| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.2, | |
| "eval_steps": 25, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21333333333333335, | |
| "grad_norm": 0.02025536447763443, | |
| "learning_rate": 9.901664203302126e-05, | |
| "loss": 10.3793, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.21333333333333335, | |
| "eval_loss": 10.375043869018555, | |
| "eval_runtime": 0.1759, | |
| "eval_samples_per_second": 284.179, | |
| "eval_steps_per_second": 73.887, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.4266666666666667, | |
| "grad_norm": 0.01990126073360443, | |
| "learning_rate": 9.610954559391703e-05, | |
| "loss": 10.3797, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.029884908348321915, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 10.3795, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.8533333333333334, | |
| "grad_norm": 0.024962255731225014, | |
| "learning_rate": 8.511087728614862e-05, | |
| "loss": 10.3784, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.04544679448008537, | |
| "learning_rate": 7.75e-05, | |
| "loss": 18.1411, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.021901274099946022, | |
| "learning_rate": 6.890576474687263e-05, | |
| "loss": 10.2224, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.4933333333333334, | |
| "grad_norm": 0.023775460198521614, | |
| "learning_rate": 5.970378084704441e-05, | |
| "loss": 10.7961, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.7066666666666666, | |
| "grad_norm": 0.02373623661696911, | |
| "learning_rate": 5.0296219152955604e-05, | |
| "loss": 10.1354, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.029921194538474083, | |
| "learning_rate": 4.109423525312738e-05, | |
| "loss": 11.9958, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.030700622126460075, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 10.9644, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.3466666666666667, | |
| "grad_norm": 0.02127590961754322, | |
| "learning_rate": 2.4889122713851394e-05, | |
| "loss": 10.323, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 0.022083817049860954, | |
| "learning_rate": 1.8594235253127375e-05, | |
| "loss": 10.3683, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.7733333333333334, | |
| "grad_norm": 0.02354702726006508, | |
| "learning_rate": 1.389045440608296e-05, | |
| "loss": 10.4097, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.986666666666667, | |
| "grad_norm": 0.030587617307901382, | |
| "learning_rate": 1.0983357966978745e-05, | |
| "loss": 10.7642, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.021685440093278885, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3842, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 15, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 12830417879040.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |