| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 6.289308176100629, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6829032258064516, |
| "eval_loss": 0.10128366947174072, |
| "eval_runtime": 1.0915, |
| "eval_samples_per_second": 2840.189, |
| "eval_steps_per_second": 59.552, |
| "step": 318 |
| }, |
| { |
| "epoch": 1.5723270440251573, |
| "grad_norm": 0.4052155911922455, |
| "learning_rate": 1.6512928022361987e-05, |
| "loss": 0.207, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8464516129032258, |
| "eval_loss": 0.03363879397511482, |
| "eval_runtime": 1.093, |
| "eval_samples_per_second": 2836.147, |
| "eval_steps_per_second": 59.468, |
| "step": 636 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8703225806451613, |
| "eval_loss": 0.01689070090651512, |
| "eval_runtime": 1.0956, |
| "eval_samples_per_second": 2829.486, |
| "eval_steps_per_second": 59.328, |
| "step": 954 |
| }, |
| { |
| "epoch": 3.1446540880503147, |
| "grad_norm": 0.21519815921783447, |
| "learning_rate": 1.3018867924528303e-05, |
| "loss": 0.0579, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8835483870967742, |
| "eval_loss": 0.010945086367428303, |
| "eval_runtime": 1.0929, |
| "eval_samples_per_second": 2836.363, |
| "eval_steps_per_second": 59.472, |
| "step": 1272 |
| }, |
| { |
| "epoch": 4.716981132075472, |
| "grad_norm": 0.16116341948509216, |
| "learning_rate": 9.52480782669462e-06, |
| "loss": 0.0383, |
| "step": 1500 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8935483870967742, |
| "eval_loss": 0.008510111831128597, |
| "eval_runtime": 1.1027, |
| "eval_samples_per_second": 2811.306, |
| "eval_steps_per_second": 58.947, |
| "step": 1590 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.8948387096774194, |
| "eval_loss": 0.007168926764279604, |
| "eval_runtime": 1.1063, |
| "eval_samples_per_second": 2802.213, |
| "eval_steps_per_second": 58.756, |
| "step": 1908 |
| }, |
| { |
| "epoch": 6.289308176100629, |
| "grad_norm": 0.143650084733963, |
| "learning_rate": 6.030747728860937e-06, |
| "loss": 0.0322, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2862, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9, |
| "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": 603995663965932.0, |
| "train_batch_size": 48, |
| "trial_name": null, |
| "trial_params": { |
| "alpha": 0.5667920712540218, |
| "num_train_epochs": 9, |
| "temperature": 14 |
| } |
| } |
|
|
