{ "best_metric": 1.1469987630844116, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.006671559143371806, "eval_steps": 25, "global_step": 25, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0002668623657348722, "grad_norm": 3.227802276611328, "learning_rate": 0.0001, "loss": 1.6172, "step": 1 }, { "epoch": 0.0002668623657348722, "eval_loss": 1.9063847064971924, "eval_runtime": 321.7231, "eval_samples_per_second": 4.905, "eval_steps_per_second": 2.452, "step": 1 }, { "epoch": 0.0005337247314697444, "grad_norm": 2.450011968612671, "learning_rate": 0.0002, "loss": 1.3715, "step": 2 }, { "epoch": 0.0008005870972046167, "grad_norm": 0.9362994432449341, "learning_rate": 0.00019978589232386035, "loss": 1.2027, "step": 3 }, { "epoch": 0.0010674494629394889, "grad_norm": 1.2160959243774414, "learning_rate": 0.00019914448613738106, "loss": 0.9595, "step": 4 }, { "epoch": 0.0013343118286743613, "grad_norm": 1.4689968824386597, "learning_rate": 0.00019807852804032305, "loss": 0.7926, "step": 5 }, { "epoch": 0.0016011741944092334, "grad_norm": 2.0516695976257324, "learning_rate": 0.00019659258262890683, "loss": 0.9129, "step": 6 }, { "epoch": 0.0018680365601441056, "grad_norm": 0.6819640398025513, "learning_rate": 0.0001946930129495106, "loss": 0.8064, "step": 7 }, { "epoch": 0.0021348989258789777, "grad_norm": 0.9235527515411377, "learning_rate": 0.0001923879532511287, "loss": 0.7465, "step": 8 }, { "epoch": 0.0024017612916138503, "grad_norm": 0.756666898727417, "learning_rate": 0.00018968727415326884, "loss": 0.7217, "step": 9 }, { "epoch": 0.0026686236573487225, "grad_norm": 0.7653118968009949, "learning_rate": 0.00018660254037844388, "loss": 1.0959, "step": 10 }, { "epoch": 0.0029354860230835947, "grad_norm": 0.854770302772522, "learning_rate": 0.00018314696123025454, "loss": 0.5922, "step": 11 }, { "epoch": 0.003202348388818467, "grad_norm": 0.7380660176277161, "learning_rate": 0.00017933533402912354, "loss": 0.7272, "step": 12 }, { "epoch": 0.003469210754553339, "grad_norm": 0.6519638895988464, "learning_rate": 0.00017518398074789775, "loss": 0.6851, "step": 13 }, { "epoch": 0.003736073120288211, "grad_norm": 0.6560354232788086, "learning_rate": 0.00017071067811865476, "loss": 0.7284, "step": 14 }, { "epoch": 0.004002935486023084, "grad_norm": 0.5490040183067322, "learning_rate": 0.00016593458151000688, "loss": 0.7328, "step": 15 }, { "epoch": 0.0042697978517579555, "grad_norm": 0.7207716703414917, "learning_rate": 0.00016087614290087208, "loss": 0.5902, "step": 16 }, { "epoch": 0.004536660217492828, "grad_norm": 0.7940784096717834, "learning_rate": 0.00015555702330196023, "loss": 0.7201, "step": 17 }, { "epoch": 0.004803522583227701, "grad_norm": 0.7808439135551453, "learning_rate": 0.00015000000000000001, "loss": 0.6098, "step": 18 }, { "epoch": 0.005070384948962572, "grad_norm": 0.9322609901428223, "learning_rate": 0.00014422886902190014, "loss": 1.0192, "step": 19 }, { "epoch": 0.005337247314697445, "grad_norm": 0.6111686825752258, "learning_rate": 0.000138268343236509, "loss": 1.0272, "step": 20 }, { "epoch": 0.005604109680432317, "grad_norm": 0.7473171949386597, "learning_rate": 0.00013214394653031616, "loss": 1.0828, "step": 21 }, { "epoch": 0.005870972046167189, "grad_norm": 0.6169211268424988, "learning_rate": 0.00012588190451025207, "loss": 0.9449, "step": 22 }, { "epoch": 0.006137834411902062, "grad_norm": 0.5477904677391052, "learning_rate": 0.00011950903220161285, "loss": 0.8641, "step": 23 }, { "epoch": 0.006404696777636934, "grad_norm": 0.6941477060317993, "learning_rate": 0.00011305261922200519, "loss": 1.1681, "step": 24 }, { "epoch": 0.006671559143371806, "grad_norm": 0.649423360824585, "learning_rate": 0.00010654031292301432, "loss": 1.3437, "step": 25 }, { "epoch": 0.006671559143371806, "eval_loss": 1.1469987630844116, "eval_runtime": 325.4881, "eval_samples_per_second": 4.848, "eval_steps_per_second": 2.424, "step": 25 } ], "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": false }, "attributes": {} } }, "total_flos": 1.37856974585856e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }