| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.072, |
| "eval_steps": 500, |
| "global_step": 4500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0016, |
| "grad_norm": 5.90625, |
| "learning_rate": 3.96e-06, |
| "loss": 3.1, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.0032, |
| "grad_norm": 6.625, |
| "learning_rate": 7.960000000000002e-06, |
| "loss": 3.1, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.0048, |
| "grad_norm": 4.125, |
| "learning_rate": 1.196e-05, |
| "loss": 2.98, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.0064, |
| "grad_norm": 3.78125, |
| "learning_rate": 1.5960000000000003e-05, |
| "loss": 2.72, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.008, |
| "grad_norm": 3.71875, |
| "learning_rate": 1.9960000000000002e-05, |
| "loss": 2.58, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.0096, |
| "grad_norm": 3.234375, |
| "learning_rate": 1.9968064516129034e-05, |
| "loss": 2.47, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.0112, |
| "grad_norm": 3.625, |
| "learning_rate": 1.9935806451612905e-05, |
| "loss": 2.44, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.0128, |
| "grad_norm": 3.328125, |
| "learning_rate": 1.9903548387096776e-05, |
| "loss": 2.45, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.0144, |
| "grad_norm": 3.234375, |
| "learning_rate": 1.9871290322580646e-05, |
| "loss": 2.41, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.016, |
| "grad_norm": 2.984375, |
| "learning_rate": 1.9839032258064517e-05, |
| "loss": 2.38, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.0176, |
| "grad_norm": 2.921875, |
| "learning_rate": 1.9806774193548387e-05, |
| "loss": 2.36, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.0192, |
| "grad_norm": 3.234375, |
| "learning_rate": 1.9774516129032258e-05, |
| "loss": 2.42, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.0208, |
| "grad_norm": 3.125, |
| "learning_rate": 1.9742258064516132e-05, |
| "loss": 2.44, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.0224, |
| "grad_norm": 3.03125, |
| "learning_rate": 1.9710000000000003e-05, |
| "loss": 2.4, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.024, |
| "grad_norm": 3.28125, |
| "learning_rate": 1.9677741935483873e-05, |
| "loss": 2.37, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.0256, |
| "grad_norm": 3.09375, |
| "learning_rate": 1.9645483870967744e-05, |
| "loss": 2.42, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.0272, |
| "grad_norm": 3.078125, |
| "learning_rate": 1.9613225806451615e-05, |
| "loss": 2.38, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.0288, |
| "grad_norm": 3.140625, |
| "learning_rate": 1.9580967741935485e-05, |
| "loss": 2.39, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.0304, |
| "grad_norm": 3.296875, |
| "learning_rate": 1.9548709677419356e-05, |
| "loss": 2.39, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.032, |
| "grad_norm": 3.515625, |
| "learning_rate": 1.9516451612903226e-05, |
| "loss": 2.33, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.0336, |
| "grad_norm": 3.375, |
| "learning_rate": 1.9484193548387097e-05, |
| "loss": 2.38, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.0352, |
| "grad_norm": 3.328125, |
| "learning_rate": 1.945193548387097e-05, |
| "loss": 2.36, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.0368, |
| "grad_norm": 3.375, |
| "learning_rate": 1.9419677419354842e-05, |
| "loss": 2.39, |
| "step": 2300 |
| }, |
| { |
| "epoch": 0.0384, |
| "grad_norm": 3.109375, |
| "learning_rate": 1.938741935483871e-05, |
| "loss": 2.4, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 3.3125, |
| "learning_rate": 1.9355161290322583e-05, |
| "loss": 2.4, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.0416, |
| "grad_norm": 3.15625, |
| "learning_rate": 1.9322903225806454e-05, |
| "loss": 2.39, |
| "step": 2600 |
| }, |
| { |
| "epoch": 0.0432, |
| "grad_norm": 3.171875, |
| "learning_rate": 1.9290645161290324e-05, |
| "loss": 2.39, |
| "step": 2700 |
| }, |
| { |
| "epoch": 0.0448, |
| "grad_norm": 3.15625, |
| "learning_rate": 1.9258387096774195e-05, |
| "loss": 2.39, |
| "step": 2800 |
| }, |
| { |
| "epoch": 0.0464, |
| "grad_norm": 3.78125, |
| "learning_rate": 1.9226129032258065e-05, |
| "loss": 2.39, |
| "step": 2900 |
| }, |
| { |
| "epoch": 0.048, |
| "grad_norm": 2.75, |
| "learning_rate": 1.9193870967741936e-05, |
| "loss": 2.37, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.0496, |
| "grad_norm": 3.109375, |
| "learning_rate": 1.9161612903225807e-05, |
| "loss": 2.38, |
| "step": 3100 |
| }, |
| { |
| "epoch": 0.0512, |
| "grad_norm": 3.203125, |
| "learning_rate": 1.912935483870968e-05, |
| "loss": 2.44, |
| "step": 3200 |
| }, |
| { |
| "epoch": 0.0528, |
| "grad_norm": 3.515625, |
| "learning_rate": 1.909709677419355e-05, |
| "loss": 2.36, |
| "step": 3300 |
| }, |
| { |
| "epoch": 0.0544, |
| "grad_norm": 3.765625, |
| "learning_rate": 1.906483870967742e-05, |
| "loss": 2.38, |
| "step": 3400 |
| }, |
| { |
| "epoch": 0.056, |
| "grad_norm": 3.09375, |
| "learning_rate": 1.9032580645161293e-05, |
| "loss": 2.44, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.0576, |
| "grad_norm": 3.578125, |
| "learning_rate": 1.9000322580645163e-05, |
| "loss": 2.39, |
| "step": 3600 |
| }, |
| { |
| "epoch": 0.0592, |
| "grad_norm": 3.578125, |
| "learning_rate": 1.8968064516129034e-05, |
| "loss": 2.44, |
| "step": 3700 |
| }, |
| { |
| "epoch": 0.0608, |
| "grad_norm": 3.28125, |
| "learning_rate": 1.8935806451612904e-05, |
| "loss": 2.37, |
| "step": 3800 |
| }, |
| { |
| "epoch": 0.0624, |
| "grad_norm": 3.1875, |
| "learning_rate": 1.8903548387096775e-05, |
| "loss": 2.36, |
| "step": 3900 |
| }, |
| { |
| "epoch": 0.064, |
| "grad_norm": 3.03125, |
| "learning_rate": 1.8871290322580646e-05, |
| "loss": 2.36, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.0656, |
| "grad_norm": 3.15625, |
| "learning_rate": 1.883903225806452e-05, |
| "loss": 2.39, |
| "step": 4100 |
| }, |
| { |
| "epoch": 0.0672, |
| "grad_norm": 3.390625, |
| "learning_rate": 1.880677419354839e-05, |
| "loss": 2.3, |
| "step": 4200 |
| }, |
| { |
| "epoch": 0.0688, |
| "grad_norm": 3.375, |
| "learning_rate": 1.8774516129032257e-05, |
| "loss": 2.4, |
| "step": 4300 |
| }, |
| { |
| "epoch": 0.0704, |
| "grad_norm": 3.359375, |
| "learning_rate": 1.874225806451613e-05, |
| "loss": 2.4, |
| "step": 4400 |
| }, |
| { |
| "epoch": 0.072, |
| "grad_norm": 3.0625, |
| "learning_rate": 1.8710000000000002e-05, |
| "loss": 2.32, |
| "step": 4500 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 62500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.8813026304e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
