archgen-2b-v1 / trainer_state.json
matthewdelorenzo's picture
Upload 16 files
c63c0f3 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9985974754558204,
"eval_steps": 500,
"global_step": 267,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.9985974754558204,
"step": 267,
"total_flos": 1.3901992019623936e+17,
"train_loss": 0.5984635370947449,
"train_runtime": 5970.3946,
"train_samples_per_second": 1.433,
"train_steps_per_second": 0.045
}
],
"logging_steps": 500,
"max_steps": 267,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 1.3901992019623936e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}