{ "best_metric": 2.065424919128418, "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": 0.1900586038827896, "learning_rate": 5e-05, "loss": 2.5556, "step": 1 }, { "epoch": 0.0018750732450486347, "eval_loss": 2.7236664295196533, "eval_runtime": 2.0198, "eval_samples_per_second": 24.754, "eval_steps_per_second": 6.436, "step": 1 }, { "epoch": 0.0037501464900972694, "grad_norm": 0.3085673451423645, "learning_rate": 0.0001, "loss": 2.4983, "step": 2 }, { "epoch": 0.005625219735145904, "grad_norm": 0.3981899917125702, "learning_rate": 9.990365154573717e-05, "loss": 2.3013, "step": 3 }, { "epoch": 0.007500292980194539, "grad_norm": 0.44829872250556946, "learning_rate": 9.961501876182148e-05, "loss": 2.0061, "step": 4 }, { "epoch": 0.009375366225243174, "grad_norm": 0.4812873601913452, "learning_rate": 9.913533761814537e-05, "loss": 1.9114, "step": 5 }, { "epoch": 0.011250439470291808, "grad_norm": 0.7002121210098267, "learning_rate": 9.846666218300807e-05, "loss": 1.8413, "step": 6 }, { "epoch": 0.013125512715340444, "grad_norm": 0.7537447214126587, "learning_rate": 9.761185582727977e-05, "loss": 1.8732, "step": 7 }, { "epoch": 0.015000585960389078, "grad_norm": 0.8023700714111328, "learning_rate": 9.657457896300791e-05, "loss": 1.8305, "step": 8 }, { "epoch": 0.016875659205437713, "grad_norm": 0.8676446676254272, "learning_rate": 9.535927336897098e-05, "loss": 1.721, "step": 9 }, { "epoch": 0.01875073245048635, "grad_norm": 0.9874446392059326, "learning_rate": 9.397114317029975e-05, "loss": 1.5916, "step": 10 }, { "epoch": 0.02062580569553498, "grad_norm": 1.4691710472106934, "learning_rate": 9.241613255361455e-05, "loss": 2.0056, "step": 11 }, { "epoch": 0.022500878940583616, "grad_norm": 2.402691125869751, "learning_rate": 9.070090031310558e-05, "loss": 2.4262, "step": 12 }, { "epoch": 0.024375952185632252, "grad_norm": 1.7341423034667969, "learning_rate": 8.883279133655399e-05, "loss": 2.6671, "step": 13 }, { "epoch": 0.026251025430680888, "grad_norm": 1.931779384613037, "learning_rate": 8.681980515339464e-05, "loss": 2.5665, "step": 14 }, { "epoch": 0.02812609867572952, "grad_norm": 1.689328670501709, "learning_rate": 8.467056167950311e-05, "loss": 2.4579, "step": 15 }, { "epoch": 0.030001171920778155, "grad_norm": 1.3696123361587524, "learning_rate": 8.239426430539243e-05, "loss": 2.0914, "step": 16 }, { "epoch": 0.03187624516582679, "grad_norm": 1.2168139219284058, "learning_rate": 8.000066048588211e-05, "loss": 1.838, "step": 17 }, { "epoch": 0.033751318410875426, "grad_norm": 0.8948566317558289, "learning_rate": 7.75e-05, "loss": 1.7814, "step": 18 }, { "epoch": 0.03562639165592406, "grad_norm": 0.660253643989563, "learning_rate": 7.490299105985507e-05, "loss": 1.7363, "step": 19 }, { "epoch": 0.0375014649009727, "grad_norm": 0.706805944442749, "learning_rate": 7.222075445642904e-05, "loss": 1.8359, "step": 20 }, { "epoch": 0.03937653814602133, "grad_norm": 1.0919932126998901, "learning_rate": 6.946477593864228e-05, "loss": 1.7698, "step": 21 }, { "epoch": 0.04125161139106996, "grad_norm": 1.2657562494277954, "learning_rate": 6.664685702961344e-05, "loss": 1.6058, "step": 22 }, { "epoch": 0.0431266846361186, "grad_norm": 1.6102139949798584, "learning_rate": 6.377906449072578e-05, "loss": 1.8011, "step": 23 }, { "epoch": 0.04500175788116723, "grad_norm": 2.0994489192962646, "learning_rate": 6.087367864990233e-05, "loss": 1.9134, "step": 24 }, { "epoch": 0.046876831126215865, "grad_norm": 3.8206686973571777, "learning_rate": 5.794314081535644e-05, "loss": 2.5391, "step": 25 }, { "epoch": 0.046876831126215865, "eval_loss": 2.0982673168182373, "eval_runtime": 2.0054, "eval_samples_per_second": 24.933, "eval_steps_per_second": 6.482, "step": 25 }, { "epoch": 0.048751904371264504, "grad_norm": 0.2745285630226135, "learning_rate": 5.500000000000001e-05, "loss": 2.4923, "step": 26 }, { "epoch": 0.050626977616313136, "grad_norm": 0.30487480759620667, "learning_rate": 5.205685918464356e-05, "loss": 2.2179, "step": 27 }, { "epoch": 0.052502050861361775, "grad_norm": 0.2965129017829895, "learning_rate": 4.912632135009769e-05, "loss": 1.8993, "step": 28 }, { "epoch": 0.05437712410641041, "grad_norm": 0.3265594244003296, "learning_rate": 4.6220935509274235e-05, "loss": 1.8554, "step": 29 }, { "epoch": 0.05625219735145904, "grad_norm": 0.3232311010360718, "learning_rate": 4.3353142970386564e-05, "loss": 1.7311, "step": 30 }, { "epoch": 0.05812727059650768, "grad_norm": 0.28687211871147156, "learning_rate": 4.053522406135775e-05, "loss": 1.6268, "step": 31 }, { "epoch": 0.06000234384155631, "grad_norm": 0.35023847222328186, "learning_rate": 3.777924554357096e-05, "loss": 1.6425, "step": 32 }, { "epoch": 0.06187741708660494, "grad_norm": 0.3960030972957611, "learning_rate": 3.509700894014496e-05, "loss": 1.621, "step": 33 }, { "epoch": 0.06375249033165357, "grad_norm": 0.5620121955871582, "learning_rate": 3.250000000000001e-05, "loss": 1.5961, "step": 34 }, { "epoch": 0.06562756357670221, "grad_norm": 0.7287745475769043, "learning_rate": 2.9999339514117912e-05, "loss": 1.5636, "step": 35 }, { "epoch": 0.06750263682175085, "grad_norm": 1.0015517473220825, "learning_rate": 2.760573569460757e-05, "loss": 1.611, "step": 36 }, { "epoch": 0.06937771006679948, "grad_norm": 1.3635504245758057, "learning_rate": 2.53294383204969e-05, "loss": 2.1942, "step": 37 }, { "epoch": 0.07125278331184812, "grad_norm": 0.18668261170387268, "learning_rate": 2.3180194846605367e-05, "loss": 2.5232, "step": 38 }, { "epoch": 0.07312785655689676, "grad_norm": 0.17155809700489044, "learning_rate": 2.1167208663446025e-05, "loss": 2.4562, "step": 39 }, { "epoch": 0.0750029298019454, "grad_norm": 0.20558178424835205, "learning_rate": 1.9299099686894423e-05, "loss": 2.1893, "step": 40 }, { "epoch": 0.07687800304699402, "grad_norm": 0.2487691044807434, "learning_rate": 1.758386744638546e-05, "loss": 1.888, "step": 41 }, { "epoch": 0.07875307629204266, "grad_norm": 0.24857781827449799, "learning_rate": 1.602885682970026e-05, "loss": 1.7956, "step": 42 }, { "epoch": 0.0806281495370913, "grad_norm": 0.26391762495040894, "learning_rate": 1.464072663102903e-05, "loss": 1.6385, "step": 43 }, { "epoch": 0.08250322278213992, "grad_norm": 0.28500398993492126, "learning_rate": 1.3425421036992098e-05, "loss": 1.7647, "step": 44 }, { "epoch": 0.08437829602718856, "grad_norm": 0.3273405134677887, "learning_rate": 1.2388144172720251e-05, "loss": 1.5637, "step": 45 }, { "epoch": 0.0862533692722372, "grad_norm": 0.42559829354286194, "learning_rate": 1.1533337816991932e-05, "loss": 1.6502, "step": 46 }, { "epoch": 0.08812844251728583, "grad_norm": 0.5782425403594971, "learning_rate": 1.0864662381854632e-05, "loss": 1.5796, "step": 47 }, { "epoch": 0.09000351576233447, "grad_norm": 0.8577106595039368, "learning_rate": 1.0384981238178534e-05, "loss": 1.6572, "step": 48 }, { "epoch": 0.0918785890073831, "grad_norm": 0.9834227561950684, "learning_rate": 1.0096348454262845e-05, "loss": 1.8339, "step": 49 }, { "epoch": 0.09375366225243173, "grad_norm": 2.0529823303222656, "learning_rate": 1e-05, "loss": 2.4189, "step": 50 }, { "epoch": 0.09375366225243173, "eval_loss": 2.065424919128418, "eval_runtime": 2.0149, "eval_samples_per_second": 24.815, "eval_steps_per_second": 6.452, "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 }