it5-summarization-mlsum / trainer_state.json
artelabsuper
add trained model
5b3e33d
raw
history blame
5.72 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.0,
"global_step": 21332,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.09,
"learning_rate": 4.882805175323458e-05,
"loss": 2.894,
"step": 500
},
{
"epoch": 0.19,
"learning_rate": 4.7656103506469155e-05,
"loss": 2.3094,
"step": 1000
},
{
"epoch": 0.28,
"learning_rate": 4.648415525970373e-05,
"loss": 2.256,
"step": 1500
},
{
"epoch": 0.38,
"learning_rate": 4.5312207012938315e-05,
"loss": 2.2547,
"step": 2000
},
{
"epoch": 0.47,
"learning_rate": 4.4140258766172885e-05,
"loss": 2.2201,
"step": 2500
},
{
"epoch": 0.56,
"learning_rate": 4.296831051940747e-05,
"loss": 2.1982,
"step": 3000
},
{
"epoch": 0.66,
"learning_rate": 4.1796362272642045e-05,
"loss": 2.2123,
"step": 3500
},
{
"epoch": 0.75,
"learning_rate": 4.0624414025876614e-05,
"loss": 2.178,
"step": 4000
},
{
"epoch": 0.84,
"learning_rate": 3.94524657791112e-05,
"loss": 2.1991,
"step": 4500
},
{
"epoch": 0.94,
"learning_rate": 3.8280517532345774e-05,
"loss": 2.1734,
"step": 5000
},
{
"epoch": 1.03,
"learning_rate": 3.710856928558035e-05,
"loss": 2.1487,
"step": 5500
},
{
"epoch": 1.13,
"learning_rate": 3.593662103881493e-05,
"loss": 2.1605,
"step": 6000
},
{
"epoch": 1.22,
"learning_rate": 3.476467279204951e-05,
"loss": 2.1316,
"step": 6500
},
{
"epoch": 1.31,
"learning_rate": 3.359272454528408e-05,
"loss": 2.1173,
"step": 7000
},
{
"epoch": 1.41,
"learning_rate": 3.242077629851866e-05,
"loss": 2.1218,
"step": 7500
},
{
"epoch": 1.5,
"learning_rate": 3.124882805175324e-05,
"loss": 2.1017,
"step": 8000
},
{
"epoch": 1.59,
"learning_rate": 3.0076879804987813e-05,
"loss": 2.1083,
"step": 8500
},
{
"epoch": 1.69,
"learning_rate": 2.8904931558222393e-05,
"loss": 2.1279,
"step": 9000
},
{
"epoch": 1.78,
"learning_rate": 2.7732983311456966e-05,
"loss": 2.1056,
"step": 9500
},
{
"epoch": 1.88,
"learning_rate": 2.6561035064691543e-05,
"loss": 2.1081,
"step": 10000
},
{
"epoch": 1.97,
"learning_rate": 2.5389086817926123e-05,
"loss": 2.1229,
"step": 10500
},
{
"epoch": 2.06,
"learning_rate": 2.42171385711607e-05,
"loss": 2.1051,
"step": 11000
},
{
"epoch": 2.16,
"learning_rate": 2.3045190324395276e-05,
"loss": 2.0861,
"step": 11500
},
{
"epoch": 2.25,
"learning_rate": 2.1873242077629852e-05,
"loss": 2.0813,
"step": 12000
},
{
"epoch": 2.34,
"learning_rate": 2.070129383086443e-05,
"loss": 2.0704,
"step": 12500
},
{
"epoch": 2.44,
"learning_rate": 1.952934558409901e-05,
"loss": 2.0753,
"step": 13000
},
{
"epoch": 2.53,
"learning_rate": 1.8357397337333585e-05,
"loss": 2.0803,
"step": 13500
},
{
"epoch": 2.63,
"learning_rate": 1.718544909056816e-05,
"loss": 2.0947,
"step": 14000
},
{
"epoch": 2.72,
"learning_rate": 1.6013500843802738e-05,
"loss": 2.0526,
"step": 14500
},
{
"epoch": 2.81,
"learning_rate": 1.4841552597037315e-05,
"loss": 2.0683,
"step": 15000
},
{
"epoch": 2.91,
"learning_rate": 1.3669604350271891e-05,
"loss": 2.0641,
"step": 15500
},
{
"epoch": 3.0,
"learning_rate": 1.249765610350647e-05,
"loss": 2.0679,
"step": 16000
},
{
"epoch": 3.09,
"learning_rate": 1.1325707856741047e-05,
"loss": 2.0329,
"step": 16500
},
{
"epoch": 3.19,
"learning_rate": 1.0153759609975624e-05,
"loss": 2.0512,
"step": 17000
},
{
"epoch": 3.28,
"learning_rate": 8.9818113632102e-06,
"loss": 2.0731,
"step": 17500
},
{
"epoch": 3.38,
"learning_rate": 7.809863116444779e-06,
"loss": 2.0693,
"step": 18000
},
{
"epoch": 3.47,
"learning_rate": 6.637914869679355e-06,
"loss": 2.0459,
"step": 18500
},
{
"epoch": 3.56,
"learning_rate": 5.4659666229139326e-06,
"loss": 2.0371,
"step": 19000
},
{
"epoch": 3.66,
"learning_rate": 4.294018376148509e-06,
"loss": 2.0285,
"step": 19500
},
{
"epoch": 3.75,
"learning_rate": 3.122070129383087e-06,
"loss": 2.0494,
"step": 20000
},
{
"epoch": 3.84,
"learning_rate": 1.9501218826176638e-06,
"loss": 2.0385,
"step": 20500
},
{
"epoch": 3.94,
"learning_rate": 7.781736358522408e-07,
"loss": 2.0785,
"step": 21000
},
{
"epoch": 4.0,
"step": 21332,
"total_flos": 7.623777879473818e+16,
"train_loss": 2.132151625336569,
"train_runtime": 19550.5305,
"train_samples_per_second": 6.547,
"train_steps_per_second": 1.091
}
],
"max_steps": 21332,
"num_train_epochs": 4,
"total_flos": 7.623777879473818e+16,
"trial_name": null,
"trial_params": null
}