| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 200, |
| "global_step": 550, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.18210789893011609, |
| "grad_norm": 1.9093080759048462, |
| "learning_rate": 8.351851851851852e-05, |
| "loss": 0.7988, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.36421579786023217, |
| "grad_norm": 2.0605411529541016, |
| "learning_rate": 6.500000000000001e-05, |
| "loss": 0.6122, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.36421579786023217, |
| "eval_loss": 0.6302775144577026, |
| "eval_runtime": 182.615, |
| "eval_samples_per_second": 4.594, |
| "eval_steps_per_second": 1.15, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5463236967903483, |
| "grad_norm": 2.6198949813842773, |
| "learning_rate": 4.648148148148148e-05, |
| "loss": 0.5011, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.7284315957204643, |
| "grad_norm": 3.0732743740081787, |
| "learning_rate": 2.7962962962962965e-05, |
| "loss": 0.4019, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.7284315957204643, |
| "eval_loss": 0.4941433072090149, |
| "eval_runtime": 147.7283, |
| "eval_samples_per_second": 5.679, |
| "eval_steps_per_second": 1.422, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.9105394946505805, |
| "grad_norm": 3.1388325691223145, |
| "learning_rate": 9.444444444444445e-06, |
| "loss": 0.3344, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 550, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.624248273860198e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
