| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.023781212841854936, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0023781212841854932, | |
| "grad_norm": 0.4231848418712616, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2323, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023781212841854932, | |
| "eval_loss": 2.068248987197876, | |
| "eval_runtime": 5.9544, | |
| "eval_samples_per_second": 29.894, | |
| "eval_steps_per_second": 14.947, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0047562425683709865, | |
| "grad_norm": 0.45535340905189514, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0231, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007134363852556481, | |
| "grad_norm": 0.28963589668273926, | |
| "learning_rate": 6e-05, | |
| "loss": 1.8086, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007134363852556481, | |
| "eval_loss": 2.0672354698181152, | |
| "eval_runtime": 4.9775, | |
| "eval_samples_per_second": 35.761, | |
| "eval_steps_per_second": 17.88, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009512485136741973, | |
| "grad_norm": 0.2574818730354309, | |
| "learning_rate": 8e-05, | |
| "loss": 2.0286, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011890606420927468, | |
| "grad_norm": 0.4121098518371582, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9101, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014268727705112961, | |
| "grad_norm": 0.3913452923297882, | |
| "learning_rate": 0.00012, | |
| "loss": 1.9592, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014268727705112961, | |
| "eval_loss": 2.049959421157837, | |
| "eval_runtime": 4.955, | |
| "eval_samples_per_second": 35.923, | |
| "eval_steps_per_second": 17.962, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016646848989298454, | |
| "grad_norm": 0.22511990368366241, | |
| "learning_rate": 0.00014, | |
| "loss": 2.0205, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019024970273483946, | |
| "grad_norm": 0.29633215069770813, | |
| "learning_rate": 0.00016, | |
| "loss": 1.9259, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02140309155766944, | |
| "grad_norm": 0.29478707909584045, | |
| "learning_rate": 0.00018, | |
| "loss": 1.9776, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02140309155766944, | |
| "eval_loss": 1.9992634057998657, | |
| "eval_runtime": 5.0221, | |
| "eval_samples_per_second": 35.443, | |
| "eval_steps_per_second": 17.722, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.023781212841854936, | |
| "grad_norm": 0.4828934371471405, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6849, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 857008295116800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |