| { |
| "best_global_step": 2500, |
| "best_metric": 0.08692806959152222, |
| "best_model_checkpoint": "D:\\Task_design\\Topic\\willingness_train\\outputs\\qwen7b-lora-topic_willingness\\checkpoint-2500", |
| "epoch": 0.05488865835652379, |
| "eval_steps": 1250, |
| "global_step": 2500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.001097773167130476, |
| "grad_norm": 6656.0, |
| "learning_rate": 7.168983174835406e-06, |
| "loss": 63.2808, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.002195546334260952, |
| "grad_norm": 3392.0, |
| "learning_rate": 1.4484272128749086e-05, |
| "loss": 37.1328, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.0032933195013914274, |
| "grad_norm": 125.0, |
| "learning_rate": 2.1799561082662766e-05, |
| "loss": 3.812, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.004391092668521904, |
| "grad_norm": 604.0, |
| "learning_rate": 2.9114850036576446e-05, |
| "loss": 2.6617, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.005488865835652379, |
| "grad_norm": 314.0, |
| "learning_rate": 3.6430138990490126e-05, |
| "loss": 1.4918, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.006586639002782855, |
| "grad_norm": 141.0, |
| "learning_rate": 4.3745427944403806e-05, |
| "loss": 0.7991, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.007684412169913331, |
| "grad_norm": 478.0, |
| "learning_rate": 5.1060716898317486e-05, |
| "loss": 0.8998, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.008782185337043807, |
| "grad_norm": 688.0, |
| "learning_rate": 5.8376005852231167e-05, |
| "loss": 0.4973, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.009879958504174282, |
| "grad_norm": 900.0, |
| "learning_rate": 6.569129480614485e-05, |
| "loss": 1.6899, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.010977731671304758, |
| "grad_norm": 724.0, |
| "learning_rate": 7.300658376005852e-05, |
| "loss": 1.1575, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.012075504838435233, |
| "grad_norm": 51.0, |
| "learning_rate": 8.032187271397221e-05, |
| "loss": 0.6105, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.01317327800556571, |
| "grad_norm": 100.5, |
| "learning_rate": 8.763716166788588e-05, |
| "loss": 0.3713, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.014271051172696185, |
| "grad_norm": 430.0, |
| "learning_rate": 9.495245062179955e-05, |
| "loss": 0.4425, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.015368824339826661, |
| "grad_norm": 139.0, |
| "learning_rate": 0.00010226773957571325, |
| "loss": 0.4892, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.01646659750695714, |
| "grad_norm": 524.0, |
| "learning_rate": 0.00010958302852962691, |
| "loss": 1.1915, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.017564370674087615, |
| "grad_norm": 41.5, |
| "learning_rate": 0.00011689831748354061, |
| "loss": 0.6968, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.01866214384121809, |
| "grad_norm": 240.0, |
| "learning_rate": 0.0001242136064374543, |
| "loss": 1.25, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.019759917008348563, |
| "grad_norm": 15.875, |
| "learning_rate": 0.00013152889539136796, |
| "loss": 0.7973, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.02085769017547904, |
| "grad_norm": 298.0, |
| "learning_rate": 0.00013884418434528163, |
| "loss": 1.183, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.021955463342609515, |
| "grad_norm": 330.0, |
| "learning_rate": 0.00014615947329919534, |
| "loss": 0.6259, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.02305323650973999, |
| "grad_norm": 330.0, |
| "learning_rate": 0.00015347476225310898, |
| "loss": 0.49, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.024151009676870467, |
| "grad_norm": 83.5, |
| "learning_rate": 0.00016079005120702268, |
| "loss": 0.6314, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.025248782844000943, |
| "grad_norm": 129.0, |
| "learning_rate": 0.00016810534016093638, |
| "loss": 0.6512, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.02634655601113142, |
| "grad_norm": 142.0, |
| "learning_rate": 0.00017542062911485006, |
| "loss": 0.665, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.027444329178261895, |
| "grad_norm": 104.5, |
| "learning_rate": 0.00018273591806876373, |
| "loss": 0.3758, |
| "step": 1250 |
| }, |
| { |
| "epoch": 0.027444329178261895, |
| "eval_loss": 0.0266411192715168, |
| "eval_mae": 0.13352739810943604, |
| "eval_rmse": 0.163221076130867, |
| "eval_runtime": 173.4238, |
| "eval_samples_per_second": 11.532, |
| "eval_steps_per_second": 11.532, |
| "step": 1250 |
| }, |
| { |
| "epoch": 0.02854210234539237, |
| "grad_norm": 75.0, |
| "learning_rate": 0.0001900512070226774, |
| "loss": 0.3099, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.029639875512522847, |
| "grad_norm": 204.0, |
| "learning_rate": 0.0001973664959765911, |
| "loss": 0.2033, |
| "step": 1350 |
| }, |
| { |
| "epoch": 0.030737648679653323, |
| "grad_norm": 32.75, |
| "learning_rate": 0.00019985513807152557, |
| "loss": 0.8338, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.0318354218467838, |
| "grad_norm": 55.5, |
| "learning_rate": 0.00019962879130828429, |
| "loss": 0.2504, |
| "step": 1450 |
| }, |
| { |
| "epoch": 0.03293319501391428, |
| "grad_norm": 130.0, |
| "learning_rate": 0.00019940244454504303, |
| "loss": 0.6087, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.03403096818104475, |
| "grad_norm": 74.0, |
| "learning_rate": 0.00019917609778180172, |
| "loss": 0.3358, |
| "step": 1550 |
| }, |
| { |
| "epoch": 0.03512874134817523, |
| "grad_norm": 16.5, |
| "learning_rate": 0.00019894975101856043, |
| "loss": 0.2247, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.0362265145153057, |
| "grad_norm": 42.5, |
| "learning_rate": 0.00019872340425531918, |
| "loss": 0.251, |
| "step": 1650 |
| }, |
| { |
| "epoch": 0.03732428768243618, |
| "grad_norm": 139.0, |
| "learning_rate": 0.00019849705749207786, |
| "loss": 0.3527, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.038422060849566654, |
| "grad_norm": 126.5, |
| "learning_rate": 0.00019827071072883658, |
| "loss": 0.8417, |
| "step": 1750 |
| }, |
| { |
| "epoch": 0.03951983401669713, |
| "grad_norm": 30.5, |
| "learning_rate": 0.0001980443639655953, |
| "loss": 0.4691, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.040617607183827606, |
| "grad_norm": 125.0, |
| "learning_rate": 0.000197818017202354, |
| "loss": 0.2967, |
| "step": 1850 |
| }, |
| { |
| "epoch": 0.04171538035095808, |
| "grad_norm": 148.0, |
| "learning_rate": 0.00019759167043911273, |
| "loss": 0.2911, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.04281315351808856, |
| "grad_norm": 42.0, |
| "learning_rate": 0.00019736532367587144, |
| "loss": 0.2031, |
| "step": 1950 |
| }, |
| { |
| "epoch": 0.04391092668521903, |
| "grad_norm": 70.5, |
| "learning_rate": 0.00019713897691263016, |
| "loss": 0.2217, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.04500869985234951, |
| "grad_norm": 93.0, |
| "learning_rate": 0.00019691263014938887, |
| "loss": 0.2336, |
| "step": 2050 |
| }, |
| { |
| "epoch": 0.04610647301947998, |
| "grad_norm": 52.75, |
| "learning_rate": 0.0001966862833861476, |
| "loss": 0.3005, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.04720424618661046, |
| "grad_norm": 25.625, |
| "learning_rate": 0.0001964599366229063, |
| "loss": 0.1911, |
| "step": 2150 |
| }, |
| { |
| "epoch": 0.048302019353740934, |
| "grad_norm": 9.125, |
| "learning_rate": 0.00019623358985966502, |
| "loss": 0.3816, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.04939979252087141, |
| "grad_norm": 3.359375, |
| "learning_rate": 0.00019600724309642374, |
| "loss": 0.1897, |
| "step": 2250 |
| }, |
| { |
| "epoch": 0.050497565688001886, |
| "grad_norm": 56.75, |
| "learning_rate": 0.00019578089633318245, |
| "loss": 0.1517, |
| "step": 2300 |
| }, |
| { |
| "epoch": 0.051595338855132365, |
| "grad_norm": 15.0625, |
| "learning_rate": 0.00019555454956994117, |
| "loss": 0.3616, |
| "step": 2350 |
| }, |
| { |
| "epoch": 0.05269311202226284, |
| "grad_norm": 152.0, |
| "learning_rate": 0.00019532820280669988, |
| "loss": 0.3372, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.05379088518939332, |
| "grad_norm": 21.875, |
| "learning_rate": 0.00019510185604345857, |
| "loss": 0.1929, |
| "step": 2450 |
| }, |
| { |
| "epoch": 0.05488865835652379, |
| "grad_norm": 45.75, |
| "learning_rate": 0.0001948755092802173, |
| "loss": 0.1391, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.05488865835652379, |
| "eval_loss": 0.011679456569254398, |
| "eval_mae": 0.08692806959152222, |
| "eval_rmse": 0.10807153582572937, |
| "eval_runtime": 180.831, |
| "eval_samples_per_second": 11.06, |
| "eval_steps_per_second": 11.06, |
| "step": 2500 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 45547, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 1250, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.0170749247488e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
