| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00026468155500413565, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.6468155500413566e-05, | |
| "grad_norm": 2.9249105864437297e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.6468155500413566e-05, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 88.4186, | |
| "eval_samples_per_second": 179.917, | |
| "eval_steps_per_second": 89.958, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.293631100082713e-05, | |
| "grad_norm": 1.881800744740758e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 7.94044665012407e-05, | |
| "grad_norm": 9.297357792092953e-06, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.94044665012407e-05, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 87.5708, | |
| "eval_samples_per_second": 181.659, | |
| "eval_steps_per_second": 90.829, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010587262200165426, | |
| "grad_norm": 1.1598300261539407e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00013234077750206782, | |
| "grad_norm": 7.736736006336287e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001588089330024814, | |
| "grad_norm": 4.066749170306139e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001588089330024814, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 87.6866, | |
| "eval_samples_per_second": 181.419, | |
| "eval_steps_per_second": 90.709, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00018527708850289495, | |
| "grad_norm": 5.161886656424031e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00021174524400330852, | |
| "grad_norm": 2.6241363229928538e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00023821339950372207, | |
| "grad_norm": 1.9505538148223422e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00023821339950372207, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 88.1528, | |
| "eval_samples_per_second": 180.459, | |
| "eval_steps_per_second": 90.23, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00026468155500413565, | |
| "grad_norm": 1.4031124919711147e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 249035980800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |