| { | |
| "best_metric": 2.0661635398864746, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.09375366225243173, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018750732450486347, | |
| "grad_norm": 0.18874938786029816, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5556, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018750732450486347, | |
| "eval_loss": 2.7236664295196533, | |
| "eval_runtime": 2.0016, | |
| "eval_samples_per_second": 24.98, | |
| "eval_steps_per_second": 6.495, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0037501464900972694, | |
| "grad_norm": 0.31151771545410156, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4983, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005625219735145904, | |
| "grad_norm": 0.4015798568725586, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.301, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007500292980194539, | |
| "grad_norm": 0.44802185893058777, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.0067, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009375366225243174, | |
| "grad_norm": 0.4803531765937805, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.9123, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011250439470291808, | |
| "grad_norm": 0.7162438631057739, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.8433, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013125512715340444, | |
| "grad_norm": 0.7702191472053528, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.8747, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.015000585960389078, | |
| "grad_norm": 0.8283402323722839, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.8316, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.016875659205437713, | |
| "grad_norm": 0.879456102848053, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.7199, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01875073245048635, | |
| "grad_norm": 0.9850853085517883, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.5914, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02062580569553498, | |
| "grad_norm": 1.483264446258545, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.0067, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.022500878940583616, | |
| "grad_norm": 2.40802264213562, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.4243, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.024375952185632252, | |
| "grad_norm": 1.7160142660140991, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.6676, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.026251025430680888, | |
| "grad_norm": 1.923504114151001, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.5663, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02812609867572952, | |
| "grad_norm": 1.6850132942199707, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.4577, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.030001171920778155, | |
| "grad_norm": 1.3820738792419434, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.0914, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03187624516582679, | |
| "grad_norm": 1.234266996383667, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.8374, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.033751318410875426, | |
| "grad_norm": 0.9019191265106201, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.7821, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03562639165592406, | |
| "grad_norm": 0.6670633554458618, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.7362, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0375014649009727, | |
| "grad_norm": 0.7307754755020142, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.8354, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03937653814602133, | |
| "grad_norm": 1.1211742162704468, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.769, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04125161139106996, | |
| "grad_norm": 1.2934951782226562, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.6058, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0431266846361186, | |
| "grad_norm": 1.6635746955871582, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.8029, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04500175788116723, | |
| "grad_norm": 2.1599605083465576, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.916, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.046876831126215865, | |
| "grad_norm": 3.889531373977661, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.5461, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.046876831126215865, | |
| "eval_loss": 2.099208116531372, | |
| "eval_runtime": 2.021, | |
| "eval_samples_per_second": 24.74, | |
| "eval_steps_per_second": 6.432, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.048751904371264504, | |
| "grad_norm": 0.28709402680397034, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.4925, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.050626977616313136, | |
| "grad_norm": 0.3136753737926483, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.2179, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.052502050861361775, | |
| "grad_norm": 0.2910340428352356, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.8988, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05437712410641041, | |
| "grad_norm": 0.32023727893829346, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.8543, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05625219735145904, | |
| "grad_norm": 0.3204735517501831, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.7303, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05812727059650768, | |
| "grad_norm": 0.2874813973903656, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.6267, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06000234384155631, | |
| "grad_norm": 0.3387392461299896, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.6418, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06187741708660494, | |
| "grad_norm": 0.40089866518974304, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.6216, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06375249033165357, | |
| "grad_norm": 0.5712559223175049, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.5959, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06562756357670221, | |
| "grad_norm": 0.7323669195175171, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.5624, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06750263682175085, | |
| "grad_norm": 1.0115784406661987, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.6113, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06937771006679948, | |
| "grad_norm": 1.3737353086471558, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 2.1971, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07125278331184812, | |
| "grad_norm": 0.1865454912185669, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.5232, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07312785655689676, | |
| "grad_norm": 0.17241472005844116, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.4565, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0750029298019454, | |
| "grad_norm": 0.20789682865142822, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.1895, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07687800304699402, | |
| "grad_norm": 0.25847384333610535, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.8888, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07875307629204266, | |
| "grad_norm": 0.25743380188941956, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.7961, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0806281495370913, | |
| "grad_norm": 0.2695237100124359, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.6383, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.08250322278213992, | |
| "grad_norm": 0.2877432405948639, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.7638, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.08437829602718856, | |
| "grad_norm": 0.3283619284629822, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.5621, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0862533692722372, | |
| "grad_norm": 0.4257296025753021, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.6518, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08812844251728583, | |
| "grad_norm": 0.5808598399162292, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.5782, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.09000351576233447, | |
| "grad_norm": 0.8608271479606628, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.6541, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0918785890073831, | |
| "grad_norm": 0.9926491975784302, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.8349, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.09375366225243173, | |
| "grad_norm": 2.0560526847839355, | |
| "learning_rate": 1e-05, | |
| "loss": 2.4243, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09375366225243173, | |
| "eval_loss": 2.0661635398864746, | |
| "eval_runtime": 2.1063, | |
| "eval_samples_per_second": 23.738, | |
| "eval_steps_per_second": 6.172, | |
| "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": 1.0597019060849869e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |