| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0361990950226245, | |
| "eval_steps": 500, | |
| "global_step": 28, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03619909502262444, | |
| "grad_norm": 2.867363214492798, | |
| "learning_rate": 3.7037037037037036e-07, | |
| "loss": 0.7721, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07239819004524888, | |
| "grad_norm": 2.795196771621704, | |
| "learning_rate": 7.407407407407407e-07, | |
| "loss": 0.7534, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1085972850678733, | |
| "grad_norm": 2.8518760204315186, | |
| "learning_rate": 1.111111111111111e-06, | |
| "loss": 0.7531, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14479638009049775, | |
| "grad_norm": 2.7276031970977783, | |
| "learning_rate": 1.4814814814814815e-06, | |
| "loss": 0.7604, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.18099547511312217, | |
| "grad_norm": 2.6922106742858887, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.7775, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2171945701357466, | |
| "grad_norm": 2.8505051136016846, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 0.7689, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.25339366515837103, | |
| "grad_norm": 2.711665153503418, | |
| "learning_rate": 2.5925925925925925e-06, | |
| "loss": 0.7687, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2895927601809955, | |
| "grad_norm": 2.7716190814971924, | |
| "learning_rate": 2.962962962962963e-06, | |
| "loss": 0.769, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3257918552036199, | |
| "grad_norm": 2.607780933380127, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.7674, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.36199095022624433, | |
| "grad_norm": 2.305697202682495, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.7529, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.39819004524886875, | |
| "grad_norm": 1.5863313674926758, | |
| "learning_rate": 4.074074074074074e-06, | |
| "loss": 0.7259, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4343891402714932, | |
| "grad_norm": 1.2682443857192993, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 0.7206, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 1.010533332824707, | |
| "learning_rate": 4.814814814814815e-06, | |
| "loss": 0.6921, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5067873303167421, | |
| "grad_norm": 0.9136636257171631, | |
| "learning_rate": 5.185185185185185e-06, | |
| "loss": 0.6987, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5429864253393665, | |
| "grad_norm": 1.275439739227295, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 0.6997, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.579185520361991, | |
| "grad_norm": 1.4839826822280884, | |
| "learning_rate": 5.925925925925926e-06, | |
| "loss": 0.6773, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 1.5695866346359253, | |
| "learning_rate": 6.296296296296297e-06, | |
| "loss": 0.6582, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6515837104072398, | |
| "grad_norm": 1.6517796516418457, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.6912, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6877828054298643, | |
| "grad_norm": 1.3464380502700806, | |
| "learning_rate": 7.0370370370370375e-06, | |
| "loss": 0.6636, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7239819004524887, | |
| "grad_norm": 1.0865730047225952, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.6571, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7601809954751131, | |
| "grad_norm": 0.8862206339836121, | |
| "learning_rate": 7.77777777777778e-06, | |
| "loss": 0.6583, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7963800904977375, | |
| "grad_norm": 0.9783180952072144, | |
| "learning_rate": 8.148148148148148e-06, | |
| "loss": 0.6688, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.832579185520362, | |
| "grad_norm": 0.7160141468048096, | |
| "learning_rate": 8.518518518518519e-06, | |
| "loss": 0.6408, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8687782805429864, | |
| "grad_norm": 0.6991405487060547, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 0.6447, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9049773755656109, | |
| "grad_norm": 0.7763178944587708, | |
| "learning_rate": 9.25925925925926e-06, | |
| "loss": 0.6512, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.5905259847640991, | |
| "learning_rate": 9.62962962962963e-06, | |
| "loss": 0.6337, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9773755656108597, | |
| "grad_norm": 0.7515297532081604, | |
| "learning_rate": 1e-05, | |
| "loss": 0.655, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0361990950226245, | |
| "grad_norm": 1.260597825050354, | |
| "learning_rate": 9.999582149277188e-06, | |
| "loss": 1.2675, | |
| "step": 28 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 270, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 28, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 35571485245440.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |