| { | |
| "best_metric": 0.34442776441574097, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03772161448509996, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007544322897019992, | |
| "grad_norm": 0.8308587074279785, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2964, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007544322897019992, | |
| "eval_loss": 0.7299715876579285, | |
| "eval_runtime": 20.2482, | |
| "eval_samples_per_second": 110.281, | |
| "eval_steps_per_second": 13.828, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015088645794039985, | |
| "grad_norm": 1.1042485237121582, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4161, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002263296869105998, | |
| "grad_norm": 1.4411886930465698, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6274, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003017729158807997, | |
| "grad_norm": 1.3803136348724365, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7206, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003772161448509996, | |
| "grad_norm": 1.6238412857055664, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6611, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004526593738211996, | |
| "grad_norm": 1.4129446744918823, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.7248, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005281026027913994, | |
| "grad_norm": 1.8948041200637817, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.8552, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006035458317615994, | |
| "grad_norm": 1.9643433094024658, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.8506, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0067898906073179935, | |
| "grad_norm": 1.233587384223938, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.5796, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007544322897019992, | |
| "grad_norm": 1.038683533668518, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.4606, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008298755186721992, | |
| "grad_norm": 1.0833423137664795, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.4563, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009053187476423991, | |
| "grad_norm": 1.1593278646469116, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.5112, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00980761976612599, | |
| "grad_norm": 0.9469462037086487, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.4577, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010562052055827989, | |
| "grad_norm": 0.9820336103439331, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.3953, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011316484345529988, | |
| "grad_norm": 0.8230754733085632, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.2721, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012070916635231988, | |
| "grad_norm": 1.001030445098877, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.4971, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.012825348924933987, | |
| "grad_norm": 1.0248661041259766, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.4235, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.013579781214635987, | |
| "grad_norm": 0.9030658006668091, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.3756, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.014334213504337986, | |
| "grad_norm": 0.8215460181236267, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.3629, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.015088645794039984, | |
| "grad_norm": 0.8405181169509888, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3189, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015843078083741986, | |
| "grad_norm": 0.9004895091056824, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.2999, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.016597510373443983, | |
| "grad_norm": 0.8422564268112183, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.3529, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01735194266314598, | |
| "grad_norm": 0.9507232308387756, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.4296, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.018106374952847983, | |
| "grad_norm": 0.7352273464202881, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.2783, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01886080724254998, | |
| "grad_norm": 0.7454931139945984, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.2902, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01886080724254998, | |
| "eval_loss": 0.37303784489631653, | |
| "eval_runtime": 20.2994, | |
| "eval_samples_per_second": 110.003, | |
| "eval_steps_per_second": 13.794, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01961523953225198, | |
| "grad_norm": 0.7916195392608643, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.3521, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02036967182195398, | |
| "grad_norm": 0.8140760660171509, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.2878, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.021124104111655977, | |
| "grad_norm": 0.8776665925979614, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.3625, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02187853640135798, | |
| "grad_norm": 0.9702516794204712, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.3975, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.022632968691059976, | |
| "grad_norm": 0.8504037261009216, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.299, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.023387400980761978, | |
| "grad_norm": 0.7773805260658264, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.3011, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.024141833270463976, | |
| "grad_norm": 0.67751145362854, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.2111, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.024896265560165973, | |
| "grad_norm": 0.9894010424613953, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.3064, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.025650697849867975, | |
| "grad_norm": 0.7872379422187805, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.327, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.026405130139569973, | |
| "grad_norm": 0.714971125125885, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2041, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.027159562429271974, | |
| "grad_norm": 0.8356368541717529, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.3212, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02791399471897397, | |
| "grad_norm": 0.8638647794723511, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.2885, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.028668427008675973, | |
| "grad_norm": 1.0834510326385498, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.4168, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02942285929837797, | |
| "grad_norm": 0.9180977940559387, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.2998, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03017729158807997, | |
| "grad_norm": 0.8694742918014526, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.3141, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03093172387778197, | |
| "grad_norm": 0.8900282382965088, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.2984, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03168615616748397, | |
| "grad_norm": 1.0807785987854004, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.3059, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03244058845718597, | |
| "grad_norm": 0.9371557235717773, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.3262, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03319502074688797, | |
| "grad_norm": 1.1675786972045898, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.3664, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.033949453036589965, | |
| "grad_norm": 0.9846644997596741, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.292, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03470388532629196, | |
| "grad_norm": 1.1046561002731323, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.3549, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03545831761599397, | |
| "grad_norm": 1.3664727210998535, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.4048, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.036212749905695965, | |
| "grad_norm": 1.5488460063934326, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.4229, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03696718219539796, | |
| "grad_norm": 1.8980265855789185, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.3193, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03772161448509996, | |
| "grad_norm": 3.1977779865264893, | |
| "learning_rate": 0.0, | |
| "loss": 0.5885, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03772161448509996, | |
| "eval_loss": 0.34442776441574097, | |
| "eval_runtime": 20.2984, | |
| "eval_samples_per_second": 110.009, | |
| "eval_steps_per_second": 13.794, | |
| "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": 5, | |
| "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": 1999744829227008.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |