| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004253056884635832, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004253056884635832, | |
| "grad_norm": 0.28993722796440125, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7273, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004253056884635832, | |
| "eval_loss": 0.7156436443328857, | |
| "eval_runtime": 50.1945, | |
| "eval_samples_per_second": 19.723, | |
| "eval_steps_per_second": 9.862, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008506113769271664, | |
| "grad_norm": 0.28686344623565674, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6559, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012759170653907496, | |
| "grad_norm": 0.33761271834373474, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6571, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012759170653907496, | |
| "eval_loss": 0.7138599157333374, | |
| "eval_runtime": 48.935, | |
| "eval_samples_per_second": 20.231, | |
| "eval_steps_per_second": 10.115, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017012227538543328, | |
| "grad_norm": 0.34971219301223755, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7821, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002126528442317916, | |
| "grad_norm": 0.44829320907592773, | |
| "learning_rate": 0.0001, | |
| "loss": 0.785, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002551834130781499, | |
| "grad_norm": 0.4680666923522949, | |
| "learning_rate": 0.00012, | |
| "loss": 0.7126, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002551834130781499, | |
| "eval_loss": 0.6896650791168213, | |
| "eval_runtime": 48.9464, | |
| "eval_samples_per_second": 20.226, | |
| "eval_steps_per_second": 10.113, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029771398192450825, | |
| "grad_norm": 0.35045647621154785, | |
| "learning_rate": 0.00014, | |
| "loss": 0.605, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0034024455077086655, | |
| "grad_norm": 0.3555477559566498, | |
| "learning_rate": 0.00016, | |
| "loss": 0.6754, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003827751196172249, | |
| "grad_norm": 0.409112811088562, | |
| "learning_rate": 0.00018, | |
| "loss": 0.6161, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003827751196172249, | |
| "eval_loss": 0.6577900648117065, | |
| "eval_runtime": 48.952, | |
| "eval_samples_per_second": 20.224, | |
| "eval_steps_per_second": 10.112, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004253056884635832, | |
| "grad_norm": 0.5077799558639526, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6153, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3144259221848064.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |