| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 130, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007692307692307693, | |
| "grad_norm": 1824.0493249890733, | |
| "learning_rate": 1.5384615384615387e-06, | |
| "loss": 28.7448, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.038461538461538464, | |
| "grad_norm": 338.1051064004804, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 21.1097, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07692307692307693, | |
| "grad_norm": 60.27893910460336, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 13.8645, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11538461538461539, | |
| "grad_norm": 19.31150319920863, | |
| "learning_rate": 1.9985583705641418e-05, | |
| "loss": 5.697, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 69.03270795451746, | |
| "learning_rate": 1.9823877374156647e-05, | |
| "loss": 2.3869, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19230769230769232, | |
| "grad_norm": 76.45052582249555, | |
| "learning_rate": 1.9485364419471454e-05, | |
| "loss": 1.7302, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23076923076923078, | |
| "grad_norm": 18.876039351066055, | |
| "learning_rate": 1.8976137276390145e-05, | |
| "loss": 1.5732, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2692307692307692, | |
| "grad_norm": 23.947629924642698, | |
| "learning_rate": 1.8305360832480118e-05, | |
| "loss": 1.3462, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 24.85999234906976, | |
| "learning_rate": 1.7485107481711014e-05, | |
| "loss": 1.2076, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.34615384615384615, | |
| "grad_norm": 16.833283516923675, | |
| "learning_rate": 1.653013984983585e-05, | |
| "loss": 1.1067, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 5.260723361500702, | |
| "learning_rate": 1.5457645101945046e-05, | |
| "loss": 1.0689, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4230769230769231, | |
| "grad_norm": 8.067805674932265, | |
| "learning_rate": 1.4286925614030542e-05, | |
| "loss": 1.0097, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 14.86263828160759, | |
| "learning_rate": 1.303905157574247e-05, | |
| "loss": 0.978, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 6.459278631918247, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.9093, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5384615384615384, | |
| "grad_norm": 2.9078399705453846, | |
| "learning_rate": 1.0402659401094154e-05, | |
| "loss": 0.8944, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5769230769230769, | |
| "grad_norm": 7.660903004613179, | |
| "learning_rate": 9.061590105968208e-06, | |
| "loss": 0.8973, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 5.302988730231839, | |
| "learning_rate": 7.73740997570278e-06, | |
| "loss": 0.8763, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6538461538461539, | |
| "grad_norm": 4.5745469835172825, | |
| "learning_rate": 6.453951129574644e-06, | |
| "loss": 0.85, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6923076923076923, | |
| "grad_norm": 2.9833461950622047, | |
| "learning_rate": 5.234312799786921e-06, | |
| "loss": 0.8283, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7307692307692307, | |
| "grad_norm": 1.3718638590118337, | |
| "learning_rate": 4.100445599768774e-06, | |
| "loss": 0.8142, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 1.0682148259587978, | |
| "learning_rate": 3.0727564649040066e-06, | |
| "loss": 0.8049, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8076923076923077, | |
| "grad_norm": 0.9650280690913742, | |
| "learning_rate": 2.1697413758237785e-06, | |
| "loss": 0.8029, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.8461538461538461, | |
| "grad_norm": 1.0735752809829815, | |
| "learning_rate": 1.407652474377832e-06, | |
| "loss": 0.793, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8846153846153846, | |
| "grad_norm": 0.7668233578378257, | |
| "learning_rate": 8.002055634117578e-07, | |
| "loss": 0.7941, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 0.9841012840352416, | |
| "learning_rate": 3.5833325466437697e-07, | |
| "loss": 0.7823, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9615384615384616, | |
| "grad_norm": 0.7158242209277041, | |
| "learning_rate": 8.99882075409153e-08, | |
| "loss": 0.776, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.8276248743240251, | |
| "learning_rate": 0.0, | |
| "loss": 0.7805, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.284010648727417, | |
| "eval_runtime": 0.4599, | |
| "eval_samples_per_second": 26.092, | |
| "eval_steps_per_second": 2.174, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 130, | |
| "total_flos": 17867533713408.0, | |
| "train_loss": 2.5464949974646935, | |
| "train_runtime": 907.3672, | |
| "train_samples_per_second": 36.642, | |
| "train_steps_per_second": 0.143 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 130, | |
| "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": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 17867533713408.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |