| { | |
| "best_metric": 1.6812231540679932, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.002109482122139015, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.437928488556059e-05, | |
| "grad_norm": 2.006699800491333, | |
| "learning_rate": 2e-05, | |
| "loss": 3.2076, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.437928488556059e-05, | |
| "eval_loss": 3.053614616394043, | |
| "eval_runtime": 684.3123, | |
| "eval_samples_per_second": 7.292, | |
| "eval_steps_per_second": 3.646, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016875856977112118, | |
| "grad_norm": 1.8254175186157227, | |
| "learning_rate": 4e-05, | |
| "loss": 3.2674, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002531378546566818, | |
| "grad_norm": 1.7289915084838867, | |
| "learning_rate": 6e-05, | |
| "loss": 2.6135, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00033751713954224236, | |
| "grad_norm": 1.9319523572921753, | |
| "learning_rate": 8e-05, | |
| "loss": 3.0923, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00042189642442780296, | |
| "grad_norm": 2.202440023422241, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7622, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00042189642442780296, | |
| "eval_loss": 2.9773123264312744, | |
| "eval_runtime": 633.4802, | |
| "eval_samples_per_second": 7.877, | |
| "eval_steps_per_second": 3.939, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005062757093133636, | |
| "grad_norm": 2.228121519088745, | |
| "learning_rate": 0.00012, | |
| "loss": 3.3856, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005906549941989242, | |
| "grad_norm": 2.447239398956299, | |
| "learning_rate": 0.00014, | |
| "loss": 3.0831, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006750342790844847, | |
| "grad_norm": 2.0314934253692627, | |
| "learning_rate": 0.00016, | |
| "loss": 2.6546, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007594135639700454, | |
| "grad_norm": 2.0331554412841797, | |
| "learning_rate": 0.00018, | |
| "loss": 2.5455, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008437928488556059, | |
| "grad_norm": 2.057798147201538, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9237, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008437928488556059, | |
| "eval_loss": 2.2591044902801514, | |
| "eval_runtime": 639.9815, | |
| "eval_samples_per_second": 7.797, | |
| "eval_steps_per_second": 3.899, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009281721337411666, | |
| "grad_norm": 2.0957143306732178, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.2103, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0010125514186267272, | |
| "grad_norm": 2.29392409324646, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.0412, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0010969307035122878, | |
| "grad_norm": 2.3551414012908936, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.9778, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0011813099883978483, | |
| "grad_norm": 2.25308895111084, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.8254, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0012656892732834089, | |
| "grad_norm": 2.125375270843506, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.7395, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0012656892732834089, | |
| "eval_loss": 1.7618757486343384, | |
| "eval_runtime": 662.1575, | |
| "eval_samples_per_second": 7.536, | |
| "eval_steps_per_second": 3.768, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013500685581689694, | |
| "grad_norm": 2.5470008850097656, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.8919, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0014344478430545302, | |
| "grad_norm": 3.481562376022339, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.619, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0015188271279400908, | |
| "grad_norm": 1.946924090385437, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.3688, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0016032064128256513, | |
| "grad_norm": 2.0693461894989014, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.8018, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0016875856977112118, | |
| "grad_norm": 1.8328882455825806, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.6836, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0016875856977112118, | |
| "eval_loss": 1.7000869512557983, | |
| "eval_runtime": 650.9527, | |
| "eval_samples_per_second": 7.666, | |
| "eval_steps_per_second": 3.833, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0017719649825967724, | |
| "grad_norm": 2.9439198970794678, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.8969, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0018563442674823332, | |
| "grad_norm": 2.2414660453796387, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.9756, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0019407235523678937, | |
| "grad_norm": 1.903572678565979, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.321, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0020251028372534545, | |
| "grad_norm": 3.2975940704345703, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.421, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002109482122139015, | |
| "grad_norm": 2.134070873260498, | |
| "learning_rate": 0.0, | |
| "loss": 1.6586, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002109482122139015, | |
| "eval_loss": 1.6812231540679932, | |
| "eval_runtime": 658.7929, | |
| "eval_samples_per_second": 7.574, | |
| "eval_steps_per_second": 3.787, | |
| "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": 818853102747648.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |