| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.5161290322580645, | |
| "eval_steps": 500, | |
| "global_step": 28, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12903225806451613, | |
| "grad_norm": 2.0922131538391113, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.6097, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 2.037680149078369, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.5815, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.3870967741935484, | |
| "grad_norm": 1.9914177656173706, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5731, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 1.7522591352462769, | |
| "learning_rate": 9.960573506572391e-06, | |
| "loss": 0.5499, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "grad_norm": 1.2676565647125244, | |
| "learning_rate": 9.842915805643156e-06, | |
| "loss": 0.5117, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.7741935483870968, | |
| "grad_norm": 0.952801525592804, | |
| "learning_rate": 9.648882429441258e-06, | |
| "loss": 0.4997, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.9032258064516129, | |
| "grad_norm": 1.187522053718567, | |
| "learning_rate": 9.381533400219319e-06, | |
| "loss": 0.5062, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.187522053718567, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 0.4698, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.129032258064516, | |
| "grad_norm": 1.5576032400131226, | |
| "learning_rate": 8.644843137107058e-06, | |
| "loss": 0.4722, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.2580645161290323, | |
| "grad_norm": 1.07254958152771, | |
| "learning_rate": 8.18711994874345e-06, | |
| "loss": 0.4426, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.3870967741935485, | |
| "grad_norm": 0.8922549486160278, | |
| "learning_rate": 7.679133974894984e-06, | |
| "loss": 0.4364, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.5161290322580645, | |
| "grad_norm": 0.7638566493988037, | |
| "learning_rate": 7.128896457825364e-06, | |
| "loss": 0.417, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.6451612903225805, | |
| "grad_norm": 0.6911720633506775, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 0.4195, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.7741935483870968, | |
| "grad_norm": 0.6178150177001953, | |
| "learning_rate": 5.936906572928625e-06, | |
| "loss": 0.4147, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.903225806451613, | |
| "grad_norm": 0.46914201974868774, | |
| "learning_rate": 5.3139525976465675e-06, | |
| "loss": 0.4204, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.37992069125175476, | |
| "learning_rate": 4.686047402353433e-06, | |
| "loss": 0.3935, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.129032258064516, | |
| "grad_norm": 0.4508312940597534, | |
| "learning_rate": 4.063093427071376e-06, | |
| "loss": 0.3939, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.258064516129032, | |
| "grad_norm": 0.3774235248565674, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 0.3945, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.3870967741935485, | |
| "grad_norm": 0.3686850368976593, | |
| "learning_rate": 2.871103542174637e-06, | |
| "loss": 0.3761, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.5161290322580645, | |
| "grad_norm": 0.3773055672645569, | |
| "learning_rate": 2.320866025105016e-06, | |
| "loss": 0.3804, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.6451612903225805, | |
| "grad_norm": 0.33530160784721375, | |
| "learning_rate": 1.8128800512565514e-06, | |
| "loss": 0.3861, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.774193548387097, | |
| "grad_norm": 0.3947732448577881, | |
| "learning_rate": 1.3551568628929434e-06, | |
| "loss": 0.3731, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.903225806451613, | |
| "grad_norm": 0.34654495120048523, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 0.378, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.3812512755393982, | |
| "learning_rate": 6.184665997806832e-07, | |
| "loss": 0.372, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 3.129032258064516, | |
| "grad_norm": 0.366245836019516, | |
| "learning_rate": 3.511175705587433e-07, | |
| "loss": 0.3714, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 3.258064516129032, | |
| "grad_norm": 0.3321492671966553, | |
| "learning_rate": 1.5708419435684463e-07, | |
| "loss": 0.3653, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 3.3870967741935485, | |
| "grad_norm": 0.28523552417755127, | |
| "learning_rate": 3.9426493427611177e-08, | |
| "loss": 0.3678, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 3.5161290322580645, | |
| "grad_norm": 0.3045349717140198, | |
| "learning_rate": 0.0, | |
| "loss": 0.3741, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.5161290322580645, | |
| "step": 28, | |
| "total_flos": 74554711998464.0, | |
| "train_loss": 0.43752551823854446, | |
| "train_runtime": 3591.335, | |
| "train_samples_per_second": 0.538, | |
| "train_steps_per_second": 0.008 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 28, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 8, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 74554711998464.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |