delivery_truck_classification / trainer_state.json
JEdward7777's picture
End of training
18af02a
raw
history blame
10.2 kB
{
"best_metric": 1.0,
"best_model_checkpoint": "delivery_truck_classification/checkpoint-13",
"epoch": 39.666666666666664,
"global_step": 40,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.67,
"eval_accuracy": 0.18181818181818182,
"eval_loss": 1.868780255317688,
"eval_runtime": 1.5131,
"eval_samples_per_second": 14.54,
"eval_steps_per_second": 0.661,
"step": 1
},
{
"epoch": 1.67,
"eval_accuracy": 0.18181818181818182,
"eval_loss": 1.7919577360153198,
"eval_runtime": 1.7289,
"eval_samples_per_second": 12.725,
"eval_steps_per_second": 0.578,
"step": 2
},
{
"epoch": 2.67,
"eval_accuracy": 0.36363636363636365,
"eval_loss": 1.6533408164978027,
"eval_runtime": 1.6458,
"eval_samples_per_second": 13.368,
"eval_steps_per_second": 0.608,
"step": 3
},
{
"epoch": 3.67,
"eval_accuracy": 0.45454545454545453,
"eval_loss": 1.4775406122207642,
"eval_runtime": 1.6663,
"eval_samples_per_second": 13.203,
"eval_steps_per_second": 0.6,
"step": 4
},
{
"epoch": 4.67,
"eval_accuracy": 0.5909090909090909,
"eval_loss": 1.2912439107894897,
"eval_runtime": 1.6991,
"eval_samples_per_second": 12.948,
"eval_steps_per_second": 0.589,
"step": 5
},
{
"epoch": 5.67,
"eval_accuracy": 0.7272727272727273,
"eval_loss": 1.147495150566101,
"eval_runtime": 1.713,
"eval_samples_per_second": 12.843,
"eval_steps_per_second": 0.584,
"step": 6
},
{
"epoch": 6.67,
"eval_accuracy": 0.7727272727272727,
"eval_loss": 1.0265945196151733,
"eval_runtime": 1.5543,
"eval_samples_per_second": 14.154,
"eval_steps_per_second": 0.643,
"step": 7
},
{
"epoch": 7.67,
"eval_accuracy": 0.7727272727272727,
"eval_loss": 0.9196190237998962,
"eval_runtime": 1.677,
"eval_samples_per_second": 13.119,
"eval_steps_per_second": 0.596,
"step": 8
},
{
"epoch": 8.67,
"eval_accuracy": 0.8181818181818182,
"eval_loss": 0.8272687792778015,
"eval_runtime": 1.7098,
"eval_samples_per_second": 12.867,
"eval_steps_per_second": 0.585,
"step": 9
},
{
"epoch": 9.67,
"eval_accuracy": 0.8181818181818182,
"eval_loss": 0.7491626739501953,
"eval_runtime": 1.6687,
"eval_samples_per_second": 13.184,
"eval_steps_per_second": 0.599,
"step": 10
},
{
"epoch": 10.67,
"eval_accuracy": 0.9090909090909091,
"eval_loss": 0.6857182383537292,
"eval_runtime": 1.6621,
"eval_samples_per_second": 13.236,
"eval_steps_per_second": 0.602,
"step": 11
},
{
"epoch": 11.67,
"eval_accuracy": 0.9090909090909091,
"eval_loss": 0.6368551850318909,
"eval_runtime": 1.555,
"eval_samples_per_second": 14.148,
"eval_steps_per_second": 0.643,
"step": 12
},
{
"epoch": 12.67,
"eval_accuracy": 1.0,
"eval_loss": 0.5916178226470947,
"eval_runtime": 1.5463,
"eval_samples_per_second": 14.227,
"eval_steps_per_second": 0.647,
"step": 13
},
{
"epoch": 13.67,
"eval_accuracy": 1.0,
"eval_loss": 0.5461986660957336,
"eval_runtime": 1.751,
"eval_samples_per_second": 12.564,
"eval_steps_per_second": 0.571,
"step": 14
},
{
"epoch": 14.67,
"eval_accuracy": 1.0,
"eval_loss": 0.4926997423171997,
"eval_runtime": 1.6672,
"eval_samples_per_second": 13.196,
"eval_steps_per_second": 0.6,
"step": 15
},
{
"epoch": 15.67,
"eval_accuracy": 1.0,
"eval_loss": 0.4390135705471039,
"eval_runtime": 1.6819,
"eval_samples_per_second": 13.08,
"eval_steps_per_second": 0.595,
"step": 16
},
{
"epoch": 16.67,
"eval_accuracy": 1.0,
"eval_loss": 0.3913687765598297,
"eval_runtime": 1.7338,
"eval_samples_per_second": 12.689,
"eval_steps_per_second": 0.577,
"step": 17
},
{
"epoch": 17.67,
"eval_accuracy": 1.0,
"eval_loss": 0.3446086645126343,
"eval_runtime": 1.6759,
"eval_samples_per_second": 13.127,
"eval_steps_per_second": 0.597,
"step": 18
},
{
"epoch": 18.67,
"eval_accuracy": 1.0,
"eval_loss": 0.30193081498146057,
"eval_runtime": 1.53,
"eval_samples_per_second": 14.379,
"eval_steps_per_second": 0.654,
"step": 19
},
{
"epoch": 19.67,
"learning_rate": 2.777777777777778e-05,
"loss": 1.7058,
"step": 20
},
{
"epoch": 19.67,
"eval_accuracy": 1.0,
"eval_loss": 0.26113784313201904,
"eval_runtime": 1.6899,
"eval_samples_per_second": 13.018,
"eval_steps_per_second": 0.592,
"step": 20
},
{
"epoch": 20.67,
"eval_accuracy": 1.0,
"eval_loss": 0.22893615067005157,
"eval_runtime": 1.6979,
"eval_samples_per_second": 12.957,
"eval_steps_per_second": 0.589,
"step": 21
},
{
"epoch": 21.67,
"eval_accuracy": 1.0,
"eval_loss": 0.19601884484291077,
"eval_runtime": 1.7011,
"eval_samples_per_second": 12.933,
"eval_steps_per_second": 0.588,
"step": 22
},
{
"epoch": 22.67,
"eval_accuracy": 1.0,
"eval_loss": 0.17112015187740326,
"eval_runtime": 1.7223,
"eval_samples_per_second": 12.774,
"eval_steps_per_second": 0.581,
"step": 23
},
{
"epoch": 23.67,
"eval_accuracy": 1.0,
"eval_loss": 0.1567678302526474,
"eval_runtime": 1.7218,
"eval_samples_per_second": 12.778,
"eval_steps_per_second": 0.581,
"step": 24
},
{
"epoch": 24.67,
"eval_accuracy": 1.0,
"eval_loss": 0.14628903567790985,
"eval_runtime": 1.5212,
"eval_samples_per_second": 14.462,
"eval_steps_per_second": 0.657,
"step": 25
},
{
"epoch": 25.67,
"eval_accuracy": 1.0,
"eval_loss": 0.13830214738845825,
"eval_runtime": 1.7359,
"eval_samples_per_second": 12.673,
"eval_steps_per_second": 0.576,
"step": 26
},
{
"epoch": 26.67,
"eval_accuracy": 1.0,
"eval_loss": 0.13232018053531647,
"eval_runtime": 1.6428,
"eval_samples_per_second": 13.392,
"eval_steps_per_second": 0.609,
"step": 27
},
{
"epoch": 27.67,
"eval_accuracy": 1.0,
"eval_loss": 0.12681324779987335,
"eval_runtime": 2.2983,
"eval_samples_per_second": 9.572,
"eval_steps_per_second": 0.435,
"step": 28
},
{
"epoch": 28.67,
"eval_accuracy": 1.0,
"eval_loss": 0.1198858991265297,
"eval_runtime": 1.6718,
"eval_samples_per_second": 13.16,
"eval_steps_per_second": 0.598,
"step": 29
},
{
"epoch": 29.67,
"eval_accuracy": 1.0,
"eval_loss": 0.11446233093738556,
"eval_runtime": 1.6684,
"eval_samples_per_second": 13.186,
"eval_steps_per_second": 0.599,
"step": 30
},
{
"epoch": 30.67,
"eval_accuracy": 1.0,
"eval_loss": 0.11288688331842422,
"eval_runtime": 1.5105,
"eval_samples_per_second": 14.565,
"eval_steps_per_second": 0.662,
"step": 31
},
{
"epoch": 31.67,
"eval_accuracy": 1.0,
"eval_loss": 0.10953269153833389,
"eval_runtime": 1.7039,
"eval_samples_per_second": 12.911,
"eval_steps_per_second": 0.587,
"step": 32
},
{
"epoch": 32.67,
"eval_accuracy": 1.0,
"eval_loss": 0.10787732154130936,
"eval_runtime": 1.7185,
"eval_samples_per_second": 12.802,
"eval_steps_per_second": 0.582,
"step": 33
},
{
"epoch": 33.67,
"eval_accuracy": 1.0,
"eval_loss": 0.10531877726316452,
"eval_runtime": 1.8305,
"eval_samples_per_second": 12.019,
"eval_steps_per_second": 0.546,
"step": 34
},
{
"epoch": 34.67,
"eval_accuracy": 1.0,
"eval_loss": 0.10338964313268661,
"eval_runtime": 1.6703,
"eval_samples_per_second": 13.171,
"eval_steps_per_second": 0.599,
"step": 35
},
{
"epoch": 35.67,
"eval_accuracy": 1.0,
"eval_loss": 0.09904544055461884,
"eval_runtime": 1.5401,
"eval_samples_per_second": 14.285,
"eval_steps_per_second": 0.649,
"step": 36
},
{
"epoch": 36.67,
"eval_accuracy": 1.0,
"eval_loss": 0.09628929942846298,
"eval_runtime": 1.5486,
"eval_samples_per_second": 14.206,
"eval_steps_per_second": 0.646,
"step": 37
},
{
"epoch": 37.67,
"eval_accuracy": 1.0,
"eval_loss": 0.09520366042852402,
"eval_runtime": 1.6769,
"eval_samples_per_second": 13.12,
"eval_steps_per_second": 0.596,
"step": 38
},
{
"epoch": 38.67,
"eval_accuracy": 1.0,
"eval_loss": 0.09436272829771042,
"eval_runtime": 1.7152,
"eval_samples_per_second": 12.826,
"eval_steps_per_second": 0.583,
"step": 39
},
{
"epoch": 39.67,
"learning_rate": 0.0,
"loss": 0.6083,
"step": 40
},
{
"epoch": 39.67,
"eval_accuracy": 1.0,
"eval_loss": 0.0941963642835617,
"eval_runtime": 1.7089,
"eval_samples_per_second": 12.874,
"eval_steps_per_second": 0.585,
"step": 40
},
{
"epoch": 39.67,
"step": 40,
"total_flos": 1.893243704668324e+17,
"train_loss": 1.1570292234420776,
"train_runtime": 934.4965,
"train_samples_per_second": 8.218,
"train_steps_per_second": 0.043
}
],
"max_steps": 40,
"num_train_epochs": 40,
"total_flos": 1.893243704668324e+17,
"trial_name": null,
"trial_params": null
}