| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 48, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 0.04137394207755112, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1671, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 0.037803193435615265, | |
| "learning_rate": 2e-05, | |
| "loss": 0.167, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 0.04445740088277594, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1607, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.0380231527607073, | |
| "learning_rate": 4e-05, | |
| "loss": 0.1591, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 0.046362646963448, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1597, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 0.05235320825077946, | |
| "learning_rate": 4.9933307091588796e-05, | |
| "loss": 0.1616, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4375, | |
| "grad_norm": 0.05740591760676448, | |
| "learning_rate": 4.973358420187776e-05, | |
| "loss": 0.1459, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.04283964782544257, | |
| "learning_rate": 4.9401896938898185e-05, | |
| "loss": 0.1332, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5625, | |
| "grad_norm": 0.036679242954440874, | |
| "learning_rate": 4.894001499771015e-05, | |
| "loss": 0.1293, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 0.033723367633845105, | |
| "learning_rate": 4.83504027183137e-05, | |
| "loss": 0.1342, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6875, | |
| "grad_norm": 0.037227526954279944, | |
| "learning_rate": 4.763620593732867e-05, | |
| "loss": 0.128, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.044207038446114774, | |
| "learning_rate": 4.6801235203595195e-05, | |
| "loss": 0.1275, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8125, | |
| "grad_norm": 0.04394682449442954, | |
| "learning_rate": 4.584994544724695e-05, | |
| "loss": 0.1142, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.875, | |
| "grad_norm": 0.03406265181060845, | |
| "learning_rate": 4.478741221073136e-05, | |
| "loss": 0.1161, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9375, | |
| "grad_norm": 0.030054446617056498, | |
| "learning_rate": 4.361930456859455e-05, | |
| "loss": 0.1087, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.028409394434840918, | |
| "learning_rate": 4.235185488051585e-05, | |
| "loss": 0.1126, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0625, | |
| "grad_norm": 0.023153227915814832, | |
| "learning_rate": 4.099182553897229e-05, | |
| "loss": 0.1054, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.125, | |
| "grad_norm": 0.021598055829915037, | |
| "learning_rate": 3.954647288894883e-05, | |
| "loss": 0.1007, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1875, | |
| "grad_norm": 0.02123540151753295, | |
| "learning_rate": 3.8023508512198256e-05, | |
| "loss": 0.1001, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.02137306513970009, | |
| "learning_rate": 3.6431058082615964e-05, | |
| "loss": 0.0968, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.3125, | |
| "grad_norm": 0.02433397130782817, | |
| "learning_rate": 3.47776180122539e-05, | |
| "loss": 0.0983, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.375, | |
| "grad_norm": 0.021942525621062504, | |
| "learning_rate": 3.307201011928616e-05, | |
| "loss": 0.0935, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4375, | |
| "grad_norm": 0.021261141593508576, | |
| "learning_rate": 3.132333455979202e-05, | |
| "loss": 0.0887, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.02142792591828939, | |
| "learning_rate": 2.954092127448591e-05, | |
| "loss": 0.0888, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5625, | |
| "grad_norm": 0.020750630946201602, | |
| "learning_rate": 2.7734280209446865e-05, | |
| "loss": 0.0891, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.625, | |
| "grad_norm": 0.019872557078390127, | |
| "learning_rate": 2.5913050576441477e-05, | |
| "loss": 0.0872, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6875, | |
| "grad_norm": 0.019131650653635524, | |
| "learning_rate": 2.4086949423558526e-05, | |
| "loss": 0.0835, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.019027351901529727, | |
| "learning_rate": 2.2265719790553147e-05, | |
| "loss": 0.0827, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.8125, | |
| "grad_norm": 0.019517019388363612, | |
| "learning_rate": 2.0459078725514092e-05, | |
| "loss": 0.0769, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.875, | |
| "grad_norm": 0.019073963774100196, | |
| "learning_rate": 1.867666544020798e-05, | |
| "loss": 0.0768, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.9375, | |
| "grad_norm": 0.020535779704439937, | |
| "learning_rate": 1.692798988071385e-05, | |
| "loss": 0.0703, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.01735083491599702, | |
| "learning_rate": 1.5222381987746104e-05, | |
| "loss": 0.0721, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0625, | |
| "grad_norm": 0.016996572618955864, | |
| "learning_rate": 1.3568941917384036e-05, | |
| "loss": 0.0729, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.125, | |
| "grad_norm": 0.016947999154191592, | |
| "learning_rate": 1.1976491487801748e-05, | |
| "loss": 0.0683, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.1875, | |
| "grad_norm": 0.01759855889883996, | |
| "learning_rate": 1.0453527111051184e-05, | |
| "loss": 0.0682, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 0.016563435997106427, | |
| "learning_rate": 9.008174461027724e-06, | |
| "loss": 0.0701, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.3125, | |
| "grad_norm": 0.0154902825546126, | |
| "learning_rate": 7.648145119484152e-06, | |
| "loss": 0.0673, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.375, | |
| "grad_norm": 0.01691672911978778, | |
| "learning_rate": 6.380695431405453e-06, | |
| "loss": 0.0694, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.4375, | |
| "grad_norm": 0.01530029785885113, | |
| "learning_rate": 5.2125877892686496e-06, | |
| "loss": 0.0681, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.017885100797614902, | |
| "learning_rate": 4.150054552753055e-06, | |
| "loss": 0.0627, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.5625, | |
| "grad_norm": 0.016638045960609936, | |
| "learning_rate": 3.198764796404807e-06, | |
| "loss": 0.0669, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.625, | |
| "grad_norm": 0.016208072151038286, | |
| "learning_rate": 2.3637940626713346e-06, | |
| "loss": 0.0678, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.6875, | |
| "grad_norm": 0.016401199651084344, | |
| "learning_rate": 1.649597281686302e-06, | |
| "loss": 0.0649, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "grad_norm": 0.01598951472231698, | |
| "learning_rate": 1.0599850022898539e-06, | |
| "loss": 0.0674, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.8125, | |
| "grad_norm": 0.015277414785260311, | |
| "learning_rate": 5.981030611018234e-07, | |
| "loss": 0.0634, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.875, | |
| "grad_norm": 0.01537912920538106, | |
| "learning_rate": 2.664157981222437e-07, | |
| "loss": 0.0637, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.9375, | |
| "grad_norm": 0.015282877713047758, | |
| "learning_rate": 6.66929084112089e-08, | |
| "loss": 0.0667, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.01629157768683682, | |
| "learning_rate": 0.0, | |
| "loss": 0.0622, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 48, | |
| "total_flos": 882865236606976.0, | |
| "train_loss": 0.0980342753076305, | |
| "train_runtime": 1550.4315, | |
| "train_samples_per_second": 0.484, | |
| "train_steps_per_second": 0.031 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 48, | |
| "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": 882865236606976.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |