| { | |
| "best_metric": 1.5591756105422974, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1519756838905775, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00303951367781155, | |
| "grad_norm": 39.25678253173828, | |
| "learning_rate": 0.0001, | |
| "loss": 14.3657, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00303951367781155, | |
| "eval_loss": 5.164518356323242, | |
| "eval_runtime": 66.7703, | |
| "eval_samples_per_second": 2.082, | |
| "eval_steps_per_second": 1.048, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0060790273556231, | |
| "grad_norm": 29.87421417236328, | |
| "learning_rate": 0.0002, | |
| "loss": 14.3471, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00911854103343465, | |
| "grad_norm": 32.23124313354492, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 12.0201, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0121580547112462, | |
| "grad_norm": 19.307538986206055, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 7.74, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015197568389057751, | |
| "grad_norm": 21.378904342651367, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 9.5993, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0182370820668693, | |
| "grad_norm": 12.437470436096191, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 5.2253, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02127659574468085, | |
| "grad_norm": 15.79073715209961, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 5.6309, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0243161094224924, | |
| "grad_norm": 17.300029754638672, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 6.4527, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02735562310030395, | |
| "grad_norm": 18.60094451904297, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 4.0331, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.030395136778115502, | |
| "grad_norm": 14.477279663085938, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 2.7553, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03343465045592705, | |
| "grad_norm": 20.4468936920166, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 3.609, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0364741641337386, | |
| "grad_norm": 12.317439079284668, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 1.454, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03951367781155015, | |
| "grad_norm": 16.474454879760742, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 2.0624, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0425531914893617, | |
| "grad_norm": 53.46656799316406, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.3277, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04559270516717325, | |
| "grad_norm": 28.371129989624023, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 3.6916, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0486322188449848, | |
| "grad_norm": 19.709819793701172, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 3.0925, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05167173252279635, | |
| "grad_norm": 23.58650779724121, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 3.6568, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0547112462006079, | |
| "grad_norm": 25.604393005371094, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 5.1104, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.057750759878419454, | |
| "grad_norm": 28.768024444580078, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 4.2082, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.060790273556231005, | |
| "grad_norm": 26.117097854614258, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 4.7796, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06382978723404255, | |
| "grad_norm": 30.500864028930664, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 5.4252, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0668693009118541, | |
| "grad_norm": 15.24867057800293, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 3.1976, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06990881458966565, | |
| "grad_norm": 26.67298698425293, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 7.0914, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0729483282674772, | |
| "grad_norm": 45.49403762817383, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 12.9969, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07598784194528875, | |
| "grad_norm": 44.33664321899414, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 10.3561, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07598784194528875, | |
| "eval_loss": 2.4314424991607666, | |
| "eval_runtime": 66.7784, | |
| "eval_samples_per_second": 2.082, | |
| "eval_steps_per_second": 1.048, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0790273556231003, | |
| "grad_norm": 31.762439727783203, | |
| "learning_rate": 0.0001, | |
| "loss": 7.3931, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08206686930091185, | |
| "grad_norm": 46.987701416015625, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 11.0254, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0851063829787234, | |
| "grad_norm": 39.347415924072266, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 9.7276, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08814589665653495, | |
| "grad_norm": 27.018573760986328, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 6.8205, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0911854103343465, | |
| "grad_norm": 38.160160064697266, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 8.0631, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09422492401215805, | |
| "grad_norm": 20.63794708251953, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 5.7677, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0972644376899696, | |
| "grad_norm": 26.39188003540039, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 7.9546, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10030395136778116, | |
| "grad_norm": 32.68507385253906, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 5.3357, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1033434650455927, | |
| "grad_norm": 23.021486282348633, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 4.2771, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10638297872340426, | |
| "grad_norm": 38.087120056152344, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 7.5119, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1094224924012158, | |
| "grad_norm": 35.39018249511719, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 8.1111, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11246200607902736, | |
| "grad_norm": 68.58114624023438, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 10.3492, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.11550151975683891, | |
| "grad_norm": 35.49908447265625, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 5.9193, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.11854103343465046, | |
| "grad_norm": 49.49984359741211, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 6.7471, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12158054711246201, | |
| "grad_norm": 25.06878089904785, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 3.6904, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12462006079027356, | |
| "grad_norm": 52.52233123779297, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 6.2508, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1276595744680851, | |
| "grad_norm": 40.56067657470703, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 5.418, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13069908814589665, | |
| "grad_norm": 48.30466079711914, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 6.1278, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1337386018237082, | |
| "grad_norm": 100.85240936279297, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 8.8476, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.13677811550151975, | |
| "grad_norm": 44.3907585144043, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 6.1738, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1398176291793313, | |
| "grad_norm": 58.735931396484375, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 10.7501, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 71.46258544921875, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 10.3434, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1458966565349544, | |
| "grad_norm": 102.83684539794922, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 10.9469, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.14893617021276595, | |
| "grad_norm": 55.492740631103516, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 10.7603, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1519756838905775, | |
| "grad_norm": 73.8077163696289, | |
| "learning_rate": 0.0, | |
| "loss": 12.376, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1519756838905775, | |
| "eval_loss": 1.5591756105422974, | |
| "eval_runtime": 66.7749, | |
| "eval_samples_per_second": 2.082, | |
| "eval_steps_per_second": 1.048, | |
| "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": 1.20047422930944e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |