| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00033769618037478646, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.1256539345826217e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1840.5672, | |
| "eval_samples_per_second": 20.323, | |
| "eval_steps_per_second": 10.162, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.3769618037478645e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.628269672913108e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1839.3787, | |
| "eval_samples_per_second": 20.336, | |
| "eval_steps_per_second": 10.168, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.753923607495729e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00010130885411243594, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00011256539345826216, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1839.6422, | |
| "eval_samples_per_second": 20.333, | |
| "eval_steps_per_second": 10.167, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00013507847214991458, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00016884809018739323, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00016884809018739323, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1837.8636, | |
| "eval_samples_per_second": 20.353, | |
| "eval_steps_per_second": 10.176, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00020261770822487188, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00022513078691652433, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1835.4087, | |
| "eval_samples_per_second": 20.38, | |
| "eval_steps_per_second": 10.19, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00023638732626235054, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00027015694429982916, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0002814134836456554, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1834.8766, | |
| "eval_samples_per_second": 20.386, | |
| "eval_steps_per_second": 10.193, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00030392656233730784, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00033769618037478646, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00033769618037478646, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1836.0553, | |
| "eval_samples_per_second": 20.373, | |
| "eval_steps_per_second": 10.187, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4135709237575680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |