schnell's picture
Training in progress, epoch 1
f130419
raw
history blame
6.06 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"global_step": 22940,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 1.5566625155666254e-05,
"loss": 9.0543,
"step": 500
},
{
"epoch": 0.04,
"learning_rate": 3.113325031133251e-05,
"loss": 6.7369,
"step": 1000
},
{
"epoch": 0.07,
"learning_rate": 4.6699875466998756e-05,
"loss": 6.0998,
"step": 1500
},
{
"epoch": 0.09,
"learning_rate": 6.226650062266502e-05,
"loss": 5.4282,
"step": 2000
},
{
"epoch": 0.11,
"learning_rate": 7.783312577833126e-05,
"loss": 4.749,
"step": 2500
},
{
"epoch": 0.13,
"learning_rate": 9.339975093399751e-05,
"loss": 4.3351,
"step": 3000
},
{
"epoch": 0.15,
"learning_rate": 9.990941915030131e-05,
"loss": 4.0473,
"step": 3500
},
{
"epoch": 0.17,
"learning_rate": 9.975216073068553e-05,
"loss": 3.8251,
"step": 4000
},
{
"epoch": 0.2,
"learning_rate": 9.959490231106974e-05,
"loss": 3.6631,
"step": 4500
},
{
"epoch": 0.22,
"learning_rate": 9.943764389145395e-05,
"loss": 3.532,
"step": 5000
},
{
"epoch": 0.24,
"learning_rate": 9.928038547183816e-05,
"loss": 3.4285,
"step": 5500
},
{
"epoch": 0.26,
"learning_rate": 9.912312705222237e-05,
"loss": 3.3414,
"step": 6000
},
{
"epoch": 0.28,
"learning_rate": 9.89658686326066e-05,
"loss": 3.2622,
"step": 6500
},
{
"epoch": 0.31,
"learning_rate": 9.880861021299081e-05,
"loss": 3.2048,
"step": 7000
},
{
"epoch": 0.33,
"learning_rate": 9.865135179337502e-05,
"loss": 3.1463,
"step": 7500
},
{
"epoch": 0.35,
"learning_rate": 9.849409337375923e-05,
"loss": 3.0932,
"step": 8000
},
{
"epoch": 0.37,
"learning_rate": 9.833683495414345e-05,
"loss": 3.0433,
"step": 8500
},
{
"epoch": 0.39,
"learning_rate": 9.817957653452766e-05,
"loss": 3.0056,
"step": 9000
},
{
"epoch": 0.41,
"learning_rate": 9.802231811491189e-05,
"loss": 2.9611,
"step": 9500
},
{
"epoch": 0.44,
"learning_rate": 9.78650596952961e-05,
"loss": 2.9247,
"step": 10000
},
{
"epoch": 0.46,
"learning_rate": 9.77078012756803e-05,
"loss": 2.8874,
"step": 10500
},
{
"epoch": 0.48,
"learning_rate": 9.755054285606452e-05,
"loss": 2.8569,
"step": 11000
},
{
"epoch": 0.5,
"learning_rate": 9.739328443644873e-05,
"loss": 2.8276,
"step": 11500
},
{
"epoch": 0.52,
"learning_rate": 9.723602601683295e-05,
"loss": 2.7987,
"step": 12000
},
{
"epoch": 0.54,
"learning_rate": 9.70790821140564e-05,
"loss": 2.7716,
"step": 12500
},
{
"epoch": 0.57,
"learning_rate": 9.69218236944406e-05,
"loss": 2.745,
"step": 13000
},
{
"epoch": 0.59,
"learning_rate": 9.676456527482482e-05,
"loss": 2.7229,
"step": 13500
},
{
"epoch": 0.61,
"learning_rate": 9.660730685520904e-05,
"loss": 2.7021,
"step": 14000
},
{
"epoch": 0.63,
"learning_rate": 9.645036295243249e-05,
"loss": 2.679,
"step": 14500
},
{
"epoch": 0.65,
"learning_rate": 9.62931045328167e-05,
"loss": 2.6618,
"step": 15000
},
{
"epoch": 0.68,
"learning_rate": 9.61358461132009e-05,
"loss": 2.6444,
"step": 15500
},
{
"epoch": 0.7,
"learning_rate": 9.597858769358512e-05,
"loss": 2.6249,
"step": 16000
},
{
"epoch": 0.72,
"learning_rate": 9.582164379080856e-05,
"loss": 2.6169,
"step": 16500
},
{
"epoch": 0.74,
"learning_rate": 9.566438537119277e-05,
"loss": 2.5936,
"step": 17000
},
{
"epoch": 0.76,
"learning_rate": 9.5507126951577e-05,
"loss": 2.5854,
"step": 17500
},
{
"epoch": 0.78,
"learning_rate": 9.535018304880043e-05,
"loss": 2.5693,
"step": 18000
},
{
"epoch": 0.81,
"learning_rate": 9.519292462918465e-05,
"loss": 2.5525,
"step": 18500
},
{
"epoch": 0.83,
"learning_rate": 9.503566620956886e-05,
"loss": 2.539,
"step": 19000
},
{
"epoch": 0.85,
"learning_rate": 9.487840778995309e-05,
"loss": 2.5256,
"step": 19500
},
{
"epoch": 0.87,
"learning_rate": 9.47211493703373e-05,
"loss": 2.5207,
"step": 20000
},
{
"epoch": 0.89,
"learning_rate": 9.45638909507215e-05,
"loss": 2.5017,
"step": 20500
},
{
"epoch": 0.92,
"learning_rate": 9.440663253110572e-05,
"loss": 2.4895,
"step": 21000
},
{
"epoch": 0.94,
"learning_rate": 9.424968862832916e-05,
"loss": 2.4808,
"step": 21500
},
{
"epoch": 0.96,
"learning_rate": 9.409243020871337e-05,
"loss": 2.4713,
"step": 22000
},
{
"epoch": 0.98,
"learning_rate": 9.39351717890976e-05,
"loss": 2.4602,
"step": 22500
},
{
"epoch": 1.0,
"eval_accuracy": 0.5603946985569819,
"eval_loss": 2.3326776027679443,
"eval_runtime": 361.5158,
"eval_samples_per_second": 492.238,
"eval_steps_per_second": 30.765,
"step": 22940
}
],
"max_steps": 321160,
"num_train_epochs": 14,
"total_flos": 1.7360137911435264e+17,
"trial_name": null,
"trial_params": null
}