cebfil-roberta / checkpoint-20000 /trainer_state.json
jfernandez's picture
Upload 21 files
35526ee
raw
history blame
5.23 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.7599939200486396,
"global_step": 20000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 4.90500075999392e-05,
"loss": 7.9101,
"step": 500
},
{
"epoch": 0.04,
"learning_rate": 4.81000151998784e-05,
"loss": 7.5794,
"step": 1000
},
{
"epoch": 0.06,
"learning_rate": 4.7150022799817604e-05,
"loss": 7.5385,
"step": 1500
},
{
"epoch": 0.08,
"learning_rate": 4.620003039975681e-05,
"loss": 7.5241,
"step": 2000
},
{
"epoch": 0.09,
"learning_rate": 4.5250037999696e-05,
"loss": 7.5219,
"step": 2500
},
{
"epoch": 0.11,
"learning_rate": 4.4300045599635205e-05,
"loss": 7.5021,
"step": 3000
},
{
"epoch": 0.13,
"learning_rate": 4.33500531995744e-05,
"loss": 7.4248,
"step": 3500
},
{
"epoch": 0.15,
"learning_rate": 4.240006079951361e-05,
"loss": 7.4127,
"step": 4000
},
{
"epoch": 0.17,
"learning_rate": 4.145006839945281e-05,
"loss": 7.4314,
"step": 4500
},
{
"epoch": 0.19,
"learning_rate": 4.050007599939201e-05,
"loss": 7.4032,
"step": 5000
},
{
"epoch": 0.21,
"learning_rate": 3.9550083599331206e-05,
"loss": 7.4693,
"step": 5500
},
{
"epoch": 0.23,
"learning_rate": 3.860009119927041e-05,
"loss": 7.4423,
"step": 6000
},
{
"epoch": 0.25,
"learning_rate": 3.765009879920961e-05,
"loss": 7.444,
"step": 6500
},
{
"epoch": 0.27,
"learning_rate": 3.670010639914881e-05,
"loss": 7.4172,
"step": 7000
},
{
"epoch": 0.28,
"learning_rate": 3.575011399908801e-05,
"loss": 7.427,
"step": 7500
},
{
"epoch": 0.3,
"learning_rate": 3.4800121599027206e-05,
"loss": 7.422,
"step": 8000
},
{
"epoch": 0.32,
"learning_rate": 3.3850129198966415e-05,
"loss": 7.4367,
"step": 8500
},
{
"epoch": 0.34,
"learning_rate": 3.290013679890561e-05,
"loss": 7.4049,
"step": 9000
},
{
"epoch": 0.36,
"learning_rate": 3.1950144398844814e-05,
"loss": 7.3746,
"step": 9500
},
{
"epoch": 0.38,
"learning_rate": 3.100015199878401e-05,
"loss": 7.3933,
"step": 10000
},
{
"epoch": 0.4,
"learning_rate": 3.005015959872321e-05,
"loss": 7.3898,
"step": 10500
},
{
"epoch": 0.42,
"learning_rate": 2.9100167198662416e-05,
"loss": 7.4056,
"step": 11000
},
{
"epoch": 0.44,
"learning_rate": 2.8150174798601615e-05,
"loss": 7.3624,
"step": 11500
},
{
"epoch": 0.46,
"learning_rate": 2.7200182398540814e-05,
"loss": 7.3256,
"step": 12000
},
{
"epoch": 0.47,
"learning_rate": 2.6250189998480014e-05,
"loss": 7.3855,
"step": 12500
},
{
"epoch": 0.49,
"learning_rate": 2.5300197598419213e-05,
"loss": 7.3835,
"step": 13000
},
{
"epoch": 0.51,
"learning_rate": 2.4350205198358412e-05,
"loss": 7.4472,
"step": 13500
},
{
"epoch": 0.53,
"learning_rate": 2.3400212798297615e-05,
"loss": 7.3903,
"step": 14000
},
{
"epoch": 0.55,
"learning_rate": 2.2450220398236815e-05,
"loss": 7.3914,
"step": 14500
},
{
"epoch": 0.57,
"learning_rate": 2.1500227998176014e-05,
"loss": 7.3494,
"step": 15000
},
{
"epoch": 0.59,
"learning_rate": 2.0550235598115217e-05,
"loss": 7.3547,
"step": 15500
},
{
"epoch": 0.61,
"learning_rate": 1.9600243198054416e-05,
"loss": 7.4164,
"step": 16000
},
{
"epoch": 0.63,
"learning_rate": 1.865025079799362e-05,
"loss": 7.4019,
"step": 16500
},
{
"epoch": 0.65,
"learning_rate": 1.7700258397932818e-05,
"loss": 7.3963,
"step": 17000
},
{
"epoch": 0.66,
"learning_rate": 1.6750265997872018e-05,
"loss": 7.3885,
"step": 17500
},
{
"epoch": 0.68,
"learning_rate": 1.580027359781122e-05,
"loss": 7.317,
"step": 18000
},
{
"epoch": 0.7,
"learning_rate": 1.4850281197750418e-05,
"loss": 7.3519,
"step": 18500
},
{
"epoch": 0.72,
"learning_rate": 1.390028879768962e-05,
"loss": 7.3486,
"step": 19000
},
{
"epoch": 0.74,
"learning_rate": 1.295029639762882e-05,
"loss": 7.3544,
"step": 19500
},
{
"epoch": 0.76,
"learning_rate": 1.200030399756802e-05,
"loss": 7.3557,
"step": 20000
}
],
"max_steps": 26316,
"num_train_epochs": 1,
"total_flos": 4297035955567104.0,
"trial_name": null,
"trial_params": null
}