| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.991137370753323, | |
| "eval_steps": 500, | |
| "global_step": 1014, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.29542097488921715, | |
| "grad_norm": 1.8936359882354736, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.2777, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5908419497784343, | |
| "grad_norm": 0.42867106199264526, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9288, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8862629246676514, | |
| "grad_norm": 0.5983214378356934, | |
| "learning_rate": 4.726477024070022e-05, | |
| "loss": 0.6469, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.1816838995568686, | |
| "grad_norm": 0.5473693013191223, | |
| "learning_rate": 4.452954048140044e-05, | |
| "loss": 0.5595, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.4771048744460857, | |
| "grad_norm": 0.5971556901931763, | |
| "learning_rate": 4.179431072210066e-05, | |
| "loss": 0.537, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.7725258493353029, | |
| "grad_norm": 0.6025377511978149, | |
| "learning_rate": 3.9059080962800876e-05, | |
| "loss": 0.5271, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.06794682422452, | |
| "grad_norm": 0.9687663912773132, | |
| "learning_rate": 3.6323851203501094e-05, | |
| "loss": 0.5318, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.363367799113737, | |
| "grad_norm": 0.673847496509552, | |
| "learning_rate": 3.358862144420131e-05, | |
| "loss": 0.5116, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.658788774002954, | |
| "grad_norm": 0.7841825485229492, | |
| "learning_rate": 3.085339168490153e-05, | |
| "loss": 0.5114, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.9542097488921715, | |
| "grad_norm": 0.8053774237632751, | |
| "learning_rate": 2.811816192560175e-05, | |
| "loss": 0.5049, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.2496307237813884, | |
| "grad_norm": 0.8071188926696777, | |
| "learning_rate": 2.538293216630197e-05, | |
| "loss": 0.5045, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.5450516986706058, | |
| "grad_norm": 0.8850335478782654, | |
| "learning_rate": 2.264770240700219e-05, | |
| "loss": 0.4958, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.8404726735598227, | |
| "grad_norm": 1.001068115234375, | |
| "learning_rate": 1.9912472647702408e-05, | |
| "loss": 0.4927, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.13589364844904, | |
| "grad_norm": 1.3853482007980347, | |
| "learning_rate": 1.7177242888402626e-05, | |
| "loss": 0.494, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.431314623338257, | |
| "grad_norm": 1.1378982067108154, | |
| "learning_rate": 1.4442013129102846e-05, | |
| "loss": 0.4853, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 4.726735598227474, | |
| "grad_norm": 1.11444890499115, | |
| "learning_rate": 1.1706783369803063e-05, | |
| "loss": 0.4797, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.022156573116692, | |
| "grad_norm": 1.133715033531189, | |
| "learning_rate": 8.971553610503283e-06, | |
| "loss": 0.4822, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.317577548005908, | |
| "grad_norm": 1.230751633644104, | |
| "learning_rate": 6.2363238512035015e-06, | |
| "loss": 0.475, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.612998522895126, | |
| "grad_norm": 1.201663613319397, | |
| "learning_rate": 3.50109409190372e-06, | |
| "loss": 0.4729, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 5.908419497784343, | |
| "grad_norm": 1.250101089477539, | |
| "learning_rate": 7.658643326039388e-07, | |
| "loss": 0.4689, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1014, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "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": 1.6016891541848064e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |