| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9927536231884058, |
| "eval_steps": 20, |
| "global_step": 137, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.036231884057971016, |
| "grad_norm": 1.5703125, |
| "learning_rate": 3.139372514179859e-05, |
| "loss": 2.648, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.07246376811594203, |
| "grad_norm": 1.6015625, |
| "learning_rate": 7.063588156904684e-05, |
| "loss": 2.5698, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.10869565217391304, |
| "grad_norm": 1.328125, |
| "learning_rate": 9.417686158405852e-05, |
| "loss": 2.535, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.14492753623188406, |
| "grad_norm": 1.109375, |
| "learning_rate": 9.412834297056845e-05, |
| "loss": 2.5239, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.18115942028985507, |
| "grad_norm": 1.125, |
| "learning_rate": 9.402598775863905e-05, |
| "loss": 2.5369, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.21739130434782608, |
| "grad_norm": 1.125, |
| "learning_rate": 9.386995220630276e-05, |
| "loss": 2.5074, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2536231884057971, |
| "grad_norm": 1.1015625, |
| "learning_rate": 9.366047452134543e-05, |
| "loss": 2.4874, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.2898550724637681, |
| "grad_norm": 1.1328125, |
| "learning_rate": 9.339787449765238e-05, |
| "loss": 2.5084, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.32608695652173914, |
| "grad_norm": 1.0234375, |
| "learning_rate": 9.308255302700287e-05, |
| "loss": 2.4878, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.36231884057971014, |
| "grad_norm": 1.046875, |
| "learning_rate": 9.271499148705883e-05, |
| "loss": 2.4854, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.39855072463768115, |
| "grad_norm": 1.0703125, |
| "learning_rate": 9.229575100648155e-05, |
| "loss": 2.501, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.43478260869565216, |
| "grad_norm": 1.03125, |
| "learning_rate": 9.182547160829867e-05, |
| "loss": 2.461, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.47101449275362317, |
| "grad_norm": 1.0, |
| "learning_rate": 9.130487123282887e-05, |
| "loss": 2.4792, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.5072463768115942, |
| "grad_norm": 0.9921875, |
| "learning_rate": 9.073474464165638e-05, |
| "loss": 2.4696, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.5434782608695652, |
| "grad_norm": 0.98046875, |
| "learning_rate": 9.011596220432776e-05, |
| "loss": 2.4758, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.5797101449275363, |
| "grad_norm": 0.953125, |
| "learning_rate": 8.944946856962415e-05, |
| "loss": 2.4634, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.6159420289855072, |
| "grad_norm": 0.875, |
| "learning_rate": 8.873628122343667e-05, |
| "loss": 2.4623, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.6521739130434783, |
| "grad_norm": 0.94140625, |
| "learning_rate": 8.797748893544693e-05, |
| "loss": 2.4326, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.6884057971014492, |
| "grad_norm": 0.93359375, |
| "learning_rate": 8.717425009698402e-05, |
| "loss": 2.4757, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.7246376811594203, |
| "grad_norm": 0.953125, |
| "learning_rate": 8.632779095259514e-05, |
| "loss": 2.4531, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.7608695652173914, |
| "grad_norm": 0.90625, |
| "learning_rate": 8.54394037280301e-05, |
| "loss": 2.4681, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.7971014492753623, |
| "grad_norm": 0.921875, |
| "learning_rate": 8.45104446574969e-05, |
| "loss": 2.4615, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.8333333333333334, |
| "grad_norm": 0.93359375, |
| "learning_rate": 8.35423319132008e-05, |
| "loss": 2.4599, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.8695652173913043, |
| "grad_norm": 1.0390625, |
| "learning_rate": 8.253654344032692e-05, |
| "loss": 2.4509, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.8695652173913043, |
| "eval_loss": 2.4220075607299805, |
| "eval_runtime": 13.5232, |
| "eval_samples_per_second": 14.715, |
| "eval_steps_per_second": 14.715, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.9057971014492754, |
| "grad_norm": 1.015625, |
| "learning_rate": 8.149461470077207e-05, |
| "loss": 2.449, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.9420289855072463, |
| "grad_norm": 0.84375, |
| "learning_rate": 8.041813632907031e-05, |
| "loss": 2.4368, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.9782608695652174, |
| "grad_norm": 0.91015625, |
| "learning_rate": 7.930875170409012e-05, |
| "loss": 2.4394, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.9927536231884058, |
| "eval_loss": 2.4152843952178955, |
| "eval_runtime": 12.1031, |
| "eval_samples_per_second": 16.442, |
| "eval_steps_per_second": 16.442, |
| "step": 137 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 414, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 20, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.792294366347264e+17, |
| "train_batch_size": 100, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
