| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 612, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.032679738562091505, | |
| "grad_norm": 5.336216449737549, | |
| "learning_rate": 3.2520325203252037e-06, | |
| "loss": 1.4653, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06535947712418301, | |
| "grad_norm": 4.05853796005249, | |
| "learning_rate": 6.504065040650407e-06, | |
| "loss": 1.2502, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09803921568627451, | |
| "grad_norm": 4.095743656158447, | |
| "learning_rate": 9.756097560975611e-06, | |
| "loss": 1.1818, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.13071895424836602, | |
| "grad_norm": 4.049984931945801, | |
| "learning_rate": 1.3008130081300815e-05, | |
| "loss": 1.1616, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.16339869281045752, | |
| "grad_norm": 4.275440216064453, | |
| "learning_rate": 1.6260162601626018e-05, | |
| "loss": 1.1681, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.19607843137254902, | |
| "grad_norm": 3.7174243927001953, | |
| "learning_rate": 1.9512195121951222e-05, | |
| "loss": 1.1263, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.22875816993464052, | |
| "grad_norm": 3.68149471282959, | |
| "learning_rate": 1.9940417581113062e-05, | |
| "loss": 1.1764, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.26143790849673204, | |
| "grad_norm": 3.664177656173706, | |
| "learning_rate": 1.9718803741191918e-05, | |
| "loss": 1.1296, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.29411764705882354, | |
| "grad_norm": 3.219787120819092, | |
| "learning_rate": 1.9336954955188042e-05, | |
| "loss": 1.1026, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.32679738562091504, | |
| "grad_norm": 3.5025317668914795, | |
| "learning_rate": 1.880116680445757e-05, | |
| "loss": 1.1542, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.35947712418300654, | |
| "grad_norm": 3.2319493293762207, | |
| "learning_rate": 1.812027288495843e-05, | |
| "loss": 1.1492, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.39215686274509803, | |
| "grad_norm": 2.933061122894287, | |
| "learning_rate": 1.730549916681868e-05, | |
| "loss": 1.1107, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.42483660130718953, | |
| "grad_norm": 3.0482289791107178, | |
| "learning_rate": 1.6370278910578644e-05, | |
| "loss": 1.1077, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.45751633986928103, | |
| "grad_norm": 3.3377017974853516, | |
| "learning_rate": 1.5330031191602395e-05, | |
| "loss": 1.1246, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.49019607843137253, | |
| "grad_norm": 3.618112564086914, | |
| "learning_rate": 1.420190668415002e-05, | |
| "loss": 1.101, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5228758169934641, | |
| "grad_norm": 3.0649290084838867, | |
| "learning_rate": 1.3004504896395564e-05, | |
| "loss": 1.0556, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 3.0544955730438232, | |
| "learning_rate": 1.1757567518366883e-05, | |
| "loss": 1.0287, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 2.709897994995117, | |
| "learning_rate": 1.0481652938612374e-05, | |
| "loss": 1.0145, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.6209150326797386, | |
| "grad_norm": 2.6121253967285156, | |
| "learning_rate": 9.197797295872709e-06, | |
| "loss": 1.0179, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.6535947712418301, | |
| "grad_norm": 3.049081563949585, | |
| "learning_rate": 7.927167654034622e-06, | |
| "loss": 0.9818, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6862745098039216, | |
| "grad_norm": 3.008591413497925, | |
| "learning_rate": 6.690713018507917e-06, | |
| "loss": 0.9431, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.7189542483660131, | |
| "grad_norm": 3.0657355785369873, | |
| "learning_rate": 5.508818947755687e-06, | |
| "loss": 0.9978, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.7516339869281046, | |
| "grad_norm": 2.533656597137451, | |
| "learning_rate": 4.4009714544339755e-06, | |
| "loss": 0.9494, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.7843137254901961, | |
| "grad_norm": 2.7470057010650635, | |
| "learning_rate": 3.3854357374383905e-06, | |
| "loss": 0.962, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.8169934640522876, | |
| "grad_norm": 2.5096466541290283, | |
| "learning_rate": 2.478955041636435e-06, | |
| "loss": 0.9592, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8496732026143791, | |
| "grad_norm": 2.438676357269287, | |
| "learning_rate": 1.6964746102169582e-06, | |
| "loss": 0.9327, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.8823529411764706, | |
| "grad_norm": 2.47017240524292, | |
| "learning_rate": 1.0508952808836682e-06, | |
| "loss": 0.9249, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.9150326797385621, | |
| "grad_norm": 2.9075846672058105, | |
| "learning_rate": 5.528607883782599e-07, | |
| "loss": 0.9466, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.9477124183006536, | |
| "grad_norm": 2.7440707683563232, | |
| "learning_rate": 2.1058228009902094e-07, | |
| "loss": 0.9481, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.9803921568627451, | |
| "grad_norm": 2.9985830783843994, | |
| "learning_rate": 2.9702938044468e-08, | |
| "loss": 0.951, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 612, | |
| "total_flos": 16017543659520.0, | |
| "train_loss": 1.0669627922033174, | |
| "train_runtime": 18486.1158, | |
| "train_samples_per_second": 0.132, | |
| "train_steps_per_second": 0.033 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 612, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 16017543659520.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |