| { | |
| "best_metric": 3.5156401281710714e-05, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.000646629765661373, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.2932595313227458e-05, | |
| "grad_norm": 12.3665771484375, | |
| "learning_rate": 0.0001, | |
| "loss": 4.7667, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.2932595313227458e-05, | |
| "eval_loss": 5.663321018218994, | |
| "eval_runtime": 4042.9337, | |
| "eval_samples_per_second": 8.053, | |
| "eval_steps_per_second": 4.027, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.5865190626454916e-05, | |
| "grad_norm": 13.965386390686035, | |
| "learning_rate": 0.0002, | |
| "loss": 4.6426, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.8797785939682375e-05, | |
| "grad_norm": 13.06217098236084, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 4.1725, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.173038125290983e-05, | |
| "grad_norm": 9.654458999633789, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 2.252, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 6.46629765661373e-05, | |
| "grad_norm": 6.366847991943359, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 1.2929, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 7.759557187936475e-05, | |
| "grad_norm": 3.7300143241882324, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.4743, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 9.052816719259221e-05, | |
| "grad_norm": 2.255476951599121, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.2423, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00010346076250581966, | |
| "grad_norm": 1.4915378093719482, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0855, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00011639335781904713, | |
| "grad_norm": 0.2951045632362366, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.011, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001293259531322746, | |
| "grad_norm": 0.023305028676986694, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0005, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00014225854844550205, | |
| "grad_norm": 0.003954252693802118, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.0001, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0001551911437587295, | |
| "grad_norm": 0.0012373141944408417, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00016812373907195696, | |
| "grad_norm": 0.0023228523787111044, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.0001, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00018105633438518441, | |
| "grad_norm": 0.005288443528115749, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0001, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00019398892969841187, | |
| "grad_norm": 0.00128844880964607, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00020692152501163933, | |
| "grad_norm": 0.0020125224255025387, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00021985412032486678, | |
| "grad_norm": 0.0037247403524816036, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.0001, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00023278671563809427, | |
| "grad_norm": 0.014811231754720211, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0001, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0002457193109513217, | |
| "grad_norm": 0.007926372811198235, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.0001, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0002586519062645492, | |
| "grad_norm": 0.02340223640203476, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0002, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0002715845015777766, | |
| "grad_norm": 0.0066363937221467495, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.0001, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0002845170968910041, | |
| "grad_norm": 0.002405409701168537, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.0001, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0002974496922042315, | |
| "grad_norm": 0.0022278388496488333, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.0001, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.000310382287517459, | |
| "grad_norm": 0.002495991997420788, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.0001, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0003233148828306865, | |
| "grad_norm": 0.0063591911457479, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.0001, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0003233148828306865, | |
| "eval_loss": 7.495559111703187e-05, | |
| "eval_runtime": 4069.8131, | |
| "eval_samples_per_second": 8.0, | |
| "eval_steps_per_second": 4.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0003362474781439139, | |
| "grad_norm": 0.006929947063326836, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0001, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0003491800734571414, | |
| "grad_norm": 0.004468102473765612, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.0001, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00036211266877036883, | |
| "grad_norm": 0.001515953685157001, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0003750452640835963, | |
| "grad_norm": 0.004584501497447491, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.0001, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.00038797785939682374, | |
| "grad_norm": 0.003514234907925129, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.0001, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0004009104547100512, | |
| "grad_norm": 0.003772181225940585, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.0001, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.00041384305002327865, | |
| "grad_norm": 0.0021776333451271057, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0001, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.00042677564533650614, | |
| "grad_norm": 0.002284293994307518, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00043970824064973356, | |
| "grad_norm": 0.002807403914630413, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0001, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.00045264083596296105, | |
| "grad_norm": 0.00221768650226295, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00046557343127618853, | |
| "grad_norm": 0.00265073892660439, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.0001, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.00047850602658941596, | |
| "grad_norm": 0.0032683610916137695, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.0001, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0004914386219026434, | |
| "grad_norm": 0.0017475264612585306, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0005043712172158709, | |
| "grad_norm": 0.002534898929297924, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.0001, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0005173038125290984, | |
| "grad_norm": 0.0014598339330404997, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0005302364078423258, | |
| "grad_norm": 0.0030341579113155603, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.0001, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0005431690031555532, | |
| "grad_norm": 0.0016653327038511634, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0005561015984687808, | |
| "grad_norm": 0.0010284342570230365, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0005690341937820082, | |
| "grad_norm": 0.0015539777232334018, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0005819667890952356, | |
| "grad_norm": 0.0010054032318294048, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.000594899384408463, | |
| "grad_norm": 0.001314558438025415, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0006078319797216906, | |
| "grad_norm": 0.0010848251404240727, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.000620764575034918, | |
| "grad_norm": 0.0015894053503870964, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0006336971703481454, | |
| "grad_norm": 0.0016238840762525797, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.000646629765661373, | |
| "grad_norm": 0.0026105751749128103, | |
| "learning_rate": 0.0, | |
| "loss": 0.0001, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.000646629765661373, | |
| "eval_loss": 3.5156401281710714e-05, | |
| "eval_runtime": 4069.9805, | |
| "eval_samples_per_second": 8.0, | |
| "eval_steps_per_second": 4.0, | |
| "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": 1.30626883682304e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |