gowitheflow-1998
init
b62a0d6
{
"best_metric": 0.7769453778278917,
"best_model_checkpoint": "2-parallel-pt-nl-pl-**zxh4546/allnli_wikispan_unsup_ensemble_last**-64-128-3e-5-9400/checkpoint-9200",
"epoch": 1.0014915832090348,
"global_step": 9400,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 6e-06,
"loss": 68.9386,
"step": 200
},
{
"epoch": 0.04,
"learning_rate": 1.2e-05,
"loss": 29.743,
"step": 400
},
{
"epoch": 0.06,
"learning_rate": 1.8e-05,
"loss": 22.6828,
"step": 600
},
{
"epoch": 0.09,
"learning_rate": 2.4e-05,
"loss": 18.3538,
"step": 800
},
{
"epoch": 0.11,
"learning_rate": 3e-05,
"loss": 16.8795,
"step": 1000
},
{
"epoch": 0.13,
"learning_rate": 2.9285714285714284e-05,
"loss": 15.0949,
"step": 1200
},
{
"epoch": 0.15,
"learning_rate": 2.857142857142857e-05,
"loss": 13.1123,
"step": 1400
},
{
"epoch": 0.17,
"learning_rate": 2.7857142857142858e-05,
"loss": 11.6076,
"step": 1600
},
{
"epoch": 0.19,
"learning_rate": 2.7142857142857144e-05,
"loss": 11.0653,
"step": 1800
},
{
"epoch": 0.21,
"learning_rate": 2.6428571428571428e-05,
"loss": 10.2023,
"step": 2000
},
{
"epoch": 0.23,
"learning_rate": 2.5714285714285714e-05,
"loss": 9.4697,
"step": 2200
},
{
"epoch": 0.26,
"learning_rate": 2.5e-05,
"loss": 9.073,
"step": 2400
},
{
"epoch": 0.28,
"learning_rate": 2.4285714285714288e-05,
"loss": 8.2219,
"step": 2600
},
{
"epoch": 0.3,
"learning_rate": 2.357142857142857e-05,
"loss": 8.1709,
"step": 2800
},
{
"epoch": 0.32,
"learning_rate": 2.2857142857142858e-05,
"loss": 7.6007,
"step": 3000
},
{
"epoch": 0.34,
"learning_rate": 2.2142857142857145e-05,
"loss": 7.3222,
"step": 3200
},
{
"epoch": 0.36,
"learning_rate": 2.1428571428571428e-05,
"loss": 6.8397,
"step": 3400
},
{
"epoch": 0.38,
"learning_rate": 2.0714285714285715e-05,
"loss": 6.7136,
"step": 3600
},
{
"epoch": 0.4,
"learning_rate": 1.9999999999999998e-05,
"loss": 6.4772,
"step": 3800
},
{
"epoch": 0.43,
"learning_rate": 1.928571428571429e-05,
"loss": 6.136,
"step": 4000
},
{
"epoch": 0.45,
"learning_rate": 1.8571428571428572e-05,
"loss": 6.3031,
"step": 4200
},
{
"epoch": 0.47,
"learning_rate": 1.785714285714286e-05,
"loss": 5.8973,
"step": 4400
},
{
"epoch": 0.49,
"learning_rate": 1.7142857142857142e-05,
"loss": 5.849,
"step": 4600
},
{
"epoch": 0.51,
"learning_rate": 1.6428571428571432e-05,
"loss": 5.7724,
"step": 4800
},
{
"epoch": 0.53,
"learning_rate": 1.5714285714285715e-05,
"loss": 5.5508,
"step": 5000
},
{
"epoch": 0.55,
"learning_rate": 1.5e-05,
"loss": 5.1375,
"step": 5200
},
{
"epoch": 0.58,
"learning_rate": 1.4285714285714285e-05,
"loss": 5.3564,
"step": 5400
},
{
"epoch": 0.6,
"learning_rate": 1.3571428571428572e-05,
"loss": 5.173,
"step": 5600
},
{
"epoch": 0.62,
"learning_rate": 1.2857142857142857e-05,
"loss": 4.8572,
"step": 5800
},
{
"epoch": 0.64,
"learning_rate": 1.2142857142857144e-05,
"loss": 5.0517,
"step": 6000
},
{
"epoch": 0.66,
"learning_rate": 1.1428571428571429e-05,
"loss": 4.8886,
"step": 6200
},
{
"epoch": 0.68,
"learning_rate": 1.0714285714285714e-05,
"loss": 4.7235,
"step": 6400
},
{
"epoch": 0.7,
"learning_rate": 9.999999999999999e-06,
"loss": 4.4131,
"step": 6600
},
{
"epoch": 0.72,
"learning_rate": 9.285714285714286e-06,
"loss": 4.6411,
"step": 6800
},
{
"epoch": 0.75,
"learning_rate": 8.571428571428571e-06,
"loss": 4.3489,
"step": 7000
},
{
"epoch": 0.77,
"learning_rate": 7.857142857142858e-06,
"loss": 4.4199,
"step": 7200
},
{
"epoch": 0.79,
"learning_rate": 7.142857142857143e-06,
"loss": 4.2557,
"step": 7400
},
{
"epoch": 0.81,
"learning_rate": 6.428571428571429e-06,
"loss": 3.9598,
"step": 7600
},
{
"epoch": 0.83,
"learning_rate": 5.7142857142857145e-06,
"loss": 4.1423,
"step": 7800
},
{
"epoch": 0.85,
"learning_rate": 4.9999999999999996e-06,
"loss": 3.9408,
"step": 8000
},
{
"epoch": 0.87,
"learning_rate": 4.2857142857142855e-06,
"loss": 4.1499,
"step": 8200
},
{
"epoch": 0.89,
"learning_rate": 3.5714285714285714e-06,
"loss": 4.0065,
"step": 8400
},
{
"epoch": 0.92,
"learning_rate": 2.8571428571428573e-06,
"loss": 3.7546,
"step": 8600
},
{
"epoch": 0.94,
"learning_rate": 2.1428571428571427e-06,
"loss": 3.8722,
"step": 8800
},
{
"epoch": 0.96,
"learning_rate": 1.4285714285714286e-06,
"loss": 3.7097,
"step": 9000
},
{
"epoch": 0.98,
"learning_rate": 7.142857142857143e-07,
"loss": 4.0694,
"step": 9200
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 3.8382,
"step": 9400
},
{
"epoch": 1.0,
"step": 9400,
"total_flos": 622939976497152.0,
"train_loss": 8.931647637549867,
"train_runtime": 5062.6195,
"train_samples_per_second": 237.664,
"train_steps_per_second": 1.857
}
],
"max_steps": 9400,
"num_train_epochs": 2,
"total_flos": 622939976497152.0,
"trial_name": null,
"trial_params": null
}