| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 1590, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9968553459119497, | |
| "grad_norm": 0.7694054245948792, | |
| "learning_rate": 1.6012578616352204e-05, | |
| "loss": 0.5022, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6154838709677419, | |
| "eval_loss": 0.26054030656814575, | |
| "eval_runtime": 1.7184, | |
| "eval_samples_per_second": 1803.999, | |
| "eval_steps_per_second": 37.826, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.9937106918238994, | |
| "grad_norm": 0.5620624423027039, | |
| "learning_rate": 1.2025157232704403e-05, | |
| "loss": 0.2176, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8261290322580646, | |
| "eval_loss": 0.12605048716068268, | |
| "eval_runtime": 1.7265, | |
| "eval_samples_per_second": 1795.523, | |
| "eval_steps_per_second": 37.648, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 2.990566037735849, | |
| "grad_norm": 0.5527320504188538, | |
| "learning_rate": 8.037735849056606e-06, | |
| "loss": 0.1353, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8703225806451613, | |
| "eval_loss": 0.08548224717378616, | |
| "eval_runtime": 1.7614, | |
| "eval_samples_per_second": 1759.937, | |
| "eval_steps_per_second": 36.902, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.9874213836477987, | |
| "grad_norm": 0.4752902388572693, | |
| "learning_rate": 4.0503144654088055e-06, | |
| "loss": 0.1054, | |
| "step": 1268 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8825806451612903, | |
| "eval_loss": 0.06941940635442734, | |
| "eval_runtime": 1.8003, | |
| "eval_samples_per_second": 1721.946, | |
| "eval_steps_per_second": 36.105, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.984276729559748, | |
| "grad_norm": 0.3840288817882538, | |
| "learning_rate": 6.289308176100629e-08, | |
| "loss": 0.0936, | |
| "step": 1585 | |
| } | |
| ], | |
| "logging_steps": 317, | |
| "max_steps": 1590, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 1000000000.0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 413495819944032.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.022171071491301153, | |
| "num_train_epochs": 5, | |
| "temperature": 4 | |
| } | |
| } | |