| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.036121458403883054, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001806072920194153, | |
| "eval_loss": NaN, | |
| "eval_runtime": 130.3095, | |
| "eval_samples_per_second": 35.784, | |
| "eval_steps_per_second": 17.896, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007224291680776611, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009030364600970764, | |
| "eval_loss": NaN, | |
| "eval_runtime": 120.3983, | |
| "eval_samples_per_second": 38.73, | |
| "eval_steps_per_second": 19.369, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.014448583361553222, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.018060729201941527, | |
| "eval_loss": NaN, | |
| "eval_runtime": 124.8414, | |
| "eval_samples_per_second": 37.351, | |
| "eval_steps_per_second": 18.68, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.021672875042329835, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.027091093802912292, | |
| "eval_loss": NaN, | |
| "eval_runtime": 118.5263, | |
| "eval_samples_per_second": 39.341, | |
| "eval_steps_per_second": 19.675, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.028897166723106445, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.036121458403883054, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.036121458403883054, | |
| "eval_loss": NaN, | |
| "eval_runtime": 120.8447, | |
| "eval_samples_per_second": 38.587, | |
| "eval_steps_per_second": 19.298, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 40, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 3 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2876546834432e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |