{ "best_metric": 1.9969189167022705, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.029523018728665005, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005904603745733001, "grad_norm": 17.38508415222168, "learning_rate": 5e-05, "loss": 6.2419, "step": 1 }, { "epoch": 0.0005904603745733001, "eval_loss": 8.437135696411133, "eval_runtime": 0.5006, "eval_samples_per_second": 99.887, "eval_steps_per_second": 25.971, "step": 1 }, { "epoch": 0.0011809207491466002, "grad_norm": 36.33082580566406, "learning_rate": 0.0001, "loss": 7.2628, "step": 2 }, { "epoch": 0.0017713811237199005, "grad_norm": 31.663164138793945, "learning_rate": 9.990365154573717e-05, "loss": 7.5891, "step": 3 }, { "epoch": 0.0023618414982932005, "grad_norm": 11.801265716552734, "learning_rate": 9.961501876182148e-05, "loss": 6.2904, "step": 4 }, { "epoch": 0.0029523018728665005, "grad_norm": 48.22990417480469, "learning_rate": 9.913533761814537e-05, "loss": 6.6358, "step": 5 }, { "epoch": 0.003542762247439801, "grad_norm": 17.07508659362793, "learning_rate": 9.846666218300807e-05, "loss": 6.1791, "step": 6 }, { "epoch": 0.0041332226220131005, "grad_norm": 6.440609455108643, "learning_rate": 9.761185582727977e-05, "loss": 6.1573, "step": 7 }, { "epoch": 0.004723682996586401, "grad_norm": 5.693165302276611, "learning_rate": 9.657457896300791e-05, "loss": 5.9697, "step": 8 }, { "epoch": 0.005314143371159701, "grad_norm": 4.884424686431885, "learning_rate": 9.535927336897098e-05, "loss": 5.557, "step": 9 }, { "epoch": 0.005904603745733001, "grad_norm": 4.971529483795166, "learning_rate": 9.397114317029975e-05, "loss": 5.5059, "step": 10 }, { "epoch": 0.006495064120306301, "grad_norm": 4.848908424377441, "learning_rate": 9.241613255361455e-05, "loss": 5.6318, "step": 11 }, { "epoch": 0.007085524494879602, "grad_norm": 4.540520191192627, "learning_rate": 9.070090031310558e-05, "loss": 5.2879, "step": 12 }, { "epoch": 0.0076759848694529014, "grad_norm": 5.37409782409668, "learning_rate": 8.883279133655399e-05, "loss": 4.3364, "step": 13 }, { "epoch": 0.008266445244026201, "grad_norm": 5.091475486755371, "learning_rate": 8.681980515339464e-05, "loss": 4.3171, "step": 14 }, { "epoch": 0.008856905618599501, "grad_norm": 4.849145889282227, "learning_rate": 8.467056167950311e-05, "loss": 4.2864, "step": 15 }, { "epoch": 0.009447365993172802, "grad_norm": 5.3735809326171875, "learning_rate": 8.239426430539243e-05, "loss": 4.5548, "step": 16 }, { "epoch": 0.010037826367746102, "grad_norm": 5.725705146789551, "learning_rate": 8.000066048588211e-05, "loss": 4.5118, "step": 17 }, { "epoch": 0.010628286742319403, "grad_norm": 6.016762733459473, "learning_rate": 7.75e-05, "loss": 4.0229, "step": 18 }, { "epoch": 0.011218747116892702, "grad_norm": 7.6975250244140625, "learning_rate": 7.490299105985507e-05, "loss": 4.2581, "step": 19 }, { "epoch": 0.011809207491466002, "grad_norm": 7.248927116394043, "learning_rate": 7.222075445642904e-05, "loss": 3.945, "step": 20 }, { "epoch": 0.012399667866039302, "grad_norm": 8.233935356140137, "learning_rate": 6.946477593864228e-05, "loss": 3.5037, "step": 21 }, { "epoch": 0.012990128240612603, "grad_norm": 7.0697407722473145, "learning_rate": 6.664685702961344e-05, "loss": 3.6214, "step": 22 }, { "epoch": 0.013580588615185903, "grad_norm": 13.036471366882324, "learning_rate": 6.377906449072578e-05, "loss": 3.6104, "step": 23 }, { "epoch": 0.014171048989759204, "grad_norm": 10.6988525390625, "learning_rate": 6.087367864990233e-05, "loss": 3.4308, "step": 24 }, { "epoch": 0.014761509364332502, "grad_norm": 8.208454132080078, "learning_rate": 5.794314081535644e-05, "loss": 3.4858, "step": 25 }, { "epoch": 0.014761509364332502, "eval_loss": 2.7142794132232666, "eval_runtime": 0.4999, "eval_samples_per_second": 100.026, "eval_steps_per_second": 26.007, "step": 25 }, { "epoch": 0.015351969738905803, "grad_norm": 5.699878215789795, "learning_rate": 5.500000000000001e-05, "loss": 2.2477, "step": 26 }, { "epoch": 0.0159424301134791, "grad_norm": 7.3144612312316895, "learning_rate": 5.205685918464356e-05, "loss": 3.0987, "step": 27 }, { "epoch": 0.016532890488052402, "grad_norm": 7.50764274597168, "learning_rate": 4.912632135009769e-05, "loss": 2.8751, "step": 28 }, { "epoch": 0.017123350862625702, "grad_norm": 6.4948039054870605, "learning_rate": 4.6220935509274235e-05, "loss": 2.6886, "step": 29 }, { "epoch": 0.017713811237199003, "grad_norm": 13.463104248046875, "learning_rate": 4.3353142970386564e-05, "loss": 2.9681, "step": 30 }, { "epoch": 0.018304271611772303, "grad_norm": 9.158689498901367, "learning_rate": 4.053522406135775e-05, "loss": 2.7377, "step": 31 }, { "epoch": 0.018894731986345604, "grad_norm": 6.033637046813965, "learning_rate": 3.777924554357096e-05, "loss": 2.7305, "step": 32 }, { "epoch": 0.019485192360918904, "grad_norm": 10.262680053710938, "learning_rate": 3.509700894014496e-05, "loss": 2.6665, "step": 33 }, { "epoch": 0.020075652735492205, "grad_norm": 8.832808494567871, "learning_rate": 3.250000000000001e-05, "loss": 2.6649, "step": 34 }, { "epoch": 0.020666113110065505, "grad_norm": 7.658655643463135, "learning_rate": 2.9999339514117912e-05, "loss": 2.4372, "step": 35 }, { "epoch": 0.021256573484638806, "grad_norm": 5.869558811187744, "learning_rate": 2.760573569460757e-05, "loss": 2.7042, "step": 36 }, { "epoch": 0.021847033859212106, "grad_norm": 6.306788921356201, "learning_rate": 2.53294383204969e-05, "loss": 2.7355, "step": 37 }, { "epoch": 0.022437494233785403, "grad_norm": 5.178953647613525, "learning_rate": 2.3180194846605367e-05, "loss": 2.4691, "step": 38 }, { "epoch": 0.023027954608358703, "grad_norm": 6.899292469024658, "learning_rate": 2.1167208663446025e-05, "loss": 2.3852, "step": 39 }, { "epoch": 0.023618414982932004, "grad_norm": 7.314828872680664, "learning_rate": 1.9299099686894423e-05, "loss": 2.3326, "step": 40 }, { "epoch": 0.024208875357505304, "grad_norm": 5.12600564956665, "learning_rate": 1.758386744638546e-05, "loss": 2.2436, "step": 41 }, { "epoch": 0.024799335732078605, "grad_norm": 6.7783918380737305, "learning_rate": 1.602885682970026e-05, "loss": 2.3238, "step": 42 }, { "epoch": 0.025389796106651905, "grad_norm": 7.407707691192627, "learning_rate": 1.464072663102903e-05, "loss": 2.4676, "step": 43 }, { "epoch": 0.025980256481225206, "grad_norm": 6.619644641876221, "learning_rate": 1.3425421036992098e-05, "loss": 2.543, "step": 44 }, { "epoch": 0.026570716855798506, "grad_norm": 6.882936000823975, "learning_rate": 1.2388144172720251e-05, "loss": 2.381, "step": 45 }, { "epoch": 0.027161177230371807, "grad_norm": 6.69130802154541, "learning_rate": 1.1533337816991932e-05, "loss": 2.4668, "step": 46 }, { "epoch": 0.027751637604945107, "grad_norm": 6.239401817321777, "learning_rate": 1.0864662381854632e-05, "loss": 2.481, "step": 47 }, { "epoch": 0.028342097979518407, "grad_norm": 5.6806960105896, "learning_rate": 1.0384981238178534e-05, "loss": 2.6168, "step": 48 }, { "epoch": 0.028932558354091704, "grad_norm": 6.273911952972412, "learning_rate": 1.0096348454262845e-05, "loss": 2.7033, "step": 49 }, { "epoch": 0.029523018728665005, "grad_norm": 10.321796417236328, "learning_rate": 1e-05, "loss": 2.8148, "step": 50 }, { "epoch": 0.029523018728665005, "eval_loss": 1.9969189167022705, "eval_runtime": 0.5013, "eval_samples_per_second": 99.731, "eval_steps_per_second": 25.93, "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": 8.33416392081408e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }