_second": 29.314, | |
| "eval_steps_per_second": 7.622, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04094689699296225, | |
| "grad_norm": 72.95249938964844, | |
| "learning_rate": 0.0001, | |
| "loss": 8.3093, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.061420345489443376, | |
| "grad_norm": 14.521111488342285, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 7.8942, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0818937939859245, | |
| "grad_norm": 15.53856372833252, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 7.8602, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10236724248240563, | |
| "grad_norm": 10.05084228515625, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 7.1523, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12284069097888675, | |
| "grad_norm": 10.203170776367188, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 6.708, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1433141394753679, | |
| "grad_norm": 9.880365371704102, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 6.5577, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.163787587971849, | |
| "grad_norm": 12.834639549255371, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 5.7343, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.18426103646833014, | |
| "grad_norm": 13.360304832458496, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 5.1449, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.20473448496481125, | |
| "grad_norm": 10.789073944091797, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 5.7037, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2252079334612924, | |
| "grad_norm": 11.60144329071045, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 6.2567, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2456813819577735, | |
| "grad_norm": 13.579934120178223, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 6.0197, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.26615483045425464, | |
| "grad_norm": 17.290565490722656, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 5.7356, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2866282789507358, | |
| "grad_norm": 13.604474067687988, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 5.3973, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.30710172744721687, | |
| "grad_norm": 7.635220050811768, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 5.3141, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.327575175943698, | |
| "grad_norm": 9.153149604797363, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 4.7792, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.34804862444017914, | |
| "grad_norm": 7.714826583862305, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 4.5357, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3685220729366603, | |
| "grad_norm": 8.57360553741455, | |
| "learning_rate": 7.75e-05, | |
| "loss": 4.4712, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3889955214331414, | |
| "grad_norm": 10.09951400756836, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 4.4008, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4094689699296225, | |
| "grad_norm": 9.976293563842773, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.5635, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42994241842610365, | |
| "grad_norm": 9.296375274658203, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.3148, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4504158669225848, | |
| "grad_norm": 110.87342071533203, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.4638, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4708893154190659, | |
| "grad_norm": 155.48568725585938, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 4.9609, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.491362763915547, | |
| "grad_norm": 98.27151489257812, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 4.3888, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5118362124120281, | |
| "grad_norm": 6.915646076202393, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 4.6978, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5118362124120281, | |
| "eval_loss": 3.584397315979004, | |
| "eval_runtime": 1.7066, | |
| "eval_samples_per_second": 29.299, | |
| "eval_steps_per_second": 7.618, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5323096609085093, | |
| "grad_norm": 9.44233226776123, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 4.2071, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5527831094049904, | |
| "grad_norm": 5.62533712387085, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 4.4023, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5732565579014716, | |
| "grad_norm": 6.5841851234436035, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 3.6272, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5937300063979527, | |
| "grad_norm": 3.9638733863830566, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.6042, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6142034548944337, | |
| "grad_norm": 3.8045289516448975, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 3.8018, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6346769033909149, | |
| "grad_norm": 4.675745010375977, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 4.1539, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.655150351887396, | |
| "grad_norm": 7.304325103759766, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.5739, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6756238003838771, | |
| "grad_norm": 8.27237319946289, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.9565, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6960972488803583, | |
| "grad_norm": 4.600338459014893, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.6638, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7165706973768394, | |
| "grad_norm": 6.785358428955078, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 3.8978, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7370441458733206, | |
| "grad_norm": 13.49142074584961, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 3.8446, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7575175943698017, | |
| "grad_norm": 5.301874160766602, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 4.1858, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.7779910428662828, | |
| "grad_norm": 5.839453220367432, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 3.7766, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7984644913627639, | |
| "grad_norm": 4.404445648193359, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 3.9701, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.818937939859245, | |
| "grad_norm": 4.650479793548584, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 3.3742, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8394113883557262, | |
| "grad_norm": 3.8081395626068115, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.4152, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8598848368522073, | |
| "grad_norm": 3.4957478046417236, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 3.4227, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8803582853486884, | |
| "grad_norm": 3.3087618350982666, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 3.4167, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9008317338451696, | |
| "grad_norm": 6.3253397941589355, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.0345, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9213051823416507, | |
| "grad_norm": 6.485597133636475, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.5626, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9417786308381318, | |
| "grad_norm": 2.990126848220825, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.5906, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.9622520793346129, | |
| "grad_norm": 8.486502647399902, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 4.0102, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.982725527831094, | |
| "grad_norm": 13.994930267333984, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 3.7827, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0134357005758157, | |
| "grad_norm": 8.235879898071289, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 6.6262, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.033909149072297, | |
| "grad_norm": 5.423706531524658, | |
| "learning_rate": 1e-05, | |
| "loss": 3.513, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.033909149072297, | |
| "eval_loss": 3.0633466243743896, | |
| "eval_runtime": 1.7028, | |
| "eval_samples_per_second": 29.364, | |
| "eval_steps_per_second": 7.635, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.33416392081408e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |