| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02280701754385965, | |
| "eval_steps": 13, | |
| "global_step": 26, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008771929824561404, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.8087, | |
| "eval_samples_per_second": 30.735, | |
| "eval_steps_per_second": 15.367, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008771929824561403, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011403508771929825, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.2396, | |
| "eval_samples_per_second": 33.151, | |
| "eval_steps_per_second": 16.575, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.017543859649122806, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02280701754385965, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.2505, | |
| "eval_samples_per_second": 33.101, | |
| "eval_steps_per_second": 16.551, | |
| "step": 26 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2298571168677888.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |