| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008655510675129832, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00028851702250432774, | |
| "eval_loss": NaN, | |
| "eval_runtime": 79.9498, | |
| "eval_samples_per_second": 18.261, | |
| "eval_steps_per_second": 9.131, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008655510675129833, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014425851125216388, | |
| "eval_loss": NaN, | |
| "eval_runtime": 79.9253, | |
| "eval_samples_per_second": 18.267, | |
| "eval_steps_per_second": 9.134, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017311021350259665, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00259665320253895, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0028851702250432777, | |
| "eval_loss": NaN, | |
| "eval_runtime": 79.959, | |
| "eval_samples_per_second": 18.259, | |
| "eval_steps_per_second": 9.13, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003462204270051933, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004327755337564916, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004327755337564916, | |
| "eval_loss": NaN, | |
| "eval_runtime": 80.1027, | |
| "eval_samples_per_second": 18.227, | |
| "eval_steps_per_second": 9.113, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0051933064050779, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005770340450086555, | |
| "eval_loss": NaN, | |
| "eval_runtime": 80.0816, | |
| "eval_samples_per_second": 18.231, | |
| "eval_steps_per_second": 9.116, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006058857472590883, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006924408540103866, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007212925562608194, | |
| "eval_loss": NaN, | |
| "eval_runtime": 80.0778, | |
| "eval_samples_per_second": 18.232, | |
| "eval_steps_per_second": 9.116, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007789959607616849, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.008655510675129832, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008655510675129832, | |
| "eval_loss": NaN, | |
| "eval_runtime": 80.0397, | |
| "eval_samples_per_second": 18.241, | |
| "eval_steps_per_second": 9.12, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.054695455981568e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |