| { | |
| "best_metric": 0.05516192317008972, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6451612903225806, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012903225806451613, | |
| "grad_norm": 11.947517395019531, | |
| "learning_rate": 5e-05, | |
| "loss": 8.32, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012903225806451613, | |
| "eval_loss": 7.702047824859619, | |
| "eval_runtime": 4.139, | |
| "eval_samples_per_second": 12.08, | |
| "eval_steps_per_second": 3.141, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.025806451612903226, | |
| "grad_norm": 9.677274703979492, | |
| "learning_rate": 0.0001, | |
| "loss": 8.0379, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03870967741935484, | |
| "grad_norm": 9.281054496765137, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 7.8202, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05161290322580645, | |
| "grad_norm": 7.989272594451904, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.0376, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06451612903225806, | |
| "grad_norm": 6.648435592651367, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.6491, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07741935483870968, | |
| "grad_norm": 6.078338146209717, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.5293, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09032258064516129, | |
| "grad_norm": 5.388497352600098, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.3717, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1032258064516129, | |
| "grad_norm": 5.360282897949219, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.8228, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11612903225806452, | |
| "grad_norm": 4.965456008911133, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.7077, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12903225806451613, | |
| "grad_norm": 3.2490646839141846, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.3754, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14193548387096774, | |
| "grad_norm": 2.913276195526123, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.0078, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15483870967741936, | |
| "grad_norm": 2.8188986778259277, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.8377, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16774193548387098, | |
| "grad_norm": 2.063952922821045, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.4751, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.18064516129032257, | |
| "grad_norm": 3.9418764114379883, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.3594, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1935483870967742, | |
| "grad_norm": 1.246826410293579, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.2689, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2064516129032258, | |
| "grad_norm": 1.8163890838623047, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1908, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.21935483870967742, | |
| "grad_norm": 2.057271718978882, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.3231, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23225806451612904, | |
| "grad_norm": 3.259661912918091, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.313, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24516129032258063, | |
| "grad_norm": 3.280681848526001, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.3727, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 2.004863977432251, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.2143, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2709677419354839, | |
| "grad_norm": 1.1544404029846191, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.2519, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2838709677419355, | |
| "grad_norm": 1.4197533130645752, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.1727, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2967741935483871, | |
| "grad_norm": 1.4496575593948364, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.2865, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3096774193548387, | |
| "grad_norm": 0.921154260635376, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.1033, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3225806451612903, | |
| "grad_norm": 2.2900607585906982, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.215, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3225806451612903, | |
| "eval_loss": 0.11587636917829514, | |
| "eval_runtime": 4.2054, | |
| "eval_samples_per_second": 11.89, | |
| "eval_steps_per_second": 3.091, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.33548387096774196, | |
| "grad_norm": 0.6196833252906799, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0815, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.34838709677419355, | |
| "grad_norm": 1.389115333557129, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.1802, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.36129032258064514, | |
| "grad_norm": 0.7861359119415283, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0859, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3741935483870968, | |
| "grad_norm": 0.6421568393707275, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.1309, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3870967741935484, | |
| "grad_norm": 0.9904139637947083, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.2293, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.9061548709869385, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.1937, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4129032258064516, | |
| "grad_norm": 1.0943150520324707, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.1755, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4258064516129032, | |
| "grad_norm": 0.8827422857284546, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.2004, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.43870967741935485, | |
| "grad_norm": 1.2713053226470947, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.1994, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.45161290322580644, | |
| "grad_norm": 1.8664768934249878, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.2095, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4645161290322581, | |
| "grad_norm": 1.5270920991897583, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.19, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4774193548387097, | |
| "grad_norm": 2.041300058364868, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.1653, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.49032258064516127, | |
| "grad_norm": 0.4778480529785156, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.1365, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5032258064516129, | |
| "grad_norm": 0.8028175234794617, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0985, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 0.9442226886749268, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.1129, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5290322580645161, | |
| "grad_norm": 1.3180819749832153, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.1321, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5419354838709678, | |
| "grad_norm": 0.7343201041221619, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.1373, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5548387096774193, | |
| "grad_norm": 1.6494495868682861, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.2925, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.567741935483871, | |
| "grad_norm": 1.4144569635391235, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.2289, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5806451612903226, | |
| "grad_norm": 0.785733163356781, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.1329, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5935483870967742, | |
| "grad_norm": 1.2976585626602173, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.2443, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6064516129032258, | |
| "grad_norm": 1.1602989435195923, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.1924, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6193548387096774, | |
| "grad_norm": 0.6371066570281982, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.1168, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.632258064516129, | |
| "grad_norm": 0.46553662419319153, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0942, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "grad_norm": 0.7974909543991089, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1389, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "eval_loss": 0.05516192317008972, | |
| "eval_runtime": 4.1583, | |
| "eval_samples_per_second": 12.024, | |
| "eval_steps_per_second": 3.126, | |
| "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": 5.32019209568256e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |