finetuned_pegasus / trainer_state.json
Mousumi44
pegasus
92603c5
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.9216,
"global_step": 75,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05,
"learning_rate": 2e-05,
"loss": 7.7788,
"step": 2
},
{
"epoch": 0.1,
"learning_rate": 4e-05,
"loss": 7.6098,
"step": 4
},
{
"epoch": 0.15,
"learning_rate": 4.9315068493150684e-05,
"loss": 7.3839,
"step": 6
},
{
"epoch": 0.2,
"learning_rate": 4.794520547945205e-05,
"loss": 7.1239,
"step": 8
},
{
"epoch": 0.26,
"learning_rate": 4.657534246575342e-05,
"loss": 6.844,
"step": 10
},
{
"epoch": 0.31,
"learning_rate": 4.520547945205479e-05,
"loss": 6.8217,
"step": 12
},
{
"epoch": 0.36,
"learning_rate": 4.383561643835617e-05,
"loss": 6.5852,
"step": 14
},
{
"epoch": 0.41,
"learning_rate": 4.2465753424657536e-05,
"loss": 6.4827,
"step": 16
},
{
"epoch": 0.46,
"learning_rate": 4.1095890410958905e-05,
"loss": 6.4289,
"step": 18
},
{
"epoch": 0.51,
"learning_rate": 3.9726027397260274e-05,
"loss": 6.275,
"step": 20
},
{
"epoch": 0.56,
"learning_rate": 3.8356164383561644e-05,
"loss": 6.2334,
"step": 22
},
{
"epoch": 0.61,
"learning_rate": 3.698630136986301e-05,
"loss": 6.254,
"step": 24
},
{
"epoch": 0.67,
"learning_rate": 3.561643835616438e-05,
"loss": 6.1053,
"step": 26
},
{
"epoch": 0.72,
"learning_rate": 3.424657534246575e-05,
"loss": 6.1087,
"step": 28
},
{
"epoch": 0.77,
"learning_rate": 3.287671232876712e-05,
"loss": 6.0152,
"step": 30
},
{
"epoch": 0.82,
"learning_rate": 3.1506849315068496e-05,
"loss": 5.9039,
"step": 32
},
{
"epoch": 0.87,
"learning_rate": 3.0136986301369862e-05,
"loss": 5.9487,
"step": 34
},
{
"epoch": 0.92,
"learning_rate": 2.8767123287671234e-05,
"loss": 5.9647,
"step": 36
},
{
"epoch": 0.97,
"learning_rate": 2.7397260273972603e-05,
"loss": 5.9559,
"step": 38
},
{
"epoch": 1.03,
"learning_rate": 2.6027397260273973e-05,
"loss": 6.0371,
"step": 40
},
{
"epoch": 1.08,
"learning_rate": 2.4657534246575342e-05,
"loss": 5.8627,
"step": 42
},
{
"epoch": 1.13,
"learning_rate": 2.328767123287671e-05,
"loss": 5.8017,
"step": 44
},
{
"epoch": 1.18,
"learning_rate": 2.1917808219178083e-05,
"loss": 5.8414,
"step": 46
},
{
"epoch": 1.23,
"learning_rate": 2.0547945205479453e-05,
"loss": 5.8787,
"step": 48
},
{
"epoch": 1.28,
"learning_rate": 1.9178082191780822e-05,
"loss": 5.8423,
"step": 50
},
{
"epoch": 1.33,
"learning_rate": 1.780821917808219e-05,
"loss": 5.7113,
"step": 52
},
{
"epoch": 1.38,
"learning_rate": 1.643835616438356e-05,
"loss": 5.8619,
"step": 54
},
{
"epoch": 1.44,
"learning_rate": 1.5068493150684931e-05,
"loss": 5.7901,
"step": 56
},
{
"epoch": 1.49,
"learning_rate": 1.3698630136986302e-05,
"loss": 5.6903,
"step": 58
},
{
"epoch": 1.54,
"learning_rate": 1.2328767123287671e-05,
"loss": 5.6354,
"step": 60
},
{
"epoch": 1.59,
"learning_rate": 1.0958904109589042e-05,
"loss": 5.7176,
"step": 62
},
{
"epoch": 1.64,
"learning_rate": 9.589041095890411e-06,
"loss": 5.7527,
"step": 64
},
{
"epoch": 1.69,
"learning_rate": 8.21917808219178e-06,
"loss": 5.8004,
"step": 66
},
{
"epoch": 1.74,
"learning_rate": 6.849315068493151e-06,
"loss": 5.7,
"step": 68
},
{
"epoch": 1.79,
"learning_rate": 5.479452054794521e-06,
"loss": 5.7405,
"step": 70
},
{
"epoch": 1.84,
"learning_rate": 4.10958904109589e-06,
"loss": 5.782,
"step": 72
},
{
"epoch": 1.9,
"learning_rate": 2.7397260273972604e-06,
"loss": 5.6801,
"step": 74
}
],
"max_steps": 78,
"num_train_epochs": 2,
"total_flos": 5.552394818342093e+16,
"trial_name": null,
"trial_params": null
}