albert-base-v2-mnli / trainer_state.json
Alireza1044's picture
add model
ce8224e
raw
history blame
6.57 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.0,
"global_step": 24544,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08,
"learning_rate": 2.9388852672750976e-05,
"loss": 0.6805,
"step": 500
},
{
"epoch": 0.16,
"learning_rate": 2.877770534550196e-05,
"loss": 0.5507,
"step": 1000
},
{
"epoch": 0.24,
"learning_rate": 2.8166558018252934e-05,
"loss": 0.5379,
"step": 1500
},
{
"epoch": 0.33,
"learning_rate": 2.7555410691003913e-05,
"loss": 0.5057,
"step": 2000
},
{
"epoch": 0.41,
"learning_rate": 2.694426336375489e-05,
"loss": 0.4835,
"step": 2500
},
{
"epoch": 0.49,
"learning_rate": 2.6333116036505867e-05,
"loss": 0.4697,
"step": 3000
},
{
"epoch": 0.57,
"learning_rate": 2.5721968709256846e-05,
"loss": 0.4676,
"step": 3500
},
{
"epoch": 0.65,
"learning_rate": 2.511082138200782e-05,
"loss": 0.4621,
"step": 4000
},
{
"epoch": 0.73,
"learning_rate": 2.4499674054758804e-05,
"loss": 0.4496,
"step": 4500
},
{
"epoch": 0.81,
"learning_rate": 2.388852672750978e-05,
"loss": 0.4382,
"step": 5000
},
{
"epoch": 0.9,
"learning_rate": 2.3277379400260758e-05,
"loss": 0.4452,
"step": 5500
},
{
"epoch": 0.98,
"learning_rate": 2.2666232073011734e-05,
"loss": 0.4366,
"step": 6000
},
{
"epoch": 1.06,
"learning_rate": 2.2055084745762713e-05,
"loss": 0.3681,
"step": 6500
},
{
"epoch": 1.14,
"learning_rate": 2.144393741851369e-05,
"loss": 0.3505,
"step": 7000
},
{
"epoch": 1.22,
"learning_rate": 2.0832790091264667e-05,
"loss": 0.3528,
"step": 7500
},
{
"epoch": 1.3,
"learning_rate": 2.0221642764015646e-05,
"loss": 0.3458,
"step": 8000
},
{
"epoch": 1.39,
"learning_rate": 1.9610495436766625e-05,
"loss": 0.3527,
"step": 8500
},
{
"epoch": 1.47,
"learning_rate": 1.89993481095176e-05,
"loss": 0.3432,
"step": 9000
},
{
"epoch": 1.55,
"learning_rate": 1.838820078226858e-05,
"loss": 0.3428,
"step": 9500
},
{
"epoch": 1.63,
"learning_rate": 1.7777053455019558e-05,
"loss": 0.3478,
"step": 10000
},
{
"epoch": 1.71,
"learning_rate": 1.7165906127770537e-05,
"loss": 0.3424,
"step": 10500
},
{
"epoch": 1.79,
"learning_rate": 1.6554758800521512e-05,
"loss": 0.3433,
"step": 11000
},
{
"epoch": 1.87,
"learning_rate": 1.5943611473272488e-05,
"loss": 0.3417,
"step": 11500
},
{
"epoch": 1.96,
"learning_rate": 1.533246414602347e-05,
"loss": 0.3323,
"step": 12000
},
{
"epoch": 2.04,
"learning_rate": 1.4721316818774445e-05,
"loss": 0.2957,
"step": 12500
},
{
"epoch": 2.12,
"learning_rate": 1.4110169491525424e-05,
"loss": 0.2283,
"step": 13000
},
{
"epoch": 2.2,
"learning_rate": 1.3499022164276401e-05,
"loss": 0.2252,
"step": 13500
},
{
"epoch": 2.28,
"learning_rate": 1.288787483702738e-05,
"loss": 0.2299,
"step": 14000
},
{
"epoch": 2.36,
"learning_rate": 1.2276727509778357e-05,
"loss": 0.2373,
"step": 14500
},
{
"epoch": 2.44,
"learning_rate": 1.1665580182529336e-05,
"loss": 0.2281,
"step": 15000
},
{
"epoch": 2.53,
"learning_rate": 1.1054432855280312e-05,
"loss": 0.2314,
"step": 15500
},
{
"epoch": 2.61,
"learning_rate": 1.044328552803129e-05,
"loss": 0.2409,
"step": 16000
},
{
"epoch": 2.69,
"learning_rate": 9.83213820078227e-06,
"loss": 0.2375,
"step": 16500
},
{
"epoch": 2.77,
"learning_rate": 9.220990873533247e-06,
"loss": 0.2308,
"step": 17000
},
{
"epoch": 2.85,
"learning_rate": 8.609843546284226e-06,
"loss": 0.2371,
"step": 17500
},
{
"epoch": 2.93,
"learning_rate": 7.998696219035203e-06,
"loss": 0.2328,
"step": 18000
},
{
"epoch": 3.01,
"learning_rate": 7.38754889178618e-06,
"loss": 0.2145,
"step": 18500
},
{
"epoch": 3.1,
"learning_rate": 6.776401564537158e-06,
"loss": 0.1336,
"step": 19000
},
{
"epoch": 3.18,
"learning_rate": 6.165254237288136e-06,
"loss": 0.1356,
"step": 19500
},
{
"epoch": 3.26,
"learning_rate": 5.554106910039114e-06,
"loss": 0.1381,
"step": 20000
},
{
"epoch": 3.34,
"learning_rate": 4.942959582790091e-06,
"loss": 0.1343,
"step": 20500
},
{
"epoch": 3.42,
"learning_rate": 4.331812255541069e-06,
"loss": 0.1385,
"step": 21000
},
{
"epoch": 3.5,
"learning_rate": 3.720664928292047e-06,
"loss": 0.1316,
"step": 21500
},
{
"epoch": 3.59,
"learning_rate": 3.109517601043025e-06,
"loss": 0.1314,
"step": 22000
},
{
"epoch": 3.67,
"learning_rate": 2.498370273794003e-06,
"loss": 0.1221,
"step": 22500
},
{
"epoch": 3.75,
"learning_rate": 1.8872229465449805e-06,
"loss": 0.1301,
"step": 23000
},
{
"epoch": 3.83,
"learning_rate": 1.2760756192959583e-06,
"loss": 0.1249,
"step": 23500
},
{
"epoch": 3.91,
"learning_rate": 6.649282920469362e-07,
"loss": 0.1215,
"step": 24000
},
{
"epoch": 3.99,
"learning_rate": 5.378096479791395e-08,
"loss": 0.1225,
"step": 24500
},
{
"epoch": 4.0,
"step": 24544,
"total_flos": 9385760063993856.0,
"train_loss": 0.3001841343599317,
"train_runtime": 18121.6674,
"train_samples_per_second": 86.681,
"train_steps_per_second": 1.354
}
],
"max_steps": 24544,
"num_train_epochs": 4,
"total_flos": 9385760063993856.0,
"trial_name": null,
"trial_params": null
}