{ "best_metric": 0.53879714012146, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.021379513081589568, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0004275902616317913, "grad_norm": 8.391215324401855, "learning_rate": 5e-05, "loss": 7.0327, "step": 1 }, { "epoch": 0.0004275902616317913, "eval_loss": 0.6975424289703369, "eval_runtime": 4.7085, "eval_samples_per_second": 10.619, "eval_steps_per_second": 2.761, "step": 1 }, { "epoch": 0.0008551805232635826, "grad_norm": 11.932012557983398, "learning_rate": 0.0001, "loss": 9.4884, "step": 2 }, { "epoch": 0.001282770784895374, "grad_norm": 8.802075386047363, "learning_rate": 9.990365154573717e-05, "loss": 9.2186, "step": 3 }, { "epoch": 0.0017103610465271652, "grad_norm": 27.2766056060791, "learning_rate": 9.961501876182148e-05, "loss": 10.3906, "step": 4 }, { "epoch": 0.0021379513081589566, "grad_norm": 20.10179328918457, "learning_rate": 9.913533761814537e-05, "loss": 10.4248, "step": 5 }, { "epoch": 0.002565541569790748, "grad_norm": 9.658151626586914, "learning_rate": 9.846666218300807e-05, "loss": 9.7941, "step": 6 }, { "epoch": 0.0029931318314225393, "grad_norm": 8.7197847366333, "learning_rate": 9.761185582727977e-05, "loss": 9.9185, "step": 7 }, { "epoch": 0.0034207220930543305, "grad_norm": 9.281495094299316, "learning_rate": 9.657457896300791e-05, "loss": 10.2751, "step": 8 }, { "epoch": 0.003848312354686122, "grad_norm": 8.022472381591797, "learning_rate": 9.535927336897098e-05, "loss": 10.6021, "step": 9 }, { "epoch": 0.004275902616317913, "grad_norm": 7.8892998695373535, "learning_rate": 9.397114317029975e-05, "loss": 10.0772, "step": 10 }, { "epoch": 0.004703492877949704, "grad_norm": 8.109823226928711, "learning_rate": 9.241613255361455e-05, "loss": 10.0034, "step": 11 }, { "epoch": 0.005131083139581496, "grad_norm": 10.048957824707031, "learning_rate": 9.070090031310558e-05, "loss": 10.6619, "step": 12 }, { "epoch": 0.0055586734012132875, "grad_norm": 6.909541606903076, "learning_rate": 8.883279133655399e-05, "loss": 7.6315, "step": 13 }, { "epoch": 0.005986263662845079, "grad_norm": 10.860377311706543, "learning_rate": 8.681980515339464e-05, "loss": 8.1656, "step": 14 }, { "epoch": 0.00641385392447687, "grad_norm": 7.818599700927734, "learning_rate": 8.467056167950311e-05, "loss": 8.6555, "step": 15 }, { "epoch": 0.006841444186108661, "grad_norm": 6.410884380340576, "learning_rate": 8.239426430539243e-05, "loss": 8.851, "step": 16 }, { "epoch": 0.007269034447740453, "grad_norm": 6.579470634460449, "learning_rate": 8.000066048588211e-05, "loss": 8.0487, "step": 17 }, { "epoch": 0.007696624709372244, "grad_norm": 7.002913475036621, "learning_rate": 7.75e-05, "loss": 9.0117, "step": 18 }, { "epoch": 0.008124214971004035, "grad_norm": 6.50584077835083, "learning_rate": 7.490299105985507e-05, "loss": 9.1714, "step": 19 }, { "epoch": 0.008551805232635826, "grad_norm": 6.4462714195251465, "learning_rate": 7.222075445642904e-05, "loss": 8.9649, "step": 20 }, { "epoch": 0.008979395494267618, "grad_norm": 6.682434558868408, "learning_rate": 6.946477593864228e-05, "loss": 9.3569, "step": 21 }, { "epoch": 0.009406985755899409, "grad_norm": 7.054783821105957, "learning_rate": 6.664685702961344e-05, "loss": 9.7019, "step": 22 }, { "epoch": 0.009834576017531202, "grad_norm": 6.702040195465088, "learning_rate": 6.377906449072578e-05, "loss": 9.5754, "step": 23 }, { "epoch": 0.010262166279162993, "grad_norm": 7.628874778747559, "learning_rate": 6.087367864990233e-05, "loss": 9.8834, "step": 24 }, { "epoch": 0.010689756540794784, "grad_norm": 9.231013298034668, "learning_rate": 5.794314081535644e-05, "loss": 10.593, "step": 25 }, { "epoch": 0.010689756540794784, "eval_loss": 0.5549858212471008, "eval_runtime": 4.7576, "eval_samples_per_second": 10.51, "eval_steps_per_second": 2.732, "step": 25 }, { "epoch": 0.011117346802426575, "grad_norm": 6.102064609527588, "learning_rate": 5.500000000000001e-05, "loss": 5.7123, "step": 26 }, { "epoch": 0.011544937064058366, "grad_norm": 7.0178656578063965, "learning_rate": 5.205685918464356e-05, "loss": 7.5794, "step": 27 }, { "epoch": 0.011972527325690157, "grad_norm": 6.182474136352539, "learning_rate": 4.912632135009769e-05, "loss": 7.5756, "step": 28 }, { "epoch": 0.012400117587321948, "grad_norm": 5.909448146820068, "learning_rate": 4.6220935509274235e-05, "loss": 7.8836, "step": 29 }, { "epoch": 0.01282770784895374, "grad_norm": 6.4864726066589355, "learning_rate": 4.3353142970386564e-05, "loss": 8.2802, "step": 30 }, { "epoch": 0.01325529811058553, "grad_norm": 6.8360443115234375, "learning_rate": 4.053522406135775e-05, "loss": 8.946, "step": 31 }, { "epoch": 0.013682888372217322, "grad_norm": 6.480278491973877, "learning_rate": 3.777924554357096e-05, "loss": 8.9649, "step": 32 }, { "epoch": 0.014110478633849115, "grad_norm": 6.515498161315918, "learning_rate": 3.509700894014496e-05, "loss": 8.7772, "step": 33 }, { "epoch": 0.014538068895480906, "grad_norm": 6.456510066986084, "learning_rate": 3.250000000000001e-05, "loss": 9.118, "step": 34 }, { "epoch": 0.014965659157112697, "grad_norm": 6.677673816680908, "learning_rate": 2.9999339514117912e-05, "loss": 9.3821, "step": 35 }, { "epoch": 0.015393249418744488, "grad_norm": 7.584144592285156, "learning_rate": 2.760573569460757e-05, "loss": 9.8773, "step": 36 }, { "epoch": 0.01582083968037628, "grad_norm": 7.644411087036133, "learning_rate": 2.53294383204969e-05, "loss": 10.0979, "step": 37 }, { "epoch": 0.01624842994200807, "grad_norm": 6.097660064697266, "learning_rate": 2.3180194846605367e-05, "loss": 7.3581, "step": 38 }, { "epoch": 0.01667602020363986, "grad_norm": 5.650531768798828, "learning_rate": 2.1167208663446025e-05, "loss": 6.9252, "step": 39 }, { "epoch": 0.017103610465271653, "grad_norm": 6.409210205078125, "learning_rate": 1.9299099686894423e-05, "loss": 7.6358, "step": 40 }, { "epoch": 0.017531200726903444, "grad_norm": 6.688713073730469, "learning_rate": 1.758386744638546e-05, "loss": 8.1115, "step": 41 }, { "epoch": 0.017958790988535235, "grad_norm": 6.200973033905029, "learning_rate": 1.602885682970026e-05, "loss": 8.2123, "step": 42 }, { "epoch": 0.018386381250167026, "grad_norm": 6.261044025421143, "learning_rate": 1.464072663102903e-05, "loss": 8.687, "step": 43 }, { "epoch": 0.018813971511798817, "grad_norm": 5.8840179443359375, "learning_rate": 1.3425421036992098e-05, "loss": 8.2914, "step": 44 }, { "epoch": 0.01924156177343061, "grad_norm": 6.317307472229004, "learning_rate": 1.2388144172720251e-05, "loss": 8.8269, "step": 45 }, { "epoch": 0.019669152035062403, "grad_norm": 6.801748275756836, "learning_rate": 1.1533337816991932e-05, "loss": 9.2658, "step": 46 }, { "epoch": 0.020096742296694194, "grad_norm": 6.915708065032959, "learning_rate": 1.0864662381854632e-05, "loss": 9.0082, "step": 47 }, { "epoch": 0.020524332558325985, "grad_norm": 6.995912551879883, "learning_rate": 1.0384981238178534e-05, "loss": 9.375, "step": 48 }, { "epoch": 0.020951922819957777, "grad_norm": 8.353010177612305, "learning_rate": 1.0096348454262845e-05, "loss": 10.1514, "step": 49 }, { "epoch": 0.021379513081589568, "grad_norm": 9.611238479614258, "learning_rate": 1e-05, "loss": 10.2421, "step": 50 }, { "epoch": 0.021379513081589568, "eval_loss": 0.53879714012146, "eval_runtime": 4.7618, "eval_samples_per_second": 10.5, "eval_steps_per_second": 2.73, "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": 5.7570367304944845e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }