Dissertation_txt / model /trainer_state.json
zswwsz's picture
Upload model/trainer_state.json
8c94d8e
raw
history blame
8.19 kB
{
"best_metric": 1.182452917098999,
"best_model_checkpoint": "./morror_art/result/reliable_emotion_result/checkpoint-2000",
"epoch": 31.25,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.56,
"eval_accuracy": 0.42930591259640105,
"eval_f1": 0.1868972445793083,
"eval_loss": 1.7191803455352783,
"eval_precision": 0.2025839793281654,
"eval_recall": 0.22199126036335337,
"eval_runtime": 2.7719,
"eval_samples_per_second": 280.677,
"eval_steps_per_second": 9.019,
"step": 100
},
{
"epoch": 3.12,
"eval_accuracy": 0.4524421593830334,
"eval_f1": 0.2149024437672066,
"eval_loss": 1.6538349390029907,
"eval_precision": 0.37657527657527656,
"eval_recall": 0.2353983725491661,
"eval_runtime": 2.783,
"eval_samples_per_second": 279.552,
"eval_steps_per_second": 8.983,
"step": 200
},
{
"epoch": 4.69,
"eval_accuracy": 0.5115681233933161,
"eval_f1": 0.33074987040848147,
"eval_loss": 1.5857356786727905,
"eval_precision": 0.5428199014042249,
"eval_recall": 0.32108994695783016,
"eval_runtime": 2.7888,
"eval_samples_per_second": 278.976,
"eval_steps_per_second": 8.965,
"step": 300
},
{
"epoch": 6.25,
"eval_accuracy": 0.5565552699228792,
"eval_f1": 0.4161166014878656,
"eval_loss": 1.4921071529388428,
"eval_precision": 0.5565738087504556,
"eval_recall": 0.3968583979510398,
"eval_runtime": 2.799,
"eval_samples_per_second": 277.959,
"eval_steps_per_second": 8.932,
"step": 400
},
{
"epoch": 7.81,
"learning_rate": 8.4375e-07,
"loss": 1.6444,
"step": 500
},
{
"epoch": 7.81,
"eval_accuracy": 0.5861182519280206,
"eval_f1": 0.4672858411340351,
"eval_loss": 1.402477741241455,
"eval_precision": 0.5480559028934396,
"eval_recall": 0.44796779170121126,
"eval_runtime": 2.7961,
"eval_samples_per_second": 278.248,
"eval_steps_per_second": 8.941,
"step": 500
},
{
"epoch": 9.38,
"eval_accuracy": 0.6041131105398457,
"eval_f1": 0.4938778627428773,
"eval_loss": 1.3338950872421265,
"eval_precision": 0.5812539949673737,
"eval_recall": 0.4710188546520362,
"eval_runtime": 2.7901,
"eval_samples_per_second": 278.843,
"eval_steps_per_second": 8.96,
"step": 600
},
{
"epoch": 10.94,
"eval_accuracy": 0.6053984575835476,
"eval_f1": 0.5149637371929131,
"eval_loss": 1.2827644348144531,
"eval_precision": 0.5659987886173603,
"eval_recall": 0.49700226942818704,
"eval_runtime": 2.8002,
"eval_samples_per_second": 277.838,
"eval_steps_per_second": 8.928,
"step": 700
},
{
"epoch": 12.5,
"eval_accuracy": 0.5989717223650386,
"eval_f1": 0.5167747217663895,
"eval_loss": 1.2506176233291626,
"eval_precision": 0.5614425347641262,
"eval_recall": 0.501430294437385,
"eval_runtime": 2.7918,
"eval_samples_per_second": 278.675,
"eval_steps_per_second": 8.955,
"step": 800
},
{
"epoch": 14.06,
"eval_accuracy": 0.6079691516709511,
"eval_f1": 0.5337228259352974,
"eval_loss": 1.2291851043701172,
"eval_precision": 0.5685525150056127,
"eval_recall": 0.5212833775624935,
"eval_runtime": 2.7899,
"eval_samples_per_second": 278.866,
"eval_steps_per_second": 8.961,
"step": 900
},
{
"epoch": 15.62,
"learning_rate": 6.875e-07,
"loss": 1.2545,
"step": 1000
},
{
"epoch": 15.62,
"eval_accuracy": 0.6118251928020566,
"eval_f1": 0.5350338181209471,
"eval_loss": 1.2144538164138794,
"eval_precision": 0.5722802199449438,
"eval_recall": 0.5185495090784064,
"eval_runtime": 2.7871,
"eval_samples_per_second": 279.139,
"eval_steps_per_second": 8.97,
"step": 1000
},
{
"epoch": 17.19,
"eval_accuracy": 0.6002570694087404,
"eval_f1": 0.5310042396866123,
"eval_loss": 1.2041194438934326,
"eval_precision": 0.5669317496265911,
"eval_recall": 0.5209501050904749,
"eval_runtime": 2.798,
"eval_samples_per_second": 278.053,
"eval_steps_per_second": 8.935,
"step": 1100
},
{
"epoch": 18.75,
"eval_accuracy": 0.6015424164524421,
"eval_f1": 0.5393733522687661,
"eval_loss": 1.198676347732544,
"eval_precision": 0.5627632135099613,
"eval_recall": 0.5344309959982473,
"eval_runtime": 2.7984,
"eval_samples_per_second": 278.013,
"eval_steps_per_second": 8.934,
"step": 1200
},
{
"epoch": 20.31,
"eval_accuracy": 0.6079691516709511,
"eval_f1": 0.5440601737065413,
"eval_loss": 1.1934562921524048,
"eval_precision": 0.5697745425273956,
"eval_recall": 0.533870395050335,
"eval_runtime": 2.794,
"eval_samples_per_second": 278.453,
"eval_steps_per_second": 8.948,
"step": 1300
},
{
"epoch": 21.88,
"eval_accuracy": 0.6066838046272494,
"eval_f1": 0.5532469090552911,
"eval_loss": 1.1859593391418457,
"eval_precision": 0.5628326867947885,
"eval_recall": 0.5535443197160673,
"eval_runtime": 2.7969,
"eval_samples_per_second": 278.169,
"eval_steps_per_second": 8.939,
"step": 1400
},
{
"epoch": 23.44,
"learning_rate": 5.3125e-07,
"loss": 1.0564,
"step": 1500
},
{
"epoch": 23.44,
"eval_accuracy": 0.5976863753213367,
"eval_f1": 0.5397416952276272,
"eval_loss": 1.1842819452285767,
"eval_precision": 0.5546631037379889,
"eval_recall": 0.5382763590689703,
"eval_runtime": 2.7933,
"eval_samples_per_second": 278.526,
"eval_steps_per_second": 8.95,
"step": 1500
},
{
"epoch": 25.0,
"eval_accuracy": 0.6053984575835476,
"eval_f1": 0.5511333940300814,
"eval_loss": 1.1826814413070679,
"eval_precision": 0.5585272241686065,
"eval_recall": 0.5511726724738778,
"eval_runtime": 2.7884,
"eval_samples_per_second": 279.014,
"eval_steps_per_second": 8.966,
"step": 1600
},
{
"epoch": 26.56,
"eval_accuracy": 0.6079691516709511,
"eval_f1": 0.5501171802317507,
"eval_loss": 1.1809784173965454,
"eval_precision": 0.5602569368582185,
"eval_recall": 0.5463119059408004,
"eval_runtime": 2.7883,
"eval_samples_per_second": 279.025,
"eval_steps_per_second": 8.966,
"step": 1700
},
{
"epoch": 28.12,
"eval_accuracy": 0.6002570694087404,
"eval_f1": 0.5406821213065259,
"eval_loss": 1.184258222579956,
"eval_precision": 0.553482439133083,
"eval_recall": 0.5368929633601643,
"eval_runtime": 2.7967,
"eval_samples_per_second": 278.18,
"eval_steps_per_second": 8.939,
"step": 1800
},
{
"epoch": 29.69,
"eval_accuracy": 0.602827763496144,
"eval_f1": 0.5467224382858954,
"eval_loss": 1.1806961297988892,
"eval_precision": 0.5566500675799514,
"eval_recall": 0.5435262116375483,
"eval_runtime": 2.787,
"eval_samples_per_second": 279.151,
"eval_steps_per_second": 8.97,
"step": 1900
},
{
"epoch": 31.25,
"learning_rate": 3.75e-07,
"loss": 0.9424,
"step": 2000
},
{
"epoch": 31.25,
"eval_accuracy": 0.5989717223650386,
"eval_f1": 0.5449153976552915,
"eval_loss": 1.182452917098999,
"eval_precision": 0.5512140217572096,
"eval_recall": 0.5448380783567264,
"eval_runtime": 2.7919,
"eval_samples_per_second": 278.661,
"eval_steps_per_second": 8.954,
"step": 2000
}
],
"max_steps": 3200,
"num_train_epochs": 50,
"total_flos": 5943081258536472.0,
"trial_name": null,
"trial_params": null
}