| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 677, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03692762186115214, | |
| "grad_norm": 3.40625, | |
| "learning_rate": 4.9995413210794864e-05, | |
| "loss": 0.3368, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07385524372230429, | |
| "grad_norm": 5.25, | |
| "learning_rate": 4.97592868002957e-05, | |
| "loss": 0.2453, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11078286558345643, | |
| "grad_norm": 4.59375, | |
| "learning_rate": 4.916868067943256e-05, | |
| "loss": 0.2346, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.14771048744460857, | |
| "grad_norm": 0.99609375, | |
| "learning_rate": 4.8232050579921445e-05, | |
| "loss": 0.2781, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.18463810930576072, | |
| "grad_norm": 16.375, | |
| "learning_rate": 4.6962806272773564e-05, | |
| "loss": 0.3521, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.22156573116691286, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 4.537911958006149e-05, | |
| "loss": 0.2264, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.258493353028065, | |
| "grad_norm": 1.390625, | |
| "learning_rate": 4.350366420820771e-05, | |
| "loss": 0.2168, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.29542097488921715, | |
| "grad_norm": 1.34375, | |
| "learning_rate": 4.1363291127612845e-05, | |
| "loss": 0.2245, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.33234859675036926, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 3.8988644146226606e-05, | |
| "loss": 0.1472, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.36927621861152143, | |
| "grad_norm": 1.28125, | |
| "learning_rate": 3.641372118091017e-05, | |
| "loss": 0.208, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.40620384047267355, | |
| "grad_norm": 0.462890625, | |
| "learning_rate": 3.367538750788563e-05, | |
| "loss": 0.1818, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.4431314623338257, | |
| "grad_norm": 0.515625, | |
| "learning_rate": 3.0812847961085526e-05, | |
| "loss": 0.1381, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.48005908419497784, | |
| "grad_norm": 1.4140625, | |
| "learning_rate": 2.7867085634960016e-05, | |
| "loss": 0.2824, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.51698670605613, | |
| "grad_norm": 0.87890625, | |
| "learning_rate": 2.488027512785632e-05, | |
| "loss": 0.1669, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5539143279172821, | |
| "grad_norm": 1.0078125, | |
| "learning_rate": 2.1895178726588674e-05, | |
| "loss": 0.1927, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.5908419497784343, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 1.8954534177048744e-05, | |
| "loss": 0.2234, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6277695716395865, | |
| "grad_norm": 0.71875, | |
| "learning_rate": 1.6100442806169422e-05, | |
| "loss": 0.1433, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.6646971935007385, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 1.3373766755524564e-05, | |
| "loss": 0.1273, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.7016248153618907, | |
| "grad_norm": 0.83984375, | |
| "learning_rate": 1.0813543956395675e-05, | |
| "loss": 0.3048, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.7385524372230429, | |
| "grad_norm": 0.2412109375, | |
| "learning_rate": 8.456429222131082e-06, | |
| "loss": 0.1167, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7754800590841949, | |
| "grad_norm": 0.8671875, | |
| "learning_rate": 6.336169459700933e-06, | |
| "loss": 0.1868, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.8124076809453471, | |
| "grad_norm": 0.9375, | |
| "learning_rate": 4.483120513865411e-06, | |
| "loss": 0.1595, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.8493353028064993, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 2.9238125613177403e-06, | |
| "loss": 0.1497, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.8862629246676514, | |
| "grad_norm": 1.015625, | |
| "learning_rate": 1.6805702770716053e-06, | |
| "loss": 0.169, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.9231905465288035, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 7.711932111862025e-07, | |
| "loss": 0.1455, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.9601181683899557, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 2.08700951888241e-07, | |
| "loss": 0.1586, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.9970457902511078, | |
| "grad_norm": 1.546875, | |
| "learning_rate": 1.1467236007867144e-09, | |
| "loss": 0.1187, | |
| "step": 675 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 677, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 750, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.243328822817587e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |