| { | |
| "best_metric": 0.37230128049850464, | |
| "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": 0.8231602311134338, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2964, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007544322897019992, | |
| "eval_loss": 0.7299715876579285, | |
| "eval_runtime": 20.3308, | |
| "eval_samples_per_second": 109.833, | |
| "eval_steps_per_second": 13.772, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015088645794039985, | |
| "grad_norm": 1.0937308073043823, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4161, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002263296869105998, | |
| "grad_norm": 1.4483824968338013, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6274, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003017729158807997, | |
| "grad_norm": 1.377671480178833, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7207, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003772161448509996, | |
| "grad_norm": 1.5944675207138062, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6621, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004526593738211996, | |
| "grad_norm": 1.4301366806030273, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.7252, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005281026027913994, | |
| "grad_norm": 1.9113917350769043, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.8553, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006035458317615994, | |
| "grad_norm": 1.9879858493804932, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.851, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0067898906073179935, | |
| "grad_norm": 1.2465602159500122, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.5799, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007544322897019992, | |
| "grad_norm": 1.0430891513824463, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.4601, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008298755186721992, | |
| "grad_norm": 1.101256251335144, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.4572, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009053187476423991, | |
| "grad_norm": 1.1609636545181274, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.5102, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00980761976612599, | |
| "grad_norm": 0.9504103660583496, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.4559, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010562052055827989, | |
| "grad_norm": 0.9961653351783752, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.3969, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011316484345529988, | |
| "grad_norm": 0.8323320746421814, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.2716, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012070916635231988, | |
| "grad_norm": 1.0118781328201294, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.4961, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.012825348924933987, | |
| "grad_norm": 1.0223515033721924, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.4229, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.013579781214635987, | |
| "grad_norm": 0.9041861891746521, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.3738, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.014334213504337986, | |
| "grad_norm": 0.817409336566925, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.3622, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.015088645794039984, | |
| "grad_norm": 0.8515728116035461, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3196, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015843078083741986, | |
| "grad_norm": 0.9067891240119934, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.3002, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.016597510373443983, | |
| "grad_norm": 0.8353717923164368, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.3525, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01735194266314598, | |
| "grad_norm": 0.9469252228736877, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.4298, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.018106374952847983, | |
| "grad_norm": 0.7375007271766663, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.2796, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01886080724254998, | |
| "grad_norm": 0.7474462985992432, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.2905, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01886080724254998, | |
| "eval_loss": 0.37230128049850464, | |
| "eval_runtime": 20.4102, | |
| "eval_samples_per_second": 109.406, | |
| "eval_steps_per_second": 13.719, | |
| "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 | |
| } | |