| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0012553351744915891, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00025106703489831785, | |
| "grad_norm": 4.487054824829102, | |
| "learning_rate": 1e-05, | |
| "loss": 6.6038, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00025106703489831785, | |
| "eval_loss": 6.619215965270996, | |
| "eval_runtime": 610.4984, | |
| "eval_samples_per_second": 10.989, | |
| "eval_steps_per_second": 5.496, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005021340697966357, | |
| "grad_norm": 3.958220958709717, | |
| "learning_rate": 2e-05, | |
| "loss": 6.1541, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005021340697966357, | |
| "eval_loss": 6.49931526184082, | |
| "eval_runtime": 294.0697, | |
| "eval_samples_per_second": 22.814, | |
| "eval_steps_per_second": 11.409, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007532011046949536, | |
| "grad_norm": 4.486939430236816, | |
| "learning_rate": 3e-05, | |
| "loss": 6.3343, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010042681395932714, | |
| "grad_norm": 4.553582668304443, | |
| "learning_rate": 4e-05, | |
| "loss": 6.2004, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010042681395932714, | |
| "eval_loss": 6.3572869300842285, | |
| "eval_runtime": 295.368, | |
| "eval_samples_per_second": 22.714, | |
| "eval_steps_per_second": 11.359, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012553351744915891, | |
| "grad_norm": 5.016958236694336, | |
| "learning_rate": 5e-05, | |
| "loss": 6.2392, | |
| "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": 7398256992583680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |