| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02107481559536354, | |
| "eval_steps": 10, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01053740779768177, | |
| "grad_norm": 3.3616116046905518, | |
| "learning_rate": 4.982437653670531e-05, | |
| "loss": 1.7881, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01053740779768177, | |
| "eval_loss": 0.6833231449127197, | |
| "eval_runtime": 13.3064, | |
| "eval_samples_per_second": 36.073, | |
| "eval_steps_per_second": 2.255, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02107481559536354, | |
| "grad_norm": 1.3658663034439087, | |
| "learning_rate": 4.964875307341061e-05, | |
| "loss": 0.5571, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02107481559536354, | |
| "eval_loss": 0.5293903350830078, | |
| "eval_runtime": 13.4286, | |
| "eval_samples_per_second": 35.745, | |
| "eval_steps_per_second": 2.234, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2847, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2424174658977792.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |