| { | |
| "best_metric": 0.3726862370967865, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01886080724254998, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007544322897019992, | |
| "grad_norm": 0.8210492134094238, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2964, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007544322897019992, | |
| "eval_loss": 0.7299715876579285, | |
| "eval_runtime": 20.4059, | |
| "eval_samples_per_second": 109.429, | |
| "eval_steps_per_second": 13.722, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015088645794039985, | |
| "grad_norm": 1.0887432098388672, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4161, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002263296869105998, | |
| "grad_norm": 1.4382431507110596, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6272, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003017729158807997, | |
| "grad_norm": 1.3836487531661987, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7209, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003772161448509996, | |
| "grad_norm": 1.604011058807373, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6609, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004526593738211996, | |
| "grad_norm": 1.419691801071167, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.725, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005281026027913994, | |
| "grad_norm": 1.9001708030700684, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.8551, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006035458317615994, | |
| "grad_norm": 1.9900678396224976, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.8507, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0067898906073179935, | |
| "grad_norm": 1.2424248456954956, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.5811, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007544322897019992, | |
| "grad_norm": 1.0436562299728394, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.46, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008298755186721992, | |
| "grad_norm": 1.094989538192749, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.458, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009053187476423991, | |
| "grad_norm": 1.1770530939102173, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.5117, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00980761976612599, | |
| "grad_norm": 0.9547999501228333, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.458, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010562052055827989, | |
| "grad_norm": 0.9950444102287292, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.397, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011316484345529988, | |
| "grad_norm": 0.8353845477104187, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.2724, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012070916635231988, | |
| "grad_norm": 1.0144917964935303, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.4976, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.012825348924933987, | |
| "grad_norm": 1.0305901765823364, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.4253, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.013579781214635987, | |
| "grad_norm": 0.9045003652572632, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.3756, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.014334213504337986, | |
| "grad_norm": 0.8268274068832397, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.364, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.015088645794039984, | |
| "grad_norm": 0.8311420679092407, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3196, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015843078083741986, | |
| "grad_norm": 0.9112005233764648, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.2999, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.016597510373443983, | |
| "grad_norm": 0.8404811024665833, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.3525, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01735194266314598, | |
| "grad_norm": 0.9411618709564209, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.4295, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.018106374952847983, | |
| "grad_norm": 0.7401957511901855, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.2783, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01886080724254998, | |
| "grad_norm": 0.7432383298873901, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.2903, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01886080724254998, | |
| "eval_loss": 0.3726862370967865, | |
| "eval_runtime": 20.3618, | |
| "eval_samples_per_second": 109.666, | |
| "eval_steps_per_second": 13.751, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 1033684525252608.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |