| { | |
| "best_metric": 0.46879658102989197, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6201550387596899, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012403100775193798, | |
| "grad_norm": 36.18206024169922, | |
| "learning_rate": 5e-05, | |
| "loss": 12.6612, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012403100775193798, | |
| "eval_loss": 14.17723274230957, | |
| "eval_runtime": 2.0527, | |
| "eval_samples_per_second": 24.358, | |
| "eval_steps_per_second": 6.333, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.024806201550387597, | |
| "grad_norm": 34.50545883178711, | |
| "learning_rate": 0.0001, | |
| "loss": 12.7119, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.037209302325581395, | |
| "grad_norm": 29.503662109375, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.3526, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04961240310077519, | |
| "grad_norm": 24.90972137451172, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.7179, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06201550387596899, | |
| "grad_norm": 17.757352828979492, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.775, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07441860465116279, | |
| "grad_norm": 11.634033203125, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.5315, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08682170542635659, | |
| "grad_norm": 10.418181419372559, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.7079, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09922480620155039, | |
| "grad_norm": 10.920205116271973, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.2043, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11162790697674418, | |
| "grad_norm": 2.8824594020843506, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.7578, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12403100775193798, | |
| "grad_norm": 5.826957702636719, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.8208, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13643410852713178, | |
| "grad_norm": 6.743420600891113, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.6584, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.14883720930232558, | |
| "grad_norm": 3.898432493209839, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.522, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16124031007751938, | |
| "grad_norm": 15.718518257141113, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.7515, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.17364341085271318, | |
| "grad_norm": 10.08508014678955, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.7923, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.18604651162790697, | |
| "grad_norm": 7.129915714263916, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.7918, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.19844961240310077, | |
| "grad_norm": 4.513343334197998, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.6827, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.21085271317829457, | |
| "grad_norm": 1.3946938514709473, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.5873, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.22325581395348837, | |
| "grad_norm": 1.8656858205795288, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.5747, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.23565891472868217, | |
| "grad_norm": 1.4627933502197266, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.5384, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.24806201550387597, | |
| "grad_norm": 0.9287298917770386, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.5297, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26046511627906976, | |
| "grad_norm": 0.9762687683105469, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.4391, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.27286821705426356, | |
| "grad_norm": 1.4817274808883667, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.522, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.28527131782945736, | |
| "grad_norm": 1.7564687728881836, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.4228, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.29767441860465116, | |
| "grad_norm": 2.1884002685546875, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.3228, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.31007751937984496, | |
| "grad_norm": 2.240156888961792, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.3588, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.31007751937984496, | |
| "eval_loss": 0.528091311454773, | |
| "eval_runtime": 2.0803, | |
| "eval_samples_per_second": 24.035, | |
| "eval_steps_per_second": 6.249, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.32248062015503876, | |
| "grad_norm": 6.642690181732178, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.8365, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.33488372093023255, | |
| "grad_norm": 3.7332913875579834, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.6802, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.34728682170542635, | |
| "grad_norm": 1.695497751235962, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.5761, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.35968992248062015, | |
| "grad_norm": 1.8069305419921875, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.6018, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "grad_norm": 1.9271109104156494, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.5892, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.38449612403100775, | |
| "grad_norm": 2.6150898933410645, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.5628, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.39689922480620154, | |
| "grad_norm": 2.0166444778442383, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.544, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.40930232558139534, | |
| "grad_norm": 2.3682992458343506, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.4747, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.42170542635658914, | |
| "grad_norm": 1.7106528282165527, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.4567, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.43410852713178294, | |
| "grad_norm": 1.7924227714538574, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.4622, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.44651162790697674, | |
| "grad_norm": 1.8440314531326294, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.3794, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.45891472868217054, | |
| "grad_norm": 2.1702985763549805, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.3674, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.47131782945736433, | |
| "grad_norm": 3.5106520652770996, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.4877, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.48372093023255813, | |
| "grad_norm": 3.0614447593688965, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.6244, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.49612403100775193, | |
| "grad_norm": 2.051356792449951, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.5893, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5085271317829457, | |
| "grad_norm": 1.6510694026947021, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.5597, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5209302325581395, | |
| "grad_norm": 0.8817880749702454, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.5195, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 1.1567829847335815, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.5009, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5457364341085271, | |
| "grad_norm": 1.164838433265686, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.5142, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5581395348837209, | |
| "grad_norm": 2.1000521183013916, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.4716, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5705426356589147, | |
| "grad_norm": 2.214428424835205, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.4248, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5829457364341085, | |
| "grad_norm": 1.865970253944397, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.4353, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5953488372093023, | |
| "grad_norm": 1.5044881105422974, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.4025, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6077519379844961, | |
| "grad_norm": 1.0346555709838867, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.3396, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6201550387596899, | |
| "grad_norm": 0.7697737812995911, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3228, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6201550387596899, | |
| "eval_loss": 0.46879658102989197, | |
| "eval_runtime": 2.075, | |
| "eval_samples_per_second": 24.097, | |
| "eval_steps_per_second": 6.265, | |
| "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": 1.62480894509056e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |