| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 24.0, | |
| "eval_steps": 500, | |
| "global_step": 192, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.29974979162216187, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 3.4405, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.3932454288005829, | |
| "learning_rate": 0.0001968583161128631, | |
| "loss": 3.3216, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "grad_norm": 0.42628756165504456, | |
| "learning_rate": 0.00019297764858882514, | |
| "loss": 3.1985, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.44253304600715637, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 3.0415, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "grad_norm": 0.4085797071456909, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.8932, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "grad_norm": 0.4421256184577942, | |
| "learning_rate": 0.00017289686274214118, | |
| "loss": 2.755, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "grad_norm": 0.44413742423057556, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 2.6121, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.4906141757965088, | |
| "learning_rate": 0.00015358267949789966, | |
| "loss": 2.4968, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "grad_norm": 0.4448947012424469, | |
| "learning_rate": 0.00014257792915650728, | |
| "loss": 2.3734, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "grad_norm": 0.40546461939811707, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.2633, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "grad_norm": 0.4101080000400543, | |
| "learning_rate": 0.00011873813145857249, | |
| "loss": 2.2142, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "grad_norm": 0.6073424220085144, | |
| "learning_rate": 0.00010627905195293135, | |
| "loss": 2.1403, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 16.25, | |
| "grad_norm": 0.3520808815956116, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 2.1088, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "grad_norm": 0.37706121802330017, | |
| "learning_rate": 8.126186854142752e-05, | |
| "loss": 2.1054, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "grad_norm": 0.3702649474143982, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 2.0671, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.47354856133461, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 2.0506, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 21.25, | |
| "grad_norm": 0.35600489377975464, | |
| "learning_rate": 4.6417320502100316e-05, | |
| "loss": 2.0311, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "grad_norm": 0.3341175317764282, | |
| "learning_rate": 3.6257601025131026e-05, | |
| "loss": 2.0347, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 23.75, | |
| "grad_norm": 0.3715374171733856, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 2.0274, | |
| "step": 190 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 32, | |
| "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": 337394471436288.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |