Brain_Tumor_Classification / trainer_state.json
Devarshi's picture
End of training
00ad0d3
raw
history blame
6.08 kB
{
"best_metric": 0.9613120269133726,
"best_model_checkpoint": "Brain_Tumor_Classification/checkpoint-332",
"epoch": 3.991044776119403,
"global_step": 332,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.12,
"learning_rate": 1.4705882352941177e-05,
"loss": 1.4267,
"step": 10
},
{
"epoch": 0.24,
"learning_rate": 2.9411764705882354e-05,
"loss": 1.2467,
"step": 20
},
{
"epoch": 0.36,
"learning_rate": 4.411764705882353e-05,
"loss": 1.0154,
"step": 30
},
{
"epoch": 0.48,
"learning_rate": 4.8993288590604034e-05,
"loss": 0.709,
"step": 40
},
{
"epoch": 0.6,
"learning_rate": 4.731543624161074e-05,
"loss": 0.604,
"step": 50
},
{
"epoch": 0.72,
"learning_rate": 4.5637583892617453e-05,
"loss": 0.5955,
"step": 60
},
{
"epoch": 0.84,
"learning_rate": 4.395973154362416e-05,
"loss": 0.485,
"step": 70
},
{
"epoch": 0.96,
"learning_rate": 4.228187919463087e-05,
"loss": 0.4369,
"step": 80
},
{
"epoch": 0.99,
"eval_accuracy": 0.9091673675357443,
"eval_f1": 0.9091673675357443,
"eval_loss": 0.2500155568122864,
"eval_precision": 0.9091673675357443,
"eval_recall": 0.9091673675357443,
"eval_runtime": 64.8347,
"eval_samples_per_second": 18.339,
"eval_steps_per_second": 0.586,
"step": 83
},
{
"epoch": 1.08,
"learning_rate": 4.060402684563759e-05,
"loss": 0.4492,
"step": 90
},
{
"epoch": 1.2,
"learning_rate": 3.89261744966443e-05,
"loss": 0.3878,
"step": 100
},
{
"epoch": 1.32,
"learning_rate": 3.724832214765101e-05,
"loss": 0.3951,
"step": 110
},
{
"epoch": 1.44,
"learning_rate": 3.557046979865772e-05,
"loss": 0.3708,
"step": 120
},
{
"epoch": 1.56,
"learning_rate": 3.389261744966443e-05,
"loss": 0.342,
"step": 130
},
{
"epoch": 1.68,
"learning_rate": 3.221476510067114e-05,
"loss": 0.3343,
"step": 140
},
{
"epoch": 1.8,
"learning_rate": 3.0536912751677856e-05,
"loss": 0.314,
"step": 150
},
{
"epoch": 1.92,
"learning_rate": 2.885906040268457e-05,
"loss": 0.3777,
"step": 160
},
{
"epoch": 1.99,
"eval_accuracy": 0.9301934398654331,
"eval_f1": 0.9301934398654331,
"eval_loss": 0.17629508674144745,
"eval_precision": 0.9301934398654331,
"eval_recall": 0.9301934398654331,
"eval_runtime": 69.6074,
"eval_samples_per_second": 17.082,
"eval_steps_per_second": 0.546,
"step": 166
},
{
"epoch": 2.05,
"learning_rate": 2.7181208053691276e-05,
"loss": 0.3736,
"step": 170
},
{
"epoch": 2.17,
"learning_rate": 2.550335570469799e-05,
"loss": 0.3141,
"step": 180
},
{
"epoch": 2.29,
"learning_rate": 2.38255033557047e-05,
"loss": 0.3334,
"step": 190
},
{
"epoch": 2.41,
"learning_rate": 2.2147651006711412e-05,
"loss": 0.3104,
"step": 200
},
{
"epoch": 2.53,
"learning_rate": 2.0469798657718122e-05,
"loss": 0.266,
"step": 210
},
{
"epoch": 2.64,
"learning_rate": 1.8791946308724835e-05,
"loss": 0.2586,
"step": 220
},
{
"epoch": 2.76,
"learning_rate": 1.7114093959731545e-05,
"loss": 0.2747,
"step": 230
},
{
"epoch": 2.88,
"learning_rate": 1.5436241610738255e-05,
"loss": 0.2684,
"step": 240
},
{
"epoch": 2.99,
"eval_accuracy": 0.9512195121951219,
"eval_f1": 0.9512195121951219,
"eval_loss": 0.12147016078233719,
"eval_precision": 0.9512195121951219,
"eval_recall": 0.9512195121951219,
"eval_runtime": 62.5572,
"eval_samples_per_second": 19.007,
"eval_steps_per_second": 0.607,
"step": 249
},
{
"epoch": 3.01,
"learning_rate": 1.3758389261744966e-05,
"loss": 0.2589,
"step": 250
},
{
"epoch": 3.13,
"learning_rate": 1.208053691275168e-05,
"loss": 0.2467,
"step": 260
},
{
"epoch": 3.25,
"learning_rate": 1.040268456375839e-05,
"loss": 0.2406,
"step": 270
},
{
"epoch": 3.37,
"learning_rate": 8.724832214765101e-06,
"loss": 0.2289,
"step": 280
},
{
"epoch": 3.49,
"learning_rate": 7.046979865771812e-06,
"loss": 0.2812,
"step": 290
},
{
"epoch": 3.61,
"learning_rate": 5.3691275167785235e-06,
"loss": 0.2478,
"step": 300
},
{
"epoch": 3.73,
"learning_rate": 3.6912751677852355e-06,
"loss": 0.2235,
"step": 310
},
{
"epoch": 3.85,
"learning_rate": 2.013422818791946e-06,
"loss": 0.207,
"step": 320
},
{
"epoch": 3.97,
"learning_rate": 3.355704697986577e-07,
"loss": 0.2363,
"step": 330
},
{
"epoch": 3.99,
"eval_accuracy": 0.9613120269133726,
"eval_f1": 0.9613120269133726,
"eval_loss": 0.1092575266957283,
"eval_precision": 0.9613120269133726,
"eval_recall": 0.9613120269133726,
"eval_runtime": 64.3459,
"eval_samples_per_second": 18.478,
"eval_steps_per_second": 0.591,
"step": 332
},
{
"epoch": 3.99,
"step": 332,
"total_flos": 1.061932048026071e+18,
"train_loss": 0.4249281358108463,
"train_runtime": 6173.988,
"train_samples_per_second": 6.932,
"train_steps_per_second": 0.054
}
],
"max_steps": 332,
"num_train_epochs": 4,
"total_flos": 1.061932048026071e+18,
"trial_name": null,
"trial_params": null
}