{ "best_metric": 10.302452087402344, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 1.0256410256410255, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.020512820512820513, "grad_norm": 0.286721408367157, "learning_rate": 5e-05, "loss": 10.3777, "step": 1 }, { "epoch": 0.020512820512820513, "eval_loss": 10.361001014709473, "eval_runtime": 0.1132, "eval_samples_per_second": 441.801, "eval_steps_per_second": 114.868, "step": 1 }, { "epoch": 0.041025641025641026, "grad_norm": 0.269033282995224, "learning_rate": 0.0001, "loss": 10.3865, "step": 2 }, { "epoch": 0.06153846153846154, "grad_norm": 0.27711397409439087, "learning_rate": 9.990365154573717e-05, "loss": 10.3908, "step": 3 }, { "epoch": 0.08205128205128205, "grad_norm": 0.2814181447029114, "learning_rate": 9.961501876182148e-05, "loss": 10.3769, "step": 4 }, { "epoch": 0.10256410256410256, "grad_norm": 0.2789865732192993, "learning_rate": 9.913533761814537e-05, "loss": 10.3615, "step": 5 }, { "epoch": 0.12307692307692308, "grad_norm": 0.2830169200897217, "learning_rate": 9.846666218300807e-05, "loss": 10.3724, "step": 6 }, { "epoch": 0.14358974358974358, "grad_norm": 0.2746325731277466, "learning_rate": 9.761185582727977e-05, "loss": 10.3623, "step": 7 }, { "epoch": 0.1641025641025641, "grad_norm": 0.29302048683166504, "learning_rate": 9.657457896300791e-05, "loss": 10.3534, "step": 8 }, { "epoch": 0.18461538461538463, "grad_norm": 0.31308242678642273, "learning_rate": 9.535927336897098e-05, "loss": 10.3419, "step": 9 }, { "epoch": 0.20512820512820512, "grad_norm": 0.30729126930236816, "learning_rate": 9.397114317029975e-05, "loss": 10.3533, "step": 10 }, { "epoch": 0.22564102564102564, "grad_norm": 0.33675631880760193, "learning_rate": 9.241613255361455e-05, "loss": 10.3431, "step": 11 }, { "epoch": 0.24615384615384617, "grad_norm": 0.3637239634990692, "learning_rate": 9.070090031310558e-05, "loss": 10.3579, "step": 12 }, { "epoch": 0.26666666666666666, "grad_norm": 0.29550689458847046, "learning_rate": 8.883279133655399e-05, "loss": 10.3676, "step": 13 }, { "epoch": 0.28717948717948716, "grad_norm": 0.2810358703136444, "learning_rate": 8.681980515339464e-05, "loss": 10.3811, "step": 14 }, { "epoch": 0.3076923076923077, "grad_norm": 0.2913273572921753, "learning_rate": 8.467056167950311e-05, "loss": 10.3655, "step": 15 }, { "epoch": 0.3282051282051282, "grad_norm": 0.32051295042037964, "learning_rate": 8.239426430539243e-05, "loss": 10.3656, "step": 16 }, { "epoch": 0.3487179487179487, "grad_norm": 0.30518609285354614, "learning_rate": 8.000066048588211e-05, "loss": 10.3532, "step": 17 }, { "epoch": 0.36923076923076925, "grad_norm": 0.3246760964393616, "learning_rate": 7.75e-05, "loss": 10.3349, "step": 18 }, { "epoch": 0.38974358974358975, "grad_norm": 0.34310439229011536, "learning_rate": 7.490299105985507e-05, "loss": 10.3409, "step": 19 }, { "epoch": 0.41025641025641024, "grad_norm": 0.37758487462997437, "learning_rate": 7.222075445642904e-05, "loss": 10.3244, "step": 20 }, { "epoch": 0.4307692307692308, "grad_norm": 0.3841375410556793, "learning_rate": 6.946477593864228e-05, "loss": 10.3281, "step": 21 }, { "epoch": 0.4512820512820513, "grad_norm": 0.4036903381347656, "learning_rate": 6.664685702961344e-05, "loss": 10.3264, "step": 22 }, { "epoch": 0.4717948717948718, "grad_norm": 0.4160035252571106, "learning_rate": 6.377906449072578e-05, "loss": 10.3146, "step": 23 }, { "epoch": 0.49230769230769234, "grad_norm": 0.43653735518455505, "learning_rate": 6.087367864990233e-05, "loss": 10.334, "step": 24 }, { "epoch": 0.5128205128205128, "grad_norm": 0.3721294105052948, "learning_rate": 5.794314081535644e-05, "loss": 10.3471, "step": 25 }, { "epoch": 0.5128205128205128, "eval_loss": 10.323394775390625, "eval_runtime": 0.0959, "eval_samples_per_second": 521.472, "eval_steps_per_second": 135.583, "step": 25 }, { "epoch": 0.5333333333333333, "grad_norm": 0.35155364871025085, "learning_rate": 5.500000000000001e-05, "loss": 10.3635, "step": 26 }, { "epoch": 0.5538461538461539, "grad_norm": 0.3796391189098358, "learning_rate": 5.205685918464356e-05, "loss": 10.3495, "step": 27 }, { "epoch": 0.5743589743589743, "grad_norm": 0.38944631814956665, "learning_rate": 4.912632135009769e-05, "loss": 10.3472, "step": 28 }, { "epoch": 0.5948717948717949, "grad_norm": 0.3875417411327362, "learning_rate": 4.6220935509274235e-05, "loss": 10.3383, "step": 29 }, { "epoch": 0.6153846153846154, "grad_norm": 0.4149477183818817, "learning_rate": 4.3353142970386564e-05, "loss": 10.3198, "step": 30 }, { "epoch": 0.6358974358974359, "grad_norm": 0.42636293172836304, "learning_rate": 4.053522406135775e-05, "loss": 10.3185, "step": 31 }, { "epoch": 0.6564102564102564, "grad_norm": 0.43451759219169617, "learning_rate": 3.777924554357096e-05, "loss": 10.3118, "step": 32 }, { "epoch": 0.676923076923077, "grad_norm": 0.4598996341228485, "learning_rate": 3.509700894014496e-05, "loss": 10.3206, "step": 33 }, { "epoch": 0.6974358974358974, "grad_norm": 0.45923203229904175, "learning_rate": 3.250000000000001e-05, "loss": 10.3161, "step": 34 }, { "epoch": 0.717948717948718, "grad_norm": 0.477365642786026, "learning_rate": 2.9999339514117912e-05, "loss": 10.3025, "step": 35 }, { "epoch": 0.7384615384615385, "grad_norm": 0.49920061230659485, "learning_rate": 2.760573569460757e-05, "loss": 10.3202, "step": 36 }, { "epoch": 0.7589743589743589, "grad_norm": 0.4537535011768341, "learning_rate": 2.53294383204969e-05, "loss": 10.325, "step": 37 }, { "epoch": 0.7794871794871795, "grad_norm": 0.4087854027748108, "learning_rate": 2.3180194846605367e-05, "loss": 10.3412, "step": 38 }, { "epoch": 0.8, "grad_norm": 0.44184836745262146, "learning_rate": 2.1167208663446025e-05, "loss": 10.3441, "step": 39 }, { "epoch": 0.8205128205128205, "grad_norm": 0.4397507309913635, "learning_rate": 1.9299099686894423e-05, "loss": 10.3281, "step": 40 }, { "epoch": 0.841025641025641, "grad_norm": 0.437427818775177, "learning_rate": 1.758386744638546e-05, "loss": 10.3175, "step": 41 }, { "epoch": 0.8615384615384616, "grad_norm": 0.4404502511024475, "learning_rate": 1.602885682970026e-05, "loss": 10.3258, "step": 42 }, { "epoch": 0.882051282051282, "grad_norm": 0.4655083119869232, "learning_rate": 1.464072663102903e-05, "loss": 10.3021, "step": 43 }, { "epoch": 0.9025641025641026, "grad_norm": 0.4786524772644043, "learning_rate": 1.3425421036992098e-05, "loss": 10.302, "step": 44 }, { "epoch": 0.9230769230769231, "grad_norm": 0.5160654187202454, "learning_rate": 1.2388144172720251e-05, "loss": 10.2986, "step": 45 }, { "epoch": 0.9435897435897436, "grad_norm": 0.4955737888813019, "learning_rate": 1.1533337816991932e-05, "loss": 10.2909, "step": 46 }, { "epoch": 0.9641025641025641, "grad_norm": 0.5149694681167603, "learning_rate": 1.0864662381854632e-05, "loss": 10.2978, "step": 47 }, { "epoch": 0.9846153846153847, "grad_norm": 0.5238509178161621, "learning_rate": 1.0384981238178534e-05, "loss": 10.3114, "step": 48 }, { "epoch": 1.005128205128205, "grad_norm": 0.5735796093940735, "learning_rate": 1.0096348454262845e-05, "loss": 12.8739, "step": 49 }, { "epoch": 1.0256410256410255, "grad_norm": 0.46631649136543274, "learning_rate": 1e-05, "loss": 10.1867, "step": 50 }, { "epoch": 1.0256410256410255, "eval_loss": 10.302452087402344, "eval_runtime": 0.0887, "eval_samples_per_second": 563.575, "eval_steps_per_second": 146.529, "step": 50 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": 42768059596800.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }