| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005599378468989942, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011198756937979884, | |
| "grad_norm": 7.355754852294922, | |
| "learning_rate": 1e-05, | |
| "loss": 2.5011, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011198756937979884, | |
| "eval_loss": 2.5844409465789795, | |
| "eval_runtime": 414.4622, | |
| "eval_samples_per_second": 36.288, | |
| "eval_steps_per_second": 18.144, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00022397513875959768, | |
| "grad_norm": 7.669259071350098, | |
| "learning_rate": 2e-05, | |
| "loss": 2.6951, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00022397513875959768, | |
| "eval_loss": 2.5014777183532715, | |
| "eval_runtime": 369.4686, | |
| "eval_samples_per_second": 40.707, | |
| "eval_steps_per_second": 20.354, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00033596270813939655, | |
| "grad_norm": 6.046054840087891, | |
| "learning_rate": 3e-05, | |
| "loss": 2.1406, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00044795027751919536, | |
| "grad_norm": 6.388694763183594, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2288, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00044795027751919536, | |
| "eval_loss": 2.2816696166992188, | |
| "eval_runtime": 217.4326, | |
| "eval_samples_per_second": 69.171, | |
| "eval_steps_per_second": 34.585, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005599378468989942, | |
| "grad_norm": 5.648911952972412, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9038, | |
| "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": 1223694483456000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |