| { | |
| "best_metric": 1.260650873184204, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.011259993244004054, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00022519986488008108, | |
| "grad_norm": 2.175715208053589, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0737, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00022519986488008108, | |
| "eval_loss": 4.712589263916016, | |
| "eval_runtime": 3.0907, | |
| "eval_samples_per_second": 16.177, | |
| "eval_steps_per_second": 4.206, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00045039972976016217, | |
| "grad_norm": 2.907069444656372, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7281, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006755995946402432, | |
| "grad_norm": 3.0735440254211426, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.7773, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009007994595203243, | |
| "grad_norm": 3.2849786281585693, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.1898, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0011259993244004053, | |
| "grad_norm": 4.5575737953186035, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.717, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0013511991892804864, | |
| "grad_norm": 3.065314531326294, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.2598, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015763990541605676, | |
| "grad_norm": 2.4317545890808105, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.058, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0018015989190406487, | |
| "grad_norm": 3.0763533115386963, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.8734, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0020267987839207298, | |
| "grad_norm": 2.344825506210327, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.8211, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0022519986488008107, | |
| "grad_norm": 3.3821871280670166, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.7377, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002477198513680892, | |
| "grad_norm": 2.402078151702881, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.6293, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002702398378560973, | |
| "grad_norm": 1.6599009037017822, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.7797, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0029275982434410538, | |
| "grad_norm": 3.5056912899017334, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.7936, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003152798108321135, | |
| "grad_norm": 2.6768195629119873, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.6186, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003377997973201216, | |
| "grad_norm": 1.297431230545044, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.5091, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0036031978380812973, | |
| "grad_norm": 1.0749551057815552, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.4247, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0038283977029613782, | |
| "grad_norm": 1.2177400588989258, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.4305, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0040535975678414595, | |
| "grad_norm": 1.1429535150527954, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.3364, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00427879743272154, | |
| "grad_norm": 1.1341633796691895, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.5143, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004503997297601621, | |
| "grad_norm": 0.9919440746307373, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.4574, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004729197162481703, | |
| "grad_norm": 1.0507696866989136, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.4162, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004954397027361784, | |
| "grad_norm": 1.1296511888504028, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.4329, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0051795968922418644, | |
| "grad_norm": 1.0661320686340332, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.4493, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005404796757121946, | |
| "grad_norm": 0.972745418548584, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.4163, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005629996622002027, | |
| "grad_norm": 1.6437320709228516, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.6262, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005629996622002027, | |
| "eval_loss": 1.3769758939743042, | |
| "eval_runtime": 3.0119, | |
| "eval_samples_per_second": 16.601, | |
| "eval_steps_per_second": 4.316, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0058551964868821076, | |
| "grad_norm": 1.5193920135498047, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.4401, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.006080396351762189, | |
| "grad_norm": 1.2190526723861694, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.3128, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00630559621664227, | |
| "grad_norm": 1.185204029083252, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.346, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.006530796081522351, | |
| "grad_norm": 0.9483022689819336, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.3156, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.006755995946402432, | |
| "grad_norm": 1.055773377418518, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.2951, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006981195811282513, | |
| "grad_norm": 0.8046019673347473, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.1903, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.007206395676162595, | |
| "grad_norm": 0.9744685888290405, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.272, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.007431595541042675, | |
| "grad_norm": 0.9115360975265503, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.3022, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0076567954059227564, | |
| "grad_norm": 1.0355730056762695, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.3344, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.007881995270802838, | |
| "grad_norm": 1.0381739139556885, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.3516, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.008107195135682919, | |
| "grad_norm": 1.140064001083374, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.4159, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.008332395000563, | |
| "grad_norm": 1.489823579788208, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.489, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.00855759486544308, | |
| "grad_norm": 0.9764193296432495, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.2021, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.008782794730323161, | |
| "grad_norm": 1.035754919052124, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.2263, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.009007994595203243, | |
| "grad_norm": 1.046346664428711, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.292, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009233194460083324, | |
| "grad_norm": 0.8970901966094971, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.3079, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.009458394324963405, | |
| "grad_norm": 0.7692161798477173, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.3526, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.009683594189843487, | |
| "grad_norm": 0.7230208516120911, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.3218, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.009908794054723568, | |
| "grad_norm": 0.7119923233985901, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.2683, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.010133993919603648, | |
| "grad_norm": 0.7796542644500732, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.3427, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.010359193784483729, | |
| "grad_norm": 0.7200309038162231, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.2604, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01058439364936381, | |
| "grad_norm": 0.9918878674507141, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.3989, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.010809593514243892, | |
| "grad_norm": 1.0034048557281494, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.4172, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.011034793379123973, | |
| "grad_norm": 1.2579437494277954, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.4476, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.011259993244004054, | |
| "grad_norm": 1.7536529302597046, | |
| "learning_rate": 1e-05, | |
| "loss": 1.4892, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.011259993244004054, | |
| "eval_loss": 1.260650873184204, | |
| "eval_runtime": 3.0632, | |
| "eval_samples_per_second": 16.323, | |
| "eval_steps_per_second": 4.244, | |
| "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": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |