| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2, | |
| "eval_steps": 500, | |
| "global_step": 267, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00749063670411985, | |
| "grad_norm": 4.558547019958496, | |
| "learning_rate": 4.831460674157304e-05, | |
| "loss": 3.2586, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0149812734082397, | |
| "grad_norm": 4.060137748718262, | |
| "learning_rate": 4.644194756554308e-05, | |
| "loss": 2.9414, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02247191011235955, | |
| "grad_norm": 4.330236434936523, | |
| "learning_rate": 4.456928838951311e-05, | |
| "loss": 2.7364, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0299625468164794, | |
| "grad_norm": 3.8646533489227295, | |
| "learning_rate": 4.269662921348315e-05, | |
| "loss": 2.6617, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03745318352059925, | |
| "grad_norm": 4.332949161529541, | |
| "learning_rate": 4.082397003745319e-05, | |
| "loss": 2.5693, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0449438202247191, | |
| "grad_norm": 3.7690067291259766, | |
| "learning_rate": 3.8951310861423226e-05, | |
| "loss": 2.6648, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.052434456928838954, | |
| "grad_norm": 3.539844274520874, | |
| "learning_rate": 3.7078651685393264e-05, | |
| "loss": 2.6171, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0599250936329588, | |
| "grad_norm": 4.24369478225708, | |
| "learning_rate": 3.52059925093633e-05, | |
| "loss": 2.4795, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06741573033707865, | |
| "grad_norm": 4.186371326446533, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.6167, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0749063670411985, | |
| "grad_norm": 3.6899819374084473, | |
| "learning_rate": 3.1460674157303374e-05, | |
| "loss": 2.4597, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08239700374531835, | |
| "grad_norm": 4.035410404205322, | |
| "learning_rate": 2.958801498127341e-05, | |
| "loss": 2.3755, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0898876404494382, | |
| "grad_norm": 3.86106538772583, | |
| "learning_rate": 2.7715355805243448e-05, | |
| "loss": 2.4617, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09737827715355805, | |
| "grad_norm": 5.214311599731445, | |
| "learning_rate": 2.5842696629213486e-05, | |
| "loss": 2.3476, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.10486891385767791, | |
| "grad_norm": 4.270963191986084, | |
| "learning_rate": 2.3970037453183522e-05, | |
| "loss": 2.4596, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.11235955056179775, | |
| "grad_norm": 3.6309258937835693, | |
| "learning_rate": 2.209737827715356e-05, | |
| "loss": 2.3118, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1198501872659176, | |
| "grad_norm": 3.888986349105835, | |
| "learning_rate": 2.0224719101123596e-05, | |
| "loss": 2.3443, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.12734082397003746, | |
| "grad_norm": 2.937702178955078, | |
| "learning_rate": 1.8352059925093635e-05, | |
| "loss": 2.4183, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.1348314606741573, | |
| "grad_norm": 3.4217689037323, | |
| "learning_rate": 1.647940074906367e-05, | |
| "loss": 2.4306, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.14232209737827714, | |
| "grad_norm": 3.5683271884918213, | |
| "learning_rate": 1.4606741573033709e-05, | |
| "loss": 2.3407, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.149812734082397, | |
| "grad_norm": 3.605642318725586, | |
| "learning_rate": 1.2734082397003746e-05, | |
| "loss": 2.3402, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15730337078651685, | |
| "grad_norm": 2.3034493923187256, | |
| "learning_rate": 1.0861423220973783e-05, | |
| "loss": 2.1756, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.1647940074906367, | |
| "grad_norm": 3.481696605682373, | |
| "learning_rate": 8.98876404494382e-06, | |
| "loss": 2.1487, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.17228464419475656, | |
| "grad_norm": 3.515986919403076, | |
| "learning_rate": 7.116104868913858e-06, | |
| "loss": 2.2253, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.1797752808988764, | |
| "grad_norm": 3.26123046875, | |
| "learning_rate": 5.243445692883896e-06, | |
| "loss": 2.3215, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.18726591760299627, | |
| "grad_norm": 4.033005714416504, | |
| "learning_rate": 3.3707865168539327e-06, | |
| "loss": 2.2975, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.1947565543071161, | |
| "grad_norm": 3.7090864181518555, | |
| "learning_rate": 1.4981273408239701e-06, | |
| "loss": 2.2616, | |
| "step": 260 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 267, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1032285369139200.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |