| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 2.2222222222222223, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.044444444444444446, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.044444444444444446, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.4655, | |
| "eval_samples_per_second": 107.402, | |
| "eval_steps_per_second": 27.924, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13333333333333333, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99474502074547e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.978992356229419e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.95277879752973e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3111111111111111, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.916165567627362e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.869238178417235e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.812106230991248e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.744903159659843e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4888888888888889, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.667785920309994e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.580934623827455e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5777777777777777, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.484552115439445e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.378863500960222e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.26411562104602e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7555555555555555, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.008534593284501e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.868298366769954e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8444444444444444, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.720195323348545e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.564571364540588e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9333333333333333, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.401789957312768e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.232231285184201e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0222222222222221, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.056291360290201e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.874381098477599e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.686925359591727e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.4689, | |
| "eval_samples_per_second": 106.639, | |
| "eval_steps_per_second": 27.726, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1555555555555554, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.494361955196587e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.29714062604563e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.2444444444444445, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.095721991691411e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.2888888888888888, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.890576474687263e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.682183201893642e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.3777777777777778, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.471028885455128e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.257606686061673e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.4666666666666668, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.042415061148954e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.511111111111111, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.825956600727932e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.5555555555555556, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.608736853562596e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3912631464374064e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.6444444444444444, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.1740433992720704e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.6888888888888889, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9575849388510473e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.7333333333333334, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.742393313938327e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5289711145448735e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.8222222222222222, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.317816798106359e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.8666666666666667, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.109423525312738e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.911111111111111, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.904278008308589e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.9555555555555557, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7028593739543715e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5056380448034144e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.0444444444444443, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.313074640408273e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.088888888888889, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1256189015224025e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9437086397097995e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.1777777777777776, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7677687148157998e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5982100426872337e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.4668, | |
| "eval_samples_per_second": 107.112, | |
| "eval_steps_per_second": 27.849, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 68, | |
| "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": 7.83042868150272e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |