| { | |
| "best_metric": 4.958001136779785, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.01408153207068929, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002816306414137858, | |
| "grad_norm": 48.62163543701172, | |
| "learning_rate": 0.0001, | |
| "loss": 23.4818, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002816306414137858, | |
| "eval_loss": 7.5018486976623535, | |
| "eval_runtime": 400.4908, | |
| "eval_samples_per_second": 3.733, | |
| "eval_steps_per_second": 1.868, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005632612828275716, | |
| "grad_norm": 50.03125762939453, | |
| "learning_rate": 0.0002, | |
| "loss": 25.3606, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008448919242413575, | |
| "grad_norm": 36.288734436035156, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 24.6152, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011265225656551432, | |
| "grad_norm": 35.620784759521484, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 21.223, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014081532070689292, | |
| "grad_norm": 38.215370178222656, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 18.8518, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001689783848482715, | |
| "grad_norm": 24.101730346679688, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 18.2537, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001971414489896501, | |
| "grad_norm": 23.53477668762207, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 18.4047, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022530451313102864, | |
| "grad_norm": 22.56336212158203, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 17.9984, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0025346757727240724, | |
| "grad_norm": 25.97075080871582, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 18.8505, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0028163064141378583, | |
| "grad_norm": 29.8724365234375, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 19.6848, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003097937055551644, | |
| "grad_norm": 73.4782943725586, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 19.3712, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00337956769696543, | |
| "grad_norm": 52.7482795715332, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 18.7228, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0036611983383792158, | |
| "grad_norm": 26.27608299255371, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 19.0088, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003942828979793002, | |
| "grad_norm": 28.202800750732422, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 18.9887, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004224459621206787, | |
| "grad_norm": 50.869102478027344, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 20.59, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004506090262620573, | |
| "grad_norm": 32.090274810791016, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 18.3551, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004787720904034359, | |
| "grad_norm": 29.982337951660156, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 18.6836, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005069351545448145, | |
| "grad_norm": 35.667816162109375, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 19.2915, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00535098218686193, | |
| "grad_norm": 26.442718505859375, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 20.3658, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005632612828275717, | |
| "grad_norm": 33.17983627319336, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 20.531, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005914243469689502, | |
| "grad_norm": 24.06730842590332, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 19.4856, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006195874111103288, | |
| "grad_norm": 22.876537322998047, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 20.0974, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006477504752517074, | |
| "grad_norm": 23.80173683166504, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 19.9339, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00675913539393086, | |
| "grad_norm": 23.31247329711914, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 20.3456, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007040766035344645, | |
| "grad_norm": 21.842885971069336, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 19.6822, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007040766035344645, | |
| "eval_loss": 5.01399564743042, | |
| "eval_runtime": 403.6754, | |
| "eval_samples_per_second": 3.703, | |
| "eval_steps_per_second": 1.853, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0073223966767584315, | |
| "grad_norm": 22.809677124023438, | |
| "learning_rate": 0.0001, | |
| "loss": 19.6608, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007604027318172217, | |
| "grad_norm": 26.614421844482422, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 20.0502, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007885657959586003, | |
| "grad_norm": 22.92184066772461, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 20.2952, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.008167288600999788, | |
| "grad_norm": 25.129104614257812, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 20.0264, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008448919242413575, | |
| "grad_norm": 25.90605354309082, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 20.6772, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008730549883827361, | |
| "grad_norm": 23.097158432006836, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 19.3772, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.009012180525241146, | |
| "grad_norm": 19.780305862426758, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 19.4421, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.009293811166654932, | |
| "grad_norm": 23.319713592529297, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 19.4254, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009575441808068718, | |
| "grad_norm": 25.547657012939453, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 20.5563, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009857072449482503, | |
| "grad_norm": 22.37945556640625, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 21.7697, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01013870309089629, | |
| "grad_norm": 25.38311195373535, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 21.9471, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010420333732310076, | |
| "grad_norm": 20.930171966552734, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 21.8591, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01070196437372386, | |
| "grad_norm": 30.409629821777344, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 23.305, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010983595015137647, | |
| "grad_norm": 19.549955368041992, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 22.0507, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.011265225656551433, | |
| "grad_norm": 25.194637298583984, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 22.3263, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011546856297965218, | |
| "grad_norm": 24.036544799804688, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 22.2299, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011828486939379004, | |
| "grad_norm": 24.677072525024414, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 22.3443, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01211011758079279, | |
| "grad_norm": 23.8966121673584, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 22.0331, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.012391748222206575, | |
| "grad_norm": 21.31231117248535, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 21.334, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012673378863620362, | |
| "grad_norm": 22.37716293334961, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 22.0767, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012955009505034148, | |
| "grad_norm": 22.888154983520508, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 22.6545, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.013236640146447933, | |
| "grad_norm": 21.42641830444336, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 24.4605, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.01351827078786172, | |
| "grad_norm": 22.642194747924805, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 24.1472, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013799901429275506, | |
| "grad_norm": 31.944076538085938, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 23.9481, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01408153207068929, | |
| "grad_norm": 50.73974609375, | |
| "learning_rate": 0.0, | |
| "loss": 26.5203, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01408153207068929, | |
| "eval_loss": 4.958001136779785, | |
| "eval_runtime": 403.6789, | |
| "eval_samples_per_second": 3.703, | |
| "eval_steps_per_second": 1.853, | |
| "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": 7.03129498681344e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |