| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 2226, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9968553459119497, | |
| "grad_norm": 0.7022855281829834, | |
| "learning_rate": 1.7151841868823e-05, | |
| "loss": 0.4035, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.59, | |
| "eval_loss": 0.2041669636964798, | |
| "eval_runtime": 5.3525, | |
| "eval_samples_per_second": 579.169, | |
| "eval_steps_per_second": 12.144, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.9937106918238994, | |
| "grad_norm": 0.4554065763950348, | |
| "learning_rate": 1.4303683737646003e-05, | |
| "loss": 0.1712, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8219354838709677, | |
| "eval_loss": 0.10027384757995605, | |
| "eval_runtime": 5.4479, | |
| "eval_samples_per_second": 569.027, | |
| "eval_steps_per_second": 11.931, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 2.990566037735849, | |
| "grad_norm": 0.49464017152786255, | |
| "learning_rate": 1.1455525606469004e-05, | |
| "loss": 0.1083, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8780645161290322, | |
| "eval_loss": 0.06833519041538239, | |
| "eval_runtime": 5.4064, | |
| "eval_samples_per_second": 573.399, | |
| "eval_steps_per_second": 12.023, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.9874213836477987, | |
| "grad_norm": 0.3309425115585327, | |
| "learning_rate": 8.607367475292004e-06, | |
| "loss": 0.0827, | |
| "step": 1268 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8935483870967742, | |
| "eval_loss": 0.053802672773599625, | |
| "eval_runtime": 5.4522, | |
| "eval_samples_per_second": 568.582, | |
| "eval_steps_per_second": 11.922, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.984276729559748, | |
| "grad_norm": 0.2727065682411194, | |
| "learning_rate": 5.759209344115006e-06, | |
| "loss": 0.0698, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9025806451612903, | |
| "eval_loss": 0.04560532420873642, | |
| "eval_runtime": 5.4111, | |
| "eval_samples_per_second": 572.892, | |
| "eval_steps_per_second": 12.012, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 5.981132075471698, | |
| "grad_norm": 0.33385205268859863, | |
| "learning_rate": 2.911051212938006e-06, | |
| "loss": 0.063, | |
| "step": 1902 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9070967741935484, | |
| "eval_loss": 0.04146786779165268, | |
| "eval_runtime": 5.4202, | |
| "eval_samples_per_second": 571.939, | |
| "eval_steps_per_second": 11.992, | |
| "step": 1908 | |
| }, | |
| { | |
| "epoch": 6.977987421383648, | |
| "grad_norm": 0.2678754925727844, | |
| "learning_rate": 6.289308176100629e-08, | |
| "loss": 0.0595, | |
| "step": 2219 | |
| } | |
| ], | |
| "logging_steps": 317, | |
| "max_steps": 2226, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "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": 578219881979544.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.04281472072400683, | |
| "num_train_epochs": 7, | |
| "temperature": 10 | |
| } | |
| } | |