File size: 1,860 Bytes
ddb0bbd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 |
{
"best_global_step": 537,
"best_metric": 0.052135273814201355,
"best_model_checkpoint": "siglip2-finetune-full/checkpoint-537",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 537,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.9198179271708683,
"eval_loss": 0.2214546948671341,
"eval_model_preparation_time": 0.0025,
"eval_runtime": 78.9185,
"eval_samples_per_second": 72.379,
"eval_steps_per_second": 9.047,
"step": 179
},
{
"epoch": 2.0,
"eval_accuracy": 0.9529061624649859,
"eval_loss": 0.13619443774223328,
"eval_model_preparation_time": 0.0025,
"eval_runtime": 78.4297,
"eval_samples_per_second": 72.83,
"eval_steps_per_second": 9.104,
"step": 358
},
{
"epoch": 2.793296089385475,
"grad_norm": 22.69907569885254,
"learning_rate": 2.337278106508876e-06,
"loss": 0.2664,
"step": 500
},
{
"epoch": 3.0,
"eval_accuracy": 0.9812675070028011,
"eval_loss": 0.052135273814201355,
"eval_model_preparation_time": 0.0025,
"eval_runtime": 78.377,
"eval_samples_per_second": 72.879,
"eval_steps_per_second": 9.11,
"step": 537
}
],
"logging_steps": 500,
"max_steps": 895,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.4352579795383747e+18,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}
|