{ "best_metric": 0.12431660294532776, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.05829204313611192, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0011658408627222385, "grad_norm": 17.24015235900879, "learning_rate": 5e-05, "loss": 12.1759, "step": 1 }, { "epoch": 0.0011658408627222385, "eval_loss": 12.8995943069458, "eval_runtime": 175.2287, "eval_samples_per_second": 32.98, "eval_steps_per_second": 4.126, "step": 1 }, { "epoch": 0.002331681725444477, "grad_norm": 17.535289764404297, "learning_rate": 0.0001, "loss": 12.3466, "step": 2 }, { "epoch": 0.0034975225881667153, "grad_norm": 18.36772918701172, "learning_rate": 9.989294616193017e-05, "loss": 11.5776, "step": 3 }, { "epoch": 0.004663363450888954, "grad_norm": 16.71552848815918, "learning_rate": 9.957224306869053e-05, "loss": 8.4475, "step": 4 }, { "epoch": 0.005829204313611192, "grad_norm": 17.996538162231445, "learning_rate": 9.903926402016153e-05, "loss": 5.6639, "step": 5 }, { "epoch": 0.006995045176333431, "grad_norm": 16.047048568725586, "learning_rate": 9.829629131445342e-05, "loss": 3.0267, "step": 6 }, { "epoch": 0.00816088603905567, "grad_norm": 9.27939510345459, "learning_rate": 9.73465064747553e-05, "loss": 1.3969, "step": 7 }, { "epoch": 0.009326726901777908, "grad_norm": 7.133617401123047, "learning_rate": 9.619397662556435e-05, "loss": 0.834, "step": 8 }, { "epoch": 0.010492567764500145, "grad_norm": 5.511355876922607, "learning_rate": 9.484363707663442e-05, "loss": 0.4855, "step": 9 }, { "epoch": 0.011658408627222384, "grad_norm": 10.509987831115723, "learning_rate": 9.330127018922194e-05, "loss": 0.7562, "step": 10 }, { "epoch": 0.012824249489944622, "grad_norm": 7.408633708953857, "learning_rate": 9.157348061512727e-05, "loss": 0.5402, "step": 11 }, { "epoch": 0.013990090352666861, "grad_norm": 4.484230041503906, "learning_rate": 8.966766701456177e-05, "loss": 0.3087, "step": 12 }, { "epoch": 0.0151559312153891, "grad_norm": 4.411365985870361, "learning_rate": 8.759199037394887e-05, "loss": 0.3547, "step": 13 }, { "epoch": 0.01632177207811134, "grad_norm": 4.336910247802734, "learning_rate": 8.535533905932738e-05, "loss": 0.267, "step": 14 }, { "epoch": 0.017487612940833577, "grad_norm": 1.5031633377075195, "learning_rate": 8.296729075500344e-05, "loss": 0.206, "step": 15 }, { "epoch": 0.018653453803555816, "grad_norm": 1.7164764404296875, "learning_rate": 8.043807145043604e-05, "loss": 0.2121, "step": 16 }, { "epoch": 0.019819294666278055, "grad_norm": 3.2747690677642822, "learning_rate": 7.777851165098012e-05, "loss": 0.2256, "step": 17 }, { "epoch": 0.02098513552900029, "grad_norm": 1.200957179069519, "learning_rate": 7.500000000000001e-05, "loss": 0.1851, "step": 18 }, { "epoch": 0.02215097639172253, "grad_norm": 2.802654266357422, "learning_rate": 7.211443451095007e-05, "loss": 0.1723, "step": 19 }, { "epoch": 0.023316817254444767, "grad_norm": 2.411452054977417, "learning_rate": 6.91341716182545e-05, "loss": 0.1544, "step": 20 }, { "epoch": 0.024482658117167006, "grad_norm": 0.8326784372329712, "learning_rate": 6.607197326515808e-05, "loss": 0.1383, "step": 21 }, { "epoch": 0.025648498979889245, "grad_norm": 0.6607847809791565, "learning_rate": 6.294095225512603e-05, "loss": 0.1423, "step": 22 }, { "epoch": 0.026814339842611484, "grad_norm": 0.9250856041908264, "learning_rate": 5.9754516100806423e-05, "loss": 0.1132, "step": 23 }, { "epoch": 0.027980180705333722, "grad_norm": 3.356832504272461, "learning_rate": 5.6526309611002594e-05, "loss": 0.1259, "step": 24 }, { "epoch": 0.02914602156805596, "grad_norm": 1.1452975273132324, "learning_rate": 5.327015646150716e-05, "loss": 0.1304, "step": 25 }, { "epoch": 0.02914602156805596, "eval_loss": 0.1733342856168747, "eval_runtime": 175.3599, "eval_samples_per_second": 32.955, "eval_steps_per_second": 4.123, "step": 25 }, { "epoch": 0.0303118624307782, "grad_norm": 5.865137100219727, "learning_rate": 5e-05, "loss": 0.2452, "step": 26 }, { "epoch": 0.031477703293500435, "grad_norm": 3.4867568016052246, "learning_rate": 4.6729843538492847e-05, "loss": 0.2191, "step": 27 }, { "epoch": 0.03264354415622268, "grad_norm": 2.2110798358917236, "learning_rate": 4.347369038899744e-05, "loss": 0.1272, "step": 28 }, { "epoch": 0.03380938501894491, "grad_norm": 1.080565094947815, "learning_rate": 4.0245483899193595e-05, "loss": 0.1427, "step": 29 }, { "epoch": 0.034975225881667155, "grad_norm": 2.4473915100097656, "learning_rate": 3.705904774487396e-05, "loss": 0.1414, "step": 30 }, { "epoch": 0.03614106674438939, "grad_norm": 1.6242526769638062, "learning_rate": 3.392802673484193e-05, "loss": 0.1169, "step": 31 }, { "epoch": 0.03730690760711163, "grad_norm": 0.48892101645469666, "learning_rate": 3.086582838174551e-05, "loss": 0.099, "step": 32 }, { "epoch": 0.03847274846983387, "grad_norm": 1.3659566640853882, "learning_rate": 2.7885565489049946e-05, "loss": 0.1268, "step": 33 }, { "epoch": 0.03963858933255611, "grad_norm": 1.2674806118011475, "learning_rate": 2.500000000000001e-05, "loss": 0.1134, "step": 34 }, { "epoch": 0.040804430195278345, "grad_norm": 0.8224604725837708, "learning_rate": 2.2221488349019903e-05, "loss": 0.1139, "step": 35 }, { "epoch": 0.04197027105800058, "grad_norm": 1.6787289381027222, "learning_rate": 1.9561928549563968e-05, "loss": 0.1354, "step": 36 }, { "epoch": 0.04313611192072282, "grad_norm": 2.8732471466064453, "learning_rate": 1.703270924499656e-05, "loss": 0.1431, "step": 37 }, { "epoch": 0.04430195278344506, "grad_norm": 0.9703247547149658, "learning_rate": 1.4644660940672627e-05, "loss": 0.1333, "step": 38 }, { "epoch": 0.0454677936461673, "grad_norm": 0.530714213848114, "learning_rate": 1.2408009626051137e-05, "loss": 0.1256, "step": 39 }, { "epoch": 0.046633634508889535, "grad_norm": 0.4804125726222992, "learning_rate": 1.0332332985438248e-05, "loss": 0.1302, "step": 40 }, { "epoch": 0.04779947537161178, "grad_norm": 0.6326729655265808, "learning_rate": 8.426519384872733e-06, "loss": 0.1215, "step": 41 }, { "epoch": 0.04896531623433401, "grad_norm": 0.6073267459869385, "learning_rate": 6.698729810778065e-06, "loss": 0.1261, "step": 42 }, { "epoch": 0.050131157097056255, "grad_norm": 0.46726205945014954, "learning_rate": 5.156362923365588e-06, "loss": 0.1253, "step": 43 }, { "epoch": 0.05129699795977849, "grad_norm": 0.7564307451248169, "learning_rate": 3.8060233744356633e-06, "loss": 0.1214, "step": 44 }, { "epoch": 0.05246283882250073, "grad_norm": 0.7565365433692932, "learning_rate": 2.653493525244721e-06, "loss": 0.1425, "step": 45 }, { "epoch": 0.05362867968522297, "grad_norm": 0.6103953719139099, "learning_rate": 1.70370868554659e-06, "loss": 0.1005, "step": 46 }, { "epoch": 0.0547945205479452, "grad_norm": 0.5481635332107544, "learning_rate": 9.607359798384785e-07, "loss": 0.112, "step": 47 }, { "epoch": 0.055960361410667445, "grad_norm": 1.2962995767593384, "learning_rate": 4.277569313094809e-07, "loss": 0.1086, "step": 48 }, { "epoch": 0.05712620227338968, "grad_norm": 1.229022741317749, "learning_rate": 1.0705383806982606e-07, "loss": 0.1553, "step": 49 }, { "epoch": 0.05829204313611192, "grad_norm": 0.7609378695487976, "learning_rate": 0.0, "loss": 0.1328, "step": 50 }, { "epoch": 0.05829204313611192, "eval_loss": 0.12431660294532776, "eval_runtime": 175.3436, "eval_samples_per_second": 32.958, "eval_steps_per_second": 4.123, "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": 5.968083617316864e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }