| { | |
| "best_metric": 1.800140142440796, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3673094582185491, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0073461891643709825, | |
| "grad_norm": 7.234932899475098, | |
| "learning_rate": 5e-05, | |
| "loss": 6.8656, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0073461891643709825, | |
| "eval_loss": 8.155715942382812, | |
| "eval_runtime": 62.1084, | |
| "eval_samples_per_second": 14.764, | |
| "eval_steps_per_second": 1.852, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014692378328741965, | |
| "grad_norm": 8.7951021194458, | |
| "learning_rate": 0.0001, | |
| "loss": 7.2664, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02203856749311295, | |
| "grad_norm": 9.78209114074707, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.0224, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02938475665748393, | |
| "grad_norm": 9.359648704528809, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.2157, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03673094582185491, | |
| "grad_norm": 9.396818161010742, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.1793, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0440771349862259, | |
| "grad_norm": 6.48800802230835, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.7958, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.051423324150596875, | |
| "grad_norm": 3.9417362213134766, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.5118, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05876951331496786, | |
| "grad_norm": 4.9853434562683105, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.5798, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06611570247933884, | |
| "grad_norm": 4.6500325202941895, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.4128, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07346189164370982, | |
| "grad_norm": 3.4421136379241943, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.2821, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08080808080808081, | |
| "grad_norm": 3.7127418518066406, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.967, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0881542699724518, | |
| "grad_norm": 4.257928848266602, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.0112, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09550045913682277, | |
| "grad_norm": 3.667210578918457, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.2075, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.10284664830119375, | |
| "grad_norm": 4.1568217277526855, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.5852, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11019283746556474, | |
| "grad_norm": 3.56781268119812, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.2733, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11753902662993572, | |
| "grad_norm": 2.3509628772735596, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.2579, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1248852157943067, | |
| "grad_norm": 2.533644676208496, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.1316, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1322314049586777, | |
| "grad_norm": 2.614610195159912, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.8133, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13957759412304868, | |
| "grad_norm": 2.463763952255249, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.8367, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.14692378328741965, | |
| "grad_norm": 2.8602094650268555, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.9788, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15426997245179064, | |
| "grad_norm": 3.1375627517700195, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.2217, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.16161616161616163, | |
| "grad_norm": 3.0039854049682617, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.8634, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1689623507805326, | |
| "grad_norm": 2.858977794647217, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.9036, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1763085399449036, | |
| "grad_norm": 3.589897394180298, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.7665, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.18365472910927455, | |
| "grad_norm": 3.1547627449035645, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.6272, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18365472910927455, | |
| "eval_loss": 1.8613815307617188, | |
| "eval_runtime": 62.1061, | |
| "eval_samples_per_second": 14.765, | |
| "eval_steps_per_second": 1.852, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.19100091827364554, | |
| "grad_norm": 3.4452316761016846, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4563, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.19834710743801653, | |
| "grad_norm": 2.2789227962493896, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.0484, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2056932966023875, | |
| "grad_norm": 5.860487937927246, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.8531, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2130394857667585, | |
| "grad_norm": 2.3761487007141113, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.8806, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.22038567493112948, | |
| "grad_norm": 2.0185317993164062, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.1398, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22773186409550045, | |
| "grad_norm": 2.3282179832458496, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.7929, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.23507805325987144, | |
| "grad_norm": 2.7504942417144775, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.8338, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 2.712554454803467, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.9509, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2497704315886134, | |
| "grad_norm": 2.105562686920166, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.5841, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2571166207529844, | |
| "grad_norm": 2.9640512466430664, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.8982, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2644628099173554, | |
| "grad_norm": 2.4896340370178223, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.8629, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.27180899908172634, | |
| "grad_norm": 2.146752119064331, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.5085, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.27915518824609736, | |
| "grad_norm": 2.3504111766815186, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.7211, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2865013774104683, | |
| "grad_norm": 2.8673181533813477, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.2549, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2938475665748393, | |
| "grad_norm": 2.247053384780884, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.0768, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3011937557392103, | |
| "grad_norm": 2.0035057067871094, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.7571, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3085399449035813, | |
| "grad_norm": 2.2739028930664062, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.9607, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.31588613406795224, | |
| "grad_norm": 2.3509528636932373, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.8713, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.32323232323232326, | |
| "grad_norm": 2.5070559978485107, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.5904, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3305785123966942, | |
| "grad_norm": 2.3728628158569336, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.0209, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3379247015610652, | |
| "grad_norm": 2.24059796333313, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.8248, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.34527089072543615, | |
| "grad_norm": 2.2181599140167236, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.8898, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3526170798898072, | |
| "grad_norm": 2.4641213417053223, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.727, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.35996326905417814, | |
| "grad_norm": 2.3320772647857666, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.5124, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3673094582185491, | |
| "grad_norm": 2.855008363723755, | |
| "learning_rate": 0.0, | |
| "loss": 1.531, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3673094582185491, | |
| "eval_loss": 1.800140142440796, | |
| "eval_runtime": 62.0516, | |
| "eval_samples_per_second": 14.778, | |
| "eval_steps_per_second": 1.853, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |