| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.0006274903523358328, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.137451761679164e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 448.1271, | |
| "eval_samples_per_second": 7.489, | |
| "eval_steps_per_second": 3.744, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.412355285037493e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001568725880839582, | |
| "eval_loss": NaN, | |
| "eval_runtime": 454.5973, | |
| "eval_samples_per_second": 7.382, | |
| "eval_steps_per_second": 3.691, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00018824710570074986, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00028237065855112476, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003137451761679164, | |
| "eval_loss": NaN, | |
| "eval_runtime": 458.7362, | |
| "eval_samples_per_second": 7.316, | |
| "eval_steps_per_second": 3.658, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003764942114014997, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0004706177642518746, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0004706177642518746, | |
| "eval_loss": NaN, | |
| "eval_runtime": 461.5631, | |
| "eval_samples_per_second": 7.271, | |
| "eval_steps_per_second": 3.635, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005647413171022495, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006274903523358328, | |
| "eval_loss": NaN, | |
| "eval_runtime": 458.8659, | |
| "eval_samples_per_second": 7.314, | |
| "eval_steps_per_second": 3.657, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 79458808627200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |