| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.604001510003775, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0120800302000755, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0120800302000755, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.3754, | |
| "eval_samples_per_second": 2.878, | |
| "eval_steps_per_second": 2.878, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.024160060400151, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0362400906002265, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.048320120800302, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.996255097050623e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0604001510003775, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.98502662122387e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.072480181200453, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.966333261209626e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0845602114005285, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.9402061302608e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.096640241600604, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.906688714408396e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1087202718006795, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.865836800083291e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.120800302000755, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.81771838126524e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1328803322008305, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.762413546313596e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.144960362400906, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.700014344668151e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.15704039260098152, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.630624633641918e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.169120422801057, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.554359905560886e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1812004530011325, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.471347095538446e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.193280483201208, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.381724370204413e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2053605134012835, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.285640897740315e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.217440543601359, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.183256599603671e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2295205738014345, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.074741884354506e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.24160060400151, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.96027736402713e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2536806342015855, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.840053553519215e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.265760664401661, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.714270553498567e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2778406946017365, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.5831377173553e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.289920724801812, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.446873302753784e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3020007550018875, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.305704108364301e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3020007550018875, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.5276, | |
| "eval_samples_per_second": 2.853, | |
| "eval_steps_per_second": 2.853, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.31408078520196303, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.159865096379045e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3261608154020385, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.009599001440733e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.338240845602114, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.855155926634755e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3503208758021895, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.696792927217265e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.362400906002265, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.534773582772087e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3744809362023405, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.369367558508489e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.386560966402416, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.20085015643008e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3986409966024915, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.029501857121776e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.410721026802567, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.855607852917555e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.42280105700264253, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.679457573225961e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.434881087202718, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.501344202803414e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4469611174027935, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.321564193777129e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.459041147602869, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.140416772229784e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4711211778029445, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9582034401672605e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.48320120800302, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.775227473698294e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4952812382030955, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.591793418261325e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.507361268403171, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.408206581738677e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5194412986032465, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2247725263017086e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.531521328803322, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.041796559832742e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5436013590033975, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.859583227770218e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.555681389203473, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.678435806222873e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5677614194035485, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.498655797196586e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.579841449603624, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3205424267740423e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5919214798036995, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.144392147082448e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.604001510003775, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.970498142878226e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.604001510003775, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.5227, | |
| "eval_samples_per_second": 2.853, | |
| "eval_steps_per_second": 2.853, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 80, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.108872697315328e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |