| { | |
| "best_metric": 4.4408369064331055, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.034229724236784116, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006845944847356823, | |
| "grad_norm": 1.9006248712539673, | |
| "learning_rate": 5e-05, | |
| "loss": 5.537, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006845944847356823, | |
| "eval_loss": 5.087055683135986, | |
| "eval_runtime": 0.7151, | |
| "eval_samples_per_second": 69.917, | |
| "eval_steps_per_second": 18.178, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013691889694713646, | |
| "grad_norm": 1.7246968746185303, | |
| "learning_rate": 0.0001, | |
| "loss": 5.2483, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002053783454207047, | |
| "grad_norm": 1.5443031787872314, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 5.0846, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0027383779389427293, | |
| "grad_norm": 1.4513391256332397, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.9153, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0034229724236784116, | |
| "grad_norm": 1.2515331506729126, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.8242, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004107566908414094, | |
| "grad_norm": 1.1466741561889648, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.8635, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004792161393149776, | |
| "grad_norm": 0.7819433808326721, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 4.9013, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005476755877885459, | |
| "grad_norm": 0.577840268611908, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.8079, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006161350362621141, | |
| "grad_norm": 0.8350602984428406, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 4.8048, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006845944847356823, | |
| "grad_norm": 0.8675013184547424, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 4.8008, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0075305393320925056, | |
| "grad_norm": 1.118022084236145, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 4.8584, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008215133816828188, | |
| "grad_norm": 0.6637853384017944, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.8433, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00889972830156387, | |
| "grad_norm": 1.2030086517333984, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 5.0964, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009584322786299553, | |
| "grad_norm": 0.891997218132019, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 5.0018, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.010268917271035235, | |
| "grad_norm": 0.9329969882965088, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 4.7486, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010953511755770917, | |
| "grad_norm": 0.5448434948921204, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 4.6841, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0116381062405066, | |
| "grad_norm": 1.6073203086853027, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 4.5953, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.012322700725242282, | |
| "grad_norm": 2.014742374420166, | |
| "learning_rate": 7.75e-05, | |
| "loss": 4.6134, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.013007295209977964, | |
| "grad_norm": 2.2186100482940674, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 4.6135, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.013691889694713646, | |
| "grad_norm": 1.8117921352386475, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 4.6247, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014376484179449329, | |
| "grad_norm": 0.8588649034500122, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 4.615, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015061078664185011, | |
| "grad_norm": 0.5354763865470886, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 4.609, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.015745673148920693, | |
| "grad_norm": 0.7342782020568848, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 4.5877, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.016430267633656376, | |
| "grad_norm": 0.5643114447593689, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 4.6211, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017114862118392058, | |
| "grad_norm": 0.4805735647678375, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 4.6834, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017114862118392058, | |
| "eval_loss": 4.552499294281006, | |
| "eval_runtime": 0.7173, | |
| "eval_samples_per_second": 69.705, | |
| "eval_steps_per_second": 18.123, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01779945660312774, | |
| "grad_norm": 0.62814861536026, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 4.89, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.018484051087863423, | |
| "grad_norm": 0.7369610071182251, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 4.7008, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.019168645572599105, | |
| "grad_norm": 0.4340572655200958, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 4.5668, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.019853240057334787, | |
| "grad_norm": 0.39323368668556213, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 4.4916, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.02053783454207047, | |
| "grad_norm": 0.3761708736419678, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 4.4375, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021222429026806152, | |
| "grad_norm": 0.3994690477848053, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 4.5058, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.021907023511541834, | |
| "grad_norm": 0.342385858297348, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 4.5325, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.022591617996277517, | |
| "grad_norm": 0.3298172056674957, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 4.5148, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0232762124810132, | |
| "grad_norm": 0.34544578194618225, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 4.5301, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.02396080696574888, | |
| "grad_norm": 0.36276698112487793, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 4.4603, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.024645401450484564, | |
| "grad_norm": 0.3994443714618683, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 4.4842, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.025329995935220246, | |
| "grad_norm": 0.4487013518810272, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 4.571, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02601459041995593, | |
| "grad_norm": 0.5831749439239502, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 4.9017, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02669918490469161, | |
| "grad_norm": 0.49567192792892456, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 4.7503, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.027383779389427293, | |
| "grad_norm": 0.41273921728134155, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 4.5314, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.028068373874162975, | |
| "grad_norm": 0.32999297976493835, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 4.4739, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.028752968358898658, | |
| "grad_norm": 0.3798677325248718, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 4.3849, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02943756284363434, | |
| "grad_norm": 0.3015289306640625, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 4.4318, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.030122157328370022, | |
| "grad_norm": 0.3044837713241577, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 4.393, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.030806751813105705, | |
| "grad_norm": 0.2872242033481598, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 4.4336, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03149134629784139, | |
| "grad_norm": 0.3284749388694763, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 4.4342, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03217594078257707, | |
| "grad_norm": 0.2982497215270996, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 4.4723, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03286053526731275, | |
| "grad_norm": 0.3299315571784973, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 4.4427, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03354512975204844, | |
| "grad_norm": 0.3700416386127472, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 4.5147, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.034229724236784116, | |
| "grad_norm": 0.47993677854537964, | |
| "learning_rate": 1e-05, | |
| "loss": 4.5846, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.034229724236784116, | |
| "eval_loss": 4.4408369064331055, | |
| "eval_runtime": 0.7646, | |
| "eval_samples_per_second": 65.397, | |
| "eval_steps_per_second": 17.003, | |
| "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": 1.1942410556801024e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |