| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.09683426443203, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0595903165735568, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0595903165735568, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.2175, | |
| "eval_samples_per_second": 15.54, | |
| "eval_steps_per_second": 4.04, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1191806331471136, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1787709497206704, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.990754267376514e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2383612662942272, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.963055062204608e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.297951582867784, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.917016206459795e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3575418994413408, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.852826883675633e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4171322160148976, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.770750861548009e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4767225325884544, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.671125408057098e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5363128491620112, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.554359905560886e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.595903165735568, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.420934168555254e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6554934823091247, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.271396472013283e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.7150837988826816, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.106361298405805e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7746741154562383, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.926506812661105e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.8342644320297952, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.732572075439774e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8938547486033519, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.525354006175926e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9534450651769087, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.305704108364301e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0521415270018621, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.074524970549764e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.111731843575419, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.832766557397364e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1713221601489758, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.58142230608376e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.2309124767225326, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.321525044050772e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2905027932960893, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.054142744895884e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.3500931098696463, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.780374139839645e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.409683426443203, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.501344202803414e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.4692737430167597, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.218199527650208e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5288640595903167, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.932103616584568e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.5288640595903167, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.2428, | |
| "eval_samples_per_second": 15.419, | |
| "eval_steps_per_second": 4.009, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.5884543761638734, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.64423209907245e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6480446927374302, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.355767900927552e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.7076350093109869, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0678963834154326e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7672253258845436, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.781800472349794e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.8268156424581006, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.498655797196586e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8864059590316573, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2196258601603544e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.9459962756052143, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.945857255104116e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0446927374301676, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.678474955949228e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.1042830540037243, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4185776939162425e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.163873370577281, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.167233442602637e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.223463687150838, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9254750294502375e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.283054003724395, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6942958916356998e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.3426443202979517, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4746459938240742e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.4022346368715084, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2674279245602265e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.461824953445065, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0734931873388952e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.521415270018622, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8936387015941958e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.5810055865921786, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7286035279867173e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.6405959031657353, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.579065831444748e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.7001862197392925, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4456400944391146e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.7597765363128492, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3288745919429028e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.819366852886406, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2292491384519912e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.8789571694599627, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1471731163243676e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.9385474860335195, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0829837935402057e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.037243947858473, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0369449377953928e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 3.09683426443203, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0092457326234866e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.09683426443203, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.2435, | |
| "eval_samples_per_second": 15.415, | |
| "eval_steps_per_second": 4.008, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 51, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.968083617316864e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |