| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.018357980622131564, | |
| "eval_steps": 9, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002039775624681285, | |
| "eval_loss": 1.7698744535446167, | |
| "eval_runtime": 9.7023, | |
| "eval_samples_per_second": 85.134, | |
| "eval_steps_per_second": 10.719, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006119326874043855, | |
| "grad_norm": 0.1770610362291336, | |
| "learning_rate": 3e-05, | |
| "loss": 1.7347, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01223865374808771, | |
| "grad_norm": 0.17321984469890594, | |
| "learning_rate": 6e-05, | |
| "loss": 1.7032, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018357980622131564, | |
| "grad_norm": 0.1810854822397232, | |
| "learning_rate": 9e-05, | |
| "loss": 1.7703, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018357980622131564, | |
| "eval_loss": 1.7629197835922241, | |
| "eval_runtime": 9.4373, | |
| "eval_samples_per_second": 87.525, | |
| "eval_steps_per_second": 11.02, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 256629128822784.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |