| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2696629213483146, | |
| "eval_steps": 5, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.017977528089887642, | |
| "eval_loss": 11.93013858795166, | |
| "eval_runtime": 0.9844, | |
| "eval_samples_per_second": 95.493, | |
| "eval_steps_per_second": 24.381, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05393258426966292, | |
| "grad_norm": 0.15690268576145172, | |
| "learning_rate": 3e-05, | |
| "loss": 11.9306, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0898876404494382, | |
| "eval_loss": 11.929566383361816, | |
| "eval_runtime": 0.9816, | |
| "eval_samples_per_second": 95.766, | |
| "eval_steps_per_second": 24.451, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10786516853932585, | |
| "grad_norm": 0.1660546213388443, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9306, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16179775280898875, | |
| "grad_norm": 0.18455131351947784, | |
| "learning_rate": 9e-05, | |
| "loss": 11.9286, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1797752808988764, | |
| "eval_loss": 11.927314758300781, | |
| "eval_runtime": 0.9797, | |
| "eval_samples_per_second": 95.952, | |
| "eval_steps_per_second": 24.498, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2157303370786517, | |
| "grad_norm": 0.22720609605312347, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 11.9266, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2696629213483146, | |
| "grad_norm": 0.28416040539741516, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9244, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2696629213483146, | |
| "eval_loss": 11.922819137573242, | |
| "eval_runtime": 0.9826, | |
| "eval_samples_per_second": 95.669, | |
| "eval_steps_per_second": 24.426, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 142214430720.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |