| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00025593448077292216, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.531149359097404e-05, | |
| "grad_norm": 0.9269247055053711, | |
| "learning_rate": 2e-05, | |
| "loss": 2.7629, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.531149359097404e-05, | |
| "eval_loss": 3.126101493835449, | |
| "eval_runtime": 187.3728, | |
| "eval_samples_per_second": 26.343, | |
| "eval_steps_per_second": 13.172, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017062298718194808, | |
| "grad_norm": 1.0083377361297607, | |
| "learning_rate": 4e-05, | |
| "loss": 3.0406, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00025593448077292216, | |
| "grad_norm": 0.8629823923110962, | |
| "learning_rate": 6e-05, | |
| "loss": 3.1489, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00025593448077292216, | |
| "eval_loss": 3.122657060623169, | |
| "eval_runtime": 186.4576, | |
| "eval_samples_per_second": 26.473, | |
| "eval_steps_per_second": 13.236, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 700324742430720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |