phi_3-offline-dpo-noise-0.0-42 / trainer_state.json
Wenboz's picture
Model save
49256fd verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9230769230769231,
"eval_steps": 100,
"global_step": 3,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.3076923076923077,
"grad_norm": 0.22362739856280167,
"learning_rate": 5e-06,
"logits/chosen": 11.287857055664062,
"logits/rejected": 11.603424072265625,
"logps/chosen": -380.2095642089844,
"logps/rejected": -391.62744140625,
"loss": 0.6931,
"rewards/accuracies": 0.0,
"rewards/chosen": 0.0,
"rewards/margins": 0.0,
"rewards/rejected": 0.0,
"step": 1
},
{
"epoch": 0.9230769230769231,
"step": 3,
"total_flos": 0.0,
"train_loss": 0.6940749088923136,
"train_runtime": 53.4359,
"train_samples_per_second": 3.743,
"train_steps_per_second": 0.056
}
],
"logging_steps": 10,
"max_steps": 3,
"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": true
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}