| { | |
| "best_metric": 0.013853449374437332, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7858546168958742, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015717092337917484, | |
| "grad_norm": 10.561834335327148, | |
| "learning_rate": 5e-05, | |
| "loss": 3.9087, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015717092337917484, | |
| "eval_loss": 4.409885406494141, | |
| "eval_runtime": 1.4804, | |
| "eval_samples_per_second": 33.776, | |
| "eval_steps_per_second": 8.782, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03143418467583497, | |
| "grad_norm": 11.55346965789795, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2057, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.047151277013752456, | |
| "grad_norm": 9.79731559753418, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.6356, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06286836935166994, | |
| "grad_norm": 8.176977157592773, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.557, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07858546168958742, | |
| "grad_norm": 6.051332950592041, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.6899, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09430255402750491, | |
| "grad_norm": 4.841969966888428, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.0587, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1100196463654224, | |
| "grad_norm": 3.7139148712158203, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.6212, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.12573673870333987, | |
| "grad_norm": 2.9811384677886963, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.3556, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14145383104125736, | |
| "grad_norm": 1.9589557647705078, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.1954, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.15717092337917485, | |
| "grad_norm": 2.448641061782837, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.187, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17288801571709234, | |
| "grad_norm": 23.635149002075195, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.1668, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.18860510805500982, | |
| "grad_norm": 1.7201950550079346, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.0884, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2043222003929273, | |
| "grad_norm": 1.208739995956421, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.0712, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2200392927308448, | |
| "grad_norm": 1.2750734090805054, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0814, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2357563850687623, | |
| "grad_norm": 2.06817364692688, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.1169, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.25147347740667975, | |
| "grad_norm": 1.104299783706665, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1106, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.26719056974459726, | |
| "grad_norm": 0.9678297638893127, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0531, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2829076620825147, | |
| "grad_norm": 1.0201412439346313, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0976, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.29862475442043224, | |
| "grad_norm": 1.0041857957839966, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0459, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3143418467583497, | |
| "grad_norm": 0.6837925910949707, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0498, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3300589390962672, | |
| "grad_norm": 0.27539634704589844, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0125, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.34577603143418467, | |
| "grad_norm": 0.2855336666107178, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0146, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3614931237721022, | |
| "grad_norm": 0.39759957790374756, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0593, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.37721021611001965, | |
| "grad_norm": 0.8079286217689514, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0784, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3929273084479371, | |
| "grad_norm": 0.4539399743080139, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0499, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3929273084479371, | |
| "eval_loss": 0.015500125475227833, | |
| "eval_runtime": 1.3861, | |
| "eval_samples_per_second": 36.074, | |
| "eval_steps_per_second": 9.379, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4086444007858546, | |
| "grad_norm": 0.5926785469055176, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0479, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4243614931237721, | |
| "grad_norm": 0.6671425700187683, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0329, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4400785854616896, | |
| "grad_norm": 0.5285760164260864, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0533, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.45579567779960706, | |
| "grad_norm": 0.3623944818973541, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0463, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4715127701375246, | |
| "grad_norm": 0.5695236921310425, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0333, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.48722986247544203, | |
| "grad_norm": 0.2945129871368408, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0318, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5029469548133595, | |
| "grad_norm": 0.2810068726539612, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0093, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.518664047151277, | |
| "grad_norm": 0.3693678081035614, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0228, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5343811394891945, | |
| "grad_norm": 0.4901984632015228, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0278, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.550098231827112, | |
| "grad_norm": 0.4526285231113434, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0515, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5658153241650294, | |
| "grad_norm": 0.16172288358211517, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0156, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.581532416502947, | |
| "grad_norm": 0.5231755375862122, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0803, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5972495088408645, | |
| "grad_norm": 0.4872123599052429, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0544, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6129666011787819, | |
| "grad_norm": 0.3213493525981903, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0301, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6286836935166994, | |
| "grad_norm": 0.2550433278083801, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0187, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6444007858546169, | |
| "grad_norm": 0.5219851732254028, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0427, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6601178781925344, | |
| "grad_norm": 0.4075874984264374, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0446, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6758349705304518, | |
| "grad_norm": 0.39169013500213623, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0152, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6915520628683693, | |
| "grad_norm": 0.5663002729415894, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0167, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7072691552062869, | |
| "grad_norm": 0.31401506066322327, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0187, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7229862475442044, | |
| "grad_norm": 0.16422072052955627, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0208, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7387033398821218, | |
| "grad_norm": 0.20995976030826569, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0258, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7544204322200393, | |
| "grad_norm": 0.1727566123008728, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0247, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7701375245579568, | |
| "grad_norm": 0.3798152804374695, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0236, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7858546168958742, | |
| "grad_norm": 0.4489036202430725, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0365, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7858546168958742, | |
| "eval_loss": 0.013853449374437332, | |
| "eval_runtime": 1.361, | |
| "eval_samples_per_second": 36.738, | |
| "eval_steps_per_second": 9.552, | |
| "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": 8.335466128054682e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |