| { |
| "best_metric": 0.11287513375282288, |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", |
| "epoch": 0.08653326122228232, |
| "eval_steps": 25, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0017306652244456463, |
| "grad_norm": 1.5263383388519287, |
| "learning_rate": 5e-05, |
| "loss": 1.5481, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0017306652244456463, |
| "eval_loss": 0.5736979842185974, |
| "eval_runtime": 252.9149, |
| "eval_samples_per_second": 15.393, |
| "eval_steps_per_second": 1.926, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0034613304488912925, |
| "grad_norm": 1.50196373462677, |
| "learning_rate": 0.0001, |
| "loss": 1.5904, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.005191995673336939, |
| "grad_norm": 1.6720207929611206, |
| "learning_rate": 9.989294616193017e-05, |
| "loss": 1.599, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.006922660897782585, |
| "grad_norm": 1.4047436714172363, |
| "learning_rate": 9.957224306869053e-05, |
| "loss": 1.5256, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.008653326122228232, |
| "grad_norm": 1.3644955158233643, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 1.5702, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.010383991346673878, |
| "grad_norm": 1.7943435907363892, |
| "learning_rate": 9.829629131445342e-05, |
| "loss": 1.6242, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.012114656571119525, |
| "grad_norm": 1.6951757669448853, |
| "learning_rate": 9.73465064747553e-05, |
| "loss": 1.7173, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.01384532179556517, |
| "grad_norm": 2.172508955001831, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 2.125, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.015575987020010817, |
| "grad_norm": 7.738946914672852, |
| "learning_rate": 9.484363707663442e-05, |
| "loss": 3.4692, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.017306652244456464, |
| "grad_norm": 27.37078857421875, |
| "learning_rate": 9.330127018922194e-05, |
| "loss": 6.1647, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.01903731746890211, |
| "grad_norm": 31.212278366088867, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 11.2051, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.020767982693347755, |
| "grad_norm": 28.675228118896484, |
| "learning_rate": 8.966766701456177e-05, |
| "loss": 13.5948, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.0224986479177934, |
| "grad_norm": 15.533310890197754, |
| "learning_rate": 8.759199037394887e-05, |
| "loss": 8.2769, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.02422931314223905, |
| "grad_norm": 3.548496961593628, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.8627, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.025959978366684695, |
| "grad_norm": 2.5663514137268066, |
| "learning_rate": 8.296729075500344e-05, |
| "loss": 0.7302, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.02769064359113034, |
| "grad_norm": 1.756816029548645, |
| "learning_rate": 8.043807145043604e-05, |
| "loss": 0.5923, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.029421308815575985, |
| "grad_norm": 1.161169409751892, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.5619, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.031151974040021634, |
| "grad_norm": 0.7824879288673401, |
| "learning_rate": 7.500000000000001e-05, |
| "loss": 0.6292, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.03288263926446728, |
| "grad_norm": 0.7797122597694397, |
| "learning_rate": 7.211443451095007e-05, |
| "loss": 0.6977, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.03461330448891293, |
| "grad_norm": 0.8304592370986938, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.8688, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.03634396971335857, |
| "grad_norm": 1.4030123949050903, |
| "learning_rate": 6.607197326515808e-05, |
| "loss": 1.2802, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.03807463493780422, |
| "grad_norm": 3.9059696197509766, |
| "learning_rate": 6.294095225512603e-05, |
| "loss": 2.8514, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.03980530016224987, |
| "grad_norm": 6.554221153259277, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 5.5827, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.04153596538669551, |
| "grad_norm": 11.549520492553711, |
| "learning_rate": 5.6526309611002594e-05, |
| "loss": 7.4272, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.04326663061114116, |
| "grad_norm": 13.745119094848633, |
| "learning_rate": 5.327015646150716e-05, |
| "loss": 8.6658, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.04326663061114116, |
| "eval_loss": 0.13114991784095764, |
| "eval_runtime": 251.8843, |
| "eval_samples_per_second": 15.456, |
| "eval_steps_per_second": 1.933, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0449972958355868, |
| "grad_norm": 0.3784489929676056, |
| "learning_rate": 5e-05, |
| "loss": 0.3095, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.04672796106003245, |
| "grad_norm": 0.33651015162467957, |
| "learning_rate": 4.6729843538492847e-05, |
| "loss": 0.3036, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.0484586262844781, |
| "grad_norm": 0.3961086571216583, |
| "learning_rate": 4.347369038899744e-05, |
| "loss": 0.3139, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.05018929150892374, |
| "grad_norm": 0.4263656735420227, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.3529, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.05191995673336939, |
| "grad_norm": 0.46552321314811707, |
| "learning_rate": 3.705904774487396e-05, |
| "loss": 0.4548, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.05365062195781504, |
| "grad_norm": 0.33770114183425903, |
| "learning_rate": 3.392802673484193e-05, |
| "loss": 0.4576, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.05538128718226068, |
| "grad_norm": 0.4641321897506714, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.5966, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.05711195240670633, |
| "grad_norm": 0.5943290591239929, |
| "learning_rate": 2.7885565489049946e-05, |
| "loss": 0.8214, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.05884261763115197, |
| "grad_norm": 1.117336392402649, |
| "learning_rate": 2.500000000000001e-05, |
| "loss": 1.4997, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.06057328285559762, |
| "grad_norm": 2.4597384929656982, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 3.1596, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.06230394808004327, |
| "grad_norm": 7.086680889129639, |
| "learning_rate": 1.9561928549563968e-05, |
| "loss": 5.4416, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.06403461330448891, |
| "grad_norm": 6.797247409820557, |
| "learning_rate": 1.703270924499656e-05, |
| "loss": 6.6489, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.06576527852893456, |
| "grad_norm": 5.29379415512085, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 3.9137, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.06749594375338021, |
| "grad_norm": 0.2345895767211914, |
| "learning_rate": 1.2408009626051137e-05, |
| "loss": 0.2587, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.06922660897782586, |
| "grad_norm": 0.2742256820201874, |
| "learning_rate": 1.0332332985438248e-05, |
| "loss": 0.2752, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.07095727420227149, |
| "grad_norm": 0.2429785281419754, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.293, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.07268793942671714, |
| "grad_norm": 0.2798793613910675, |
| "learning_rate": 6.698729810778065e-06, |
| "loss": 0.3659, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.07441860465116279, |
| "grad_norm": 0.3929751217365265, |
| "learning_rate": 5.156362923365588e-06, |
| "loss": 0.4205, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.07614926987560844, |
| "grad_norm": 0.3679610788822174, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.4298, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.07787993510005409, |
| "grad_norm": 0.5460615754127502, |
| "learning_rate": 2.653493525244721e-06, |
| "loss": 0.5886, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.07961060032449974, |
| "grad_norm": 0.7755551934242249, |
| "learning_rate": 1.70370868554659e-06, |
| "loss": 0.88, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.08134126554894537, |
| "grad_norm": 1.5932703018188477, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 1.6708, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.08307193077339102, |
| "grad_norm": 4.295409679412842, |
| "learning_rate": 4.277569313094809e-07, |
| "loss": 3.8597, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.08480259599783667, |
| "grad_norm": 6.057656288146973, |
| "learning_rate": 1.0705383806982606e-07, |
| "loss": 5.9046, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.08653326122228232, |
| "grad_norm": 7.730199813842773, |
| "learning_rate": 0.0, |
| "loss": 7.9757, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.08653326122228232, |
| "eval_loss": 0.11287513375282288, |
| "eval_runtime": 253.0809, |
| "eval_samples_per_second": 15.382, |
| "eval_steps_per_second": 1.924, |
| "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": 6.542719156695859e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
