{ "best_metric": 0.5892420411109924, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.000561553256306945, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.12310651261389e-05, "grad_norm": 0.4133361279964447, "learning_rate": 0.0001, "loss": 0.249, "step": 1 }, { "epoch": 1.12310651261389e-05, "eval_loss": 0.8146378397941589, "eval_runtime": 13134.3165, "eval_samples_per_second": 2.854, "eval_steps_per_second": 1.427, "step": 1 }, { "epoch": 2.24621302522778e-05, "grad_norm": 0.47328856587409973, "learning_rate": 0.0002, "loss": 0.3426, "step": 2 }, { "epoch": 3.36931953784167e-05, "grad_norm": 0.5796116590499878, "learning_rate": 0.00019978589232386035, "loss": 0.3981, "step": 3 }, { "epoch": 4.49242605045556e-05, "grad_norm": 0.6268879771232605, "learning_rate": 0.00019914448613738106, "loss": 0.6075, "step": 4 }, { "epoch": 5.61553256306945e-05, "grad_norm": 0.47303611040115356, "learning_rate": 0.00019807852804032305, "loss": 0.4675, "step": 5 }, { "epoch": 6.73863907568334e-05, "grad_norm": 0.5359629988670349, "learning_rate": 0.00019659258262890683, "loss": 0.6045, "step": 6 }, { "epoch": 7.86174558829723e-05, "grad_norm": 0.462693452835083, "learning_rate": 0.0001946930129495106, "loss": 0.2506, "step": 7 }, { "epoch": 8.98485210091112e-05, "grad_norm": 0.5416392087936401, "learning_rate": 0.0001923879532511287, "loss": 0.5026, "step": 8 }, { "epoch": 0.0001010795861352501, "grad_norm": 0.6114709973335266, "learning_rate": 0.00018968727415326884, "loss": 0.3977, "step": 9 }, { "epoch": 0.000112310651261389, "grad_norm": 0.6693122386932373, "learning_rate": 0.00018660254037844388, "loss": 0.6551, "step": 10 }, { "epoch": 0.0001235417163875279, "grad_norm": 0.5685533285140991, "learning_rate": 0.00018314696123025454, "loss": 0.3929, "step": 11 }, { "epoch": 0.0001347727815136668, "grad_norm": 0.6653563976287842, "learning_rate": 0.00017933533402912354, "loss": 0.3422, "step": 12 }, { "epoch": 0.0001460038466398057, "grad_norm": 0.8029443621635437, "learning_rate": 0.00017518398074789775, "loss": 0.6446, "step": 13 }, { "epoch": 0.0001572349117659446, "grad_norm": 0.8001309037208557, "learning_rate": 0.00017071067811865476, "loss": 0.6897, "step": 14 }, { "epoch": 0.0001684659768920835, "grad_norm": 0.5024366974830627, "learning_rate": 0.00016593458151000688, "loss": 0.1967, "step": 15 }, { "epoch": 0.0001796970420182224, "grad_norm": 0.6300889253616333, "learning_rate": 0.00016087614290087208, "loss": 0.6056, "step": 16 }, { "epoch": 0.0001909281071443613, "grad_norm": 0.5821546316146851, "learning_rate": 0.00015555702330196023, "loss": 0.3552, "step": 17 }, { "epoch": 0.0002021591722705002, "grad_norm": 0.5437122583389282, "learning_rate": 0.00015000000000000001, "loss": 0.4312, "step": 18 }, { "epoch": 0.0002133902373966391, "grad_norm": 0.5699002742767334, "learning_rate": 0.00014422886902190014, "loss": 0.5065, "step": 19 }, { "epoch": 0.000224621302522778, "grad_norm": 0.7202039361000061, "learning_rate": 0.000138268343236509, "loss": 0.4888, "step": 20 }, { "epoch": 0.00023585236764891692, "grad_norm": 0.6731573343276978, "learning_rate": 0.00013214394653031616, "loss": 0.7045, "step": 21 }, { "epoch": 0.0002470834327750558, "grad_norm": 0.6215887069702148, "learning_rate": 0.00012588190451025207, "loss": 0.5809, "step": 22 }, { "epoch": 0.0002583144979011947, "grad_norm": 0.8584797978401184, "learning_rate": 0.00011950903220161285, "loss": 0.6433, "step": 23 }, { "epoch": 0.0002695455630273336, "grad_norm": 0.7280075550079346, "learning_rate": 0.00011305261922200519, "loss": 0.5682, "step": 24 }, { "epoch": 0.0002807766281534725, "grad_norm": 0.6702390909194946, "learning_rate": 0.00010654031292301432, "loss": 0.6913, "step": 25 }, { "epoch": 0.0002807766281534725, "eval_loss": 0.5954957604408264, "eval_runtime": 13213.5826, "eval_samples_per_second": 2.837, "eval_steps_per_second": 1.419, "step": 25 }, { "epoch": 0.0002920076932796114, "grad_norm": 0.7325270771980286, "learning_rate": 0.0001, "loss": 0.7688, "step": 26 }, { "epoch": 0.0003032387584057503, "grad_norm": 0.7012045979499817, "learning_rate": 9.345968707698569e-05, "loss": 0.6944, "step": 27 }, { "epoch": 0.0003144698235318892, "grad_norm": 0.6815605163574219, "learning_rate": 8.694738077799488e-05, "loss": 0.6855, "step": 28 }, { "epoch": 0.0003257008886580281, "grad_norm": 0.7034103274345398, "learning_rate": 8.049096779838719e-05, "loss": 0.6411, "step": 29 }, { "epoch": 0.000336931953784167, "grad_norm": 0.7424677014350891, "learning_rate": 7.411809548974792e-05, "loss": 0.6832, "step": 30 }, { "epoch": 0.0003481630189103059, "grad_norm": 0.7293113470077515, "learning_rate": 6.785605346968386e-05, "loss": 0.568, "step": 31 }, { "epoch": 0.0003593940840364448, "grad_norm": 0.8168377876281738, "learning_rate": 6.173165676349103e-05, "loss": 0.6995, "step": 32 }, { "epoch": 0.00037062514916258373, "grad_norm": 0.7216925024986267, "learning_rate": 5.577113097809989e-05, "loss": 0.705, "step": 33 }, { "epoch": 0.0003818562142887226, "grad_norm": 1.9464884996414185, "learning_rate": 5.000000000000002e-05, "loss": 0.6531, "step": 34 }, { "epoch": 0.0003930872794148615, "grad_norm": 0.8291040062904358, "learning_rate": 4.444297669803981e-05, "loss": 0.6667, "step": 35 }, { "epoch": 0.0004043183445410004, "grad_norm": 0.8872710466384888, "learning_rate": 3.9123857099127936e-05, "loss": 0.5128, "step": 36 }, { "epoch": 0.0004155494096671393, "grad_norm": 0.967703640460968, "learning_rate": 3.406541848999312e-05, "loss": 0.7342, "step": 37 }, { "epoch": 0.0004267804747932782, "grad_norm": 0.8660141825675964, "learning_rate": 2.9289321881345254e-05, "loss": 0.5803, "step": 38 }, { "epoch": 0.0004380115399194171, "grad_norm": 1.001227855682373, "learning_rate": 2.4816019252102273e-05, "loss": 0.617, "step": 39 }, { "epoch": 0.000449242605045556, "grad_norm": 0.9558192491531372, "learning_rate": 2.0664665970876496e-05, "loss": 0.8064, "step": 40 }, { "epoch": 0.0004604736701716949, "grad_norm": 1.4016711711883545, "learning_rate": 1.6853038769745467e-05, "loss": 1.0338, "step": 41 }, { "epoch": 0.00047170473529783383, "grad_norm": 0.9859164953231812, "learning_rate": 1.339745962155613e-05, "loss": 0.7711, "step": 42 }, { "epoch": 0.0004829358004239727, "grad_norm": 0.8740882873535156, "learning_rate": 1.0312725846731175e-05, "loss": 0.6106, "step": 43 }, { "epoch": 0.0004941668655501116, "grad_norm": 1.0575542449951172, "learning_rate": 7.612046748871327e-06, "loss": 0.6771, "step": 44 }, { "epoch": 0.0005053979306762505, "grad_norm": 1.3176660537719727, "learning_rate": 5.306987050489442e-06, "loss": 0.9257, "step": 45 }, { "epoch": 0.0005166289958023894, "grad_norm": 0.936985433101654, "learning_rate": 3.40741737109318e-06, "loss": 0.6682, "step": 46 }, { "epoch": 0.0005278600609285283, "grad_norm": 1.1479442119598389, "learning_rate": 1.921471959676957e-06, "loss": 0.7345, "step": 47 }, { "epoch": 0.0005390911260546673, "grad_norm": 1.1492356061935425, "learning_rate": 8.555138626189618e-07, "loss": 0.5426, "step": 48 }, { "epoch": 0.0005503221911808061, "grad_norm": 1.387621283531189, "learning_rate": 2.141076761396521e-07, "loss": 0.574, "step": 49 }, { "epoch": 0.000561553256306945, "grad_norm": 1.3614716529846191, "learning_rate": 0.0, "loss": 0.5347, "step": 50 }, { "epoch": 0.000561553256306945, "eval_loss": 0.5892420411109924, "eval_runtime": 13214.8134, "eval_samples_per_second": 2.837, "eval_steps_per_second": 1.418, "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": 7.41887283560448e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }