| { | |
| "best_metric": 1.32815682888031, | |
| "best_model_checkpoint": "shawgpt-ft-trial-5/checkpoint-9", | |
| "epoch": 2.88, | |
| "eval_steps": 500, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 1.3013744354248047, | |
| "learning_rate": 0.0008885909996223793, | |
| "loss": 3.779, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 2.497284412384033, | |
| "eval_runtime": 4.481, | |
| "eval_samples_per_second": 2.008, | |
| "eval_steps_per_second": 1.116, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 2.2233452796936035, | |
| "learning_rate": 0.000777517124669582, | |
| "loss": 2.1425, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 1.594606876373291, | |
| "eval_runtime": 4.4761, | |
| "eval_samples_per_second": 2.011, | |
| "eval_steps_per_second": 1.117, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 0.5042614936828613, | |
| "learning_rate": 0.0006664432497167844, | |
| "loss": 1.3668, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_loss": 1.32815682888031, | |
| "eval_runtime": 4.478, | |
| "eval_samples_per_second": 2.01, | |
| "eval_steps_per_second": 1.117, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 27, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 28269920157696.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |