| { | |
| "best_metric": 0.3445923328399658, | |
| "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": 0.8210492134094238, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2964, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007544322897019992, | |
| "eval_loss": 0.7299715876579285, | |
| "eval_runtime": 20.4059, | |
| "eval_samples_per_second": 109.429, | |
| "eval_steps_per_second": 13.722, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015088645794039985, | |
| "grad_norm": 1.0887432098388672, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4161, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002263296869105998, | |
| "grad_norm": 1.4382431507110596, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6272, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003017729158807997, | |
| "grad_norm": 1.3836487531661987, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7209, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003772161448509996, | |
| "grad_norm": 1.604011058807373, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6609, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004526593738211996, | |
| "grad_norm": 1.419691801071167, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.725, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005281026027913994, | |
| "grad_norm": 1.9001708030700684, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.8551, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006035458317615994, | |
| "grad_norm": 1.9900678396224976, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.8507, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0067898906073179935, | |
| "grad_norm": 1.2424248456954956, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.5811, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007544322897019992, | |
| "grad_norm": 1.0436562299728394, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.46, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008298755186721992, | |
| "grad_norm": 1.094989538192749, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.458, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009053187476423991, | |
| "grad_norm": 1.1770530939102173, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.5117, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00980761976612599, | |
| "grad_norm": 0.9547999501228333, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.458, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010562052055827989, | |
| "grad_norm": 0.9950444102287292, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.397, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011316484345529988, | |
| "grad_norm": 0.8353845477104187, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.2724, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012070916635231988, | |
| "grad_norm": 1.0144917964935303, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.4976, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.012825348924933987, | |
| "grad_norm": 1.0305901765823364, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.4253, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.013579781214635987, | |
| "grad_norm": 0.9045003652572632, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.3756, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.014334213504337986, | |
| "grad_norm": 0.8268274068832397, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.364, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.015088645794039984, | |
| "grad_norm": 0.8311420679092407, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3196, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015843078083741986, | |
| "grad_norm": 0.9112005233764648, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.2999, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.016597510373443983, | |
| "grad_norm": 0.8404811024665833, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.3525, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01735194266314598, | |
| "grad_norm": 0.9411618709564209, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.4295, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.018106374952847983, | |
| "grad_norm": 0.7401957511901855, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.2783, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01886080724254998, | |
| "grad_norm": 0.7432383298873901, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.2903, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01886080724254998, | |
| "eval_loss": 0.3726862370967865, | |
| "eval_runtime": 20.3618, | |
| "eval_samples_per_second": 109.666, | |
| "eval_steps_per_second": 13.751, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01961523953225198, | |
| "grad_norm": 0.7956138849258423, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.3527, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02036967182195398, | |
| "grad_norm": 0.8124170899391174, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.2873, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.021124104111655977, | |
| "grad_norm": 0.878582239151001, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.3622, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02187853640135798, | |
| "grad_norm": 0.9804088473320007, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.3978, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.022632968691059976, | |
| "grad_norm": 0.8588770031929016, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.2956, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.023387400980761978, | |
| "grad_norm": 0.783898115158081, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.301, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.024141833270463976, | |
| "grad_norm": 0.6420652270317078, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.2105, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.024896265560165973, | |
| "grad_norm": 1.0156136751174927, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.3051, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.025650697849867975, | |
| "grad_norm": 0.7897914052009583, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.3269, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.026405130139569973, | |
| "grad_norm": 0.7197304368019104, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2039, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.027159562429271974, | |
| "grad_norm": 0.8324704170227051, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.3202, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02791399471897397, | |
| "grad_norm": 0.8574749231338501, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.2887, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.028668427008675973, | |
| "grad_norm": 1.0728785991668701, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.4163, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02942285929837797, | |
| "grad_norm": 0.9155979156494141, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.2978, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03017729158807997, | |
| "grad_norm": 0.8738413453102112, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.3142, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03093172387778197, | |
| "grad_norm": 0.89309161901474, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.2975, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03168615616748397, | |
| "grad_norm": 1.0845947265625, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.3054, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03244058845718597, | |
| "grad_norm": 0.9354661107063293, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.3257, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03319502074688797, | |
| "grad_norm": 1.173690676689148, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.3655, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.033949453036589965, | |
| "grad_norm": 0.984697699546814, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.2914, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03470388532629196, | |
| "grad_norm": 1.103393316268921, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.3537, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03545831761599397, | |
| "grad_norm": 1.3742722272872925, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.4048, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.036212749905695965, | |
| "grad_norm": 1.5404117107391357, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.4235, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03696718219539796, | |
| "grad_norm": 1.8669302463531494, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.3197, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03772161448509996, | |
| "grad_norm": 3.114102602005005, | |
| "learning_rate": 0.0, | |
| "loss": 0.5909, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03772161448509996, | |
| "eval_loss": 0.3445923328399658, | |
| "eval_runtime": 20.3648, | |
| "eval_samples_per_second": 109.65, | |
| "eval_steps_per_second": 13.749, | |
| "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 | |
| } | |