ClassificationOfLeaves / trainer_state.json
Mytical's picture
Upload 8 files
d87fac9
{
"best_metric": 0.009908660314977169,
"best_model_checkpoint": "./vit-base-beans-demo-v2/checkpoint-300",
"epoch": 5.0,
"global_step": 325,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.15,
"learning_rate": 0.00019384615384615385,
"loss": 0.8469,
"step": 10
},
{
"epoch": 0.31,
"learning_rate": 0.0001876923076923077,
"loss": 0.474,
"step": 20
},
{
"epoch": 0.46,
"learning_rate": 0.00018153846153846155,
"loss": 0.4772,
"step": 30
},
{
"epoch": 0.62,
"learning_rate": 0.0001753846153846154,
"loss": 0.3322,
"step": 40
},
{
"epoch": 0.77,
"learning_rate": 0.00016923076923076923,
"loss": 0.2348,
"step": 50
},
{
"epoch": 0.92,
"learning_rate": 0.0001630769230769231,
"loss": 0.1734,
"step": 60
},
{
"epoch": 1.08,
"learning_rate": 0.00015692307692307693,
"loss": 0.2408,
"step": 70
},
{
"epoch": 1.23,
"learning_rate": 0.00015076923076923077,
"loss": 0.1521,
"step": 80
},
{
"epoch": 1.38,
"learning_rate": 0.0001446153846153846,
"loss": 0.0669,
"step": 90
},
{
"epoch": 1.54,
"learning_rate": 0.00013846153846153847,
"loss": 0.0705,
"step": 100
},
{
"epoch": 1.54,
"eval_accuracy": 0.9924812030075187,
"eval_loss": 0.056155215948820114,
"eval_runtime": 4.6463,
"eval_samples_per_second": 28.625,
"eval_steps_per_second": 3.659,
"step": 100
},
{
"epoch": 1.69,
"learning_rate": 0.0001323076923076923,
"loss": 0.0878,
"step": 110
},
{
"epoch": 1.85,
"learning_rate": 0.00012615384615384615,
"loss": 0.0617,
"step": 120
},
{
"epoch": 2.0,
"learning_rate": 0.00012,
"loss": 0.0667,
"step": 130
},
{
"epoch": 2.15,
"learning_rate": 0.00011384615384615384,
"loss": 0.0469,
"step": 140
},
{
"epoch": 2.31,
"learning_rate": 0.0001076923076923077,
"loss": 0.03,
"step": 150
},
{
"epoch": 2.46,
"learning_rate": 0.00010153846153846153,
"loss": 0.042,
"step": 160
},
{
"epoch": 2.62,
"learning_rate": 9.53846153846154e-05,
"loss": 0.0172,
"step": 170
},
{
"epoch": 2.77,
"learning_rate": 8.923076923076924e-05,
"loss": 0.0227,
"step": 180
},
{
"epoch": 2.92,
"learning_rate": 8.307692307692309e-05,
"loss": 0.0135,
"step": 190
},
{
"epoch": 3.08,
"learning_rate": 7.692307692307693e-05,
"loss": 0.0123,
"step": 200
},
{
"epoch": 3.08,
"eval_accuracy": 1.0,
"eval_loss": 0.012411748990416527,
"eval_runtime": 4.552,
"eval_samples_per_second": 29.218,
"eval_steps_per_second": 3.735,
"step": 200
},
{
"epoch": 3.23,
"learning_rate": 7.076923076923078e-05,
"loss": 0.0221,
"step": 210
},
{
"epoch": 3.38,
"learning_rate": 6.461538461538462e-05,
"loss": 0.0381,
"step": 220
},
{
"epoch": 3.54,
"learning_rate": 5.846153846153847e-05,
"loss": 0.0112,
"step": 230
},
{
"epoch": 3.69,
"learning_rate": 5.230769230769231e-05,
"loss": 0.0093,
"step": 240
},
{
"epoch": 3.85,
"learning_rate": 4.615384615384616e-05,
"loss": 0.0095,
"step": 250
},
{
"epoch": 4.0,
"learning_rate": 4e-05,
"loss": 0.0089,
"step": 260
},
{
"epoch": 4.15,
"learning_rate": 3.384615384615385e-05,
"loss": 0.0086,
"step": 270
},
{
"epoch": 4.31,
"learning_rate": 2.7692307692307694e-05,
"loss": 0.0085,
"step": 280
},
{
"epoch": 4.46,
"learning_rate": 2.1538461538461542e-05,
"loss": 0.008,
"step": 290
},
{
"epoch": 4.62,
"learning_rate": 1.5384615384615387e-05,
"loss": 0.008,
"step": 300
},
{
"epoch": 4.62,
"eval_accuracy": 1.0,
"eval_loss": 0.009908660314977169,
"eval_runtime": 4.573,
"eval_samples_per_second": 29.084,
"eval_steps_per_second": 3.717,
"step": 300
},
{
"epoch": 4.77,
"learning_rate": 9.230769230769232e-06,
"loss": 0.008,
"step": 310
},
{
"epoch": 4.92,
"learning_rate": 3.0769230769230774e-06,
"loss": 0.0079,
"step": 320
},
{
"epoch": 5.0,
"step": 325,
"total_flos": 0.0,
"train_loss": 0.11144641899145566,
"train_runtime": 271.4578,
"train_samples_per_second": 19.045,
"train_steps_per_second": 1.197
}
],
"max_steps": 325,
"num_train_epochs": 5,
"total_flos": 0.0,
"trial_name": null,
"trial_params": null
}