evoxtral / checkpoint-46 /trainer_state.json
YongkangZOU's picture
Duplicate from YongkangZOU/evoxtral-rl
be7e72c
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 46,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.10989010989010989,
"grad_norm": 0.19007250666618347,
"learning_rate": 1e-05,
"loss": 0.0155,
"step": 5
},
{
"epoch": 0.21978021978021978,
"grad_norm": 0.21089181303977966,
"learning_rate": 2.25e-05,
"loss": 0.0151,
"step": 10
},
{
"epoch": 0.32967032967032966,
"grad_norm": 0.20479902625083923,
"learning_rate": 3.5e-05,
"loss": 0.0127,
"step": 15
},
{
"epoch": 0.43956043956043955,
"grad_norm": 0.8878316283226013,
"learning_rate": 4.75e-05,
"loss": 0.0195,
"step": 20
},
{
"epoch": 0.5494505494505495,
"grad_norm": 0.7055298686027527,
"learning_rate": 4.713640064133025e-05,
"loss": 0.029,
"step": 25
},
{
"epoch": 0.6593406593406593,
"grad_norm": 0.6476932764053345,
"learning_rate": 3.6618079301094216e-05,
"loss": 0.0266,
"step": 30
},
{
"epoch": 0.7692307692307693,
"grad_norm": 0.3301375210285187,
"learning_rate": 2.1986582993616926e-05,
"loss": 0.0237,
"step": 35
},
{
"epoch": 0.8791208791208791,
"grad_norm": 0.44982224702835083,
"learning_rate": 8.421933543980126e-06,
"loss": 0.0254,
"step": 40
},
{
"epoch": 0.989010989010989,
"grad_norm": 0.43315255641937256,
"learning_rate": 7.264545643486997e-07,
"loss": 0.024,
"step": 45
}
],
"logging_steps": 5,
"max_steps": 46,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 8452396913221632.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}