joelniklaus's picture
Training in progress, step 50000
5048b80
raw
history blame
6.51 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 32.00056,
"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": 5.7318,
"step": 1000
},
{
"epoch": 1.0,
"learning_rate": 2e-05,
"loss": 3.9475,
"step": 2000
},
{
"epoch": 1.01,
"learning_rate": 3e-05,
"loss": 3.4547,
"step": 3000
},
{
"epoch": 2.0,
"learning_rate": 4e-05,
"loss": 2.9629,
"step": 4000
},
{
"epoch": 3.0,
"learning_rate": 5e-05,
"loss": 2.727,
"step": 5000
},
{
"epoch": 3.01,
"learning_rate": 6e-05,
"loss": 1.8697,
"step": 6000
},
{
"epoch": 4.0,
"learning_rate": 7e-05,
"loss": 1.5021,
"step": 7000
},
{
"epoch": 5.0,
"learning_rate": 8e-05,
"loss": 1.4643,
"step": 8000
},
{
"epoch": 5.01,
"learning_rate": 9e-05,
"loss": 1.2784,
"step": 9000
},
{
"epoch": 6.0,
"learning_rate": 0.0001,
"loss": 1.2059,
"step": 10000
},
{
"epoch": 7.0,
"learning_rate": 9.999316524962345e-05,
"loss": 1.2602,
"step": 11000
},
{
"epoch": 7.01,
"learning_rate": 9.997266286704631e-05,
"loss": 1.1214,
"step": 12000
},
{
"epoch": 8.0,
"learning_rate": 9.993849845741524e-05,
"loss": 1.0983,
"step": 13000
},
{
"epoch": 8.01,
"learning_rate": 9.989068136093873e-05,
"loss": 1.1488,
"step": 14000
},
{
"epoch": 9.0,
"learning_rate": 9.98292246503335e-05,
"loss": 1.0281,
"step": 15000
},
{
"epoch": 10.0,
"learning_rate": 9.975414512725057e-05,
"loss": 1.0586,
"step": 16000
},
{
"epoch": 10.01,
"learning_rate": 9.966546331768191e-05,
"loss": 1.062,
"step": 17000
},
{
"epoch": 11.0,
"learning_rate": 9.956320346634876e-05,
"loss": 0.973,
"step": 18000
},
{
"epoch": 12.0,
"learning_rate": 9.944739353007344e-05,
"loss": 1.0381,
"step": 19000
},
{
"epoch": 12.01,
"learning_rate": 9.931806517013612e-05,
"loss": 0.9823,
"step": 20000
},
{
"epoch": 13.0,
"learning_rate": 9.917525374361912e-05,
"loss": 0.9447,
"step": 21000
},
{
"epoch": 14.0,
"learning_rate": 9.901899829374047e-05,
"loss": 1.0206,
"step": 22000
},
{
"epoch": 14.01,
"learning_rate": 9.884934153917997e-05,
"loss": 0.9389,
"step": 23000
},
{
"epoch": 15.0,
"learning_rate": 9.86663298624003e-05,
"loss": 0.9147,
"step": 24000
},
{
"epoch": 16.0,
"learning_rate": 9.847001329696653e-05,
"loss": 1.0002,
"step": 25000
},
{
"epoch": 16.01,
"learning_rate": 9.826044551386744e-05,
"loss": 0.908,
"step": 26000
},
{
"epoch": 17.0,
"learning_rate": 9.803768380684242e-05,
"loss": 0.9088,
"step": 27000
},
{
"epoch": 17.01,
"learning_rate": 9.780178907671789e-05,
"loss": 0.9641,
"step": 28000
},
{
"epoch": 18.0,
"learning_rate": 9.755282581475769e-05,
"loss": 0.8728,
"step": 29000
},
{
"epoch": 19.0,
"learning_rate": 9.729086208503174e-05,
"loss": 0.9131,
"step": 30000
},
{
"epoch": 19.01,
"learning_rate": 9.701596950580806e-05,
"loss": 0.924,
"step": 31000
},
{
"epoch": 20.0,
"learning_rate": 9.672822322997305e-05,
"loss": 0.8533,
"step": 32000
},
{
"epoch": 21.0,
"learning_rate": 9.642770192448536e-05,
"loss": 0.9286,
"step": 33000
},
{
"epoch": 21.01,
"learning_rate": 9.611448774886924e-05,
"loss": 0.8686,
"step": 34000
},
{
"epoch": 22.0,
"learning_rate": 9.578866633275288e-05,
"loss": 0.8435,
"step": 35000
},
{
"epoch": 23.0,
"learning_rate": 9.545032675245813e-05,
"loss": 0.9246,
"step": 36000
},
{
"epoch": 23.01,
"learning_rate": 9.509956150664796e-05,
"loss": 0.8463,
"step": 37000
},
{
"epoch": 24.0,
"learning_rate": 9.473646649103818e-05,
"loss": 0.839,
"step": 38000
},
{
"epoch": 25.0,
"learning_rate": 9.43611409721806e-05,
"loss": 0.9091,
"step": 39000
},
{
"epoch": 25.01,
"learning_rate": 9.397368756032445e-05,
"loss": 0.8261,
"step": 40000
},
{
"epoch": 26.0,
"learning_rate": 9.357421218136386e-05,
"loss": 0.8504,
"step": 41000
},
{
"epoch": 26.01,
"learning_rate": 9.316282404787871e-05,
"loss": 0.879,
"step": 42000
},
{
"epoch": 27.0,
"learning_rate": 9.273963562927695e-05,
"loss": 0.8044,
"step": 43000
},
{
"epoch": 28.0,
"learning_rate": 9.230476262104677e-05,
"loss": 0.8566,
"step": 44000
},
{
"epoch": 28.01,
"learning_rate": 9.185832391312644e-05,
"loss": 0.8478,
"step": 45000
},
{
"epoch": 29.0,
"learning_rate": 9.140044155740101e-05,
"loss": 0.7946,
"step": 46000
},
{
"epoch": 30.0,
"learning_rate": 9.093124073433463e-05,
"loss": 0.8694,
"step": 47000
},
{
"epoch": 30.01,
"learning_rate": 9.045084971874738e-05,
"loss": 0.8127,
"step": 48000
},
{
"epoch": 31.0,
"learning_rate": 8.995939984474624e-05,
"loss": 0.7912,
"step": 49000
},
{
"epoch": 32.0,
"learning_rate": 8.945702546981969e-05,
"loss": 0.8722,
"step": 50000
},
{
"epoch": 32.0,
"eval_loss": 0.5036267042160034,
"eval_runtime": 16.6411,
"eval_samples_per_second": 300.462,
"eval_steps_per_second": 2.404,
"step": 50000
}
],
"max_steps": 200000,
"num_train_epochs": 9223372036854775807,
"total_flos": 8.424046934800466e+17,
"trial_name": null,
"trial_params": null
}