| { | |
| "best_metric": 1.5826470851898193, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.01839249586168843, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003678499172337686, | |
| "eval_loss": 2.6280200481414795, | |
| "eval_runtime": 65.3457, | |
| "eval_samples_per_second": 17.522, | |
| "eval_steps_per_second": 4.392, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036784991723376862, | |
| "grad_norm": 1.1987358331680298, | |
| "learning_rate": 4.02e-05, | |
| "loss": 2.5141, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0073569983446753725, | |
| "grad_norm": 1.3015245199203491, | |
| "learning_rate": 8.04e-05, | |
| "loss": 1.9684, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011035497517013059, | |
| "grad_norm": 1.007439136505127, | |
| "learning_rate": 0.0001206, | |
| "loss": 1.6286, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014713996689350745, | |
| "grad_norm": 1.1959398984909058, | |
| "learning_rate": 0.0001608, | |
| "loss": 1.5259, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01839249586168843, | |
| "grad_norm": 1.1850124597549438, | |
| "learning_rate": 0.000201, | |
| "loss": 1.373, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01839249586168843, | |
| "eval_loss": 1.5826470851898193, | |
| "eval_runtime": 65.3579, | |
| "eval_samples_per_second": 17.519, | |
| "eval_steps_per_second": 4.391, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8886804283392000.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |