| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 222, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06756756756756757, | |
| "grad_norm": 4.342727472957683, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 1.4014, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13513513513513514, | |
| "grad_norm": 1.9245249962075524, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.2016, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.20270270270270271, | |
| "grad_norm": 1.7936102622454382, | |
| "learning_rate": 4.9977343997179584e-05, | |
| "loss": 1.1028, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2702702702702703, | |
| "grad_norm": 1.6381519278495207, | |
| "learning_rate": 4.983905584269134e-05, | |
| "loss": 1.0613, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.33783783783783783, | |
| "grad_norm": 1.7385769477746682, | |
| "learning_rate": 4.957583862636889e-05, | |
| "loss": 1.011, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.40540540540540543, | |
| "grad_norm": 1.2152636926156932, | |
| "learning_rate": 4.91891643656567e-05, | |
| "loss": 0.9977, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.47297297297297297, | |
| "grad_norm": 1.0928685802601366, | |
| "learning_rate": 4.8681195499870324e-05, | |
| "loss": 0.9886, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5405405405405406, | |
| "grad_norm": 1.0178064646987002, | |
| "learning_rate": 4.805477279695852e-05, | |
| "loss": 0.9873, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6081081081081081, | |
| "grad_norm": 1.1614328285281477, | |
| "learning_rate": 4.731339946677661e-05, | |
| "loss": 0.9666, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6756756756756757, | |
| "grad_norm": 1.0722676077355953, | |
| "learning_rate": 4.6461221569715884e-05, | |
| "loss": 0.9563, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7432432432432432, | |
| "grad_norm": 1.0922390725949371, | |
| "learning_rate": 4.5503004830252146e-05, | |
| "loss": 0.9605, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.8108108108108109, | |
| "grad_norm": 0.9343071897805195, | |
| "learning_rate": 4.444410798508125e-05, | |
| "loss": 0.9439, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8783783783783784, | |
| "grad_norm": 1.0227180607983488, | |
| "learning_rate": 4.329045281488981e-05, | |
| "loss": 0.954, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.9459459459459459, | |
| "grad_norm": 1.0480562117426948, | |
| "learning_rate": 4.204849102735549e-05, | |
| "loss": 0.9431, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0135135135135136, | |
| "grad_norm": 1.260684025254624, | |
| "learning_rate": 4.072516817658065e-05, | |
| "loss": 0.8981, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.0810810810810811, | |
| "grad_norm": 1.2734241934034851, | |
| "learning_rate": 3.932788482073635e-05, | |
| "loss": 0.7769, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.1486486486486487, | |
| "grad_norm": 1.0349542653830326, | |
| "learning_rate": 3.7864455135139235e-05, | |
| "loss": 0.7436, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.2162162162162162, | |
| "grad_norm": 1.162846414767005, | |
| "learning_rate": 3.634306321221328e-05, | |
| "loss": 0.7334, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.2837837837837838, | |
| "grad_norm": 0.9484666330021186, | |
| "learning_rate": 3.477221729272535e-05, | |
| "loss": 0.7354, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.3513513513513513, | |
| "grad_norm": 1.0093923977732242, | |
| "learning_rate": 3.3160702184251446e-05, | |
| "loss": 0.7396, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.4189189189189189, | |
| "grad_norm": 1.4554684574123584, | |
| "learning_rate": 3.1517530132969326e-05, | |
| "loss": 0.7398, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.4864864864864864, | |
| "grad_norm": 1.0436919964803422, | |
| "learning_rate": 2.9851890423522204e-05, | |
| "loss": 0.7331, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.554054054054054, | |
| "grad_norm": 0.9599205426194947, | |
| "learning_rate": 2.817309798881147e-05, | |
| "loss": 0.7389, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.6216216216216215, | |
| "grad_norm": 1.029306388388882, | |
| "learning_rate": 2.6490541317113427e-05, | |
| "loss": 0.738, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.689189189189189, | |
| "grad_norm": 0.90932400154707, | |
| "learning_rate": 2.4813629947844506e-05, | |
| "loss": 0.7197, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.7567567567567568, | |
| "grad_norm": 0.9566950138674355, | |
| "learning_rate": 2.3151741849600056e-05, | |
| "loss": 0.7328, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.8243243243243243, | |
| "grad_norm": 0.9091162829255143, | |
| "learning_rate": 2.1514170974749814e-05, | |
| "loss": 0.7242, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.8918918918918919, | |
| "grad_norm": 0.9596574663856378, | |
| "learning_rate": 1.9910075283886327e-05, | |
| "loss": 0.7121, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.9594594594594594, | |
| "grad_norm": 0.9385673192651813, | |
| "learning_rate": 1.83484255307945e-05, | |
| "loss": 0.7139, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.027027027027027, | |
| "grad_norm": 1.2741421717094357, | |
| "learning_rate": 1.6837955094357533e-05, | |
| "loss": 0.6495, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.0945945945945947, | |
| "grad_norm": 1.2778194000575294, | |
| "learning_rate": 1.5387111137959655e-05, | |
| "loss": 0.5209, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.1621621621621623, | |
| "grad_norm": 1.0741954333178305, | |
| "learning_rate": 1.4004007369521943e-05, | |
| "loss": 0.5025, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.22972972972973, | |
| "grad_norm": 1.0388700441919239, | |
| "learning_rate": 1.2696378666356468e-05, | |
| "loss": 0.4995, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.2972972972972974, | |
| "grad_norm": 1.069711625718764, | |
| "learning_rate": 1.1471537818594746e-05, | |
| "loss": 0.4898, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.364864864864865, | |
| "grad_norm": 1.0378436021827815, | |
| "learning_rate": 1.0336334633099004e-05, | |
| "loss": 0.4871, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.4324324324324325, | |
| "grad_norm": 1.011148209204576, | |
| "learning_rate": 9.297117626563687e-06, | |
| "loss": 0.4927, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 1.0374664447281305, | |
| "learning_rate": 8.359698522034862e-06, | |
| "loss": 0.4984, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.5675675675675675, | |
| "grad_norm": 1.0825482045121846, | |
| "learning_rate": 7.529319747397534e-06, | |
| "loss": 0.4902, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.635135135135135, | |
| "grad_norm": 0.9962173915083111, | |
| "learning_rate": 6.810625117592363e-06, | |
| "loss": 0.4911, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.7027027027027026, | |
| "grad_norm": 1.0469170187864207, | |
| "learning_rate": 6.207633864518805e-06, | |
| "loss": 0.4924, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.77027027027027, | |
| "grad_norm": 1.0230082490963024, | |
| "learning_rate": 5.7237181598600055e-06, | |
| "loss": 0.488, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.8378378378378377, | |
| "grad_norm": 1.0056019590225027, | |
| "learning_rate": 5.361584256530833e-06, | |
| "loss": 0.4896, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.9054054054054053, | |
| "grad_norm": 1.0635035438923603, | |
| "learning_rate": 5.123257354213851e-06, | |
| "loss": 0.4938, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.972972972972973, | |
| "grad_norm": 1.0018745751299392, | |
| "learning_rate": 5.010070273621176e-06, | |
| "loss": 0.4854, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 222, | |
| "total_flos": 432075581161472.0, | |
| "train_loss": 0.7525977000996873, | |
| "train_runtime": 5814.3184, | |
| "train_samples_per_second": 4.881, | |
| "train_steps_per_second": 0.038 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 222, | |
| "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": 432075581161472.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |