| { |
| "best_metric": 0.039619311690330505, |
| "best_model_checkpoint": "miner_id_24/checkpoint-500", |
| "epoch": 0.9133421014175069, |
| "eval_steps": 500, |
| "global_step": 625, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0014613473622680112, |
| "eval_loss": 1.079929232597351, |
| "eval_runtime": 120.3442, |
| "eval_samples_per_second": 14.965, |
| "eval_steps_per_second": 3.0, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07306736811340056, |
| "grad_norm": 0.8063929677009583, |
| "learning_rate": 0.0001068, |
| "loss": 0.2017, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.14613473622680112, |
| "grad_norm": 0.5706304907798767, |
| "learning_rate": 0.0002136, |
| "loss": 0.0961, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.21920210434020165, |
| "grad_norm": 0.5012636184692383, |
| "learning_rate": 0.0002653563934694509, |
| "loss": 0.0841, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.29226947245360224, |
| "grad_norm": 0.28799599409103394, |
| "learning_rate": 0.0002524493709791471, |
| "loss": 0.1039, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.3653368405670028, |
| "grad_norm": 1.3303046226501465, |
| "learning_rate": 0.00022789875528840406, |
| "loss": 0.0776, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.4384042086804033, |
| "grad_norm": 0.5361071825027466, |
| "learning_rate": 0.00019410773171522948, |
| "loss": 0.0642, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.5114715767938038, |
| "grad_norm": 0.10300945490598679, |
| "learning_rate": 0.00015438400108287083, |
| "loss": 0.0564, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.5845389449072045, |
| "grad_norm": 0.33445683121681213, |
| "learning_rate": 0.00011261599891712914, |
| "loss": 0.0519, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.657606313020605, |
| "grad_norm": 0.13534684479236603, |
| "learning_rate": 7.28922682847705e-05, |
| "loss": 0.0438, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.7306736811340055, |
| "grad_norm": 0.07572776079177856, |
| "learning_rate": 3.9101244711595914e-05, |
| "loss": 0.0404, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.7306736811340055, |
| "eval_loss": 0.039619311690330505, |
| "eval_runtime": 119.8958, |
| "eval_samples_per_second": 15.021, |
| "eval_steps_per_second": 3.011, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.8037410492474061, |
| "grad_norm": 0.11217395961284637, |
| "learning_rate": 1.45506290208529e-05, |
| "loss": 0.0382, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.8768084173608066, |
| "grad_norm": 0.057221416383981705, |
| "learning_rate": 1.6436065305491224e-06, |
| "loss": 0.036, |
| "step": 600 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 625, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "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": 1.85151356928e+18, |
| "train_batch_size": 5, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
