| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1530221882172915, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00306044376434583, | |
| "eval_loss": 1.1510734558105469, | |
| "eval_runtime": 4.4645, | |
| "eval_samples_per_second": 30.91, | |
| "eval_steps_per_second": 15.455, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015302218821729151, | |
| "grad_norm": 0.4472001791000366, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0986, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.030604437643458302, | |
| "grad_norm": 0.5418208241462708, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0569, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.030604437643458302, | |
| "eval_loss": 1.0872843265533447, | |
| "eval_runtime": 4.4571, | |
| "eval_samples_per_second": 30.962, | |
| "eval_steps_per_second": 15.481, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.045906656465187455, | |
| "grad_norm": 0.5617879033088684, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0174, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.061208875286916604, | |
| "grad_norm": 0.6124468445777893, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8849, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.061208875286916604, | |
| "eval_loss": 0.9087503552436829, | |
| "eval_runtime": 4.4925, | |
| "eval_samples_per_second": 30.718, | |
| "eval_steps_per_second": 15.359, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07651109410864575, | |
| "grad_norm": 0.6420426368713379, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9044, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09181331293037491, | |
| "grad_norm": 0.5938111543655396, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7093, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09181331293037491, | |
| "eval_loss": 0.7915513515472412, | |
| "eval_runtime": 4.6291, | |
| "eval_samples_per_second": 29.811, | |
| "eval_steps_per_second": 14.906, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10711553175210406, | |
| "grad_norm": 0.7431860566139221, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.807, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.12241775057383321, | |
| "grad_norm": 0.6036708950996399, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7572, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12241775057383321, | |
| "eval_loss": 0.758077085018158, | |
| "eval_runtime": 4.6863, | |
| "eval_samples_per_second": 29.448, | |
| "eval_steps_per_second": 14.724, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13771996939556236, | |
| "grad_norm": 0.7929571270942688, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7973, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1530221882172915, | |
| "grad_norm": 0.7141656279563904, | |
| "learning_rate": 0.0, | |
| "loss": 0.751, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1530221882172915, | |
| "eval_loss": 0.7527812719345093, | |
| "eval_runtime": 4.5341, | |
| "eval_samples_per_second": 30.436, | |
| "eval_steps_per_second": 15.218, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1848097042857984.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |