| { |
| "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": 0.6845161290322581, |
| "eval_loss": 0.10785406082868576, |
| "eval_runtime": 1.0937, |
| "eval_samples_per_second": 2834.299, |
| "eval_steps_per_second": 59.429, |
| "step": 318 |
| }, |
| { |
| "epoch": 1.5723270440251573, |
| "grad_norm": 0.4275546073913574, |
| "learning_rate": 1.6512928022361987e-05, |
| "loss": 0.2193, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8438709677419355, |
| "eval_loss": 0.03479825332760811, |
| "eval_runtime": 1.097, |
| "eval_samples_per_second": 2825.922, |
| "eval_steps_per_second": 59.253, |
| "step": 636 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8703225806451613, |
| "eval_loss": 0.01689928211271763, |
| "eval_runtime": 1.0917, |
| "eval_samples_per_second": 2839.696, |
| "eval_steps_per_second": 59.542, |
| "step": 954 |
| }, |
| { |
| "epoch": 3.1446540880503147, |
| "grad_norm": 0.22454383969306946, |
| "learning_rate": 1.3018867924528303e-05, |
| "loss": 0.0599, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8829032258064516, |
| "eval_loss": 0.010705524124205112, |
| "eval_runtime": 1.0926, |
| "eval_samples_per_second": 2837.331, |
| "eval_steps_per_second": 59.492, |
| "step": 1272 |
| }, |
| { |
| "epoch": 4.716981132075472, |
| "grad_norm": 0.166969895362854, |
| "learning_rate": 9.52480782669462e-06, |
| "loss": 0.0389, |
| "step": 1500 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8932258064516129, |
| "eval_loss": 0.008237027563154697, |
| "eval_runtime": 1.0908, |
| "eval_samples_per_second": 2841.932, |
| "eval_steps_per_second": 59.589, |
| "step": 1590 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.895483870967742, |
| "eval_loss": 0.006902290508151054, |
| "eval_runtime": 1.2987, |
| "eval_samples_per_second": 2387.094, |
| "eval_steps_per_second": 50.052, |
| "step": 1908 |
| }, |
| { |
| "epoch": 6.289308176100629, |
| "grad_norm": 0.14763705432415009, |
| "learning_rate": 6.030747728860937e-06, |
| "loss": 0.0326, |
| "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": 520991326672152.0, |
| "train_batch_size": 48, |
| "trial_name": null, |
| "trial_params": { |
| "alpha": 0.9763664799887318, |
| "num_train_epochs": 9, |
| "temperature": 10 |
| } |
| } |
|
|
