| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.857142857142857, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 6.479386806488037, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 1.0649, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 6.759410858154297, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.1269, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 6.075666427612305, | |
| "learning_rate": 1e-05, | |
| "loss": 1.0829, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 3.0774996280670166, | |
| "learning_rate": 9.966191788709716e-06, | |
| "loss": 1.0606, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 4.653524875640869, | |
| "learning_rate": 9.86522435289912e-06, | |
| "loss": 0.9538, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 5.577620506286621, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 1.0251, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 5.1633076667785645, | |
| "learning_rate": 9.468163201617063e-06, | |
| "loss": 1.0272, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 3.929109811782837, | |
| "learning_rate": 9.177439057064684e-06, | |
| "loss": 0.9807, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 2.3803870677948, | |
| "learning_rate": 8.83022221559489e-06, | |
| "loss": 0.982, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 1.7745165824890137, | |
| "learning_rate": 8.43120818934367e-06, | |
| "loss": 0.9345, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0476190476190477, | |
| "grad_norm": 2.8096415996551514, | |
| "learning_rate": 7.985792958513932e-06, | |
| "loss": 1.3853, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 1.364638090133667, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.8596, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.2380952380952381, | |
| "grad_norm": 1.0391733646392822, | |
| "learning_rate": 6.980398830195785e-06, | |
| "loss": 0.8989, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 1.21762216091156, | |
| "learning_rate": 6.434016163555452e-06, | |
| "loss": 0.9392, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.8405648469924927, | |
| "learning_rate": 5.8682408883346535e-06, | |
| "loss": 0.8405, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 0.7101466655731201, | |
| "learning_rate": 5.290724144552379e-06, | |
| "loss": 0.8446, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.619047619047619, | |
| "grad_norm": 0.6907289028167725, | |
| "learning_rate": 4.7092758554476215e-06, | |
| "loss": 0.8376, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.7423193454742432, | |
| "learning_rate": 4.131759111665349e-06, | |
| "loss": 0.9021, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.8095238095238095, | |
| "grad_norm": 0.6552239656448364, | |
| "learning_rate": 3.5659838364445505e-06, | |
| "loss": 0.8517, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 0.5875532031059265, | |
| "learning_rate": 3.019601169804216e-06, | |
| "loss": 0.8248, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.9198485612869263, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 1.2098, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.0952380952380953, | |
| "grad_norm": 0.5890830755233765, | |
| "learning_rate": 2.0142070414860704e-06, | |
| "loss": 0.8367, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.1904761904761907, | |
| "grad_norm": 0.517128586769104, | |
| "learning_rate": 1.5687918106563326e-06, | |
| "loss": 0.8267, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 0.48176309466362, | |
| "learning_rate": 1.1697777844051105e-06, | |
| "loss": 0.7938, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.380952380952381, | |
| "grad_norm": 0.4960659146308899, | |
| "learning_rate": 8.225609429353187e-07, | |
| "loss": 0.7931, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.4761904761904763, | |
| "grad_norm": 0.48340877890586853, | |
| "learning_rate": 5.318367983829393e-07, | |
| "loss": 0.8292, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 0.425967812538147, | |
| "learning_rate": 3.015368960704584e-07, | |
| "loss": 0.8077, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.45590347051620483, | |
| "learning_rate": 1.3477564710088097e-07, | |
| "loss": 0.8222, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.761904761904762, | |
| "grad_norm": 0.40274062752723694, | |
| "learning_rate": 3.3808211290284886e-08, | |
| "loss": 0.8005, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.4444693326950073, | |
| "learning_rate": 0.0, | |
| "loss": 0.8444, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "step": 30, | |
| "total_flos": 47125239824384.0, | |
| "train_loss": 0.9328994294007619, | |
| "train_runtime": 2233.7765, | |
| "train_samples_per_second": 1.343, | |
| "train_steps_per_second": 0.013 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 47125239824384.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |