| { | |
| "best_metric": 1.9574483633041382, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.01564945226917058, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001564945226917058, | |
| "eval_loss": 2.921564817428589, | |
| "eval_runtime": 34.5348, | |
| "eval_samples_per_second": 15.607, | |
| "eval_steps_per_second": 3.909, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004694835680751174, | |
| "grad_norm": 13.620658874511719, | |
| "learning_rate": 0.00012, | |
| "loss": 10.1715, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00782472613458529, | |
| "eval_loss": 2.223052740097046, | |
| "eval_runtime": 34.5871, | |
| "eval_samples_per_second": 15.584, | |
| "eval_steps_per_second": 3.903, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009389671361502348, | |
| "grad_norm": 12.163566589355469, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 9.048, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014084507042253521, | |
| "grad_norm": 8.320079803466797, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 7.957, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01564945226917058, | |
| "eval_loss": 1.9574483633041382, | |
| "eval_runtime": 34.6128, | |
| "eval_samples_per_second": 15.572, | |
| "eval_steps_per_second": 3.9, | |
| "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": 7031294986813440.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |