vit-base-beans-demo-v5 / trainer_state.json
LUCY9912's picture
LUCY9912
4f8f524 verified
raw
history blame
5.99 kB
{
"best_metric": 0.014830452390015125,
"best_model_checkpoint": "./vit-base-beans-demo-v5/checkpoint-200",
"epoch": 4.0,
"eval_steps": 100,
"global_step": 260,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.15384615384615385,
"grad_norm": 1.9032394886016846,
"learning_rate": 0.00019230769230769233,
"loss": 0.7857,
"step": 10
},
{
"epoch": 0.3076923076923077,
"grad_norm": 1.9500536918640137,
"learning_rate": 0.00018461538461538463,
"loss": 0.3341,
"step": 20
},
{
"epoch": 0.46153846153846156,
"grad_norm": 2.6301496028900146,
"learning_rate": 0.00017692307692307693,
"loss": 0.2642,
"step": 30
},
{
"epoch": 0.6153846153846154,
"grad_norm": 0.759385347366333,
"learning_rate": 0.00016923076923076923,
"loss": 0.2736,
"step": 40
},
{
"epoch": 0.7692307692307693,
"grad_norm": 4.216528415679932,
"learning_rate": 0.00016153846153846155,
"loss": 0.1979,
"step": 50
},
{
"epoch": 0.9230769230769231,
"grad_norm": 4.917251110076904,
"learning_rate": 0.00015384615384615385,
"loss": 0.2105,
"step": 60
},
{
"epoch": 1.0769230769230769,
"grad_norm": 0.2541252076625824,
"learning_rate": 0.00014615384615384615,
"loss": 0.1687,
"step": 70
},
{
"epoch": 1.2307692307692308,
"grad_norm": 0.19838066399097443,
"learning_rate": 0.00013846153846153847,
"loss": 0.1315,
"step": 80
},
{
"epoch": 1.3846153846153846,
"grad_norm": 1.1646043062210083,
"learning_rate": 0.00013076923076923077,
"loss": 0.0779,
"step": 90
},
{
"epoch": 1.5384615384615383,
"grad_norm": 1.9909968376159668,
"learning_rate": 0.0001230769230769231,
"loss": 0.1379,
"step": 100
},
{
"epoch": 1.5384615384615383,
"eval_accuracy": 0.9924812030075187,
"eval_loss": 0.06082921847701073,
"eval_runtime": 1.2361,
"eval_samples_per_second": 107.597,
"eval_steps_per_second": 13.753,
"step": 100
},
{
"epoch": 1.6923076923076923,
"grad_norm": 3.116147994995117,
"learning_rate": 0.00011538461538461538,
"loss": 0.1208,
"step": 110
},
{
"epoch": 1.8461538461538463,
"grad_norm": 1.415778398513794,
"learning_rate": 0.0001076923076923077,
"loss": 0.0768,
"step": 120
},
{
"epoch": 2.0,
"grad_norm": 5.078306198120117,
"learning_rate": 0.0001,
"loss": 0.1049,
"step": 130
},
{
"epoch": 2.1538461538461537,
"grad_norm": 0.10255656391382217,
"learning_rate": 9.230769230769232e-05,
"loss": 0.0441,
"step": 140
},
{
"epoch": 2.3076923076923075,
"grad_norm": 6.402000904083252,
"learning_rate": 8.461538461538461e-05,
"loss": 0.0594,
"step": 150
},
{
"epoch": 2.4615384615384617,
"grad_norm": 0.6794396638870239,
"learning_rate": 7.692307692307693e-05,
"loss": 0.0191,
"step": 160
},
{
"epoch": 2.6153846153846154,
"grad_norm": 5.282905578613281,
"learning_rate": 6.923076923076924e-05,
"loss": 0.0399,
"step": 170
},
{
"epoch": 2.769230769230769,
"grad_norm": 0.07534818351268768,
"learning_rate": 6.153846153846155e-05,
"loss": 0.0278,
"step": 180
},
{
"epoch": 2.9230769230769234,
"grad_norm": 0.06815086305141449,
"learning_rate": 5.384615384615385e-05,
"loss": 0.0146,
"step": 190
},
{
"epoch": 3.076923076923077,
"grad_norm": 0.06671617925167084,
"learning_rate": 4.615384615384616e-05,
"loss": 0.0218,
"step": 200
},
{
"epoch": 3.076923076923077,
"eval_accuracy": 1.0,
"eval_loss": 0.014830452390015125,
"eval_runtime": 1.7675,
"eval_samples_per_second": 75.246,
"eval_steps_per_second": 9.618,
"step": 200
},
{
"epoch": 3.230769230769231,
"grad_norm": 0.06218823790550232,
"learning_rate": 3.846153846153846e-05,
"loss": 0.0196,
"step": 210
},
{
"epoch": 3.3846153846153846,
"grad_norm": 0.059329863637685776,
"learning_rate": 3.0769230769230774e-05,
"loss": 0.012,
"step": 220
},
{
"epoch": 3.5384615384615383,
"grad_norm": 0.06472226977348328,
"learning_rate": 2.307692307692308e-05,
"loss": 0.0114,
"step": 230
},
{
"epoch": 3.6923076923076925,
"grad_norm": 0.06397414207458496,
"learning_rate": 1.5384615384615387e-05,
"loss": 0.0112,
"step": 240
},
{
"epoch": 3.8461538461538463,
"grad_norm": 0.06259459257125854,
"learning_rate": 7.692307692307694e-06,
"loss": 0.0111,
"step": 250
},
{
"epoch": 4.0,
"grad_norm": 0.05480915680527687,
"learning_rate": 0.0,
"loss": 0.011,
"step": 260
},
{
"epoch": 4.0,
"step": 260,
"total_flos": 3.205097416476426e+17,
"train_loss": 0.1226001287309023,
"train_runtime": 81.1937,
"train_samples_per_second": 50.94,
"train_steps_per_second": 3.202
}
],
"logging_steps": 10,
"max_steps": 260,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.205097416476426e+17,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}