| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9748743718592965, | |
| "eval_steps": 500, | |
| "global_step": 222, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13400335008375208, | |
| "grad_norm": 0.4171938896179199, | |
| "learning_rate": 4.347826086956522e-05, | |
| "loss": 0.8101, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.26800670016750416, | |
| "grad_norm": 0.4708716869354248, | |
| "learning_rate": 8.695652173913044e-05, | |
| "loss": 0.8211, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4020100502512563, | |
| "grad_norm": 0.5508167743682861, | |
| "learning_rate": 9.96950085488444e-05, | |
| "loss": 0.6245, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5360134003350083, | |
| "grad_norm": 0.34629738330841064, | |
| "learning_rate": 9.821012312558058e-05, | |
| "loss": 0.6189, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6700167504187605, | |
| "grad_norm": 0.4830147624015808, | |
| "learning_rate": 9.552620875987311e-05, | |
| "loss": 0.5793, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8040201005025126, | |
| "grad_norm": 0.528333306312561, | |
| "learning_rate": 9.171001680589588e-05, | |
| "loss": 0.625, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9380234505862647, | |
| "grad_norm": 0.43927663564682007, | |
| "learning_rate": 8.685645937558896e-05, | |
| "loss": 0.5697, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0720268006700167, | |
| "grad_norm": 0.49636346101760864, | |
| "learning_rate": 8.108624878942477e-05, | |
| "loss": 0.562, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.2060301507537687, | |
| "grad_norm": 0.3749530017375946, | |
| "learning_rate": 7.454289535287968e-05, | |
| "loss": 0.5005, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.3400335008375208, | |
| "grad_norm": 0.47080516815185547, | |
| "learning_rate": 6.738913812659912e-05, | |
| "loss": 0.4522, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.474036850921273, | |
| "grad_norm": 0.450717955827713, | |
| "learning_rate": 5.980289746019892e-05, | |
| "loss": 0.4691, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.608040201005025, | |
| "grad_norm": 0.5994529724121094, | |
| "learning_rate": 5.1972849953812644e-05, | |
| "loss": 0.4904, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.742043551088777, | |
| "grad_norm": 0.5364199280738831, | |
| "learning_rate": 4.4093735902054605e-05, | |
| "loss": 0.4698, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.8760469011725294, | |
| "grad_norm": 0.5703357458114624, | |
| "learning_rate": 3.636151592846985e-05, | |
| "loss": 0.5083, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.0100502512562812, | |
| "grad_norm": 0.7257386445999146, | |
| "learning_rate": 2.8968497269310803e-05, | |
| "loss": 0.5063, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.1440536013400333, | |
| "grad_norm": 0.7995928525924683, | |
| "learning_rate": 2.2098550920327998e-05, | |
| "loss": 0.4249, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.2780569514237854, | |
| "grad_norm": 0.4787980914115906, | |
| "learning_rate": 1.5922538600418318e-05, | |
| "loss": 0.4145, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.4120603015075375, | |
| "grad_norm": 0.5283986330032349, | |
| "learning_rate": 1.0594063267640386e-05, | |
| "loss": 0.4231, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.5460636515912896, | |
| "grad_norm": 0.8906112313270569, | |
| "learning_rate": 6.2456488760703205e-06, | |
| "loss": 0.4165, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.6800670016750416, | |
| "grad_norm": 0.7813794016838074, | |
| "learning_rate": 2.9854443863662262e-06, | |
| "loss": 0.4132, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.8140703517587937, | |
| "grad_norm": 0.6210780739784241, | |
| "learning_rate": 8.945340042509797e-07, | |
| "loss": 0.424, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.948073701842546, | |
| "grad_norm": 0.7047247886657715, | |
| "learning_rate": 2.4920543691309138e-08, | |
| "loss": 0.4248, | |
| "step": 220 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 222, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 9154193387028480.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |