| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3913894324853229, | |
| "eval_steps": 100, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.019569471624266144, | |
| "grad_norm": 0.6461917161941528, | |
| "learning_rate": 2.5974025974025972e-05, | |
| "loss": 1.9953, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03913894324853229, | |
| "grad_norm": 0.35114091634750366, | |
| "learning_rate": 5.1948051948051944e-05, | |
| "loss": 1.923, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05870841487279843, | |
| "grad_norm": 0.41224125027656555, | |
| "learning_rate": 7.792207792207793e-05, | |
| "loss": 1.8037, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07827788649706457, | |
| "grad_norm": 0.4727496802806854, | |
| "learning_rate": 0.00010389610389610389, | |
| "loss": 1.597, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09784735812133072, | |
| "grad_norm": 0.5965492129325867, | |
| "learning_rate": 0.00012987012987012987, | |
| "loss": 1.3375, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11741682974559686, | |
| "grad_norm": 0.820002555847168, | |
| "learning_rate": 0.00015584415584415587, | |
| "loss": 1.0652, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.136986301369863, | |
| "grad_norm": 0.6552278399467468, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 0.7861, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.15655577299412915, | |
| "grad_norm": 0.7231012582778931, | |
| "learning_rate": 0.0001999979049808708, | |
| "loss": 0.7016, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1761252446183953, | |
| "grad_norm": 0.723237156867981, | |
| "learning_rate": 0.00019996066263830531, | |
| "loss": 0.5777, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.19569471624266144, | |
| "grad_norm": 0.5118690729141235, | |
| "learning_rate": 0.00019987688427197897, | |
| "loss": 0.5553, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.19569471624266144, | |
| "eval_loss": 0.5386264324188232, | |
| "eval_runtime": 2488.1393, | |
| "eval_samples_per_second": 0.083, | |
| "eval_steps_per_second": 0.083, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.21526418786692758, | |
| "grad_norm": 0.650175929069519, | |
| "learning_rate": 0.0001997466088843548, | |
| "loss": 0.5231, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.23483365949119372, | |
| "grad_norm": 0.4600216746330261, | |
| "learning_rate": 0.00019956989712427577, | |
| "loss": 0.4945, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.25440313111545987, | |
| "grad_norm": 0.5527154207229614, | |
| "learning_rate": 0.0001993468312587303, | |
| "loss": 0.4671, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 0.46538111567497253, | |
| "learning_rate": 0.00019907751513455302, | |
| "loss": 0.5276, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.29354207436399216, | |
| "grad_norm": 0.4237975776195526, | |
| "learning_rate": 0.00019876207413008015, | |
| "loss": 0.5122, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3131115459882583, | |
| "grad_norm": 0.40869906544685364, | |
| "learning_rate": 0.00019840065509677988, | |
| "loss": 0.4781, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.33268101761252444, | |
| "grad_norm": 0.47258374094963074, | |
| "learning_rate": 0.00019799342629088702, | |
| "loss": 0.5291, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3522504892367906, | |
| "grad_norm": 1.2339996099472046, | |
| "learning_rate": 0.00019754057729507227, | |
| "loss": 0.483, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.37181996086105673, | |
| "grad_norm": 0.32413920760154724, | |
| "learning_rate": 0.0001970423189301833, | |
| "loss": 0.4802, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3913894324853229, | |
| "grad_norm": 0.3887979984283447, | |
| "learning_rate": 0.00019649888315709843, | |
| "loss": 0.5053, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3913894324853229, | |
| "eval_loss": 0.47472819685935974, | |
| "eval_runtime": 2489.5517, | |
| "eval_samples_per_second": 0.083, | |
| "eval_steps_per_second": 0.083, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1533, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.4803114049536e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |