| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01121844811467747, | |
| "eval_steps": 9, | |
| "global_step": 27, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00041549807832138777, | |
| "eval_loss": 1.8511379957199097, | |
| "eval_runtime": 172.841, | |
| "eval_samples_per_second": 23.455, | |
| "eval_steps_per_second": 2.933, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012464942349641633, | |
| "grad_norm": 1.7350784540176392, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.8182, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0024929884699283265, | |
| "grad_norm": 1.777970314025879, | |
| "learning_rate": 3e-05, | |
| "loss": 1.8417, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00373948270489249, | |
| "grad_norm": 1.0666847229003906, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.6831, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00373948270489249, | |
| "eval_loss": 1.645044207572937, | |
| "eval_runtime": 173.3911, | |
| "eval_samples_per_second": 23.381, | |
| "eval_steps_per_second": 2.924, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004985976939856653, | |
| "grad_norm": 1.074853777885437, | |
| "learning_rate": 4.993910125649561e-05, | |
| "loss": 1.638, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0062324711748208165, | |
| "grad_norm": 1.2451493740081787, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 1.4395, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00747896540978498, | |
| "grad_norm": 0.8546340465545654, | |
| "learning_rate": 4.9031542398457974e-05, | |
| "loss": 1.4021, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00747896540978498, | |
| "eval_loss": 1.383123517036438, | |
| "eval_runtime": 173.2897, | |
| "eval_samples_per_second": 23.394, | |
| "eval_steps_per_second": 2.926, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008725459644749143, | |
| "grad_norm": 0.8779253959655762, | |
| "learning_rate": 4.817959636416969e-05, | |
| "loss": 1.3657, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009971953879713306, | |
| "grad_norm": 0.9482561945915222, | |
| "learning_rate": 4.707368982147318e-05, | |
| "loss": 1.2238, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01121844811467747, | |
| "grad_norm": 0.7827633023262024, | |
| "learning_rate": 4.572593931387604e-05, | |
| "loss": 1.2321, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01121844811467747, | |
| "eval_loss": 1.3266533613204956, | |
| "eval_runtime": 173.524, | |
| "eval_samples_per_second": 23.363, | |
| "eval_steps_per_second": 2.922, | |
| "step": 27 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0857221537660928e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |