| { | |
| "best_metric": 1.2690883874893188, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0040688448549456805, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016275379419782723, | |
| "grad_norm": 0.5501648187637329, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4521, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016275379419782723, | |
| "eval_loss": 1.4517560005187988, | |
| "eval_runtime": 366.9455, | |
| "eval_samples_per_second": 7.053, | |
| "eval_steps_per_second": 3.526, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00032550758839565446, | |
| "grad_norm": 0.4392848014831543, | |
| "learning_rate": 4e-05, | |
| "loss": 1.1311, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004882613825934817, | |
| "grad_norm": 0.6846683025360107, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4946, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006510151767913089, | |
| "grad_norm": 0.43976062536239624, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3529, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008137689709891362, | |
| "grad_norm": 0.6175621747970581, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4959, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008137689709891362, | |
| "eval_loss": 1.4441068172454834, | |
| "eval_runtime": 378.022, | |
| "eval_samples_per_second": 6.846, | |
| "eval_steps_per_second": 3.423, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009765227651869634, | |
| "grad_norm": 0.7357343435287476, | |
| "learning_rate": 0.00012, | |
| "loss": 1.69, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011392765593847907, | |
| "grad_norm": 0.6256170868873596, | |
| "learning_rate": 0.00014, | |
| "loss": 1.466, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013020303535826179, | |
| "grad_norm": 0.48867544531822205, | |
| "learning_rate": 0.00016, | |
| "loss": 1.4679, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0014647841477804452, | |
| "grad_norm": 0.4968070089817047, | |
| "learning_rate": 0.00018, | |
| "loss": 1.3181, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016275379419782724, | |
| "grad_norm": 0.7122858762741089, | |
| "learning_rate": 0.0002, | |
| "loss": 1.438, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016275379419782724, | |
| "eval_loss": 1.3901616334915161, | |
| "eval_runtime": 374.8058, | |
| "eval_samples_per_second": 6.905, | |
| "eval_steps_per_second": 3.452, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017902917361760995, | |
| "grad_norm": 0.6748654842376709, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.2344, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001953045530373927, | |
| "grad_norm": 0.4834078848361969, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.2618, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0021157993245717543, | |
| "grad_norm": 0.5972713828086853, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.3863, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0022785531187695814, | |
| "grad_norm": 0.6267929673194885, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.2961, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0024413069129674086, | |
| "grad_norm": 0.7491843104362488, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.3862, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0024413069129674086, | |
| "eval_loss": 1.3069721460342407, | |
| "eval_runtime": 370.1738, | |
| "eval_samples_per_second": 6.991, | |
| "eval_steps_per_second": 3.496, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0026040607071652357, | |
| "grad_norm": 0.40365225076675415, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.1843, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002766814501363063, | |
| "grad_norm": 0.6326920986175537, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.5703, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0029295682955608904, | |
| "grad_norm": 0.5312128663063049, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.2094, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0030923220897587176, | |
| "grad_norm": 0.5757593512535095, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.3609, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0032550758839565447, | |
| "grad_norm": 0.7328537106513977, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.1531, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0032550758839565447, | |
| "eval_loss": 1.2818273305892944, | |
| "eval_runtime": 366.2412, | |
| "eval_samples_per_second": 7.066, | |
| "eval_steps_per_second": 3.533, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003417829678154372, | |
| "grad_norm": 0.7662570476531982, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.2233, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003580583472352199, | |
| "grad_norm": 0.8125593066215515, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.2485, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0037433372665500266, | |
| "grad_norm": 0.6410349011421204, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.2007, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003906091060747854, | |
| "grad_norm": 0.6851560473442078, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.2007, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0040688448549456805, | |
| "grad_norm": 0.494051992893219, | |
| "learning_rate": 0.0, | |
| "loss": 1.0691, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0040688448549456805, | |
| "eval_loss": 1.2690883874893188, | |
| "eval_runtime": 360.8957, | |
| "eval_samples_per_second": 7.171, | |
| "eval_steps_per_second": 3.586, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 4071832839782400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |