| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.024780690885661892, | |
| "eval_steps": 200000, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016520460590441263, | |
| "grad_norm": 51.92022705078125, | |
| "learning_rate": 3.2044928972580115e-07, | |
| "loss": 13.3171, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0033040921180882525, | |
| "grad_norm": 68.25243377685547, | |
| "learning_rate": 6.508093822266271e-07, | |
| "loss": 12.9799, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.004956138177132379, | |
| "grad_norm": 69.47785186767578, | |
| "learning_rate": 9.811694747274531e-07, | |
| "loss": 12.5133, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.006608184236176505, | |
| "grad_norm": 73.07315063476562, | |
| "learning_rate": 1.311529567228279e-06, | |
| "loss": 11.9388, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.008260230295220631, | |
| "grad_norm": 82.68733215332031, | |
| "learning_rate": 1.6418896597291048e-06, | |
| "loss": 11.0616, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.009912276354264758, | |
| "grad_norm": 57.61735534667969, | |
| "learning_rate": 1.972249752229931e-06, | |
| "loss": 10.2712, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.011564322413308884, | |
| "grad_norm": 44.42943572998047, | |
| "learning_rate": 2.302609844730757e-06, | |
| "loss": 9.5253, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.01321636847235301, | |
| "grad_norm": 27.03646469116211, | |
| "learning_rate": 2.6329699372315828e-06, | |
| "loss": 8.7706, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.014868414531397135, | |
| "grad_norm": 15.231706619262695, | |
| "learning_rate": 2.9633300297324087e-06, | |
| "loss": 8.4333, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.016520460590441263, | |
| "grad_norm": 14.189949035644531, | |
| "learning_rate": 3.2936901222332346e-06, | |
| "loss": 8.0902, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.018172506649485387, | |
| "grad_norm": 12.241333961486816, | |
| "learning_rate": 3.6240502147340605e-06, | |
| "loss": 7.8862, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.019824552708529515, | |
| "grad_norm": 11.400131225585938, | |
| "learning_rate": 3.9544103072348865e-06, | |
| "loss": 7.7362, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.02147659876757364, | |
| "grad_norm": 12.072014808654785, | |
| "learning_rate": 4.284770399735712e-06, | |
| "loss": 7.6007, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.023128644826617768, | |
| "grad_norm": 11.08774185180664, | |
| "learning_rate": 4.615130492236538e-06, | |
| "loss": 7.5304, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.024780690885661892, | |
| "grad_norm": 13.02505874633789, | |
| "learning_rate": 4.945490584737364e-06, | |
| "loss": 7.4249, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 60531, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |