| { | |
| "best_metric": 1.367977261543274, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03266372693124286, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006532745386248571, | |
| "eval_loss": 1.8997453451156616, | |
| "eval_runtime": 135.0082, | |
| "eval_samples_per_second": 19.095, | |
| "eval_steps_per_second": 4.777, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006532745386248571, | |
| "grad_norm": 0.5372188687324524, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0612, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013065490772497142, | |
| "grad_norm": 0.3328971266746521, | |
| "learning_rate": 0.0001998582695676762, | |
| "loss": 1.022, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019598236158745713, | |
| "grad_norm": 0.5935003161430359, | |
| "learning_rate": 0.00019943348002101371, | |
| "loss": 1.0128, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.026130981544994283, | |
| "grad_norm": 2.405089855194092, | |
| "learning_rate": 0.00019872683547213446, | |
| "loss": 1.2233, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03266372693124286, | |
| "grad_norm": 3.8762905597686768, | |
| "learning_rate": 0.00019774033898178667, | |
| "loss": 1.6253, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03266372693124286, | |
| "eval_loss": 1.367977261543274, | |
| "eval_runtime": 137.0715, | |
| "eval_samples_per_second": 18.808, | |
| "eval_steps_per_second": 4.706, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 4.386070843726234e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |