| { | |
| "best_metric": 10.37548828125, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 3.0409356725146197, | |
| "eval_steps": 25, | |
| "global_step": 65, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04678362573099415, | |
| "grad_norm": 0.08035193383693695, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 10.3946, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "eval_loss": 10.393576622009277, | |
| "eval_runtime": 0.0768, | |
| "eval_samples_per_second": 650.798, | |
| "eval_steps_per_second": 169.208, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0935672514619883, | |
| "grad_norm": 0.07648925483226776, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 10.3947, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 0.07350781559944153, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3923, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1871345029239766, | |
| "grad_norm": 0.08065179735422134, | |
| "learning_rate": 9.994224282269737e-05, | |
| "loss": 10.3843, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.23391812865497075, | |
| "grad_norm": 0.10446092486381531, | |
| "learning_rate": 9.976911955263529e-05, | |
| "loss": 10.3794, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 0.0764802023768425, | |
| "learning_rate": 9.948107459476501e-05, | |
| "loss": 10.3948, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.32748538011695905, | |
| "grad_norm": 0.07530075311660767, | |
| "learning_rate": 9.907884735636226e-05, | |
| "loss": 10.3885, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3742690058479532, | |
| "grad_norm": 0.07579008489847183, | |
| "learning_rate": 9.856347034897919e-05, | |
| "loss": 10.3891, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.07757099717855453, | |
| "learning_rate": 9.793626653800219e-05, | |
| "loss": 10.3861, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.4678362573099415, | |
| "grad_norm": 0.10095006227493286, | |
| "learning_rate": 9.719884594661864e-05, | |
| "loss": 10.3798, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5146198830409356, | |
| "grad_norm": 0.084345243871212, | |
| "learning_rate": 9.635310152291039e-05, | |
| "loss": 10.3809, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 0.07810067385435104, | |
| "learning_rate": 9.540120428068338e-05, | |
| "loss": 10.3871, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6081871345029239, | |
| "grad_norm": 0.07608596980571747, | |
| "learning_rate": 9.43455977265062e-05, | |
| "loss": 10.3897, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6549707602339181, | |
| "grad_norm": 0.08369778096675873, | |
| "learning_rate": 9.31889915872638e-05, | |
| "loss": 10.3836, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "grad_norm": 0.08858703821897507, | |
| "learning_rate": 9.193435485432745e-05, | |
| "loss": 10.3823, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7485380116959064, | |
| "grad_norm": 0.09585383534431458, | |
| "learning_rate": 9.058490816219643e-05, | |
| "loss": 10.378, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7953216374269005, | |
| "grad_norm": 0.08524016290903091, | |
| "learning_rate": 8.914411552117559e-05, | |
| "loss": 10.3886, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.08070208132266998, | |
| "learning_rate": 8.76156754253104e-05, | |
| "loss": 10.3806, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.08314181119203568, | |
| "learning_rate": 8.600351135840589e-05, | |
| "loss": 10.3807, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.935672514619883, | |
| "grad_norm": 0.0966922715306282, | |
| "learning_rate": 8.431176172250002e-05, | |
| "loss": 10.3792, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9824561403508771, | |
| "grad_norm": 0.11607522517442703, | |
| "learning_rate": 8.254476921464484e-05, | |
| "loss": 10.3756, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0292397660818713, | |
| "grad_norm": 0.14582864940166473, | |
| "learning_rate": 8.070706967926565e-05, | |
| "loss": 16.9191, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0760233918128654, | |
| "grad_norm": 0.09495727717876434, | |
| "learning_rate": 7.880338046471331e-05, | |
| "loss": 10.564, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.1228070175438596, | |
| "grad_norm": 0.08627945184707642, | |
| "learning_rate": 7.683858831389867e-05, | |
| "loss": 9.984, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1695906432748537, | |
| "grad_norm": 0.09416957944631577, | |
| "learning_rate": 7.481773682009356e-05, | |
| "loss": 10.337, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1695906432748537, | |
| "eval_loss": 10.38400650024414, | |
| "eval_runtime": 0.0782, | |
| "eval_samples_per_second": 639.565, | |
| "eval_steps_per_second": 166.287, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2163742690058479, | |
| "grad_norm": 0.11057508736848831, | |
| "learning_rate": 7.274601348009935e-05, | |
| "loss": 10.1665, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 0.11977867782115936, | |
| "learning_rate": 7.062873637801692e-05, | |
| "loss": 10.8457, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.3099415204678362, | |
| "grad_norm": 0.09831052273511887, | |
| "learning_rate": 6.847134053380112e-05, | |
| "loss": 10.5002, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.3567251461988303, | |
| "grad_norm": 0.09686669707298279, | |
| "learning_rate": 6.627936395164243e-05, | |
| "loss": 10.2253, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.4035087719298245, | |
| "grad_norm": 0.09972165524959564, | |
| "learning_rate": 6.40584334039897e-05, | |
| "loss": 10.1396, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4502923976608186, | |
| "grad_norm": 0.10765210539102554, | |
| "learning_rate": 6.181424998770595e-05, | |
| "loss": 9.7169, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.4970760233918128, | |
| "grad_norm": 0.12939834594726562, | |
| "learning_rate": 5.955257448943445e-05, | |
| "loss": 10.9171, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.543859649122807, | |
