| { | |
| "best_metric": 0.7735704779624939, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.14958863126402394, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0029917726252804786, | |
| "grad_norm": 0.8262730240821838, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8104, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029917726252804786, | |
| "eval_loss": 3.519901752471924, | |
| "eval_runtime": 4.8254, | |
| "eval_samples_per_second": 10.362, | |
| "eval_steps_per_second": 2.694, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005983545250560957, | |
| "grad_norm": 1.837027668952942, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2348, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008975317875841436, | |
| "grad_norm": 2.279060125350952, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.2118, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011967090501121914, | |
| "grad_norm": 2.481149673461914, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.4021, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014958863126402393, | |
| "grad_norm": 4.176632404327393, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.2112, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01795063575168287, | |
| "grad_norm": 4.057385444641113, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.2833, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.020942408376963352, | |
| "grad_norm": 2.8628005981445312, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.1405, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02393418100224383, | |
| "grad_norm": 3.6795191764831543, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.1428, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02692595362752431, | |
| "grad_norm": 3.215407133102417, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.0992, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.029917726252804786, | |
| "grad_norm": 2.676081895828247, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.053, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.032909498878085267, | |
| "grad_norm": 2.3711888790130615, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.0208, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03590127150336574, | |
| "grad_norm": 2.2834978103637695, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.9472, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03889304412864622, | |
| "grad_norm": 2.9938697814941406, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.9502, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.041884816753926704, | |
| "grad_norm": 1.6415656805038452, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.5459, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04487658937920718, | |
| "grad_norm": 1.410683035850525, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.7609, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04786836200448766, | |
| "grad_norm": 1.4782236814498901, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.7283, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.050860134629768135, | |
| "grad_norm": 1.4281121492385864, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.6718, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05385190725504862, | |
| "grad_norm": 1.3908441066741943, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.7726, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.056843679880329095, | |
| "grad_norm": 1.322344422340393, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.9117, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05983545250560957, | |
| "grad_norm": 1.486789584159851, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.9284, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06282722513089005, | |
| "grad_norm": 1.1547739505767822, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.7662, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06581899775617053, | |
| "grad_norm": 1.5292367935180664, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.8921, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.068810770381451, | |
| "grad_norm": 1.394530177116394, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.9722, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07180254300673149, | |
| "grad_norm": 1.3324661254882812, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.9374, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07479431563201197, | |
| "grad_norm": 1.4819488525390625, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.0253, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07479431563201197, | |
| "eval_loss": 0.7735704779624939, | |
| "eval_runtime": 4.9242, | |
| "eval_samples_per_second": 10.154, | |
| "eval_steps_per_second": 2.64, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07778608825729244, | |
| "grad_norm": 1.5082378387451172, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.6652, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08077786088257292, | |
| "grad_norm": 1.9806829690933228, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.6724, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08376963350785341, | |
| "grad_norm": 1.6297918558120728, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.7008, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08676140613313388, | |
| "grad_norm": 1.1730655431747437, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.7125, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08975317875841436, | |
| "grad_norm": 1.1005781888961792, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.7338, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09274495138369485, | |
| "grad_norm": 1.103263258934021, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.7299, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09573672400897532, | |
| "grad_norm": 1.6705341339111328, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.798, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0987284966342558, | |
| "grad_norm": 1.9690500497817993, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.8661, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10172026925953627, | |
| "grad_norm": 1.8533998727798462, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.9183, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10471204188481675, | |
| "grad_norm": 1.480391263961792, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.8912, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10770381451009724, | |
| "grad_norm": 2.0091404914855957, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.8077, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11069558713537771, | |
| "grad_norm": 1.5077072381973267, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.877, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.11368735976065819, | |
| "grad_norm": 0.6694612503051758, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.7481, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.11667913238593867, | |
| "grad_norm": 0.8422839641571045, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.4953, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.11967090501121914, | |
| "grad_norm": 0.9925352334976196, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.5853, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12266267763649963, | |
| "grad_norm": 1.2224528789520264, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.5875, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1256544502617801, | |
| "grad_norm": 1.2105146646499634, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.5848, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1286462228870606, | |
| "grad_norm": 0.9901201725006104, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.7639, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13163799551234107, | |
| "grad_norm": 0.9849115014076233, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.6583, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.13462976813762154, | |
| "grad_norm": 1.1090823411941528, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.6682, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.137621540762902, | |
| "grad_norm": 1.226506233215332, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.8299, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1406133133881825, | |
| "grad_norm": 1.1486507654190063, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.7894, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.14360508601346297, | |
| "grad_norm": 1.1801129579544067, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.8294, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.14659685863874344, | |
| "grad_norm": 1.4629026651382446, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.8549, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.14958863126402394, | |
| "grad_norm": 1.3931605815887451, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9271, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14958863126402394, | |
| "eval_loss": 0.7797591686248779, | |
| "eval_runtime": 4.8227, | |
| "eval_samples_per_second": 10.368, | |
| "eval_steps_per_second": 2.696, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.174479344467968e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |