| { | |
| "best_metric": 2.078681707382202, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.04060089321965083, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008120178643930166, | |
| "grad_norm": 2.639324426651001, | |
| "learning_rate": 5e-05, | |
| "loss": 2.858, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008120178643930166, | |
| "eval_loss": 2.93936824798584, | |
| "eval_runtime": 3.8652, | |
| "eval_samples_per_second": 12.936, | |
| "eval_steps_per_second": 3.363, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016240357287860333, | |
| "grad_norm": 2.6153502464294434, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8967, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00243605359317905, | |
| "grad_norm": 2.274890899658203, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.7897, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0032480714575720666, | |
| "grad_norm": 1.7921241521835327, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.6611, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004060089321965083, | |
| "grad_norm": 1.3986022472381592, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.6177, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0048721071863581, | |
| "grad_norm": 1.014383316040039, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.5622, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005684125050751117, | |
| "grad_norm": 0.9104923009872437, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.51, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006496142915144133, | |
| "grad_norm": 0.769758403301239, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.4549, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007308160779537149, | |
| "grad_norm": 0.7272193431854248, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.4797, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008120178643930167, | |
| "grad_norm": 0.9747893810272217, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.4175, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008932196508323184, | |
| "grad_norm": 0.9429938197135925, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.3725, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0097442143727162, | |
| "grad_norm": 0.90215003490448, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.3684, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010556232237109216, | |
| "grad_norm": 0.8782191872596741, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.5201, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011368250101502234, | |
| "grad_norm": 0.6941512227058411, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.4751, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012180267965895249, | |
| "grad_norm": 0.571916937828064, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.2749, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012992285830288266, | |
| "grad_norm": 0.5063879489898682, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.1833, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013804303694681283, | |
| "grad_norm": 0.5536409616470337, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.196, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.014616321559074299, | |
| "grad_norm": 0.6191221475601196, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.2324, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015428339423467316, | |
| "grad_norm": 0.589053213596344, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.1859, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.016240357287860333, | |
| "grad_norm": 0.6026152968406677, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.1525, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01705237515225335, | |
| "grad_norm": 0.5579113960266113, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.254, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.017864393016646368, | |
| "grad_norm": 0.5579261183738708, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.1767, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01867641088103938, | |
| "grad_norm": 0.625429630279541, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.2522, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0194884287454324, | |
| "grad_norm": 0.6456161737442017, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.1696, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.020300446609825416, | |
| "grad_norm": 0.7212527394294739, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.1977, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.020300446609825416, | |
| "eval_loss": 2.1521599292755127, | |
| "eval_runtime": 3.4792, | |
| "eval_samples_per_second": 14.371, | |
| "eval_steps_per_second": 3.736, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.021112464474218433, | |
| "grad_norm": 0.6315709948539734, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.457, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02192448233861145, | |
| "grad_norm": 0.5546303987503052, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.2939, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.022736500203004467, | |
| "grad_norm": 0.5207832455635071, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.1513, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.023548518067397484, | |
| "grad_norm": 0.511827290058136, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.0922, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.024360535931790498, | |
| "grad_norm": 0.47535425424575806, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.0867, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.025172553796183515, | |
| "grad_norm": 0.5138943791389465, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.1385, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.025984571660576532, | |
| "grad_norm": 0.568745493888855, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.1733, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02679658952496955, | |
| "grad_norm": 0.6428608894348145, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 2.1206, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.027608607389362567, | |
| "grad_norm": 0.6441438794136047, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.1233, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.028420625253755584, | |
| "grad_norm": 0.6346638202667236, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.1293, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.029232643118148598, | |
| "grad_norm": 0.6601185202598572, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.0685, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.030044660982541615, | |
| "grad_norm": 0.7575770020484924, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 2.1927, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.030856678846934632, | |
| "grad_norm": 0.4314456284046173, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.394, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.031668696711327646, | |
| "grad_norm": 0.4646899104118347, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.3228, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.032480714575720666, | |
| "grad_norm": 0.5209022760391235, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.2017, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03329273244011368, | |
| "grad_norm": 0.5574424266815186, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 2.0931, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0341047503045067, | |
| "grad_norm": 0.5595993995666504, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 2.0513, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.034916768168899714, | |
| "grad_norm": 0.5162716507911682, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.067, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.035728786033292735, | |
| "grad_norm": 0.5021359324455261, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.0076, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03654080389768575, | |
| "grad_norm": 0.4660208821296692, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 2.0467, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03735282176207876, | |
| "grad_norm": 0.4938836395740509, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.008, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03816483962647178, | |
| "grad_norm": 0.49616798758506775, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 2.1064, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0389768574908648, | |
| "grad_norm": 0.585048496723175, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 2.0985, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03978887535525782, | |
| "grad_norm": 0.6445486545562744, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 2.075, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04060089321965083, | |
| "grad_norm": 0.948281466960907, | |
| "learning_rate": 1e-05, | |
| "loss": 2.1762, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04060089321965083, | |
| "eval_loss": 2.078681707382202, | |
| "eval_runtime": 3.4922, | |
| "eval_samples_per_second": 14.318, | |
| "eval_steps_per_second": 3.723, | |
| "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": 6.024034403242476e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |