ConvNext-base-land-cover-v0.1 / trainer_state.json
dfurman's picture
🍻 cheers
6730ee3
raw
history blame
5 kB
{
"best_metric": 0.026852501556277275,
"best_model_checkpoint": "./ConvNext-base-chesapeake-land-cover-v0/checkpoint-300",
"epoch": 4.0,
"global_step": 348,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.11,
"learning_rate": 0.0001942528735632184,
"loss": 0.8419,
"step": 10
},
{
"epoch": 0.23,
"learning_rate": 0.00018850574712643678,
"loss": 0.1669,
"step": 20
},
{
"epoch": 0.34,
"learning_rate": 0.00018275862068965518,
"loss": 0.1106,
"step": 30
},
{
"epoch": 0.46,
"learning_rate": 0.00017701149425287358,
"loss": 0.0916,
"step": 40
},
{
"epoch": 0.57,
"learning_rate": 0.00017126436781609197,
"loss": 0.0701,
"step": 50
},
{
"epoch": 0.69,
"learning_rate": 0.00016551724137931035,
"loss": 0.0838,
"step": 60
},
{
"epoch": 0.8,
"learning_rate": 0.00015977011494252874,
"loss": 0.0533,
"step": 70
},
{
"epoch": 0.92,
"learning_rate": 0.00015402298850574712,
"loss": 0.0329,
"step": 80
},
{
"epoch": 1.03,
"learning_rate": 0.00014827586206896554,
"loss": 0.0548,
"step": 90
},
{
"epoch": 1.15,
"learning_rate": 0.0001425287356321839,
"loss": 0.0341,
"step": 100
},
{
"epoch": 1.26,
"learning_rate": 0.0001367816091954023,
"loss": 0.0346,
"step": 110
},
{
"epoch": 1.38,
"learning_rate": 0.00013103448275862068,
"loss": 0.0279,
"step": 120
},
{
"epoch": 1.49,
"learning_rate": 0.00012528735632183908,
"loss": 0.0207,
"step": 130
},
{
"epoch": 1.61,
"learning_rate": 0.00011954022988505748,
"loss": 0.0157,
"step": 140
},
{
"epoch": 1.72,
"learning_rate": 0.00011379310344827588,
"loss": 0.0254,
"step": 150
},
{
"epoch": 1.84,
"learning_rate": 0.00010804597701149426,
"loss": 0.0286,
"step": 160
},
{
"epoch": 1.95,
"learning_rate": 0.00010229885057471265,
"loss": 0.028,
"step": 170
},
{
"epoch": 2.07,
"learning_rate": 9.655172413793105e-05,
"loss": 0.0158,
"step": 180
},
{
"epoch": 2.18,
"learning_rate": 9.080459770114943e-05,
"loss": 0.0126,
"step": 190
},
{
"epoch": 2.3,
"learning_rate": 8.505747126436782e-05,
"loss": 0.013,
"step": 200
},
{
"epoch": 2.41,
"learning_rate": 7.931034482758621e-05,
"loss": 0.0113,
"step": 210
},
{
"epoch": 2.53,
"learning_rate": 7.35632183908046e-05,
"loss": 0.0153,
"step": 220
},
{
"epoch": 2.64,
"learning_rate": 6.781609195402298e-05,
"loss": 0.0083,
"step": 230
},
{
"epoch": 2.76,
"learning_rate": 6.206896551724138e-05,
"loss": 0.008,
"step": 240
},
{
"epoch": 2.87,
"learning_rate": 5.632183908045977e-05,
"loss": 0.0056,
"step": 250
},
{
"epoch": 2.99,
"learning_rate": 5.057471264367817e-05,
"loss": 0.0076,
"step": 260
},
{
"epoch": 3.1,
"learning_rate": 4.482758620689655e-05,
"loss": 0.0038,
"step": 270
},
{
"epoch": 3.22,
"learning_rate": 3.908045977011495e-05,
"loss": 0.0023,
"step": 280
},
{
"epoch": 3.33,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.0032,
"step": 290
},
{
"epoch": 3.45,
"learning_rate": 2.7586206896551727e-05,
"loss": 0.0076,
"step": 300
},
{
"epoch": 3.45,
"eval_accuracy": 0.9918582375478927,
"eval_loss": 0.026852501556277275,
"eval_runtime": 14.7576,
"eval_samples_per_second": 141.486,
"eval_steps_per_second": 17.686,
"step": 300
},
{
"epoch": 3.56,
"learning_rate": 2.183908045977012e-05,
"loss": 0.0028,
"step": 310
},
{
"epoch": 3.68,
"learning_rate": 1.6091954022988507e-05,
"loss": 0.0022,
"step": 320
},
{
"epoch": 3.79,
"learning_rate": 1.0344827586206897e-05,
"loss": 0.0023,
"step": 330
},
{
"epoch": 3.91,
"learning_rate": 4.5977011494252875e-06,
"loss": 0.0017,
"step": 340
},
{
"epoch": 4.0,
"step": 348,
"total_flos": 3.522751306056622e+18,
"train_loss": 0.05303763715957088,
"train_runtime": 404.1694,
"train_samples_per_second": 110.201,
"train_steps_per_second": 0.861
}
],
"max_steps": 348,
"num_train_epochs": 4,
"total_flos": 3.522751306056622e+18,
"trial_name": null,
"trial_params": null
}