qwen2.5-3b-ArabicSFT_1epoch / trainer_state.json
RedaAlami's picture
Initial model upload
c310bd2 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 111,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"num_tokens": 30861952.0,
"step": 111,
"total_flos": 69610707615744.0,
"train_loss": 0.6555303625158362,
"train_runtime": 3309.6115,
"train_samples_per_second": 1.067,
"train_steps_per_second": 0.034
}
],
"logging_steps": 500,
"max_steps": 111,
"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": 69610707615744.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}