it5-summarization-ilpost / trainer_state.json
artelabsuper
add trained model
77f7886
raw
history blame
6.2 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.0,
"global_step": 23468,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.09,
"learning_rate": 4.893471961820351e-05,
"loss": 2.3053,
"step": 500
},
{
"epoch": 0.17,
"learning_rate": 4.7869439236407024e-05,
"loss": 1.9792,
"step": 1000
},
{
"epoch": 0.26,
"learning_rate": 4.680415885461054e-05,
"loss": 1.9158,
"step": 1500
},
{
"epoch": 0.34,
"learning_rate": 4.5738878472814045e-05,
"loss": 1.8901,
"step": 2000
},
{
"epoch": 0.43,
"learning_rate": 4.467359809101756e-05,
"loss": 1.8747,
"step": 2500
},
{
"epoch": 0.51,
"learning_rate": 4.3608317709221067e-05,
"loss": 1.8479,
"step": 3000
},
{
"epoch": 0.6,
"learning_rate": 4.254303732742458e-05,
"loss": 1.8417,
"step": 3500
},
{
"epoch": 0.68,
"learning_rate": 4.1477756945628095e-05,
"loss": 1.8416,
"step": 4000
},
{
"epoch": 0.77,
"learning_rate": 4.04124765638316e-05,
"loss": 1.8413,
"step": 4500
},
{
"epoch": 0.85,
"learning_rate": 3.934719618203511e-05,
"loss": 1.8118,
"step": 5000
},
{
"epoch": 0.94,
"learning_rate": 3.828191580023863e-05,
"loss": 1.789,
"step": 5500
},
{
"epoch": 1.02,
"learning_rate": 3.721663541844214e-05,
"loss": 1.7796,
"step": 6000
},
{
"epoch": 1.11,
"learning_rate": 3.6151355036645645e-05,
"loss": 1.7649,
"step": 6500
},
{
"epoch": 1.19,
"learning_rate": 3.508607465484916e-05,
"loss": 1.7664,
"step": 7000
},
{
"epoch": 1.28,
"learning_rate": 3.4020794273052666e-05,
"loss": 1.7606,
"step": 7500
},
{
"epoch": 1.36,
"learning_rate": 3.295551389125618e-05,
"loss": 1.7345,
"step": 8000
},
{
"epoch": 1.45,
"learning_rate": 3.1890233509459694e-05,
"loss": 1.713,
"step": 8500
},
{
"epoch": 1.53,
"learning_rate": 3.08249531276632e-05,
"loss": 1.7604,
"step": 9000
},
{
"epoch": 1.62,
"learning_rate": 2.9759672745866712e-05,
"loss": 1.7539,
"step": 9500
},
{
"epoch": 1.7,
"learning_rate": 2.8694392364070227e-05,
"loss": 1.744,
"step": 10000
},
{
"epoch": 1.79,
"learning_rate": 2.7629111982273737e-05,
"loss": 1.7442,
"step": 10500
},
{
"epoch": 1.87,
"learning_rate": 2.6563831600477245e-05,
"loss": 1.7275,
"step": 11000
},
{
"epoch": 1.96,
"learning_rate": 2.5498551218680762e-05,
"loss": 1.702,
"step": 11500
},
{
"epoch": 2.05,
"learning_rate": 2.443327083688427e-05,
"loss": 1.714,
"step": 12000
},
{
"epoch": 2.13,
"learning_rate": 2.336799045508778e-05,
"loss": 1.6891,
"step": 12500
},
{
"epoch": 2.22,
"learning_rate": 2.230271007329129e-05,
"loss": 1.7327,
"step": 13000
},
{
"epoch": 2.3,
"learning_rate": 2.1237429691494805e-05,
"loss": 1.7197,
"step": 13500
},
{
"epoch": 2.39,
"learning_rate": 2.0172149309698312e-05,
"loss": 1.6997,
"step": 14000
},
{
"epoch": 2.47,
"learning_rate": 1.9106868927901826e-05,
"loss": 1.6961,
"step": 14500
},
{
"epoch": 2.56,
"learning_rate": 1.8041588546105337e-05,
"loss": 1.6966,
"step": 15000
},
{
"epoch": 2.64,
"learning_rate": 1.6976308164308848e-05,
"loss": 1.6905,
"step": 15500
},
{
"epoch": 2.73,
"learning_rate": 1.591102778251236e-05,
"loss": 1.6984,
"step": 16000
},
{
"epoch": 2.81,
"learning_rate": 1.484574740071587e-05,
"loss": 1.673,
"step": 16500
},
{
"epoch": 2.9,
"learning_rate": 1.378046701891938e-05,
"loss": 1.6719,
"step": 17000
},
{
"epoch": 2.98,
"learning_rate": 1.2715186637122892e-05,
"loss": 1.6932,
"step": 17500
},
{
"epoch": 3.07,
"learning_rate": 1.1649906255326403e-05,
"loss": 1.679,
"step": 18000
},
{
"epoch": 3.15,
"learning_rate": 1.0584625873529914e-05,
"loss": 1.6691,
"step": 18500
},
{
"epoch": 3.24,
"learning_rate": 9.519345491733426e-06,
"loss": 1.6633,
"step": 19000
},
{
"epoch": 3.32,
"learning_rate": 8.454065109936937e-06,
"loss": 1.6607,
"step": 19500
},
{
"epoch": 3.41,
"learning_rate": 7.3887847281404465e-06,
"loss": 1.6757,
"step": 20000
},
{
"epoch": 3.49,
"learning_rate": 6.323504346343959e-06,
"loss": 1.6765,
"step": 20500
},
{
"epoch": 3.58,
"learning_rate": 5.25822396454747e-06,
"loss": 1.6758,
"step": 21000
},
{
"epoch": 3.66,
"learning_rate": 4.19294358275098e-06,
"loss": 1.6745,
"step": 21500
},
{
"epoch": 3.75,
"learning_rate": 3.1276632009544914e-06,
"loss": 1.665,
"step": 22000
},
{
"epoch": 3.84,
"learning_rate": 2.0623828191580025e-06,
"loss": 1.6721,
"step": 22500
},
{
"epoch": 3.92,
"learning_rate": 9.971024373615137e-07,
"loss": 1.6684,
"step": 23000
},
{
"epoch": 4.0,
"step": 23468,
"total_flos": 9.246597801402931e+16,
"train_loss": 1.7515089764228484,
"train_runtime": 22215.4472,
"train_samples_per_second": 6.338,
"train_steps_per_second": 1.056
}
],
"max_steps": 23468,
"num_train_epochs": 4,
"total_flos": 9.246597801402931e+16,
"trial_name": null,
"trial_params": null
}