| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1, |
| "grad_norm": 18.916099095189473, |
| "learning_rate": 1.0000000000000002e-06, |
| "loss": 0.9574, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 21.53952313643694, |
| "learning_rate": 5e-06, |
| "loss": 0.8754, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 5.798825182601948, |
| "learning_rate": 1e-05, |
| "loss": 0.746, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.6230876445770264, |
| "eval_runtime": 5.7302, |
| "eval_samples_per_second": 53.052, |
| "eval_steps_per_second": 1.745, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 3.2446769999187137, |
| "learning_rate": 9.924038765061042e-06, |
| "loss": 0.5866, |
| "step": 15 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 2.9248994732336526, |
| "learning_rate": 9.698463103929542e-06, |
| "loss": 0.5258, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.3843041658401489, |
| "eval_runtime": 5.7293, |
| "eval_samples_per_second": 53.061, |
| "eval_steps_per_second": 1.745, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 3.044511051436622, |
| "learning_rate": 9.330127018922195e-06, |
| "loss": 0.3601, |
| "step": 25 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 2.817325596304153, |
| "learning_rate": 8.83022221559489e-06, |
| "loss": 0.3183, |
| "step": 30 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.1999027132987976, |
| "eval_runtime": 5.7226, |
| "eval_samples_per_second": 53.123, |
| "eval_steps_per_second": 1.747, |
| "step": 30 |
| }, |
| { |
| "epoch": 3.5, |
| "grad_norm": 3.4431057415284267, |
| "learning_rate": 8.213938048432697e-06, |
| "loss": 0.1832, |
| "step": 35 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 2.7772199860436415, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 0.16, |
| "step": 40 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.0864211916923523, |
| "eval_runtime": 5.7261, |
| "eval_samples_per_second": 53.09, |
| "eval_steps_per_second": 1.746, |
| "step": 40 |
| }, |
| { |
| "epoch": 4.5, |
| "grad_norm": 3.315697037143245, |
| "learning_rate": 6.710100716628345e-06, |
| "loss": 0.0802, |
| "step": 45 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 2.0887623280319887, |
| "learning_rate": 5.8682408883346535e-06, |
| "loss": 0.0811, |
| "step": 50 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.04959693178534508, |
| "eval_runtime": 5.7295, |
| "eval_samples_per_second": 53.059, |
| "eval_steps_per_second": 1.745, |
| "step": 50 |
| }, |
| { |
| "epoch": 5.5, |
| "grad_norm": 2.1432132959969725, |
| "learning_rate": 5e-06, |
| "loss": 0.0479, |
| "step": 55 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 1.8407217223386276, |
| "learning_rate": 4.131759111665349e-06, |
| "loss": 0.0502, |
| "step": 60 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.034496039152145386, |
| "eval_runtime": 5.726, |
| "eval_samples_per_second": 53.091, |
| "eval_steps_per_second": 1.746, |
| "step": 60 |
| }, |
| { |
| "epoch": 6.5, |
| "grad_norm": 1.5928033449038717, |
| "learning_rate": 3.289899283371657e-06, |
| "loss": 0.0339, |
| "step": 65 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 1.359878925254289, |
| "learning_rate": 2.5000000000000015e-06, |
| "loss": 0.035, |
| "step": 70 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.025400497019290924, |
| "eval_runtime": 5.7281, |
| "eval_samples_per_second": 53.072, |
| "eval_steps_per_second": 1.746, |
| "step": 70 |
| }, |
| { |
| "epoch": 7.5, |
| "grad_norm": 1.1463040760182688, |
| "learning_rate": 1.7860619515673034e-06, |
| "loss": 0.0248, |
| "step": 75 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 1.0125936690851214, |
| "learning_rate": 1.1697777844051105e-06, |
| "loss": 0.0241, |
| "step": 80 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.0185158122330904, |
| "eval_runtime": 5.7304, |
| "eval_samples_per_second": 53.051, |
| "eval_steps_per_second": 1.745, |
| "step": 80 |
| }, |
| { |
| "epoch": 8.5, |
| "grad_norm": 0.8554989663331637, |
| "learning_rate": 6.698729810778065e-07, |
| "loss": 0.0177, |
| "step": 85 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 0.6771852125259162, |
| "learning_rate": 3.015368960704584e-07, |
| "loss": 0.0165, |
| "step": 90 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.014229783788323402, |
| "eval_runtime": 5.7297, |
| "eval_samples_per_second": 53.057, |
| "eval_steps_per_second": 1.745, |
| "step": 90 |
| }, |
| { |
| "epoch": 9.5, |
| "grad_norm": 0.5405112996842772, |
| "learning_rate": 7.59612349389599e-08, |
| "loss": 0.0135, |
| "step": 95 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.5192308458018222, |
| "learning_rate": 0.0, |
| "loss": 0.0129, |
| "step": 100 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.01297028735280037, |
| "eval_runtime": 5.7028, |
| "eval_samples_per_second": 53.307, |
| "eval_steps_per_second": 1.754, |
| "step": 100 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 100, |
| "total_flos": 20937965568000.0, |
| "train_loss": 0.21048430703580379, |
| "train_runtime": 572.8088, |
| "train_samples_per_second": 10.737, |
| "train_steps_per_second": 0.175 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 100, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 20937965568000.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
