| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0, | |
| "eval_steps": 25, | |
| "global_step": 42, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0517, | |
| "eval_samples_per_second": 24.37, | |
| "eval_steps_per_second": 6.336, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.21428571428571427, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.986128001799077e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.94459753267812e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.875664641789545e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.779754323328192e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.509529358847655e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6428571428571429, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.336880739593416e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7857142857142857, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.921826845200139e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9285714285714286, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.422516217485826e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.14503363531613e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.0714285714285714, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.85124354122177e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.542957248827961e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.2142857142857142, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.2857142857142856, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.890576474687263e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.3571428571428572, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.550504137351576e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.203955092681039e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8530659307753036e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.5714285714285714, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.6428571428571428, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.1469340692246995e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7960449073189606e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.7857142857142856, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4494958626484276e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.7857142857142856, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0977, | |
| "eval_samples_per_second": 23.836, | |
| "eval_steps_per_second": 6.197, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8571428571428572, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.109423525312738e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.9285714285714286, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.45704275117204e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.0714285714285716, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1487564587782306e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.142857142857143, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.854966364683872e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.2142857142857144, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.577483782514174e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.357142857142857, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0781731547998614e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.4285714285714284, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8594235253127375e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6631192604065855e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.490470641152345e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.642857142857143, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.7142857142857144, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2202456766718093e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.7857142857142856, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1243353582104556e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0554024673218807e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.928571428571429, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0138719982009242e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 42, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 8.900105372644147e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |