| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01628052598622417, | |
| "eval_steps": 13, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004174493842621582, | |
| "eval_loss": 3.6245229244232178, | |
| "eval_runtime": 19.7002, | |
| "eval_samples_per_second": 51.218, | |
| "eval_steps_per_second": 25.634, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004174493842621582, | |
| "grad_norm": 1.0256178379058838, | |
| "learning_rate": 0.0002, | |
| "loss": 3.1777, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005426841995408057, | |
| "eval_loss": 3.121401071548462, | |
| "eval_runtime": 18.3833, | |
| "eval_samples_per_second": 54.887, | |
| "eval_steps_per_second": 27.471, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008348987685243165, | |
| "grad_norm": 1.7537938356399536, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.9006, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010853683990816114, | |
| "eval_loss": 2.9640495777130127, | |
| "eval_runtime": 18.6391, | |
| "eval_samples_per_second": 54.134, | |
| "eval_steps_per_second": 27.094, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012523481527864746, | |
| "grad_norm": 1.0255998373031616, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8861, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01628052598622417, | |
| "eval_loss": 2.917876720428467, | |
| "eval_runtime": 18.5288, | |
| "eval_samples_per_second": 54.456, | |
| "eval_steps_per_second": 27.255, | |
| "step": 39 | |
| } | |
| ], | |
| "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": 365056471597056.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |