| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 11.0, | |
| "eval_steps": 500, | |
| "global_step": 6457, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8517887563884157, | |
| "grad_norm": 0.07218749076128006, | |
| "learning_rate": 4.6128232925507207e-05, | |
| "loss": 1.4771, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.7035775127768313, | |
| "grad_norm": 3.5773040779618626e-11, | |
| "learning_rate": 4.2256465851014404e-05, | |
| "loss": 0.6892, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.555366269165247, | |
| "grad_norm": 1.4907100549597627e-18, | |
| "learning_rate": 3.838469877652161e-05, | |
| "loss": 0.391, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.4071550255536627, | |
| "grad_norm": 8.450392385839223e-09, | |
| "learning_rate": 3.4512931702028805e-05, | |
| "loss": 0.0828, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.258943781942079, | |
| "grad_norm": 6.480125307462004e-07, | |
| "learning_rate": 3.064116462753601e-05, | |
| "loss": 0.0007, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.1107325383304945, | |
| "grad_norm": 5.91474647038126e-09, | |
| "learning_rate": 2.6769397553043214e-05, | |
| "loss": 0.0076, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.9625212947189095, | |
| "grad_norm": 2.0850879616646223e-12, | |
| "learning_rate": 2.289763047855041e-05, | |
| "loss": 0.0003, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 6.814310051107325, | |
| "grad_norm": 5.3014091463410296e-06, | |
| "learning_rate": 1.9025863404057612e-05, | |
| "loss": 0.0, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 7.666098807495741, | |
| "grad_norm": 2.4710752541401426e-11, | |
| "learning_rate": 1.5154096329564816e-05, | |
| "loss": 0.0, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 8.517887563884157, | |
| "grad_norm": 1.3310883045196533, | |
| "learning_rate": 1.1282329255072017e-05, | |
| "loss": 0.0, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 9.369676320272573, | |
| "grad_norm": 1.0832469470034578e-11, | |
| "learning_rate": 7.410562180579217e-06, | |
| "loss": 0.0, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 10.221465076660989, | |
| "grad_norm": 6.389404006768018e-05, | |
| "learning_rate": 3.538795106086418e-06, | |
| "loss": 0.0, | |
| "step": 6000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6457, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 11, | |
| "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": 2.1505027241263104e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |