RSI-CB256-35 / checkpoint-1548 /trainer_state.json
prithivMLmods's picture
Upload folder using huggingface_hub
bc6b811 verified
{
"best_global_step": 1548,
"best_metric": 0.023793132975697517,
"best_model_checkpoint": "siglip2-finetune-full/checkpoint-1548",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 1548,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.6459948320413437,
"grad_norm": 10.552935600280762,
"learning_rate": 0.00013991989319092122,
"loss": 0.6623,
"step": 500
},
{
"epoch": 1.0,
"eval_accuracy": 0.9349820180223866,
"eval_loss": 0.21081215143203735,
"eval_model_preparation_time": 0.0023,
"eval_runtime": 329.2887,
"eval_samples_per_second": 75.153,
"eval_steps_per_second": 9.396,
"step": 774
},
{
"epoch": 1.2919896640826873,
"grad_norm": 2.3672032356262207,
"learning_rate": 7.316421895861149e-05,
"loss": 0.2013,
"step": 1000
},
{
"epoch": 1.937984496124031,
"grad_norm": 0.24311719834804535,
"learning_rate": 6.408544726301736e-06,
"loss": 0.0687,
"step": 1500
},
{
"epoch": 2.0,
"eval_accuracy": 0.9919182123085627,
"eval_loss": 0.023793132975697517,
"eval_model_preparation_time": 0.0023,
"eval_runtime": 328.7926,
"eval_samples_per_second": 75.266,
"eval_steps_per_second": 9.41,
"step": 1548
}
],
"logging_steps": 500,
"max_steps": 1548,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.146528897531482e+18,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}