| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0069468565474122956, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006946856547412296, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 9.3004, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006946856547412296, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.1005, | |
| "eval_samples_per_second": 148.032, | |
| "eval_steps_per_second": 74.138, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013893713094824591, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0020840569642236887, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0020840569642236887, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.3115, | |
| "eval_samples_per_second": 183.3, | |
| "eval_steps_per_second": 91.801, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0027787426189649182, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0034734282737061478, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004168113928447377, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004168113928447377, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.3655, | |
| "eval_samples_per_second": 180.361, | |
| "eval_steps_per_second": 90.329, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004862799583188607, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0055574852379298365, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006252170892671066, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006252170892671066, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.4258, | |
| "eval_samples_per_second": 177.186, | |
| "eval_steps_per_second": 88.739, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0069468565474122956, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 106210409840640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |