| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0013962092917728368, |
| "eval_steps": 3, |
| "global_step": 10, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00013962092917728367, |
| "grad_norm": 0.7171996831893921, |
| "learning_rate": 2e-05, |
| "loss": 1.8057, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00013962092917728367, |
| "eval_loss": 2.000722646713257, |
| "eval_runtime": 418.5804, |
| "eval_samples_per_second": 7.205, |
| "eval_steps_per_second": 3.603, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00027924185835456733, |
| "grad_norm": 0.8261868357658386, |
| "learning_rate": 4e-05, |
| "loss": 1.9407, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.000418862787531851, |
| "grad_norm": 0.7888999581336975, |
| "learning_rate": 6e-05, |
| "loss": 1.8775, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.000418862787531851, |
| "eval_loss": 1.9948254823684692, |
| "eval_runtime": 420.1071, |
| "eval_samples_per_second": 7.179, |
| "eval_steps_per_second": 3.59, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0005584837167091347, |
| "grad_norm": 0.8440933227539062, |
| "learning_rate": 8e-05, |
| "loss": 1.8402, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.0006981046458864184, |
| "grad_norm": 0.9196475148200989, |
| "learning_rate": 0.0001, |
| "loss": 1.7403, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.000837725575063702, |
| "grad_norm": 1.4837026596069336, |
| "learning_rate": 0.00012, |
| "loss": 2.015, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.000837725575063702, |
| "eval_loss": 1.8744913339614868, |
| "eval_runtime": 420.2043, |
| "eval_samples_per_second": 7.177, |
| "eval_steps_per_second": 3.589, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.0009773465042409858, |
| "grad_norm": 1.337710976600647, |
| "learning_rate": 0.00014, |
| "loss": 2.1059, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.0011169674334182693, |
| "grad_norm": 0.7705792188644409, |
| "learning_rate": 0.00016, |
| "loss": 1.4985, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.001256588362595553, |
| "grad_norm": 1.513479232788086, |
| "learning_rate": 0.00018, |
| "loss": 2.0342, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.001256588362595553, |
| "eval_loss": 1.6762053966522217, |
| "eval_runtime": 419.8555, |
| "eval_samples_per_second": 7.183, |
| "eval_steps_per_second": 3.592, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.0013962092917728368, |
| "grad_norm": 0.7429284453392029, |
| "learning_rate": 0.0002, |
| "loss": 1.2346, |
| "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": 2034521780256768.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
