| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05, |
| "grad_norm": 2.1411664485931396, |
| "learning_rate": 0.0003266666666666667, |
| "loss": 34.3079, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 2.7123711109161377, |
| "learning_rate": 0.00066, |
| "loss": 26.3975, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 2.4478516578674316, |
| "learning_rate": 0.0009933333333333333, |
| "loss": 24.208, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 1.5827449560165405, |
| "learning_rate": 0.000991822760447871, |
| "loss": 22.3278, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 1.648890495300293, |
| "learning_rate": 0.0009669005017492141, |
| "loss": 21.0842, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 1.509036660194397, |
| "learning_rate": 0.000926078506448917, |
| "loss": 20.095, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 1.3168805837631226, |
| "learning_rate": 0.0008707469186363446, |
| "loss": 19.4834, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 1.297710657119751, |
| "learning_rate": 0.0008027899891715287, |
| "loss": 18.9437, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 1.1592856645584106, |
| "learning_rate": 0.0007245219097820409, |
| "loss": 18.3749, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 1.155800461769104, |
| "learning_rate": 0.0006386080060392753, |
| "loss": 17.8605, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.5, |
| "eval_accuracy": 0.28156454336549924, |
| "eval_loss": 4.3490142822265625, |
| "eval_runtime": 9.9325, |
| "eval_samples_per_second": 97.66, |
| "eval_steps_per_second": 6.141, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 1.1437630653381348, |
| "learning_rate": 0.000547973972892822, |
| "loss": 17.3699, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 1.1172058582305908, |
| "learning_rate": 0.00045570624363794224, |
| "loss": 17.0134, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 1.0678249597549438, |
| "learning_rate": 0.0003649468851314669, |
| "loss": 16.751, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.9996118545532227, |
| "learning_rate": 0.00027878659847348176, |
| "loss": 16.5556, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.8965609669685364, |
| "learning_rate": 0.00020015946888825076, |
| "loss": 16.3919, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.7993431091308594, |
| "learning_rate": 0.00013174304897095113, |
| "loss": 16.2651, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.8439401388168335, |
| "learning_rate": 7.58671778454153e-05, |
| "loss": 16.1115, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.8115217685699463, |
| "learning_rate": 3.443464128710239e-05, |
| "loss": 16.0619, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.6535219550132751, |
| "learning_rate": 8.856374635655695e-06, |
| "loss": 16.0151, |
| "step": 950 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.7225023508071899, |
| "learning_rate": 3.4150841404789744e-09, |
| "loss": 16.0566, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.32063273339130327, |
| "eval_loss": 3.969637870788574, |
| "eval_runtime": 9.1804, |
| "eval_samples_per_second": 105.66, |
| "eval_steps_per_second": 6.645, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 900, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.67251663650816e+17, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
