| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.004214696647208817, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 8.429393294417634e-05, |
| "eval_loss": 0.2198059856891632, |
| "eval_runtime": 287.611, |
| "eval_samples_per_second": 17.367, |
| "eval_steps_per_second": 8.685, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0004214696647208817, |
| "grad_norm": 0.35115545988082886, |
| "learning_rate": 5e-05, |
| "loss": 0.2027, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0008429393294417634, |
| "grad_norm": 0.3351096510887146, |
| "learning_rate": 0.0001, |
| "loss": 0.1362, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0008429393294417634, |
| "eval_loss": 0.0437222495675087, |
| "eval_runtime": 289.151, |
| "eval_samples_per_second": 17.275, |
| "eval_steps_per_second": 8.639, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.001264408994162645, |
| "grad_norm": 0.03451079502701759, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.0148, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0016858786588835268, |
| "grad_norm": 0.009307351894676685, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.0014, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0016858786588835268, |
| "eval_loss": 0.0004664006410166621, |
| "eval_runtime": 290.7743, |
| "eval_samples_per_second": 17.178, |
| "eval_steps_per_second": 8.591, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0021073483236044087, |
| "grad_norm": 0.014149535447359085, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.0003, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.00252881798832529, |
| "grad_norm": 0.0014348478289321065, |
| "learning_rate": 5e-05, |
| "loss": 0.0001, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.00252881798832529, |
| "eval_loss": 7.054233719827607e-05, |
| "eval_runtime": 290.7879, |
| "eval_samples_per_second": 17.177, |
| "eval_steps_per_second": 8.59, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.002950287653046172, |
| "grad_norm": 0.0006044543697498739, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.0001, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.0033717573177670535, |
| "grad_norm": 0.0005318066105246544, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.0, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0033717573177670535, |
| "eval_loss": 5.269195753498934e-05, |
| "eval_runtime": 292.3237, |
| "eval_samples_per_second": 17.087, |
| "eval_steps_per_second": 8.545, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0037932269824879354, |
| "grad_norm": 0.00021961356105748564, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.0001, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.004214696647208817, |
| "grad_norm": 0.00041368522215634584, |
| "learning_rate": 0.0, |
| "loss": 0.0001, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.004214696647208817, |
| "eval_loss": 5.038717790739611e-05, |
| "eval_runtime": 292.2613, |
| "eval_samples_per_second": 17.091, |
| "eval_steps_per_second": 8.547, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 5, |
| "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": 8143665679564800.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
