| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013582342954159592, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027164685908319186, | |
| "grad_norm": 0.34521129727363586, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8079, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027164685908319186, | |
| "eval_loss": 0.9625586867332458, | |
| "eval_runtime": 99.314, | |
| "eval_samples_per_second": 6.243, | |
| "eval_steps_per_second": 3.121, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005432937181663837, | |
| "grad_norm": 0.37160348892211914, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9689, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005432937181663837, | |
| "eval_loss": 0.9608622789382935, | |
| "eval_runtime": 10.0684, | |
| "eval_samples_per_second": 61.579, | |
| "eval_steps_per_second": 30.789, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008149405772495755, | |
| "grad_norm": 0.3338462710380554, | |
| "learning_rate": 3e-05, | |
| "loss": 0.8246, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010865874363327675, | |
| "grad_norm": 0.41770923137664795, | |
| "learning_rate": 4e-05, | |
| "loss": 0.9052, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010865874363327675, | |
| "eval_loss": 0.9510915279388428, | |
| "eval_runtime": 10.1212, | |
| "eval_samples_per_second": 61.258, | |
| "eval_steps_per_second": 30.629, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013582342954159592, | |
| "grad_norm": 0.3597610592842102, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8222, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1312755493109760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |