m2m100_418M_br_fr / trainer_state.json
lgrobol's picture
update to new dataset version
eeaaffa verified
raw
history blame
3.87 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.0,
"global_step": 13600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.15,
"learning_rate": 4.816176470588236e-05,
"loss": 2.6313,
"step": 500
},
{
"epoch": 0.29,
"learning_rate": 4.632352941176471e-05,
"loss": 2.2069,
"step": 1000
},
{
"epoch": 0.44,
"learning_rate": 4.448529411764706e-05,
"loss": 2.035,
"step": 1500
},
{
"epoch": 0.59,
"learning_rate": 4.2647058823529415e-05,
"loss": 1.9491,
"step": 2000
},
{
"epoch": 0.74,
"learning_rate": 4.08125e-05,
"loss": 1.8742,
"step": 2500
},
{
"epoch": 0.88,
"learning_rate": 3.897426470588236e-05,
"loss": 1.8387,
"step": 3000
},
{
"epoch": 1.03,
"learning_rate": 3.713602941176471e-05,
"loss": 1.6941,
"step": 3500
},
{
"epoch": 1.18,
"learning_rate": 3.529779411764706e-05,
"loss": 1.5224,
"step": 4000
},
{
"epoch": 1.32,
"learning_rate": 3.3459558823529415e-05,
"loss": 1.4897,
"step": 4500
},
{
"epoch": 1.47,
"learning_rate": 3.1621323529411765e-05,
"loss": 1.4445,
"step": 5000
},
{
"epoch": 1.62,
"learning_rate": 2.978308823529412e-05,
"loss": 1.4593,
"step": 5500
},
{
"epoch": 1.76,
"learning_rate": 2.7944852941176468e-05,
"loss": 1.4251,
"step": 6000
},
{
"epoch": 1.91,
"learning_rate": 2.6113970588235297e-05,
"loss": 1.39,
"step": 6500
},
{
"epoch": 2.06,
"learning_rate": 2.427573529411765e-05,
"loss": 1.2959,
"step": 7000
},
{
"epoch": 2.21,
"learning_rate": 2.24375e-05,
"loss": 1.1621,
"step": 7500
},
{
"epoch": 2.35,
"learning_rate": 2.0599264705882353e-05,
"loss": 1.1374,
"step": 8000
},
{
"epoch": 2.5,
"learning_rate": 1.876102941176471e-05,
"loss": 1.1649,
"step": 8500
},
{
"epoch": 2.65,
"learning_rate": 1.6926470588235294e-05,
"loss": 1.1513,
"step": 9000
},
{
"epoch": 2.79,
"learning_rate": 1.5088235294117647e-05,
"loss": 1.1463,
"step": 9500
},
{
"epoch": 2.94,
"learning_rate": 1.3250000000000002e-05,
"loss": 1.1466,
"step": 10000
},
{
"epoch": 3.09,
"learning_rate": 1.1411764705882353e-05,
"loss": 1.0411,
"step": 10500
},
{
"epoch": 3.24,
"learning_rate": 9.573529411764706e-06,
"loss": 0.9581,
"step": 11000
},
{
"epoch": 3.38,
"learning_rate": 7.735294117647058e-06,
"loss": 0.9514,
"step": 11500
},
{
"epoch": 3.53,
"learning_rate": 5.897058823529412e-06,
"loss": 0.9429,
"step": 12000
},
{
"epoch": 3.68,
"learning_rate": 4.058823529411765e-06,
"loss": 0.9676,
"step": 12500
},
{
"epoch": 3.82,
"learning_rate": 2.2205882352941175e-06,
"loss": 0.9324,
"step": 13000
},
{
"epoch": 3.97,
"learning_rate": 3.8235294117647064e-07,
"loss": 0.9555,
"step": 13500
},
{
"epoch": 4.0,
"step": 13600,
"total_flos": 3.918346910230118e+16,
"train_loss": 1.4005291703168083,
"train_runtime": 11994.4751,
"train_samples_per_second": 18.139,
"train_steps_per_second": 1.134
}
],
"max_steps": 13600,
"num_train_epochs": 4,
"total_flos": 3.918346910230118e+16,
"trial_name": null,
"trial_params": null
}