| { | |
| "best_metric": 0.4157150089740753, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.2452830188679247, | |
| "eval_steps": 25, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.10062893081761007, | |
| "grad_norm": 1.5290278196334839, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0764, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10062893081761007, | |
| "eval_loss": 1.2052011489868164, | |
| "eval_runtime": 0.6237, | |
| "eval_samples_per_second": 107.425, | |
| "eval_steps_per_second": 14.43, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.20125786163522014, | |
| "grad_norm": 2.019923210144043, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3598, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.3018867924528302, | |
| "grad_norm": 1.3629597425460815, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 1.0401, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.4025157232704403, | |
| "grad_norm": 1.2397003173828125, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 1.0302, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5031446540880503, | |
| "grad_norm": 0.8221808671951294, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.8812, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.6037735849056604, | |
| "grad_norm": 0.7792067527770996, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.8046, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.7044025157232704, | |
| "grad_norm": 0.7474929690361023, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.7434, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.8050314465408805, | |
| "grad_norm": 0.6003227829933167, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.6428, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.9056603773584906, | |
| "grad_norm": 0.8291669487953186, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7149, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.0817610062893082, | |
| "grad_norm": 1.3076937198638916, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 1.1468, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.1823899371069182, | |
| "grad_norm": 0.5766540765762329, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.5977, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.2830188679245282, | |
| "grad_norm": 0.6781641244888306, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.5693, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.3836477987421385, | |
| "grad_norm": 0.5105268955230713, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.5356, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.4842767295597485, | |
| "grad_norm": 0.5280017256736755, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.5022, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.5849056603773586, | |
| "grad_norm": 0.5019888281822205, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.5147, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.6855345911949686, | |
| "grad_norm": 0.4098576009273529, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3917, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.7861635220125787, | |
| "grad_norm": 0.5152443051338196, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.5518, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.8867924528301887, | |
| "grad_norm": 0.573495626449585, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.5409, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.0628930817610063, | |
| "grad_norm": 0.8793962001800537, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.8408, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.1635220125786163, | |
| "grad_norm": 0.4080312252044678, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.4444, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.2641509433962264, | |
| "grad_norm": 0.36390388011932373, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.4215, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.3647798742138364, | |
| "grad_norm": 0.4323458969593048, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.455, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.4654088050314464, | |
| "grad_norm": 0.3334265351295471, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3601, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.5660377358490565, | |
| "grad_norm": 0.46867093443870544, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.5185, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.35767796635627747, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.3445, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "eval_loss": 0.4157150089740753, | |
| "eval_runtime": 0.6194, | |
| "eval_samples_per_second": 108.176, | |
| "eval_steps_per_second": 14.531, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.767295597484277, | |
| "grad_norm": 0.43570584058761597, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.4734, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.867924528301887, | |
| "grad_norm": 0.547036349773407, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.4908, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 3.0440251572327046, | |
| "grad_norm": 0.7520437240600586, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.7204, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.1446540880503147, | |
| "grad_norm": 0.4165114760398865, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.4098, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 3.2452830188679247, | |
| "grad_norm": 0.3665567934513092, | |
| "learning_rate": 0.0, | |
| "loss": 0.3763, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 5.000498352488448e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |