| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.936936936936937, | |
| "eval_steps": 500, | |
| "global_step": 26, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07207207207207207, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 110.9922, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14414414414414414, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 110.4629, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.21621621621621623, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 111.4492, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2882882882882883, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 111.1406, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.36036036036036034, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 110.6133, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 111.1738, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5045045045045045, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 110.5547, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5765765765765766, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 110.4629, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6486486486486487, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 111.1211, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7207207207207207, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 111.6113, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7927927927927928, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 110.6738, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 110.8809, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9369369369369369, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 111.459, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.072072072072072, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 124.7949, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.1441441441441442, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 111.0117, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.2162162162162162, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 110.7891, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.2882882882882882, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 110.6504, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.3603603603603602, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 110.6328, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.4324324324324325, | |
| "grad_norm": 121.68683624267578, | |
| "learning_rate": 0.0001, | |
| "loss": 111.0137, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.5045045045045045, | |
| "grad_norm": 121.82122039794922, | |
| "learning_rate": 9.96057350657239e-05, | |
| "loss": 102.458, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.5765765765765765, | |
| "grad_norm": 44.67742156982422, | |
| "learning_rate": 9.842915805643155e-05, | |
| "loss": 38.5391, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.6486486486486487, | |
| "grad_norm": 44.67742156982422, | |
| "learning_rate": 9.842915805643155e-05, | |
| "loss": 25.5386, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.7207207207207207, | |
| "grad_norm": 44.67742156982422, | |
| "learning_rate": 9.842915805643155e-05, | |
| "loss": 25.3164, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.7927927927927927, | |
| "grad_norm": 70.99137115478516, | |
| "learning_rate": 9.648882429441257e-05, | |
| "loss": 25.0601, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.864864864864865, | |
| "grad_norm": 53.298431396484375, | |
| "learning_rate": 9.381533400219318e-05, | |
| "loss": 25.7983, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.936936936936937, | |
| "grad_norm": 53.298431396484375, | |
| "learning_rate": 9.381533400219318e-05, | |
| "loss": 37.2656, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.936936936936937, | |
| "step": 26, | |
| "total_flos": 3.890443613477274e+16, | |
| "train_loss": 92.364013671875, | |
| "train_runtime": 5039.5212, | |
| "train_samples_per_second": 0.35, | |
| "train_steps_per_second": 0.005 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 26, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 3.890443613477274e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |