| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.01278772378516624, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012787723785166241, | |
| "eval_loss": NaN, | |
| "eval_runtime": 36.9041, | |
| "eval_samples_per_second": 8.942, | |
| "eval_steps_per_second": 4.471, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0038363171355498722, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00639386189258312, | |
| "eval_loss": NaN, | |
| "eval_runtime": 36.9156, | |
| "eval_samples_per_second": 8.939, | |
| "eval_steps_per_second": 4.47, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0076726342710997444, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.96057350657239e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011508951406649617, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.381533400219318e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01278772378516624, | |
| "eval_loss": NaN, | |
| "eval_runtime": 36.9255, | |
| "eval_samples_per_second": 8.937, | |
| "eval_steps_per_second": 4.468, | |
| "step": 10 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3296153189744640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |