| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 63, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.016, | |
| "grad_norm": 2.3387899124656393, | |
| "learning_rate": 0.0, | |
| "loss": 1.1321, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 2.2739175729395282, | |
| "learning_rate": 3.2258064516129035e-07, | |
| "loss": 0.9759, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 3.2333006230979437, | |
| "learning_rate": 6.451612903225807e-07, | |
| "loss": 1.0141, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 2.350357276823565, | |
| "learning_rate": 9.67741935483871e-07, | |
| "loss": 0.9947, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 2.1839271581694755, | |
| "learning_rate": 1.2903225806451614e-06, | |
| "loss": 1.023, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 2.153599307977408, | |
| "learning_rate": 1.6129032258064516e-06, | |
| "loss": 0.9609, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.112, | |
| "grad_norm": 2.1555129140427067, | |
| "learning_rate": 1.935483870967742e-06, | |
| "loss": 0.9622, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 2.008278114649717, | |
| "learning_rate": 2.2580645161290324e-06, | |
| "loss": 0.9711, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.144, | |
| "grad_norm": 1.9242182990110015, | |
| "learning_rate": 2.580645161290323e-06, | |
| "loss": 0.9673, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 1.750252408219067, | |
| "learning_rate": 2.903225806451613e-06, | |
| "loss": 0.9438, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.176, | |
| "grad_norm": 1.6939070396617073, | |
| "learning_rate": 3.225806451612903e-06, | |
| "loss": 0.8756, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 1.2834939133740737, | |
| "learning_rate": 3.548387096774194e-06, | |
| "loss": 0.9823, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.208, | |
| "grad_norm": 1.4367519479529964, | |
| "learning_rate": 3.870967741935484e-06, | |
| "loss": 0.9596, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "grad_norm": 1.3144994907230427, | |
| "learning_rate": 4.193548387096774e-06, | |
| "loss": 1.0521, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 1.0689628463958285, | |
| "learning_rate": 4.516129032258065e-06, | |
| "loss": 0.938, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 1.2021712620582392, | |
| "learning_rate": 4.838709677419355e-06, | |
| "loss": 1.0955, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.272, | |
| "grad_norm": 1.2539951248917753, | |
| "learning_rate": 5.161290322580646e-06, | |
| "loss": 0.9417, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 1.4053233581800462, | |
| "learning_rate": 5.483870967741935e-06, | |
| "loss": 0.9956, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.304, | |
| "grad_norm": 1.0278616263126648, | |
| "learning_rate": 5.806451612903226e-06, | |
| "loss": 0.7439, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 1.256128877382818, | |
| "learning_rate": 6.129032258064517e-06, | |
| "loss": 0.9542, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.336, | |
| "grad_norm": 0.9487549369343321, | |
| "learning_rate": 6.451612903225806e-06, | |
| "loss": 0.9816, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.352, | |
| "grad_norm": 1.0891896971338342, | |
| "learning_rate": 6.774193548387097e-06, | |
| "loss": 1.0704, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.368, | |
| "grad_norm": 1.1660258370107575, | |
| "learning_rate": 7.096774193548388e-06, | |
| "loss": 0.8931, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 0.9415137340919071, | |
| "learning_rate": 7.4193548387096784e-06, | |
| "loss": 0.8683, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.0798354285638785, | |
| "learning_rate": 7.741935483870968e-06, | |
| "loss": 1.0478, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.416, | |
| "grad_norm": 0.8096142802637235, | |
| "learning_rate": 8.064516129032258e-06, | |
| "loss": 0.8466, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.432, | |
| "grad_norm": 0.7447999799600428, | |
| "learning_rate": 8.387096774193549e-06, | |
| "loss": 0.7486, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.448, | |
| "grad_norm": 0.8621800122661538, | |
| "learning_rate": 8.70967741935484e-06, | |
| "loss": 0.9581, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.464, | |
| "grad_norm": 0.7940321530754582, | |
| "learning_rate": 9.03225806451613e-06, | |
| "loss": 0.8867, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.8496750615573763, | |
| "learning_rate": 9.35483870967742e-06, | |
| "loss": 0.9179, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.496, | |
| "grad_norm": 0.8798601594137285, | |
| "learning_rate": 9.67741935483871e-06, | |
| "loss": 0.8834, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.512, | |
| "grad_norm": 0.8818390794513048, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8952, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.528, | |
| "grad_norm": 0.8322934845468171, | |
| "learning_rate": 9.999683023724021e-06, | |
| "loss": 1.029, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.544, | |
| "grad_norm": 0.7007834456821566, | |
| "learning_rate": 9.998732135085665e-06, | |
| "loss": 0.8438, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.6137020406246253, | |
| "learning_rate": 9.99714745464859e-06, | |
| "loss": 0.8435, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 0.7231796555332799, | |
| "learning_rate": 9.994929183335237e-06, | |
| "loss": 0.9646, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.592, | |
| "grad_norm": 0.6180598082755802, | |
| "learning_rate": 9.992077602401358e-06, | |
| "loss": 0.9616, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.608, | |
| "grad_norm": 0.6567886708960547, | |
| "learning_rate": 9.988593073400354e-06, | |
| "loss": 0.8522, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.624, | |
| "grad_norm": 0.7454067800699115, | |
| "learning_rate": 9.984476038137437e-06, | |
| "loss": 0.9052, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.6714316518124167, | |
| "learning_rate": 9.979727018613607e-06, | |
| "loss": 0.8103, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.656, | |
| "grad_norm": 0.6229146249540587, | |
| "learning_rate": 9.974346616959476e-06, | |
| "loss": 0.8401, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "grad_norm": 0.6448840489157996, | |
| "learning_rate": 9.968335515358916e-06, | |
| "loss": 0.9144, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.688, | |
| "grad_norm": 0.528060268374605, | |
| "learning_rate": 9.961694475962562e-06, | |
| "loss": 0.8348, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.704, | |
| "grad_norm": 0.5902102953939741, | |
| "learning_rate": 9.954424340791195e-06, | |
| "loss": 0.7721, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.5526442876969153, | |
| "learning_rate": 9.94652603162896e-06, | |
| "loss": 0.8438, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.736, | |
| "grad_norm": 0.5331236922634145, | |
| "learning_rate": 9.938000549906509e-06, | |
| "loss": 0.8023, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.752, | |
| "grad_norm": 0.6339240906385807, | |
| "learning_rate": 9.92884897657402e-06, | |
| "loss": 0.894, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 0.5283804877111584, | |
| "learning_rate": 9.919072471964146e-06, | |
| "loss": 0.9069, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.784, | |
| "grad_norm": 0.5170169653511614, | |
| "learning_rate": 9.908672275644898e-06, | |
| "loss": 0.8051, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.4763529065504662, | |
| "learning_rate": 9.897649706262474e-06, | |
| "loss": 0.8301, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.816, | |
| "grad_norm": 0.4890239660294139, | |
| "learning_rate": 9.88600616137407e-06, | |
| "loss": 0.8629, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.832, | |
| "grad_norm": 0.37392633165922323, | |
| "learning_rate": 9.873743117270691e-06, | |
| "loss": 0.8343, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.848, | |
| "grad_norm": 0.5097372006252004, | |
| "learning_rate": 9.860862128789954e-06, | |
| "loss": 0.9025, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "grad_norm": 0.5331140780823508, | |
| "learning_rate": 9.847364829118963e-06, | |
| "loss": 0.7832, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.5371583880849503, | |
| "learning_rate": 9.833252929587231e-06, | |
| "loss": 0.7241, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.896, | |
| "grad_norm": 0.45993890737280607, | |
| "learning_rate": 9.818528219449705e-06, | |
| "loss": 0.8964, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.912, | |
| "grad_norm": 0.4715847632418153, | |
| "learning_rate": 9.803192565659898e-06, | |
| "loss": 0.8623, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.928, | |
| "grad_norm": 0.4942244137822645, | |
| "learning_rate": 9.78724791263318e-06, | |
| "loss": 0.7657, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.944, | |
| "grad_norm": 0.45536932211394177, | |
| "learning_rate": 9.770696282000245e-06, | |
| "loss": 0.8766, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.4891485391099054, | |
| "learning_rate": 9.753539772350792e-06, | |
| "loss": 0.8621, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.976, | |
| "grad_norm": 0.45887131278496746, | |
| "learning_rate": 9.735780558967434e-06, | |
| "loss": 0.7718, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.992, | |
| "grad_norm": 0.5002555111850944, | |
| "learning_rate": 9.717420893549902e-06, | |
| "loss": 0.8746, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.5002555111850944, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 0.7591, | |
| "step": 63 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 310, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 12613769428992.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |