| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.9411764705882355, |
| "eval_steps": 10, |
| "global_step": 21, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.6722689075630253, |
| "grad_norm": 0.5100760459899902, |
| "learning_rate": 9.444444444444444e-05, |
| "loss": 5.4502, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.403361344537815, |
| "grad_norm": 1.104417085647583, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 5.3196, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.403361344537815, |
| "eval_loss": 2.4870386123657227, |
| "eval_runtime": 17.2027, |
| "eval_samples_per_second": 14.823, |
| "eval_steps_per_second": 0.93, |
| "step": 10 |
| }, |
| { |
| "epoch": 2.134453781512605, |
| "grad_norm": 1.5200636386871338, |
| "learning_rate": 3.888888888888889e-05, |
| "loss": 5.0936, |
| "step": 15 |
| }, |
| { |
| "epoch": 2.80672268907563, |
| "grad_norm": 1.3697857856750488, |
| "learning_rate": 1.1111111111111112e-05, |
| "loss": 4.837, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.80672268907563, |
| "eval_loss": 2.157644748687744, |
| "eval_runtime": 16.452, |
| "eval_samples_per_second": 15.5, |
| "eval_steps_per_second": 0.973, |
| "step": 20 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 21, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8.63413223510016e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
