{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9937888198757764, "eval_steps": 500, "global_step": 80, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.012422360248447204, "grad_norm": 1.3089314699172974, "learning_rate": 2.5e-05, "loss": 3.7777, "step": 1 }, { "epoch": 0.062111801242236024, "grad_norm": 2.2394518852233887, "learning_rate": 0.000125, "loss": 3.9074, "step": 5 }, { "epoch": 0.12422360248447205, "grad_norm": 2.3361098766326904, "learning_rate": 0.00019961946980917456, "loss": 3.5292, "step": 10 }, { "epoch": 0.18633540372670807, "grad_norm": 2.7219650745391846, "learning_rate": 0.0001953716950748227, "loss": 2.9255, "step": 15 }, { "epoch": 0.2484472049689441, "grad_norm": 2.1357812881469727, "learning_rate": 0.00018660254037844388, "loss": 2.5287, "step": 20 }, { "epoch": 0.3105590062111801, "grad_norm": 1.425875186920166, "learning_rate": 0.0001737277336810124, "loss": 2.121, "step": 25 }, { "epoch": 0.37267080745341613, "grad_norm": 0.8381262421607971, "learning_rate": 0.0001573576436351046, "loss": 1.882, "step": 30 }, { "epoch": 0.43478260869565216, "grad_norm": 0.4776783585548401, "learning_rate": 0.000138268343236509, "loss": 1.6893, "step": 35 }, { "epoch": 0.4968944099378882, "grad_norm": 0.5259610414505005, "learning_rate": 0.00011736481776669306, "loss": 1.6159, "step": 40 }, { "epoch": 0.5590062111801242, "grad_norm": 0.4893004596233368, "learning_rate": 9.563806126346642e-05, "loss": 1.5552, "step": 45 }, { "epoch": 0.6211180124223602, "grad_norm": 0.3604605495929718, "learning_rate": 7.411809548974792e-05, "loss": 1.5203, "step": 50 }, { "epoch": 0.6832298136645962, "grad_norm": 0.40665724873542786, "learning_rate": 5.382513867649663e-05, "loss": 1.5131, "step": 55 }, { "epoch": 0.7453416149068323, "grad_norm": 0.3896912634372711, "learning_rate": 3.5721239031346066e-05, "loss": 1.4889, "step": 60 }, { "epoch": 0.8074534161490683, "grad_norm": 0.3924713730812073, "learning_rate": 2.0664665970876496e-05, "loss": 1.4691, "step": 65 }, { "epoch": 0.8695652173913043, "grad_norm": 0.3828902840614319, "learning_rate": 9.369221296335006e-06, "loss": 1.4818, "step": 70 }, { "epoch": 0.9316770186335404, "grad_norm": 0.2997172176837921, "learning_rate": 2.3703992880066638e-06, "loss": 1.4576, "step": 75 }, { "epoch": 0.9937888198757764, "grad_norm": 0.4181534945964813, "learning_rate": 0.0, "loss": 1.467, "step": 80 }, { "epoch": 0.9937888198757764, "eval_loss": 1.4779901504516602, "eval_runtime": 2.2938, "eval_samples_per_second": 89.373, "eval_steps_per_second": 0.872, "step": 80 }, { "epoch": 0.9937888198757764, "step": 80, "total_flos": 8.089924109389005e+17, "train_loss": 2.0078666627407076, "train_runtime": 559.3432, "train_samples_per_second": 36.804, "train_steps_per_second": 0.143 } ], "logging_steps": 5, "max_steps": 80, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 8.089924109389005e+17, "train_batch_size": 16, "trial_name": null, "trial_params": null }