| "grad_norm": 0.12637734413146973, | |
| "learning_rate": 5.727921259774208e-05, | |
| "loss": 10.602, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.590643274853801, | |
| "grad_norm": 0.1105811670422554, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 10.6176, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.6374269005847952, | |
| "grad_norm": 0.11131985485553741, | |
| "learning_rate": 5.2720787402257935e-05, | |
| "loss": 10.2836, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 0.11741997301578522, | |
| "learning_rate": 5.044742551056556e-05, | |
| "loss": 10.0027, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.7309941520467835, | |
| "grad_norm": 0.14288607239723206, | |
| "learning_rate": 4.8185750012294065e-05, | |
| "loss": 10.4621, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.12223335355520248, | |
| "learning_rate": 4.594156659601029e-05, | |
| "loss": 10.6583, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.8245614035087718, | |
| "grad_norm": 0.12245681881904602, | |
| "learning_rate": 4.372063604835758e-05, | |
| "loss": 9.8662, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.871345029239766, | |
| "grad_norm": 0.12315724790096283, | |
| "learning_rate": 4.152865946619889e-05, | |
| "loss": 10.76, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.9181286549707601, | |
| "grad_norm": 0.12260238081216812, | |
| "learning_rate": 3.93712636219831e-05, | |
| "loss": 10.3994, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.9649122807017543, | |
| "grad_norm": 0.15077726542949677, | |
| "learning_rate": 3.725398651990067e-05, | |
| "loss": 11.4694, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.0116959064327484, | |
| "grad_norm": 0.19197246432304382, | |
| "learning_rate": 3.518226317990646e-05, | |
| "loss": 15.752, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.0584795321637426, | |
| "grad_norm": 0.12943069636821747, | |
| "learning_rate": 3.3161411686101364e-05, | |
| "loss": 10.6442, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 0.11681056767702103, | |
| "learning_rate": 3.119661953528671e-05, | |
| "loss": 10.0928, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.152046783625731, | |
| "grad_norm": 0.12141174077987671, | |
| "learning_rate": 2.9292930320734335e-05, | |
| "loss": 10.3879, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.198830409356725, | |
| "grad_norm": 0.12950986623764038, | |
| "learning_rate": 2.745523078535517e-05, | |
| "loss": 10.1063, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.245614035087719, | |
| "grad_norm": 0.14073993265628815, | |
| "learning_rate": 2.568823827750001e-05, | |
| "loss": 9.7249, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.2923976608187133, | |
| "grad_norm": 0.14041155576705933, | |
| "learning_rate": 2.39964886415941e-05, | |
| "loss": 11.2327, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.3391812865497075, | |
| "grad_norm": 0.14114905893802643, | |
| "learning_rate": 2.2384324574689612e-05, | |
| "loss": 10.3466, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.3391812865497075, | |
| "eval_loss": 10.37548828125, | |
| "eval_runtime": 0.0757, | |
| "eval_samples_per_second": 660.475, | |
| "eval_steps_per_second": 171.723, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.3859649122807016, | |
| "grad_norm": 0.1374143660068512, | |
| "learning_rate": 2.0855884478824412e-05, | |
| "loss": 10.6913, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.4327485380116958, | |
| "grad_norm": 0.13993822038173676, | |
| "learning_rate": 1.9415091837803573e-05, | |
| "loss": 9.6339, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.47953216374269, | |
| "grad_norm": 0.1723541021347046, | |
| "learning_rate": 1.806564514567258e-05, | |
| "loss": 11.5109, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.526315789473684, | |
| "grad_norm": 0.13717088103294373, | |
| "learning_rate": 1.6811008412736208e-05, | |
| "loss": 9.4536, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.573099415204678, | |
| "grad_norm": 0.13807837665081024, | |
| "learning_rate": 1.5654402273493805e-05, | |
| "loss": 10.6052, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.6198830409356724, | |
| "grad_norm": 0.13864926993846893, | |
| "learning_rate": 1.459879571931663e-05, | |
| "loss": 10.2006, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.14294551312923431, | |
| "learning_rate": 1.3646898477089626e-05, | |
| "loss": 10.4874, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.7134502923976607, | |
| "grad_norm": 0.16176921129226685, | |
| "learning_rate": 1.2801154053381386e-05, | |
| "loss": 11.0147, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.760233918128655, | |
| "grad_norm": 0.13276654481887817, | |
| "learning_rate": 1.2063733461997805e-05, | |
| "loss": 9.6744, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.807017543859649, | |
| "grad_norm": 0.14666683971881866, | |
| "learning_rate": 1.1436529651020813e-05, | |
| "loss": 10.4008, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.853801169590643, | |
| "grad_norm": 0.1457078456878662, | |
| "learning_rate": 1.092115264363775e-05, | |
| "loss": 10.5984, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.9005847953216373, | |
| "grad_norm": 0.13246245682239532, | |
| "learning_rate": 1.0518925405234989e-05, | |
| "loss": 9.8514, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.9473684210526314, | |
| "grad_norm": 0.14585375785827637, | |
| "learning_rate": 1.023088044736472e-05, | |
| "loss": 10.7322, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.9941520467836256, | |
| "grad_norm": 0.1970202624797821, | |
| "learning_rate": 1.0057757177302627e-05, | |
| "loss": 14.7962, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.0409356725146197, | |
| "grad_norm": 0.18727658689022064, | |
| "learning_rate": 1e-05, | |
| "loss": 12.5777, | |
| "step": 65 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 65, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 55598477475840.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |