joelniklaus's picture
Training in progress, step 50000
3d31605
raw
history blame
6.5 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 8.00876,
"global_step": 50000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 1e-05,
"loss": 5.4872,
"step": 1000
},
{
"epoch": 0.01,
"learning_rate": 2e-05,
"loss": 3.6735,
"step": 2000
},
{
"epoch": 0.01,
"learning_rate": 3e-05,
"loss": 3.3205,
"step": 3000
},
{
"epoch": 0.02,
"learning_rate": 4e-05,
"loss": 2.9177,
"step": 4000
},
{
"epoch": 0.03,
"learning_rate": 5e-05,
"loss": 2.5459,
"step": 5000
},
{
"epoch": 0.03,
"learning_rate": 6e-05,
"loss": 1.9311,
"step": 6000
},
{
"epoch": 1.0,
"learning_rate": 7e-05,
"loss": 1.5357,
"step": 7000
},
{
"epoch": 1.01,
"learning_rate": 8e-05,
"loss": 1.4372,
"step": 8000
},
{
"epoch": 1.01,
"learning_rate": 9e-05,
"loss": 1.4358,
"step": 9000
},
{
"epoch": 1.02,
"learning_rate": 0.0001,
"loss": 1.4005,
"step": 10000
},
{
"epoch": 1.02,
"learning_rate": 9.999316524962345e-05,
"loss": 1.2848,
"step": 11000
},
{
"epoch": 1.03,
"learning_rate": 9.997266286704631e-05,
"loss": 1.2887,
"step": 12000
},
{
"epoch": 2.0,
"learning_rate": 9.993849845741524e-05,
"loss": 1.0934,
"step": 13000
},
{
"epoch": 2.01,
"learning_rate": 9.989068136093873e-05,
"loss": 1.1228,
"step": 14000
},
{
"epoch": 2.01,
"learning_rate": 9.98292246503335e-05,
"loss": 1.181,
"step": 15000
},
{
"epoch": 2.02,
"learning_rate": 9.975414512725057e-05,
"loss": 1.2087,
"step": 16000
},
{
"epoch": 2.02,
"learning_rate": 9.966546331768191e-05,
"loss": 1.1233,
"step": 17000
},
{
"epoch": 2.03,
"learning_rate": 9.956320346634876e-05,
"loss": 1.1639,
"step": 18000
},
{
"epoch": 3.0,
"learning_rate": 9.944739353007344e-05,
"loss": 0.9689,
"step": 19000
},
{
"epoch": 3.01,
"learning_rate": 9.931806517013612e-05,
"loss": 1.0136,
"step": 20000
},
{
"epoch": 3.01,
"learning_rate": 9.917525374361912e-05,
"loss": 1.0832,
"step": 21000
},
{
"epoch": 3.02,
"learning_rate": 9.901899829374047e-05,
"loss": 1.1333,
"step": 22000
},
{
"epoch": 3.02,
"learning_rate": 9.884934153917997e-05,
"loss": 1.0471,
"step": 23000
},
{
"epoch": 3.03,
"learning_rate": 9.86663298624003e-05,
"loss": 1.1014,
"step": 24000
},
{
"epoch": 4.0,
"learning_rate": 9.847001329696653e-05,
"loss": 0.904,
"step": 25000
},
{
"epoch": 4.01,
"learning_rate": 9.826044551386744e-05,
"loss": 0.9477,
"step": 26000
},
{
"epoch": 4.01,
"learning_rate": 9.803768380684242e-05,
"loss": 1.0228,
"step": 27000
},
{
"epoch": 4.02,
"learning_rate": 9.780178907671789e-05,
"loss": 1.0827,
"step": 28000
},
{
"epoch": 4.02,
"learning_rate": 9.755282581475769e-05,
"loss": 1.0011,
"step": 29000
},
{
"epoch": 4.03,
"learning_rate": 9.729086208503174e-05,
"loss": 1.0615,
"step": 30000
},
{
"epoch": 5.0,
"learning_rate": 9.701596950580806e-05,
"loss": 0.8596,
"step": 31000
},
{
"epoch": 5.01,
"learning_rate": 9.672822322997305e-05,
"loss": 0.9043,
"step": 32000
},
{
"epoch": 5.01,
"learning_rate": 9.642770192448536e-05,
"loss": 0.9831,
"step": 33000
},
{
"epoch": 5.02,
"learning_rate": 9.611448774886924e-05,
"loss": 1.0476,
"step": 34000
},
{
"epoch": 5.02,
"learning_rate": 9.578866633275288e-05,
"loss": 0.9662,
"step": 35000
},
{
"epoch": 5.03,
"learning_rate": 9.545032675245813e-05,
"loss": 1.0306,
"step": 36000
},
{
"epoch": 6.0,
"learning_rate": 9.509956150664796e-05,
"loss": 0.8293,
"step": 37000
},
{
"epoch": 6.01,
"learning_rate": 9.473646649103818e-05,
"loss": 0.871,
"step": 38000
},
{
"epoch": 6.01,
"learning_rate": 9.43611409721806e-05,
"loss": 0.9521,
"step": 39000
},
{
"epoch": 6.02,
"learning_rate": 9.397368756032445e-05,
"loss": 1.0195,
"step": 40000
},
{
"epoch": 6.02,
"learning_rate": 9.357421218136386e-05,
"loss": 0.9415,
"step": 41000
},
{
"epoch": 6.03,
"learning_rate": 9.316282404787871e-05,
"loss": 1.0048,
"step": 42000
},
{
"epoch": 7.0,
"learning_rate": 9.273963562927695e-05,
"loss": 0.8099,
"step": 43000
},
{
"epoch": 7.01,
"learning_rate": 9.230476262104677e-05,
"loss": 0.8435,
"step": 44000
},
{
"epoch": 7.01,
"learning_rate": 9.185832391312644e-05,
"loss": 0.9267,
"step": 45000
},
{
"epoch": 7.02,
"learning_rate": 9.140044155740101e-05,
"loss": 0.9985,
"step": 46000
},
{
"epoch": 7.02,
"learning_rate": 9.093124073433463e-05,
"loss": 0.9224,
"step": 47000
},
{
"epoch": 7.03,
"learning_rate": 9.045084971874738e-05,
"loss": 0.9826,
"step": 48000
},
{
"epoch": 8.0,
"learning_rate": 8.995939984474624e-05,
"loss": 0.7944,
"step": 49000
},
{
"epoch": 8.01,
"learning_rate": 8.945702546981969e-05,
"loss": 0.8218,
"step": 50000
},
{
"epoch": 8.01,
"eval_loss": 0.30516794323921204,
"eval_runtime": 17.3792,
"eval_samples_per_second": 287.7,
"eval_steps_per_second": 2.302,
"step": 50000
}
],
"max_steps": 200000,
"num_train_epochs": 9223372036854775807,
"total_flos": 8.42371002682835e+17,
"trial_name": null,
"trial_params": null
}