| { |
| "best_metric": 0.3640096187591553, |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", |
| "epoch": 0.013723696248856358, |
| "eval_steps": 5, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0004574565416285453, |
| "eval_loss": 1.9771651029586792, |
| "eval_runtime": 162.2414, |
| "eval_samples_per_second": 11.347, |
| "eval_steps_per_second": 2.841, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0013723696248856359, |
| "grad_norm": 2.4774668216705322, |
| "learning_rate": 0.00012, |
| "loss": 1.5771, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0022872827081427266, |
| "eval_loss": 1.0017728805541992, |
| "eval_runtime": 162.3692, |
| "eval_samples_per_second": 11.338, |
| "eval_steps_per_second": 2.839, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0027447392497712718, |
| "grad_norm": 1.7279980182647705, |
| "learning_rate": 0.0001992114701314478, |
| "loss": 1.1196, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.004117108874656907, |
| "grad_norm": 0.7745809555053711, |
| "learning_rate": 0.00018763066800438636, |
| "loss": 0.6265, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.004574565416285453, |
| "eval_loss": 0.4537348747253418, |
| "eval_runtime": 162.3245, |
| "eval_samples_per_second": 11.341, |
| "eval_steps_per_second": 2.84, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0054894784995425435, |
| "grad_norm": 0.5128909945487976, |
| "learning_rate": 0.000163742398974869, |
| "loss": 0.4514, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.006861848124428179, |
| "grad_norm": 0.47929856181144714, |
| "learning_rate": 0.00013090169943749476, |
| "loss": 0.4212, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.006861848124428179, |
| "eval_loss": 0.39974135160446167, |
| "eval_runtime": 162.3452, |
| "eval_samples_per_second": 11.34, |
| "eval_steps_per_second": 2.84, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.008234217749313814, |
| "grad_norm": 0.5202671885490417, |
| "learning_rate": 9.372094804706867e-05, |
| "loss": 0.3923, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.009149130832570906, |
| "eval_loss": 0.3763931095600128, |
| "eval_runtime": 162.4133, |
| "eval_samples_per_second": 11.335, |
| "eval_steps_per_second": 2.838, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.00960658737419945, |
| "grad_norm": 0.35927730798721313, |
| "learning_rate": 5.7422070843492734e-05, |
| "loss": 0.3669, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.010978956999085087, |
| "grad_norm": 0.31829825043678284, |
| "learning_rate": 2.7103137257858868e-05, |
| "loss": 0.3661, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.011436413540713633, |
| "eval_loss": 0.36795511841773987, |
| "eval_runtime": 162.5768, |
| "eval_samples_per_second": 11.324, |
| "eval_steps_per_second": 2.836, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.012351326623970723, |
| "grad_norm": 0.40827932953834534, |
| "learning_rate": 7.022351411174866e-06, |
| "loss": 0.3549, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.013723696248856358, |
| "grad_norm": 0.34633514285087585, |
| "learning_rate": 0.0, |
| "loss": 0.3407, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.013723696248856358, |
| "eval_loss": 0.3640096187591553, |
| "eval_runtime": 162.3702, |
| "eval_samples_per_second": 11.338, |
| "eval_steps_per_second": 2.839, |
| "step": 30 |
| } |
| ], |
| "logging_steps": 3, |
| "max_steps": 30, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 10, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.470837626077184e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
