| { | |
| "best_metric": 10.991680145263672, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.43045466774280333, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008609093354856066, | |
| "grad_norm": 10.635313034057617, | |
| "learning_rate": 5e-05, | |
| "loss": 355.0041, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008609093354856066, | |
| "eval_loss": 11.096758842468262, | |
| "eval_runtime": 0.4496, | |
| "eval_samples_per_second": 111.213, | |
| "eval_steps_per_second": 28.915, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017218186709712133, | |
| "grad_norm": 11.076752662658691, | |
| "learning_rate": 0.0001, | |
| "loss": 354.9742, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0258272800645682, | |
| "grad_norm": 13.533737182617188, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 355.034, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.034436373419424265, | |
| "grad_norm": 11.721927642822266, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 354.9048, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04304546677428033, | |
| "grad_norm": 12.535335540771484, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 354.7546, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0516545601291364, | |
| "grad_norm": 12.207901000976562, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 354.7418, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.060263653483992465, | |
| "grad_norm": 12.92765998840332, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 354.56, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06887274683884853, | |
| "grad_norm": 13.168181419372559, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 354.4257, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0774818401937046, | |
| "grad_norm": 14.865147590637207, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 354.2678, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08609093354856066, | |
| "grad_norm": 17.191944122314453, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 354.0385, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09470002690341674, | |
| "grad_norm": 21.784700393676758, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 353.6926, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1033091202582728, | |
| "grad_norm": 25.464162826538086, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 353.3433, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11191821361312887, | |
| "grad_norm": 19.105411529541016, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 353.5573, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12052730696798493, | |
| "grad_norm": 10.750304222106934, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 353.9489, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.129136400322841, | |
| "grad_norm": 12.10621452331543, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 353.794, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13774549367769706, | |
| "grad_norm": 11.745237350463867, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 353.705, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14635458703255314, | |
| "grad_norm": 11.175185203552246, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 353.6503, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1549636803874092, | |
| "grad_norm": 11.587780952453613, | |
| "learning_rate": 7.75e-05, | |
| "loss": 353.4981, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16357277374226525, | |
| "grad_norm": 11.572482109069824, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 353.4075, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17218186709712133, | |
| "grad_norm": 11.94267749786377, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 353.2624, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1807909604519774, | |
| "grad_norm": 12.672850608825684, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 353.0754, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.18940005380683347, | |
| "grad_norm": 14.19095516204834, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 352.8477, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19800914716168955, | |
| "grad_norm": 16.85199737548828, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 352.2639, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2066182405165456, | |
| "grad_norm": 20.074535369873047, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 351.6331, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.21522733387140167, | |
| "grad_norm": 24.241453170776367, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 350.9599, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21522733387140167, | |
| "eval_loss": 11.017281532287598, | |
| "eval_runtime": 0.1409, | |
| "eval_samples_per_second": 354.775, | |
| "eval_steps_per_second": 92.242, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22383642722625774, | |
| "grad_norm": 9.065348625183105, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 353.421, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2324455205811138, | |
| "grad_norm": 9.961706161499023, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 353.1088, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24105461393596986, | |
| "grad_norm": 11.364466667175293, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 352.7587, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.24966370729082593, | |
| "grad_norm": 10.180781364440918, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 352.8823, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.258272800645682, | |
| "grad_norm": 10.212959289550781, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 352.8266, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2668818940005381, | |
| "grad_norm": 9.96835708618164, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 352.8559, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2754909873553941, | |
| "grad_norm": 10.018963813781738, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 352.8179, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2841000807102502, | |
| "grad_norm": 10.431824684143066, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 352.711, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.29270917406510627, | |
| "grad_norm": 11.229265213012695, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 352.5165, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3013182674199623, | |
| "grad_norm": 13.20763111114502, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 351.8922, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3099273607748184, | |
| "grad_norm": 16.267868041992188, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 351.0787, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.31853645412967446, | |
| "grad_norm": 19.831783294677734, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 350.2882, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3271455474845305, | |
| "grad_norm": 15.882200241088867, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 351.226, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3357546408393866, | |
| "grad_norm": 9.732914924621582, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 352.6428, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.34436373419424265, | |
| "grad_norm": 9.99857234954834, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 352.571, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.35297282754909876, | |
| "grad_norm": 9.702710151672363, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 352.5199, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3615819209039548, | |
| "grad_norm": 9.81837272644043, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 352.5027, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.37019101425881085, | |
| "grad_norm": 9.183221817016602, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 352.661, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.37880010761366695, | |
| "grad_norm": 9.308856964111328, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 352.6186, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.387409200968523, | |
| "grad_norm": 9.76315975189209, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 352.499, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3960182943233791, | |
| "grad_norm": 11.07622241973877, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 352.1287, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.40462738767823514, | |
| "grad_norm": 12.31144905090332, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 351.7421, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4132364810330912, | |
| "grad_norm": 15.077690124511719, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 351.0006, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4218455743879473, | |
| "grad_norm": 18.245941162109375, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 350.2695, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.43045466774280333, | |
| "grad_norm": 21.990154266357422, | |
| "learning_rate": 1e-05, | |
| "loss": 349.6386, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.43045466774280333, | |
| "eval_loss": 10.991680145263672, | |
| "eval_runtime": 0.1335, | |
| "eval_samples_per_second": 374.611, | |
| "eval_steps_per_second": 97.399, | |
| "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": 4212542668800.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |