| { | |
| "best_metric": 0.4710901975631714, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0038014863811750396, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.602972762350079e-05, | |
| "grad_norm": 12.370462417602539, | |
| "learning_rate": 0.0001, | |
| "loss": 7.5042, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.602972762350079e-05, | |
| "eval_loss": 7.877859592437744, | |
| "eval_runtime": 2580.3387, | |
| "eval_samples_per_second": 2.146, | |
| "eval_steps_per_second": 1.073, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015205945524700157, | |
| "grad_norm": 4.348391056060791, | |
| "learning_rate": 0.0002, | |
| "loss": 7.0867, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00022808918287050236, | |
| "grad_norm": 5.850006103515625, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 6.4462, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00030411891049400314, | |
| "grad_norm": 5.417360305786133, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 6.0654, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00038014863811750395, | |
| "grad_norm": 5.490226745605469, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 4.1386, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004561783657410047, | |
| "grad_norm": 4.937723159790039, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 3.9597, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005322080933645055, | |
| "grad_norm": 4.298549175262451, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 4.4245, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006082378209880063, | |
| "grad_norm": 12.07129955291748, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 13.506, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006842675486115071, | |
| "grad_norm": 8.120107650756836, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 6.0184, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007602972762350079, | |
| "grad_norm": 8.249645233154297, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 2.788, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008363270038585087, | |
| "grad_norm": 4.474549770355225, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 2.0453, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0009123567314820094, | |
| "grad_norm": 8.384934425354004, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 2.3098, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0009883864591055103, | |
| "grad_norm": 6.300329208374023, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 1.0228, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001064416186729011, | |
| "grad_norm": 6.806110858917236, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.0228, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0011404459143525118, | |
| "grad_norm": 5.006272792816162, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.7173, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0012164756419760126, | |
| "grad_norm": 4.497860908508301, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.4711, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0012925053695995133, | |
| "grad_norm": 2.9026920795440674, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.4967, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0013685350972230143, | |
| "grad_norm": 2.7563633918762207, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.5066, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001444564824846515, | |
| "grad_norm": 3.4592440128326416, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.6263, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0015205945524700158, | |
| "grad_norm": 2.8285069465637207, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.6594, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0015966242800935166, | |
| "grad_norm": 2.328536033630371, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.4369, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0016726540077170173, | |
| "grad_norm": 2.3448400497436523, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.396, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.001748683735340518, | |
| "grad_norm": 1.3995438814163208, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.4162, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0018247134629640188, | |
| "grad_norm": 1.5537478923797607, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.3036, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0019007431905875198, | |
| "grad_norm": 6.457515716552734, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.9532, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0019007431905875198, | |
| "eval_loss": 0.5400802493095398, | |
| "eval_runtime": 2597.3196, | |
| "eval_samples_per_second": 2.132, | |
| "eval_steps_per_second": 1.066, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0019767729182110206, | |
| "grad_norm": 2.6046080589294434, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4354, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.002052802645834521, | |
| "grad_norm": 1.5984587669372559, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.4151, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002128832373458022, | |
| "grad_norm": 3.0031909942626953, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.5274, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.002204862101081523, | |
| "grad_norm": 0.9939762353897095, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.2949, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0022808918287050236, | |
| "grad_norm": 1.2130672931671143, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.3297, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0023569215563285246, | |
| "grad_norm": 3.6291580200195312, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.6363, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.002432951283952025, | |
| "grad_norm": 1.8360271453857422, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.4268, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.002508981011575526, | |
| "grad_norm": 1.8505597114562988, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.4135, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0025850107391990266, | |
| "grad_norm": 3.646937370300293, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.9458, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0026610404668225276, | |
| "grad_norm": 1.7447396516799927, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.3567, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0027370701944460286, | |
| "grad_norm": 1.7719615697860718, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.4307, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.002813099922069529, | |
| "grad_norm": 1.2421600818634033, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.3624, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.00288912964969303, | |
| "grad_norm": 2.101491689682007, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.7057, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0029651593773165306, | |
| "grad_norm": 1.3107458353042603, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.3915, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0030411891049400316, | |
| "grad_norm": 1.219789743423462, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.2561, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003117218832563532, | |
| "grad_norm": 1.4853408336639404, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.4317, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.003193248560187033, | |
| "grad_norm": 1.8641315698623657, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.7191, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.003269278287810534, | |
| "grad_norm": 1.435045599937439, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.5681, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0033453080154340347, | |
| "grad_norm": 1.6989673376083374, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.4162, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0034213377430575356, | |
| "grad_norm": 1.5967341661453247, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.4313, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003497367470681036, | |
| "grad_norm": 1.6816807985305786, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.4867, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.003573397198304537, | |
| "grad_norm": 1.977468729019165, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.4679, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0036494269259280377, | |
| "grad_norm": 1.6482903957366943, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.6017, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0037254566535515387, | |
| "grad_norm": 1.3200818300247192, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.347, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0038014863811750396, | |
| "grad_norm": 2.0896034240722656, | |
| "learning_rate": 0.0, | |
| "loss": 0.5163, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0038014863811750396, | |
| "eval_loss": 0.4710901975631714, | |
| "eval_runtime": 2597.4917, | |
| "eval_samples_per_second": 2.132, | |
| "eval_steps_per_second": 1.066, | |
| "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": 1.27239261782016e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |