| { | |
| "best_metric": 2.5645692348480225, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.00014421118285617458, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.4421118285617457e-05, | |
| "eval_loss": 3.0061817169189453, | |
| "eval_runtime": 999.7577, | |
| "eval_samples_per_second": 29.204, | |
| "eval_steps_per_second": 14.603, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.3263354856852374e-05, | |
| "grad_norm": 5.673032760620117, | |
| "learning_rate": 0.00012, | |
| "loss": 9.7449, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.210559142808729e-05, | |
| "eval_loss": 2.8476271629333496, | |
| "eval_runtime": 1018.0054, | |
| "eval_samples_per_second": 28.681, | |
| "eval_steps_per_second": 14.341, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 8.652670971370475e-05, | |
| "grad_norm": 5.520813465118408, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 10.812, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00012979006457055711, | |
| "grad_norm": 7.035129070281982, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 10.3322, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00014421118285617458, | |
| "eval_loss": 2.5645692348480225, | |
| "eval_runtime": 1008.8659, | |
| "eval_samples_per_second": 28.94, | |
| "eval_steps_per_second": 14.471, | |
| "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": 601010208768000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |