| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "wsd_11/checkpoint-213498", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 853992, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 9.78395938873291, | |
| "learning_rate": 0.00019600170493400408, | |
| "loss": 7.7642, | |
| "step": 213498 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.013250860859584237, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1496.9697, | |
| "eval_samples_per_second": 126.773, | |
| "eval_steps_per_second": 15.847, | |
| "step": 213498 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 4.8531718254089355, | |
| "learning_rate": 0.0001920032974547771, | |
| "loss": 8.7523, | |
| "step": 426996 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.013250860859584237, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1497.1718, | |
| "eval_samples_per_second": 126.756, | |
| "eval_steps_per_second": 15.845, | |
| "step": 426996 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019009493297361102, | |
| "loss": 8.7785, | |
| "step": 640494 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1461.9818, | |
| "eval_samples_per_second": 129.807, | |
| "eval_steps_per_second": 16.226, | |
| "step": 640494 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019009493297361102, | |
| "loss": 0.0, | |
| "step": 853992 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1464.1493, | |
| "eval_samples_per_second": 129.615, | |
| "eval_steps_per_second": 16.202, | |
| "step": 853992 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 10674900, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3434413409512138e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |