| { | |
| "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": 7.42179012298584, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 1.1578, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 7.411426067352295, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.1462, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 6.784687519073486, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1288, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 3.160092830657959, | |
| "learning_rate": 9.966191788709716e-06, | |
| "loss": 0.9638, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 5.82558536529541, | |
| "learning_rate": 9.86522435289912e-06, | |
| "loss": 0.9276, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 6.158791542053223, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 0.9728, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 5.891656398773193, | |
| "learning_rate": 9.468163201617063e-06, | |
| "loss": 0.938, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 3.9759347438812256, | |
| "learning_rate": 9.177439057064684e-06, | |
| "loss": 0.8628, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 3.0468554496765137, | |
| "learning_rate": 8.83022221559489e-06, | |
| "loss": 0.8703, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 2.659231424331665, | |
| "learning_rate": 8.43120818934367e-06, | |
| "loss": 0.8566, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0476190476190477, | |
| "grad_norm": 4.1684370040893555, | |
| "learning_rate": 7.985792958513932e-06, | |
| "loss": 1.2228, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 1.5882718563079834, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.8186, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.2380952380952381, | |
| "grad_norm": 1.6142245531082153, | |
| "learning_rate": 6.980398830195785e-06, | |
| "loss": 0.7946, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 1.916320562362671, | |
| "learning_rate": 6.434016163555452e-06, | |
| "loss": 0.8539, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 1.4405475854873657, | |
| "learning_rate": 5.8682408883346535e-06, | |
| "loss": 0.7039, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 1.19035005569458, | |
| "learning_rate": 5.290724144552379e-06, | |
| "loss": 0.8027, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.619047619047619, | |
| "grad_norm": 0.8802030086517334, | |
| "learning_rate": 4.7092758554476215e-06, | |
| "loss": 0.8275, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 1.3111690282821655, | |
| "learning_rate": 4.131759111665349e-06, | |
| "loss": 0.9132, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.8095238095238095, | |
| "grad_norm": 0.9706297516822815, | |
| "learning_rate": 3.5659838364445505e-06, | |
| "loss": 0.7173, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 0.9016450047492981, | |
| "learning_rate": 3.019601169804216e-06, | |
| "loss": 0.856, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.206610083580017, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 1.0468, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.0952380952380953, | |
| "grad_norm": 0.7914609313011169, | |
| "learning_rate": 2.0142070414860704e-06, | |
| "loss": 0.7511, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.1904761904761907, | |
| "grad_norm": 0.8105864524841309, | |
| "learning_rate": 1.5687918106563326e-06, | |
| "loss": 0.6867, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 0.726883590221405, | |
| "learning_rate": 1.1697777844051105e-06, | |
| "loss": 0.7336, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.380952380952381, | |
| "grad_norm": 0.621177613735199, | |
| "learning_rate": 8.225609429353187e-07, | |
| "loss": 0.8412, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.4761904761904763, | |
| "grad_norm": 0.5684846639633179, | |
| "learning_rate": 5.318367983829393e-07, | |
| "loss": 0.7218, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 0.5559888482093811, | |
| "learning_rate": 3.015368960704584e-07, | |
| "loss": 0.7787, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.5531514883041382, | |
| "learning_rate": 1.3477564710088097e-07, | |
| "loss": 0.8023, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.761904761904762, | |
| "grad_norm": 0.5628388524055481, | |
| "learning_rate": 3.3808211290284886e-08, | |
| "loss": 0.7005, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.5193307399749756, | |
| "learning_rate": 0.0, | |
| "loss": 0.7909, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "step": 30, | |
| "total_flos": 18265262981120.0, | |
| "train_loss": 0.872953059275945, | |
| "train_runtime": 1426.5748, | |
| "train_samples_per_second": 2.103, | |
| "train_steps_per_second": 0.021 | |
| } | |
| ], | |
| "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": 18265262981120.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |