| { | |
| "best_metric": 0.46879878640174866, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.9850746268656714, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05970149253731343, | |
| "grad_norm": 3.4969444274902344, | |
| "learning_rate": 5e-05, | |
| "loss": 4.0203, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05970149253731343, | |
| "eval_loss": 4.0696187019348145, | |
| "eval_runtime": 1.4729, | |
| "eval_samples_per_second": 33.947, | |
| "eval_steps_per_second": 8.826, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11940298507462686, | |
| "grad_norm": 3.6559250354766846, | |
| "learning_rate": 0.0001, | |
| "loss": 4.0385, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1791044776119403, | |
| "grad_norm": 3.5034873485565186, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.9289, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": 3.403470754623413, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.388, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 2.9451396465301514, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.9146, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3582089552238806, | |
| "grad_norm": 3.2620737552642822, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.5116, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.417910447761194, | |
| "grad_norm": 3.4186899662017822, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.1342, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": 3.5180110931396484, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.7708, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5373134328358209, | |
| "grad_norm": 3.15236234664917, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.5748, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 2.916743278503418, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.3533, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6567164179104478, | |
| "grad_norm": 2.617918014526367, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.0945, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.7164179104477612, | |
| "grad_norm": 2.6230955123901367, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.0196, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7761194029850746, | |
| "grad_norm": 2.837193012237549, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.0562, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.835820895522388, | |
| "grad_norm": 2.3078386783599854, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.9869, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 2.06661057472229, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.8797, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9552238805970149, | |
| "grad_norm": 2.422396421432495, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.8551, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0149253731343284, | |
| "grad_norm": 2.36983585357666, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.0677, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0746268656716418, | |
| "grad_norm": 1.9366710186004639, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.8165, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1343283582089552, | |
| "grad_norm": 1.3156859874725342, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.7562, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1940298507462686, | |
| "grad_norm": 1.8956644535064697, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.7083, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2537313432835822, | |
| "grad_norm": 1.5644067525863647, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.7084, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.3134328358208955, | |
| "grad_norm": 1.1243278980255127, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.6813, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.373134328358209, | |
| "grad_norm": 0.9743745923042297, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.6329, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.4328358208955223, | |
| "grad_norm": 1.0701549053192139, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.6253, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4925373134328357, | |
| "grad_norm": 1.0772173404693604, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.6433, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4925373134328357, | |
| "eval_loss": 0.622530996799469, | |
| "eval_runtime": 0.9645, | |
| "eval_samples_per_second": 51.839, | |
| "eval_steps_per_second": 13.478, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.5522388059701493, | |
| "grad_norm": 1.2284759283065796, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.6242, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6119402985074627, | |
| "grad_norm": 1.1227284669876099, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.5985, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.671641791044776, | |
| "grad_norm": 1.330870509147644, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.563, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7313432835820897, | |
| "grad_norm": 1.2725169658660889, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.6058, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7910447761194028, | |
| "grad_norm": 0.9444494247436523, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.5344, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8507462686567164, | |
| "grad_norm": 1.003670573234558, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.5498, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.9104477611940298, | |
| "grad_norm": 0.9227081537246704, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.4844, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.9701492537313432, | |
| "grad_norm": 0.98988276720047, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.5589, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.029850746268657, | |
| "grad_norm": 1.2500901222229004, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.5848, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.08955223880597, | |
| "grad_norm": 1.1457059383392334, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.5207, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.1492537313432836, | |
| "grad_norm": 1.111443281173706, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.4604, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.208955223880597, | |
| "grad_norm": 1.067543625831604, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.4344, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.2686567164179103, | |
| "grad_norm": 0.8861973881721497, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.4895, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.328358208955224, | |
| "grad_norm": 0.9545814394950867, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.4499, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.388059701492537, | |
| "grad_norm": 1.0408685207366943, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.4442, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.4477611940298507, | |
| "grad_norm": 1.24673593044281, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.469, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.5074626865671643, | |
| "grad_norm": 0.9520359635353088, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.4764, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.5671641791044775, | |
| "grad_norm": 0.8973754644393921, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.4698, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.626865671641791, | |
| "grad_norm": 0.9955081343650818, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.4454, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.6865671641791042, | |
| "grad_norm": 1.2142070531845093, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.4314, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.746268656716418, | |
| "grad_norm": 1.1162165403366089, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.4658, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.8059701492537314, | |
| "grad_norm": 1.1647312641143799, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.4592, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.8656716417910446, | |
| "grad_norm": 0.9554238319396973, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.4353, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.925373134328358, | |
| "grad_norm": 0.9301491379737854, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.445, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.9850746268656714, | |
| "grad_norm": 0.990142285823822, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5118, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.9850746268656714, | |
| "eval_loss": 0.46879878640174866, | |
| "eval_runtime": 0.9571, | |
| "eval_samples_per_second": 52.242, | |
| "eval_steps_per_second": 13.583, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 7.83042868150272e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |