| { | |
| "best_metric": 9.007640838623047, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1277139208173691, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002554278416347382, | |
| "eval_loss": 10.567898750305176, | |
| "eval_runtime": 1.5305, | |
| "eval_samples_per_second": 107.807, | |
| "eval_steps_per_second": 27.442, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02554278416347382, | |
| "grad_norm": 0.652108371257782, | |
| "learning_rate": 4.3e-05, | |
| "loss": 10.5667, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05108556832694764, | |
| "grad_norm": 1.1399426460266113, | |
| "learning_rate": 8.6e-05, | |
| "loss": 10.5238, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07662835249042145, | |
| "grad_norm": 1.5333579778671265, | |
| "learning_rate": 0.000129, | |
| "loss": 10.225, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10217113665389528, | |
| "grad_norm": 1.1316747665405273, | |
| "learning_rate": 0.000172, | |
| "loss": 9.5687, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1277139208173691, | |
| "grad_norm": 1.0548256635665894, | |
| "learning_rate": 0.000215, | |
| "loss": 9.007, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1277139208173691, | |
| "eval_loss": 9.007640838623047, | |
| "eval_runtime": 1.5083, | |
| "eval_samples_per_second": 109.397, | |
| "eval_steps_per_second": 27.847, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 392, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 490168252366848.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |