| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.932649311934556e-05, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.3108831039781854e-05, | |
| "grad_norm": 0.3176736533641815, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3064, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.3108831039781854e-05, | |
| "eval_loss": 2.764178991317749, | |
| "eval_runtime": 184.6756, | |
| "eval_samples_per_second": 98.665, | |
| "eval_steps_per_second": 49.335, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.621766207956371e-05, | |
| "grad_norm": 0.24799887835979462, | |
| "learning_rate": 4e-05, | |
| "loss": 2.6087, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 6.932649311934556e-05, | |
| "grad_norm": 0.2642222046852112, | |
| "learning_rate": 6e-05, | |
| "loss": 2.779, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 6.932649311934556e-05, | |
| "eval_loss": 2.764132022857666, | |
| "eval_runtime": 202.2714, | |
| "eval_samples_per_second": 90.082, | |
| "eval_steps_per_second": 45.043, | |
| "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": 14574376452096.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |