| { | |
| "best_metric": 0.0040573906153440475, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.008424954715868403, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016849909431736806, | |
| "grad_norm": 0.5649989247322083, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4213, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016849909431736806, | |
| "eval_loss": 0.5909122824668884, | |
| "eval_runtime": 544.2099, | |
| "eval_samples_per_second": 18.366, | |
| "eval_steps_per_second": 2.297, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003369981886347361, | |
| "grad_norm": 0.6741442680358887, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5083, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005054972829521042, | |
| "grad_norm": 0.5923657417297363, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 0.4534, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006739963772694722, | |
| "grad_norm": 0.6023609042167664, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.2927, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008424954715868402, | |
| "grad_norm": 0.6663532257080078, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.1444, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010109945659042083, | |
| "grad_norm": 0.4367070496082306, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.0676, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011794936602215764, | |
| "grad_norm": 0.15941502153873444, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.0139, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013479927545389445, | |
| "grad_norm": 0.08275063335895538, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0069, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015164918488563123, | |
| "grad_norm": 0.6395729780197144, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.0421, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016849909431736804, | |
| "grad_norm": 0.12541823089122772, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0053, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018534900374910484, | |
| "grad_norm": 0.3203907012939453, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.0044, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0020219891318084167, | |
| "grad_norm": 0.28198617696762085, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.0118, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0021904882261257847, | |
| "grad_norm": 1.7291009426116943, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.0402, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002358987320443153, | |
| "grad_norm": 1.925735592842102, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0377, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002527486414760521, | |
| "grad_norm": 0.37905728816986084, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.0106, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002695985509077889, | |
| "grad_norm": 0.2949874699115753, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.0078, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0028644846033952565, | |
| "grad_norm": 0.21088016033172607, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.0062, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0030329836977126246, | |
| "grad_norm": 0.04623870924115181, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0025, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0032014827920299927, | |
| "grad_norm": 0.0938965305685997, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.0081, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0033699818863473607, | |
| "grad_norm": 0.14240026473999023, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0085, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0035384809806647288, | |
| "grad_norm": 0.05777126923203468, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.0017, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003706980074982097, | |
| "grad_norm": 0.04713433235883713, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.0037, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.003875479169299465, | |
| "grad_norm": 0.1591893881559372, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.011, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004043978263616833, | |
| "grad_norm": 0.05540703609585762, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.0044, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0042124773579342014, | |
| "grad_norm": 0.023379579186439514, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.0012, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0042124773579342014, | |
| "eval_loss": 0.006916701328009367, | |
| "eval_runtime": 544.1604, | |
| "eval_samples_per_second": 18.368, | |
| "eval_steps_per_second": 2.297, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0043809764522515695, | |
| "grad_norm": 0.19603978097438812, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0213, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0045494755465689376, | |
| "grad_norm": 0.5282886028289795, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.0656, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004717974640886306, | |
| "grad_norm": 0.0671163946390152, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.0094, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004886473735203674, | |
| "grad_norm": 0.05665583908557892, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.0151, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005054972829521042, | |
| "grad_norm": 0.07490652799606323, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.0009, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00522347192383841, | |
| "grad_norm": 0.037155721336603165, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.0024, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.005391971018155778, | |
| "grad_norm": 0.05099332705140114, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0078, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.005560470112473145, | |
| "grad_norm": 0.17277608811855316, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.0109, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005728969206790513, | |
| "grad_norm": 0.04528217762708664, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0052, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.005897468301107881, | |
| "grad_norm": 0.008220179006457329, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0004, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006065967395425249, | |
| "grad_norm": 0.012407345697283745, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.0006, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.006234466489742617, | |
| "grad_norm": 0.017425227910280228, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.0024, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.006402965584059985, | |
| "grad_norm": 0.22802281379699707, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0073, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.006571464678377353, | |
| "grad_norm": 0.0339801162481308, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.0057, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.006739963772694721, | |
| "grad_norm": 0.020060187205672264, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.0019, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0069084628670120895, | |
| "grad_norm": 0.03689638152718544, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.0009, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0070769619613294575, | |
| "grad_norm": 0.05137154832482338, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.0044, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.007245461055646826, | |
| "grad_norm": 0.11253440380096436, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.0022, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.007413960149964194, | |
| "grad_norm": 0.009691456332802773, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0005, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.007582459244281562, | |
| "grad_norm": 0.09334763884544373, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.0031, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00775095833859893, | |
| "grad_norm": 0.025010887533426285, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.0011, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.007919457432916298, | |
| "grad_norm": 0.06059917062520981, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.0068, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.008087956527233667, | |
| "grad_norm": 0.0202567707747221, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.0009, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.008256455621551034, | |
| "grad_norm": 0.020429080352187157, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.003, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.008424954715868403, | |
| "grad_norm": 0.06769539415836334, | |
| "learning_rate": 0.0, | |
| "loss": 0.0056, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008424954715868403, | |
| "eval_loss": 0.0040573906153440475, | |
| "eval_runtime": 544.1235, | |
| "eval_samples_per_second": 18.369, | |
| "eval_steps_per_second": 2.297, | |
| "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": 2.796154706198528e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |