| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00038291436120311694, | |
| "eval_steps": 500, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.8291436120311695e-05, | |
| "grad_norm": 3.715304374694824, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2144, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.658287224062339e-05, | |
| "grad_norm": 0.7699889540672302, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0021, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00011487430836093508, | |
| "grad_norm": 0.6384534239768982, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 1.4457, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00015316574448124678, | |
| "grad_norm": 2.463369369506836, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 3.0883, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00019145718060155847, | |
| "grad_norm": 1.4535773992538452, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 2.9615, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00022974861672187016, | |
| "grad_norm": 0.6905010938644409, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7699, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00026804005284218184, | |
| "grad_norm": 0.80473792552948, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 2.2851, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00030633148896249356, | |
| "grad_norm": 0.8835957050323486, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 1.1957, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0003446229250828052, | |
| "grad_norm": 0.639277458190918, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 1.2904, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00038291436120311694, | |
| "grad_norm": 1.2057722806930542, | |
| "learning_rate": 0.0, | |
| "loss": 1.8028, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00038291436120311694, | |
| "eval_loss": NaN, | |
| "eval_runtime": 363.9578, | |
| "eval_samples_per_second": 15.106, | |
| "eval_steps_per_second": 15.106, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1628733135912960.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |