| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1848, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05411255411255411, | |
| "grad_norm": 0.18986542522907257, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 2.3446, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10822510822510822, | |
| "grad_norm": 0.1643804907798767, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 2.332, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16233766233766234, | |
| "grad_norm": 0.34427669644355774, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2662, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.21645021645021645, | |
| "grad_norm": 0.4920704960823059, | |
| "learning_rate": 1.979477194660769e-05, | |
| "loss": 2.0925, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.27056277056277056, | |
| "grad_norm": 0.6333794593811035, | |
| "learning_rate": 1.91875114972106e-05, | |
| "loss": 2.0147, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3246753246753247, | |
| "grad_norm": 0.7752760648727417, | |
| "learning_rate": 1.820314402779511e-05, | |
| "loss": 1.952, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.3787878787878788, | |
| "grad_norm": 0.8382052779197693, | |
| "learning_rate": 1.6882073502275394e-05, | |
| "loss": 1.8939, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.4329004329004329, | |
| "grad_norm": 0.8314985036849976, | |
| "learning_rate": 1.527852406712072e-05, | |
| "loss": 1.8505, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.487012987012987, | |
| "grad_norm": 1.1022111177444458, | |
| "learning_rate": 1.3458314388150115e-05, | |
| "loss": 1.8473, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.5411255411255411, | |
| "grad_norm": 0.9701792001724243, | |
| "learning_rate": 1.149615608319978e-05, | |
| "loss": 1.7982, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5952380952380952, | |
| "grad_norm": 1.1665358543395996, | |
| "learning_rate": 9.472587138144215e-06, | |
| "loss": 1.751, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.6493506493506493, | |
| "grad_norm": 1.110221266746521, | |
| "learning_rate": 7.470666176083193e-06, | |
| "loss": 1.7613, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.7034632034632035, | |
| "grad_norm": 1.02971351146698, | |
| "learning_rate": 5.572563265434528e-06, | |
| "loss": 1.7219, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.7575757575757576, | |
| "grad_norm": 0.9258909225463867, | |
| "learning_rate": 3.8561871992963585e-06, | |
| "loss": 1.7393, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.8116883116883117, | |
| "grad_norm": 1.0694141387939453, | |
| "learning_rate": 2.3919876814572197e-06, | |
| "loss": 1.6905, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.8658008658008658, | |
| "grad_norm": 0.9484215378761292, | |
| "learning_rate": 1.240063675281934e-06, | |
| "loss": 1.7174, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.9199134199134199, | |
| "grad_norm": 1.0407582521438599, | |
| "learning_rate": 4.4769660505914136e-07, | |
| "loss": 1.7107, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.974025974025974, | |
| "grad_norm": 1.056659460067749, | |
| "learning_rate": 4.740966106764222e-08, | |
| "loss": 1.6829, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 1848, | |
| "total_flos": 3.3575032356864e+16, | |
| "train_loss": 1.8945055998765028, | |
| "train_runtime": 572.07, | |
| "train_samples_per_second": 6.459, | |
| "train_steps_per_second": 3.23 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1848, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.3575032356864e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |