| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009687575684185032, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009687575684185032, | |
| "grad_norm": 0.05744075030088425, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3761, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009687575684185032, | |
| "eval_loss": 10.37628173828125, | |
| "eval_runtime": 4.6467, | |
| "eval_samples_per_second": 93.614, | |
| "eval_steps_per_second": 46.915, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019375151368370065, | |
| "grad_norm": 0.08998994529247284, | |
| "learning_rate": 4e-05, | |
| "loss": 10.374, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00290627270525551, | |
| "grad_norm": 0.055752675980329514, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3804, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00290627270525551, | |
| "eval_loss": 10.376185417175293, | |
| "eval_runtime": 4.6338, | |
| "eval_samples_per_second": 93.875, | |
| "eval_steps_per_second": 47.045, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003875030273674013, | |
| "grad_norm": 0.06058281660079956, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3726, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004843787842092516, | |
| "grad_norm": 0.0764281377196312, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3786, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00581254541051102, | |
| "grad_norm": 0.05979367718100548, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3766, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00581254541051102, | |
| "eval_loss": 10.3757963180542, | |
| "eval_runtime": 4.7038, | |
| "eval_samples_per_second": 92.478, | |
| "eval_steps_per_second": 46.345, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006781302978929523, | |
| "grad_norm": 0.055705487728118896, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3714, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007750060547348026, | |
| "grad_norm": 0.07059347629547119, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3799, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00871881811576653, | |
| "grad_norm": 0.0859907865524292, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3722, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00871881811576653, | |
| "eval_loss": 10.375100135803223, | |
| "eval_runtime": 4.7485, | |
| "eval_samples_per_second": 91.609, | |
| "eval_steps_per_second": 45.91, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009687575684185032, | |
| "grad_norm": 0.05264592170715332, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3708, | |
| "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": 1046048931840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |