| { | |
| "best_metric": 0.026113534346222878, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0030155451351718105, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.0310902703436215e-05, | |
| "grad_norm": 10.57955551147461, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8784, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.0310902703436215e-05, | |
| "eval_loss": 2.7493324279785156, | |
| "eval_runtime": 2209.7035, | |
| "eval_samples_per_second": 3.16, | |
| "eval_steps_per_second": 1.58, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012062180540687243, | |
| "grad_norm": 9.926082611083984, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6451, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00018093270811030864, | |
| "grad_norm": 10.520155906677246, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 2.3241, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00024124361081374486, | |
| "grad_norm": 6.2325615882873535, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.7219, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003015545135171811, | |
| "grad_norm": 2.1212244033813477, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.2608, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003618654162206173, | |
| "grad_norm": 4.653842926025391, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.274, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00042217631892405347, | |
| "grad_norm": 0.75608229637146, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.0142, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0004824872216274897, | |
| "grad_norm": 0.32779282331466675, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0064, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005427981243309259, | |
| "grad_norm": 0.021024387329816818, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.0004, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006031090270343622, | |
| "grad_norm": 0.004581534769386053, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0001, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006634199297377983, | |
| "grad_norm": 0.0015949731459841132, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0007237308324412346, | |
| "grad_norm": 0.0006097615114413202, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0007840417351446708, | |
| "grad_norm": 0.0006146853556856513, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0008443526378481069, | |
| "grad_norm": 0.0008460977114737034, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0009046635405515432, | |
| "grad_norm": 0.0009411271894350648, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009649744432549794, | |
| "grad_norm": 0.0069528562016785145, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0010252853459584157, | |
| "grad_norm": 0.0007321193697862327, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0010855962486618518, | |
| "grad_norm": 0.0032294231932610273, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001145907151365288, | |
| "grad_norm": 0.0008617211133241653, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0012062180540687243, | |
| "grad_norm": 0.001366589916869998, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0012665289567721605, | |
| "grad_norm": 0.001960506895557046, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0013268398594755966, | |
| "grad_norm": 6.810147285461426, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.3866, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.001387150762179033, | |
| "grad_norm": 0.007939040660858154, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.0001, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.001447461664882469, | |
| "grad_norm": 0.017563754692673683, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.0003, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0015077725675859052, | |
| "grad_norm": 0.046484433114528656, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.0006, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0015077725675859052, | |
| "eval_loss": 0.026113534346222878, | |
| "eval_runtime": 2225.6754, | |
| "eval_samples_per_second": 3.137, | |
| "eval_steps_per_second": 1.569, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0015680834702893416, | |
| "grad_norm": 0.059908702969551086, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0016283943729927777, | |
| "grad_norm": 0.09489380568265915, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.0013, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0016887052756962139, | |
| "grad_norm": 0.07761608064174652, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.0012, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0017490161783996502, | |
| "grad_norm": 0.027190126478672028, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.0004, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0018093270811030864, | |
| "grad_norm": 0.01503070443868637, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.0002, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0018696379838065225, | |
| "grad_norm": 0.010442839935421944, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.0002, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0019299488865099589, | |
| "grad_norm": 0.008365264162421227, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0001, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.001990259789213395, | |
| "grad_norm": 0.004889277741312981, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.0001, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0020505706919168314, | |
| "grad_norm": 0.002633703174069524, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0021108815946202673, | |
| "grad_norm": 0.0017473475309088826, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0021711924973237037, | |
| "grad_norm": 0.0013490833807736635, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.00223150340002714, | |
| "grad_norm": 0.002322995103895664, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.002291814302730576, | |
| "grad_norm": 0.002702017081901431, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0023521252054340123, | |
| "grad_norm": 0.0005478212842717767, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0024124361081374487, | |
| "grad_norm": 0.0005250187241472304, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0024727470108408846, | |
| "grad_norm": 0.0005369814462028444, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.002533057913544321, | |
| "grad_norm": 0.000519345689099282, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0025933688162477573, | |
| "grad_norm": 0.0004838835448026657, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0026536797189511932, | |
| "grad_norm": 0.0006146663799881935, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0027139906216546296, | |
| "grad_norm": 0.000544109963811934, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.002774301524358066, | |
| "grad_norm": 0.0004783784970641136, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.002834612427061502, | |
| "grad_norm": 0.0004780633607879281, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.002894923329764938, | |
| "grad_norm": 0.0007953947642818093, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0029552342324683746, | |
| "grad_norm": 0.0010560927912592888, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0030155451351718105, | |
| "grad_norm": 16.152246475219727, | |
| "learning_rate": 0.0, | |
| "loss": 0.7721, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0030155451351718105, | |
| "eval_loss": 0.0306876078248024, | |
| "eval_runtime": 2226.0281, | |
| "eval_samples_per_second": 3.137, | |
| "eval_steps_per_second": 1.568, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.99038693326848e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |