{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 15228, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03283425269240872, "grad_norm": 2.0115110874176025, "learning_rate": 4.836157079064881e-05, "loss": 7.8535, "step": 500 }, { "epoch": 0.06566850538481744, "grad_norm": 1.8765583038330078, "learning_rate": 4.671985815602837e-05, "loss": 7.2604, "step": 1000 }, { "epoch": 0.09850275807722617, "grad_norm": 1.813555121421814, "learning_rate": 4.507814552140793e-05, "loss": 7.0768, "step": 1500 }, { "epoch": 0.1313370107696349, "grad_norm": 2.100990056991577, "learning_rate": 4.34364328867875e-05, "loss": 6.9514, "step": 2000 }, { "epoch": 0.1641712634620436, "grad_norm": 2.4078993797302246, "learning_rate": 4.1794720252167065e-05, "loss": 6.8599, "step": 2500 }, { "epoch": 0.19700551615445233, "grad_norm": 1.9332386255264282, "learning_rate": 4.015300761754663e-05, "loss": 6.8066, "step": 3000 }, { "epoch": 0.22983976884686105, "grad_norm": 2.384559154510498, "learning_rate": 3.8511294982926185e-05, "loss": 6.7556, "step": 3500 }, { "epoch": 0.2626740215392698, "grad_norm": 2.159532308578491, "learning_rate": 3.6869582348305756e-05, "loss": 6.7005, "step": 4000 }, { "epoch": 0.29550827423167847, "grad_norm": 2.3822381496429443, "learning_rate": 3.522786971368532e-05, "loss": 6.6413, "step": 4500 }, { "epoch": 0.3283425269240872, "grad_norm": 2.6890079975128174, "learning_rate": 3.3586157079064884e-05, "loss": 6.5969, "step": 5000 }, { "epoch": 0.3611767796164959, "grad_norm": 2.734480857849121, "learning_rate": 3.194444444444444e-05, "loss": 6.5226, "step": 5500 }, { "epoch": 0.39401103230890466, "grad_norm": 3.228806257247925, "learning_rate": 3.0302731809824008e-05, "loss": 6.4609, "step": 6000 }, { "epoch": 0.42684528500131336, "grad_norm": 3.1673390865325928, "learning_rate": 2.8661019175203575e-05, "loss": 6.3505, "step": 6500 }, { "epoch": 0.4596795376937221, "grad_norm": 3.190369129180908, "learning_rate": 2.701930654058314e-05, "loss": 6.2476, "step": 7000 }, { "epoch": 0.4925137903861308, "grad_norm": 3.3769636154174805, "learning_rate": 2.53775939059627e-05, "loss": 6.1132, "step": 7500 }, { "epoch": 0.5253480430785396, "grad_norm": 3.465238332748413, "learning_rate": 2.3735881271342264e-05, "loss": 5.9959, "step": 8000 }, { "epoch": 0.5581822957709482, "grad_norm": 3.3762824535369873, "learning_rate": 2.209416863672183e-05, "loss": 5.8872, "step": 8500 }, { "epoch": 0.5910165484633569, "grad_norm": 3.428150177001953, "learning_rate": 2.0452456002101395e-05, "loss": 5.7939, "step": 9000 }, { "epoch": 0.6238508011557657, "grad_norm": 3.5672378540039062, "learning_rate": 1.881074336748096e-05, "loss": 5.7013, "step": 9500 }, { "epoch": 0.6566850538481744, "grad_norm": 3.6406631469726562, "learning_rate": 1.7169030732860522e-05, "loss": 5.6368, "step": 10000 }, { "epoch": 0.6895193065405831, "grad_norm": 3.694791555404663, "learning_rate": 1.5527318098240086e-05, "loss": 5.5591, "step": 10500 }, { "epoch": 0.7223535592329918, "grad_norm": 3.98870587348938, "learning_rate": 1.388560546361965e-05, "loss": 5.4825, "step": 11000 }, { "epoch": 0.7551878119254006, "grad_norm": 3.6506927013397217, "learning_rate": 1.2243892828999212e-05, "loss": 5.4542, "step": 11500 }, { "epoch": 0.7880220646178093, "grad_norm": 3.9111599922180176, "learning_rate": 1.0602180194378776e-05, "loss": 5.3903, "step": 12000 }, { "epoch": 0.820856317310218, "grad_norm": 3.6450743675231934, "learning_rate": 8.96046755975834e-06, "loss": 5.3594, "step": 12500 }, { "epoch": 0.8536905700026267, "grad_norm": 3.8948936462402344, "learning_rate": 7.318754925137904e-06, "loss": 5.3447, "step": 13000 }, { "epoch": 0.8865248226950354, "grad_norm": 3.537013292312622, "learning_rate": 5.6770422905174684e-06, "loss": 5.2947, "step": 13500 }, { "epoch": 0.9193590753874442, "grad_norm": 3.3274927139282227, "learning_rate": 4.035329655897032e-06, "loss": 5.2935, "step": 14000 }, { "epoch": 0.9521933280798529, "grad_norm": 3.2864270210266113, "learning_rate": 2.3936170212765957e-06, "loss": 5.2692, "step": 14500 }, { "epoch": 0.9850275807722616, "grad_norm": 3.5905466079711914, "learning_rate": 7.519043866561598e-07, "loss": 5.2641, "step": 15000 } ], "logging_steps": 500, "max_steps": 15228, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3.231269529606144e+16, "train_batch_size": 64, "trial_name": null, "trial_params": null }