| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 25, | |
| "global_step": 41, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04878048780487805, | |
| "grad_norm": 0.052720945328474045, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 11.9203, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04878048780487805, | |
| "eval_loss": 11.916321754455566, | |
| "eval_runtime": 0.0625, | |
| "eval_samples_per_second": 800.599, | |
| "eval_steps_per_second": 32.024, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 0.05649564787745476, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 11.9118, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.14634146341463414, | |
| "grad_norm": 0.06007275730371475, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 11.91, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 0.06864983588457108, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 11.908, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.24390243902439024, | |
| "grad_norm": 0.13928121328353882, | |
| "learning_rate": 0.00015, | |
| "loss": 11.888, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": 0.050554897636175156, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 11.9175, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.34146341463414637, | |
| "grad_norm": 0.051585853099823, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 11.9123, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 0.06403446942567825, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 11.9104, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.43902439024390244, | |
| "grad_norm": 0.07250206172466278, | |
| "learning_rate": 0.00027, | |
| "loss": 11.9101, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 0.12581613659858704, | |
| "learning_rate": 0.0003, | |
| "loss": 11.8811, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5365853658536586, | |
| "grad_norm": 0.051407769322395325, | |
| "learning_rate": 0.00029923039850878423, | |
| "loss": 11.9158, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 0.053157199174165726, | |
| "learning_rate": 0.00029692949118787415, | |
| "loss": 11.9121, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6341463414634146, | |
| "grad_norm": 0.064723901450634, | |
| "learning_rate": 0.0002931208884600073, | |
| "loss": 11.9034, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6829268292682927, | |
| "grad_norm": 0.07741189002990723, | |
| "learning_rate": 0.00028784367174303454, | |
| "loss": 11.8984, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7317073170731707, | |
| "grad_norm": 0.15558002889156342, | |
| "learning_rate": 0.0002811519924216873, | |
| "loss": 11.8842, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 0.0634838119149208, | |
| "learning_rate": 0.00027311451618109144, | |
| "loss": 11.914, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8292682926829268, | |
| "grad_norm": 0.07950323820114136, | |
| "learning_rate": 0.0002638137184039186, | |
| "loss": 11.9015, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8780487804878049, | |
| "grad_norm": 0.08885859698057175, | |
| "learning_rate": 0.000253345037861353, | |
| "loss": 11.9076, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.926829268292683, | |
| "grad_norm": 0.10019578784704208, | |
| "learning_rate": 0.00024181589738214943, | |
| "loss": 11.8991, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 0.17562973499298096, | |
| "learning_rate": 0.00022934460154904433, | |
| "loss": 11.8815, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.024390243902439, | |
| "grad_norm": 0.1393955796957016, | |
| "learning_rate": 0.00021605912273364513, | |
| "loss": 17.8661, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0731707317073171, | |
| "grad_norm": 0.08931300789117813, | |
| "learning_rate": 0.000202095787926723, | |
| "loss": 11.9524, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.1219512195121952, | |
| "grad_norm": 0.10830606520175934, | |
| "learning_rate": 0.00018759787983880805, | |
| "loss": 11.8534, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.170731707317073, | |
| "grad_norm": 0.11832421272993088, | |
| "learning_rate": 0.0001727141666256865, | |
| "loss": 11.853, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.2195121951219512, | |
| "grad_norm": 0.15067139267921448, | |
| "learning_rate": 0.0001575973753258069, | |
| "loss": 11.9391, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2195121951219512, | |
| "eval_loss": 11.908763885498047, | |
| "eval_runtime": 0.0607, | |
| "eval_samples_per_second": 824.1, | |
| "eval_steps_per_second": 32.964, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2682926829268293, | |
| "grad_norm": 0.16227374970912933, | |
| "learning_rate": 0.0001424026246741931, | |
| "loss": 11.866, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.3170731707317074, | |
| "grad_norm": 0.08508593589067459, | |
| "learning_rate": 0.00012728583337431353, | |
| "loss": 11.9516, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.3658536585365852, | |
| "grad_norm": 0.11364945769309998, | |
| "learning_rate": 0.0001124021201611919, | |
| "loss": 11.873, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.4146341463414633, | |
| "grad_norm": 0.1271531879901886, | |
| "learning_rate": 9.790421207327697e-05, | |
| "loss": 11.8994, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.4634146341463414, | |
| "grad_norm": 0.1775551587343216, | |
| "learning_rate": 8.394087726635483e-05, | |
| "loss": 11.8827, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.5121951219512195, | |
| "grad_norm": 0.19221873581409454, | |
| "learning_rate": 7.065539845095567e-05, | |
| "loss": 11.9097, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.5609756097560976, | |
| "grad_norm": 0.10446513444185257, | |
| "learning_rate": 5.818410261785056e-05, | |
| "loss": 11.8609, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.6097560975609757, | |
| "grad_norm": 0.11987953633069992, | |
| "learning_rate": 4.6654962138647004e-05, | |
| "loss": 11.946, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.6585365853658538, | |
| "grad_norm": 0.13893361389636993, | |
| "learning_rate": 3.618628159608137e-05, | |
| "loss": 11.8953, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.7073170731707317, | |
| "grad_norm": 0.16340382397174835, | |
| "learning_rate": 2.6885483818908586e-05, | |
| "loss": 11.8647, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.7560975609756098, | |
| "grad_norm": 0.18076759576797485, | |
| "learning_rate": 1.8848007578312686e-05, | |
| "loss": 11.8385, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.8048780487804879, | |
| "grad_norm": 0.12096209079027176, | |
| "learning_rate": 1.215632825696541e-05, | |
| "loss": 11.9756, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.8536585365853657, | |
| "grad_norm": 0.12150277197360992, | |
| "learning_rate": 6.879111539992676e-06, | |
| "loss": 11.852, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.9024390243902438, | |
| "grad_norm": 0.12834501266479492, | |
| "learning_rate": 3.070508812125827e-06, | |
| "loss": 11.9213, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.951219512195122, | |
| "grad_norm": 0.1679176688194275, | |
| "learning_rate": 7.696014912157267e-07, | |
| "loss": 11.8859, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.23847155272960663, | |
| "learning_rate": 0.0, | |
| "loss": 17.8301, | |
| "step": 41 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 41, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 261190189056.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |