| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.037292560134253215, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007458512026850643, | |
| "eval_loss": 11.130187034606934, | |
| "eval_runtime": 3.0441, | |
| "eval_samples_per_second": 185.604, | |
| "eval_steps_per_second": 92.966, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007458512026850644, | |
| "grad_norm": 1.1480289697647095, | |
| "learning_rate": 0.0001, | |
| "loss": 44.5223, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009696065634905836, | |
| "eval_loss": 11.120059967041016, | |
| "eval_runtime": 1.8319, | |
| "eval_samples_per_second": 308.419, | |
| "eval_steps_per_second": 154.483, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.014917024053701287, | |
| "grad_norm": 1.314498782157898, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 44.459, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019392131269811673, | |
| "eval_loss": 11.098611831665039, | |
| "eval_runtime": 1.8279, | |
| "eval_samples_per_second": 309.106, | |
| "eval_steps_per_second": 154.827, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02237553608055193, | |
| "grad_norm": 1.2946125268936157, | |
| "learning_rate": 5e-05, | |
| "loss": 44.3946, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02908819690471751, | |
| "eval_loss": 11.084484100341797, | |
| "eval_runtime": 1.8157, | |
| "eval_samples_per_second": 311.172, | |
| "eval_steps_per_second": 155.861, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.029834048107402575, | |
| "grad_norm": 1.4587301015853882, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 44.3598, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.037292560134253215, | |
| "grad_norm": 1.4952447414398193, | |
| "learning_rate": 0.0, | |
| "loss": 44.3477, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 954835402752.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |