| { | |
| "best_metric": 0.69820237159729, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.10710938545990092, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0021421877091980183, | |
| "grad_norm": 50.62248611450195, | |
| "learning_rate": 5e-05, | |
| "loss": 135.4433, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021421877091980183, | |
| "eval_loss": 3.7305963039398193, | |
| "eval_runtime": 5.1189, | |
| "eval_samples_per_second": 9.768, | |
| "eval_steps_per_second": 2.54, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0042843754183960366, | |
| "grad_norm": 52.64827346801758, | |
| "learning_rate": 0.0001, | |
| "loss": 135.4566, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006426563127594056, | |
| "grad_norm": 41.28614044189453, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 115.5113, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008568750836792073, | |
| "grad_norm": 47.29509353637695, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 107.7922, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010710938545990093, | |
| "grad_norm": 53.49359893798828, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 99.1172, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012853126255188111, | |
| "grad_norm": 61.016937255859375, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 84.8073, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01499531396438613, | |
| "grad_norm": 61.33747100830078, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 71.3142, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.017137501673584146, | |
| "grad_norm": 50.68693161010742, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 60.2678, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.019279689382782166, | |
| "grad_norm": 45.667503356933594, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 51.8135, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.021421877091980186, | |
| "grad_norm": 40.5544548034668, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 46.0188, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023564064801178203, | |
| "grad_norm": 49.124473571777344, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 42.3976, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.025706252510376223, | |
| "grad_norm": 58.30964279174805, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 40.1911, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02784844021957424, | |
| "grad_norm": 41.029354095458984, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 49.638, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02999062792877226, | |
| "grad_norm": 60.048622131347656, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 53.7417, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.032132815637970276, | |
| "grad_norm": 38.2186279296875, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 39.4384, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03427500334716829, | |
| "grad_norm": 29.658790588378906, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 28.6513, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.036417191056366316, | |
| "grad_norm": 28.63747787475586, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 26.4264, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03855937876556433, | |
| "grad_norm": 17.917499542236328, | |
| "learning_rate": 7.75e-05, | |
| "loss": 24.7643, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04070156647476235, | |
| "grad_norm": 10.29113483428955, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 23.5359, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04284375418396037, | |
| "grad_norm": 7.3474507331848145, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 22.8159, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04498594189315839, | |
| "grad_norm": 9.085057258605957, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 22.7155, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.047128129602356406, | |
| "grad_norm": 4.378646373748779, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 22.6023, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04927031731155442, | |
| "grad_norm": 3.777001142501831, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 22.5147, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.051412505020752446, | |
| "grad_norm": 3.55411434173584, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 22.5446, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05355469272995046, | |
| "grad_norm": 9.409378051757812, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 22.9466, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05355469272995046, | |
| "eval_loss": 0.7068415284156799, | |
| "eval_runtime": 5.0079, | |
| "eval_samples_per_second": 9.984, | |
| "eval_steps_per_second": 2.596, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05569688043914848, | |
| "grad_norm": 8.646862983703613, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 23.0047, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0578390681483465, | |
| "grad_norm": 2.957317352294922, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 22.7869, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05998125585754452, | |
| "grad_norm": 2.7320399284362793, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 22.442, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.062123443566742535, | |
| "grad_norm": 2.0762381553649902, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 22.4845, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06426563127594055, | |
| "grad_norm": 1.6332262754440308, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 22.4456, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06640781898513858, | |
| "grad_norm": 2.0493698120117188, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 22.4885, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06855000669433658, | |
| "grad_norm": 1.6183415651321411, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 22.4925, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07069219440353461, | |
| "grad_norm": 1.547934651374817, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 22.4405, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07283438211273263, | |
| "grad_norm": 2.028595447540283, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 22.5106, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07497656982193064, | |
| "grad_norm": 5.2422285079956055, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 22.4615, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07711875753112866, | |
| "grad_norm": 1.9077330827713013, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 22.4419, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07926094524032669, | |
| "grad_norm": 1.5004316568374634, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 22.4519, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0814031329495247, | |
| "grad_norm": 1.5373482704162598, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 22.4174, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08354532065872272, | |
| "grad_norm": 6.600869178771973, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 22.5424, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08568750836792074, | |
| "grad_norm": 1.9094051122665405, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 22.425, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08782969607711875, | |
| "grad_norm": 1.1293197870254517, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 22.3906, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.08997188378631678, | |
| "grad_norm": 1.5770303010940552, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 22.4555, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09211407149551479, | |
| "grad_norm": 1.7812321186065674, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 22.465, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.09425625920471281, | |
| "grad_norm": 1.4559767246246338, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 22.4248, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.09639844691391083, | |
| "grad_norm": 1.6689614057540894, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 22.4673, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09854063462310884, | |
| "grad_norm": 1.4703079462051392, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 22.4004, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10068282233230687, | |
| "grad_norm": 1.3788950443267822, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 22.4353, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.10282501004150489, | |
| "grad_norm": 1.4672656059265137, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 22.4183, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1049671977507029, | |
| "grad_norm": 1.815381407737732, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 22.4214, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.10710938545990092, | |
| "grad_norm": 0.9922463893890381, | |
| "learning_rate": 1e-05, | |
| "loss": 22.4399, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10710938545990092, | |
| "eval_loss": 0.69820237159729, | |
| "eval_runtime": 5.0539, | |
| "eval_samples_per_second": 9.893, | |
| "eval_steps_per_second": 2.572, | |
| "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": 6.059534154779853e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |