| { | |
| "best_metric": 0.8075627684593201, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.05259870475689536, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010519740951379073, | |
| "grad_norm": 37.66078567504883, | |
| "learning_rate": 5e-05, | |
| "loss": 14.8109, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010519740951379073, | |
| "eval_loss": 13.268001556396484, | |
| "eval_runtime": 2.0272, | |
| "eval_samples_per_second": 24.664, | |
| "eval_steps_per_second": 6.413, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021039481902758147, | |
| "grad_norm": 48.14912033081055, | |
| "learning_rate": 0.0001, | |
| "loss": 14.1398, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0031559222854137215, | |
| "grad_norm": 41.73773956298828, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 12.5357, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004207896380551629, | |
| "grad_norm": 39.7030029296875, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 7.3614, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005259870475689536, | |
| "grad_norm": 23.408571243286133, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.6285, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006311844570827443, | |
| "grad_norm": 23.954805374145508, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.3564, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007363818665965351, | |
| "grad_norm": 12.64648723602295, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.4816, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008415792761103259, | |
| "grad_norm": 7.248321533203125, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.0535, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009467766856241165, | |
| "grad_norm": 4.235668659210205, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.8985, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010519740951379072, | |
| "grad_norm": 3.8979365825653076, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.8346, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01157171504651698, | |
| "grad_norm": 6.265169620513916, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.853, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012623689141654886, | |
| "grad_norm": 6.652163028717041, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.8676, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013675663236792795, | |
| "grad_norm": 12.269131660461426, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.1406, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.014727637331930702, | |
| "grad_norm": 6.396784782409668, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.9183, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01577961142706861, | |
| "grad_norm": 3.7699356079101562, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.827, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016831585522206517, | |
| "grad_norm": 2.2097628116607666, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.8275, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.017883559617344422, | |
| "grad_norm": 1.7083959579467773, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.8225, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01893553371248233, | |
| "grad_norm": 2.439757823944092, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.828, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.019987507807620236, | |
| "grad_norm": 2.4405243396759033, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.812, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.021039481902758145, | |
| "grad_norm": 2.1622493267059326, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.8154, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022091455997896053, | |
| "grad_norm": 2.0287113189697266, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.8343, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02314343009303396, | |
| "grad_norm": 2.6538174152374268, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.8351, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.024195404188171867, | |
| "grad_norm": 2.780940294265747, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.8283, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.025247378283309772, | |
| "grad_norm": 2.008140802383423, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.8269, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02629935237844768, | |
| "grad_norm": 1.1456310749053955, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.8082, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02629935237844768, | |
| "eval_loss": 0.8075627684593201, | |
| "eval_runtime": 2.0782, | |
| "eval_samples_per_second": 24.06, | |
| "eval_steps_per_second": 6.256, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02735132647358559, | |
| "grad_norm": 1.6255582571029663, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.8066, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.028403300568723495, | |
| "grad_norm": 0.809135377407074, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.8051, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.029455274663861403, | |
| "grad_norm": 1.7985752820968628, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.8179, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03050724875899931, | |
| "grad_norm": 1.2974883317947388, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.808, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03155922285413722, | |
| "grad_norm": 1.3518906831741333, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.8031, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.032611196949275126, | |
| "grad_norm": 1.5183818340301514, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.8073, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.033663171044413034, | |
| "grad_norm": 1.6260573863983154, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.8144, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.034715145139550936, | |
| "grad_norm": 2.1896719932556152, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.8099, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.035767119234688845, | |
| "grad_norm": 1.9014267921447754, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.8069, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03681909332982675, | |
| "grad_norm": 1.9700180292129517, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.8166, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03787106742496466, | |
| "grad_norm": 1.4387903213500977, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.8091, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03892304152010257, | |
| "grad_norm": 1.0182123184204102, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.8039, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03997501561524047, | |
| "grad_norm": 1.6459559202194214, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.8475, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04102698971037838, | |
| "grad_norm": 1.9654988050460815, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.8169, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04207896380551629, | |
| "grad_norm": 1.2888116836547852, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.8084, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0431309379006542, | |
| "grad_norm": 1.0997812747955322, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.794, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04418291199579211, | |
| "grad_norm": 1.8465800285339355, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.8217, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04523488609093001, | |
| "grad_norm": 1.5212135314941406, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.8128, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04628686018606792, | |
| "grad_norm": 1.6653895378112793, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.8139, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.047338834281205826, | |
| "grad_norm": 1.3936947584152222, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.7985, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.048390808376343734, | |
| "grad_norm": 2.1122493743896484, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.8154, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04944278247148164, | |
| "grad_norm": 0.8528788685798645, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.8162, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.050494756566619545, | |
| "grad_norm": 1.5338293313980103, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.7937, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05154673066175745, | |
| "grad_norm": 1.9110890626907349, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.8225, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05259870475689536, | |
| "grad_norm": 1.324634313583374, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8084, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05259870475689536, | |
| "eval_loss": 0.8132852911949158, | |
| "eval_runtime": 2.0735, | |
| "eval_samples_per_second": 24.114, | |
| "eval_steps_per_second": 6.27, | |
| "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": 1.6522972753402266e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |