| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0153846153846153, | |
| "eval_steps": 25, | |
| "global_step": 49, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06153846153846154, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06153846153846154, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.4338, | |
| "eval_samples_per_second": 34.873, | |
| "eval_steps_per_second": 9.067, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.12307692307692308, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.18461538461538463, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.98995095380419e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.24615384615384617, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.959848696696512e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.90982767266464e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.36923076923076925, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.840111287744695e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4307692307692308, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.751010912235635e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.49230769230769234, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.642924490043929e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5538461538461539, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.516334761369466e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.371807106670628e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.676923076923077, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.209987021537921e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.7384615384615385, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.031597233753974e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.83743447541581e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.8615384615384616, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.628365924535892e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.405325332014611e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9846153846153847, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.169308851282099e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0461538461538462, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.921370589235178e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.1076923076923078, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.662617898340078e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1692307692307693, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.394206430927509e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.117334977768807e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2923076923076924, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.833240113985353e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.353846153846154, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.543190676203878e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4153846153846155, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.248482095624086e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.476923076923077, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.950430612308444e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.650367396534536e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.6119, | |
| "eval_samples_per_second": 81.718, | |
| "eval_steps_per_second": 21.247, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.349632603465466e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6615384615384614, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.049569387691557e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.7230769230769232, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.751517904375915e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7846153846153845, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.456809323796123e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.8461538461538463, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.166759886014648e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.9076923076923076, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.882665022231193e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.9692307692307693, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.605793569072493e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0307692307692307, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.337382101659923e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.0923076923076924, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.078629410764824e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.1538461538461537, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.830691148717902e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.2153846153846155, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5946746679853894e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.276923076923077, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3716340754641102e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.3384615384615386, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.162565524584191e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9684027662460257e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.4615384615384617, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.79001297846208e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.523076923076923, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.628192893329374e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.5846153846153848, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4836652386305349e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.646153846153846, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.35707550995607e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.707692307692308, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.248989087764366e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.769230769230769, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1598887122553061e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.830769230769231, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0901723273353597e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.8923076923076922, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.04015130330349e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.953846153846154, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0100490461958109e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.0153846153846153, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 49, | |
| "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": 1.0095212718194688e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |