| { | |
| "best_metric": 6.8306074142456055, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1678556441460344, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003357112882920688, | |
| "grad_norm": 2.5430850982666016, | |
| "learning_rate": 5e-05, | |
| "loss": 7.832, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003357112882920688, | |
| "eval_loss": 7.705937385559082, | |
| "eval_runtime": 0.7486, | |
| "eval_samples_per_second": 66.791, | |
| "eval_steps_per_second": 17.366, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006714225765841376, | |
| "grad_norm": 2.514496088027954, | |
| "learning_rate": 0.0001, | |
| "loss": 7.5496, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010071338648762064, | |
| "grad_norm": 2.5135130882263184, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 7.4873, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013428451531682753, | |
| "grad_norm": 2.626904249191284, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 7.4043, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01678556441460344, | |
| "grad_norm": 2.5633034706115723, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 7.3291, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.020142677297524128, | |
| "grad_norm": 2.401721239089966, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 7.2759, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02349979018044482, | |
| "grad_norm": 2.834110975265503, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 7.3426, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.026856903063365505, | |
| "grad_norm": 2.8407764434814453, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 7.1319, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.030214015946286196, | |
| "grad_norm": 3.355074405670166, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 7.2785, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03357112882920688, | |
| "grad_norm": 3.531038284301758, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 7.3777, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03692824171212757, | |
| "grad_norm": 4.6855058670043945, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 7.2524, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.040285354595048256, | |
| "grad_norm": 4.948916435241699, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 7.6879, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.043642467477968946, | |
| "grad_norm": 1.8742164373397827, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 7.8864, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04699958036088964, | |
| "grad_norm": 1.335532546043396, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 7.174, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05035669324381032, | |
| "grad_norm": 1.3148480653762817, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 7.0952, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05371380612673101, | |
| "grad_norm": 1.2804148197174072, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 7.0444, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0570709190096517, | |
| "grad_norm": 1.2791334390640259, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 7.0529, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06042803189257239, | |
| "grad_norm": 1.304823637008667, | |
| "learning_rate": 7.75e-05, | |
| "loss": 6.9528, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06378514477549307, | |
| "grad_norm": 1.479640245437622, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 7.1333, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06714225765841376, | |
| "grad_norm": 1.6118611097335815, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 7.0252, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07049937054133446, | |
| "grad_norm": 2.0745763778686523, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 6.8819, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07385648342425515, | |
| "grad_norm": 2.281806230545044, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 6.8558, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07721359630717582, | |
| "grad_norm": 2.6327695846557617, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 7.0346, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08057070919009651, | |
| "grad_norm": 3.486109495162964, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 7.0771, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0839278220730172, | |
| "grad_norm": 5.5846266746521, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 7.0188, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0839278220730172, | |
| "eval_loss": 7.021544933319092, | |
| "eval_runtime": 0.7649, | |
| "eval_samples_per_second": 65.364, | |
| "eval_steps_per_second": 16.995, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08728493495593789, | |
| "grad_norm": 1.2115647792816162, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 7.3506, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09064204783885858, | |
| "grad_norm": 1.0654467344284058, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 7.0821, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09399916072177927, | |
| "grad_norm": 1.0704606771469116, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 6.9776, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09735627360469996, | |
| "grad_norm": 1.156465768814087, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 6.8104, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10071338648762064, | |
| "grad_norm": 1.1990591287612915, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 6.8855, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10407049937054133, | |
| "grad_norm": 1.2621642351150513, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 6.7606, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10742761225346202, | |
| "grad_norm": 1.326280951499939, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 6.9083, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.11078472513638271, | |
| "grad_norm": 1.5722599029541016, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 6.7573, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1141418380193034, | |
| "grad_norm": 1.8806253671646118, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 6.8356, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11749895090222409, | |
| "grad_norm": 2.3613550662994385, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 6.5832, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.12085606378514478, | |
| "grad_norm": 3.0503711700439453, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 6.4064, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12421317666806546, | |
| "grad_norm": 4.733037948608398, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 6.5771, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12757028955098615, | |
| "grad_norm": 1.1526490449905396, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 7.3537, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.13092740243390685, | |
| "grad_norm": 0.9709998369216919, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 7.0119, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.13428451531682753, | |
| "grad_norm": 0.9723122715950012, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 6.9824, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1376416281997482, | |
| "grad_norm": 0.9486874341964722, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 6.9058, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1409987410826689, | |
| "grad_norm": 1.069161057472229, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 6.7611, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1443558539655896, | |
| "grad_norm": 1.207305669784546, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 6.7608, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1477129668485103, | |
| "grad_norm": 1.2742780447006226, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 6.8111, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.15107007973143097, | |
| "grad_norm": 1.5717660188674927, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 6.5346, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.15442719261435164, | |
| "grad_norm": 1.710330605506897, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 6.7916, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15778430549727235, | |
| "grad_norm": 2.0946614742279053, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 6.8355, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.16114141838019302, | |
| "grad_norm": 2.7978506088256836, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 6.66, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.16449853126311373, | |
| "grad_norm": 3.859832525253296, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 6.4211, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1678556441460344, | |
| "grad_norm": 6.498544692993164, | |
| "learning_rate": 1e-05, | |
| "loss": 6.8038, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1678556441460344, | |
| "eval_loss": 6.8306074142456055, | |
| "eval_runtime": 0.7255, | |
| "eval_samples_per_second": 68.913, | |
| "eval_steps_per_second": 17.917, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 232013797785600.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |