| { | |
| "best_metric": 0.4119807779788971, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.045119990976001806, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000902399819520036, | |
| "grad_norm": 8.212875366210938, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6447, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000902399819520036, | |
| "eval_loss": 6.4507269859313965, | |
| "eval_runtime": 2.0199, | |
| "eval_samples_per_second": 24.753, | |
| "eval_steps_per_second": 6.436, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001804799639040072, | |
| "grad_norm": 8.473448753356934, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6436, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0027071994585601083, | |
| "grad_norm": 7.5769195556640625, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.4067, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003609599278080144, | |
| "grad_norm": 5.150447368621826, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.497, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004511999097600181, | |
| "grad_norm": 3.948168992996216, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.1283, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0054143989171202165, | |
| "grad_norm": 5.283059120178223, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.9159, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0063167987366402525, | |
| "grad_norm": 3.407850503921509, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.7784, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007219198556160288, | |
| "grad_norm": 2.219080686569214, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.6191, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008121598375680324, | |
| "grad_norm": 1.9241960048675537, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.7074, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009023998195200361, | |
| "grad_norm": 1.7714288234710693, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.5067, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009926398014720396, | |
| "grad_norm": 1.5934926271438599, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.4878, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010828797834240433, | |
| "grad_norm": 1.5990341901779175, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.5536, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01173119765376047, | |
| "grad_norm": 1.3820379972457886, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.4728, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.012633597473280505, | |
| "grad_norm": 1.4526031017303467, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.5001, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.013535997292800542, | |
| "grad_norm": 1.1816612482070923, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.4505, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014438397112320577, | |
| "grad_norm": 1.2769337892532349, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.4592, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.015340796931840614, | |
| "grad_norm": 1.3497493267059326, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.4632, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01624319675136065, | |
| "grad_norm": 1.1774433851242065, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.4911, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.017145596570880686, | |
| "grad_norm": 1.2581998109817505, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.5264, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.018047996390400722, | |
| "grad_norm": 1.0584566593170166, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.459, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01895039620992076, | |
| "grad_norm": 1.1238056421279907, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.4488, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.019852796029440792, | |
| "grad_norm": 1.1382229328155518, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.4585, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02075519584896083, | |
| "grad_norm": 1.353520154953003, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.5537, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.021657595668480866, | |
| "grad_norm": 1.172533631324768, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.4503, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.022559995488000903, | |
| "grad_norm": 1.1839252710342407, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.5279, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.022559995488000903, | |
| "eval_loss": 0.4119807779788971, | |
| "eval_runtime": 2.0297, | |
| "eval_samples_per_second": 24.635, | |
| "eval_steps_per_second": 6.405, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02346239530752094, | |
| "grad_norm": 0.9872093796730042, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.4193, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.024364795127040973, | |
| "grad_norm": 1.046190619468689, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.4439, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02526719494656101, | |
| "grad_norm": 1.055621862411499, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.443, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.026169594766081047, | |
| "grad_norm": 1.030385971069336, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.4329, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.027071994585601084, | |
| "grad_norm": 1.0661410093307495, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.485, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02797439440512112, | |
| "grad_norm": 1.0831876993179321, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.406, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.028876794224641154, | |
| "grad_norm": 1.1392087936401367, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.4828, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02977919404416119, | |
| "grad_norm": 1.1672487258911133, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.437, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.030681593863681227, | |
| "grad_norm": 1.0720443725585938, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.4639, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.031583993683201264, | |
| "grad_norm": 1.0987470149993896, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.4556, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0324863935027213, | |
| "grad_norm": 1.049139380455017, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.3672, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03338879332224134, | |
| "grad_norm": 1.1732778549194336, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.4206, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03429119314176137, | |
| "grad_norm": 1.1100412607192993, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.3678, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.035193592961281404, | |
| "grad_norm": 1.4068400859832764, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.4166, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.036095992780801445, | |
| "grad_norm": 1.2302528619766235, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.4011, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03699839260032148, | |
| "grad_norm": 1.392626166343689, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.4368, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03790079241984152, | |
| "grad_norm": 1.0433331727981567, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.4715, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03880319223936155, | |
| "grad_norm": 1.0821082592010498, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.4894, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.039705592058881585, | |
| "grad_norm": 0.8876683115959167, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.3398, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.040607991878401625, | |
| "grad_norm": 1.0384588241577148, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.4193, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04151039169792166, | |
| "grad_norm": 1.1146678924560547, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.3888, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0424127915174417, | |
| "grad_norm": 1.0252597332000732, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.3859, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04331519133696173, | |
| "grad_norm": 1.4751672744750977, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.4382, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.044217591156481766, | |
| "grad_norm": 1.6967180967330933, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.3737, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.045119990976001806, | |
| "grad_norm": 1.3377171754837036, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4293, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.045119990976001806, | |
| "eval_loss": 0.42784634232521057, | |
| "eval_runtime": 2.0396, | |
| "eval_samples_per_second": 24.515, | |
| "eval_steps_per_second": 6.374, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.589463780163584e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |