| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011180992313067784, | |
| "eval_steps": 2, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002795248078266946, | |
| "grad_norm": 0.05912591516971588, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9901, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002795248078266946, | |
| "eval_loss": 11.994447708129883, | |
| "eval_runtime": 14.6956, | |
| "eval_samples_per_second": 41.033, | |
| "eval_steps_per_second": 20.55, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005590496156533892, | |
| "grad_norm": 0.0592072531580925, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9812, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005590496156533892, | |
| "eval_loss": 11.994438171386719, | |
| "eval_runtime": 0.827, | |
| "eval_samples_per_second": 729.178, | |
| "eval_steps_per_second": 365.194, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008385744234800839, | |
| "grad_norm": 0.05439087748527527, | |
| "learning_rate": 3e-05, | |
| "loss": 11.994, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011180992313067784, | |
| "grad_norm": 0.0549190379679203, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9864, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011180992313067784, | |
| "eval_loss": 11.994399070739746, | |
| "eval_runtime": 0.8665, | |
| "eval_samples_per_second": 695.902, | |
| "eval_steps_per_second": 348.528, | |
| "step": 4 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1890582528.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |