| { | |
| "best_metric": 11.5, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.008467579754016808, | |
| "eval_steps": 100, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.2337898770084044e-05, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 100.6746, | |
| "eval_samples_per_second": 98.784, | |
| "eval_steps_per_second": 49.397, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004233789877008404, | |
| "grad_norm": 3.8532682083314285e-05, | |
| "learning_rate": 1e-05, | |
| "loss": 46.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008467579754016808, | |
| "grad_norm": 1.7726280930219218e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0012701369631025212, | |
| "grad_norm": 2.8598151402547956e-05, | |
| "learning_rate": 3e-05, | |
| "loss": 46.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0016935159508033616, | |
| "grad_norm": 3.5454264434520155e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002116894938504202, | |
| "grad_norm": 3.511717659421265e-05, | |
| "learning_rate": 5e-05, | |
| "loss": 46.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0025402739262050424, | |
| "grad_norm": 6.926015339558944e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.002963652913905883, | |
| "grad_norm": 0.0002537610998842865, | |
| "learning_rate": 7e-05, | |
| "loss": 46.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0033870319016067233, | |
| "grad_norm": 4.098670251551084e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0038104108893075635, | |
| "grad_norm": 6.75772680551745e-05, | |
| "learning_rate": 9e-05, | |
| "loss": 46.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.004233789877008404, | |
| "grad_norm": 0.00013273257354740053, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.004233789877008404, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 100.7104, | |
| "eval_samples_per_second": 98.748, | |
| "eval_steps_per_second": 49.379, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.004657168864709245, | |
| "grad_norm": 0.0001554292975924909, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 46.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.005080547852410085, | |
| "grad_norm": 0.00017063747509382665, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 46.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.005503926840110925, | |
| "grad_norm": 0.0002251509140478447, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 46.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.005927305827811766, | |
| "grad_norm": 0.00025318050757050514, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 46.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.006350684815512606, | |
| "grad_norm": 0.00024476656108163297, | |
| "learning_rate": 5e-05, | |
| "loss": 46.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.006774063803213447, | |
| "grad_norm": 0.0004327484348323196, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 46.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.007197442790914287, | |
| "grad_norm": 0.00031539108022116125, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 46.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.007620821778615127, | |
| "grad_norm": 0.00022764148889109492, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 46.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.008044200766315967, | |
| "grad_norm": 0.00025987360277213156, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 46.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.008467579754016808, | |
| "grad_norm": 0.00024760179803706706, | |
| "learning_rate": 0.0, | |
| "loss": 46.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.008467579754016808, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 101.2299, | |
| "eval_samples_per_second": 98.242, | |
| "eval_steps_per_second": 49.126, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 16362094854144.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |