| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0003369768960215665, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.739537920431331e-05, | |
| "grad_norm": 0.4355680048465729, | |
| "learning_rate": 1e-05, | |
| "loss": 1.3834, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.739537920431331e-05, | |
| "eval_loss": 1.498652458190918, | |
| "eval_runtime": 529.7382, | |
| "eval_samples_per_second": 47.174, | |
| "eval_steps_per_second": 23.587, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013479075840862662, | |
| "grad_norm": 0.4358305037021637, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5812, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00013479075840862662, | |
| "eval_loss": 1.4894870519638062, | |
| "eval_runtime": 316.4558, | |
| "eval_samples_per_second": 78.968, | |
| "eval_steps_per_second": 39.484, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002021861376129399, | |
| "grad_norm": 0.41065123677253723, | |
| "learning_rate": 3e-05, | |
| "loss": 1.3727, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00026958151681725324, | |
| "grad_norm": 0.4586036503314972, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4827, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00026958151681725324, | |
| "eval_loss": 1.47844398021698, | |
| "eval_runtime": 269.0254, | |
| "eval_samples_per_second": 92.891, | |
| "eval_steps_per_second": 46.445, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003369768960215665, | |
| "grad_norm": 0.4160114824771881, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4575, | |
| "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": 648596517027840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |