| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.23959269242288112, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011979634621144056, | |
| "eval_loss": NaN, | |
| "eval_runtime": 18.4623, | |
| "eval_samples_per_second": 38.078, | |
| "eval_steps_per_second": 19.066, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04791853848457622, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05989817310572028, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.786, | |
| "eval_samples_per_second": 39.525, | |
| "eval_steps_per_second": 19.791, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09583707696915245, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.11979634621144056, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.5398, | |
| "eval_samples_per_second": 40.08, | |
| "eval_steps_per_second": 20.069, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14375561545372867, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.17969451931716082, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.4881, | |
| "eval_samples_per_second": 40.199, | |
| "eval_steps_per_second": 20.128, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1916741539383049, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.23959269242288112, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23959269242288112, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.4628, | |
| "eval_samples_per_second": 40.257, | |
| "eval_steps_per_second": 20.157, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 40, | |
| "max_steps": 200, | |
| "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": 1.32442044235776e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |