| { | |
| "best_metric": 1.3385324478149414, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.027018811847748996, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005403762369549799, | |
| "grad_norm": 0.7579950094223022, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2971, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005403762369549799, | |
| "eval_loss": 2.174750566482544, | |
| "eval_runtime": 2.9534, | |
| "eval_samples_per_second": 16.929, | |
| "eval_steps_per_second": 4.402, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010807524739099598, | |
| "grad_norm": 1.1134428977966309, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5831, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016211287108649397, | |
| "grad_norm": 1.063336730003357, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.536, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0021615049478199196, | |
| "grad_norm": 0.9375065565109253, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.599, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0027018811847748995, | |
| "grad_norm": 0.774001955986023, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.5445, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0032422574217298794, | |
| "grad_norm": 1.1132839918136597, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.4067, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0037826336586848593, | |
| "grad_norm": 0.8962889313697815, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.3983, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004323009895639839, | |
| "grad_norm": 0.5397719144821167, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.3102, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004863386132594819, | |
| "grad_norm": 0.37479284405708313, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.3458, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005403762369549799, | |
| "grad_norm": 0.43835580348968506, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.4246, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0059441386065047785, | |
| "grad_norm": 0.4866955578327179, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.3123, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006484514843459759, | |
| "grad_norm": 0.5045744180679321, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.3961, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007024891080414738, | |
| "grad_norm": 0.3350974917411804, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.1432, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007565267317369719, | |
| "grad_norm": 0.344038724899292, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.2358, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008105643554324698, | |
| "grad_norm": 0.3136480152606964, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.2589, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008646019791279679, | |
| "grad_norm": 0.2970927655696869, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.2068, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.009186396028234659, | |
| "grad_norm": 0.333193302154541, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.2867, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.009726772265189637, | |
| "grad_norm": 0.3563210070133209, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2791, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010267148502144618, | |
| "grad_norm": 0.3321801424026489, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.308, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.010807524739099598, | |
| "grad_norm": 0.3614809811115265, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.2864, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011347900976054578, | |
| "grad_norm": 0.35129594802856445, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.3312, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.011888277213009557, | |
| "grad_norm": 0.356954425573349, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.3324, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.012428653449964537, | |
| "grad_norm": 0.37991097569465637, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.3666, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.012969029686919518, | |
| "grad_norm": 0.37282314896583557, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.3366, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.013509405923874498, | |
| "grad_norm": 0.39541906118392944, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.3103, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013509405923874498, | |
| "eval_loss": 1.3474552631378174, | |
| "eval_runtime": 2.3537, | |
| "eval_samples_per_second": 21.243, | |
| "eval_steps_per_second": 5.523, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014049782160829477, | |
| "grad_norm": 0.21152514219284058, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.2167, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.014590158397784457, | |
| "grad_norm": 0.28132620453834534, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.2485, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.015130534634739437, | |
| "grad_norm": 0.28846096992492676, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.3281, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.015670910871694418, | |
| "grad_norm": 0.2903560698032379, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.2298, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.016211287108649396, | |
| "grad_norm": 0.30449891090393066, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.2678, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01675166334560438, | |
| "grad_norm": 0.3175998032093048, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.3251, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.017292039582559357, | |
| "grad_norm": 0.3025440573692322, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.2648, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.017832415819514336, | |
| "grad_norm": 0.3220917582511902, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.3114, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.018372792056469318, | |
| "grad_norm": 0.30278536677360535, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.2781, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.018913168293424296, | |
| "grad_norm": 0.3035091459751129, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.3578, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.019453544530379275, | |
| "grad_norm": 0.3576919138431549, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.2516, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.019993920767334257, | |
| "grad_norm": 0.359345406293869, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.2206, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.020534297004289236, | |
| "grad_norm": 0.23424789309501648, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.203, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.021074673241244218, | |
| "grad_norm": 0.20766839385032654, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.1936, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.021615049478199196, | |
| "grad_norm": 0.2421371042728424, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.2389, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.022155425715154175, | |
| "grad_norm": 0.24859775602817535, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.2361, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.022695801952109157, | |
| "grad_norm": 0.2736833393573761, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.3148, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.023236178189064136, | |
| "grad_norm": 0.26563286781311035, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.2846, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.023776554426019114, | |
| "grad_norm": 0.3035804033279419, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.2743, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.024316930662974096, | |
| "grad_norm": 0.2828158140182495, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.2914, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.024857306899929075, | |
| "grad_norm": 0.2898053526878357, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.2546, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.025397683136884057, | |
| "grad_norm": 0.30576568841934204, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.2922, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.025938059373839036, | |
| "grad_norm": 0.3181474208831787, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.3652, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.026478435610794014, | |
| "grad_norm": 0.34133440256118774, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.3907, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.027018811847748996, | |
| "grad_norm": 0.3962940573692322, | |
| "learning_rate": 1e-05, | |
| "loss": 1.3401, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.027018811847748996, | |
| "eval_loss": 1.3385324478149414, | |
| "eval_runtime": 2.3472, | |
| "eval_samples_per_second": 21.302, | |
| "eval_steps_per_second": 5.538, | |
| "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": 6.061338191368028e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |