gemma-dpo-22-0bs / trainer_state.json
rmdhirr's picture
Upload folder using huggingface_hub
67d69da verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 100,
"global_step": 22,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.23529411764705882,
"grad_norm": 30.439592361450195,
"learning_rate": 5.4e-06,
"logits/chosen": -1.9912779331207275,
"logits/rejected": -1.9953693151474,
"logps/chosen": -192.16635131835938,
"logps/rejected": -71.55108642578125,
"loss": 0.6294,
"rewards/accuracies": 0.550000011920929,
"rewards/chosen": 0.10031169652938843,
"rewards/margins": 0.14274156093597412,
"rewards/rejected": -0.042429856956005096,
"step": 5
},
{
"epoch": 0.47058823529411764,
"grad_norm": 19.870437622070312,
"learning_rate": 3.9e-06,
"logits/chosen": -1.9942305088043213,
"logits/rejected": -2.0469746589660645,
"logps/chosen": -183.76937866210938,
"logps/rejected": -76.84315490722656,
"loss": 0.3801,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.6416307687759399,
"rewards/margins": 0.8330594301223755,
"rewards/rejected": -0.19142863154411316,
"step": 10
},
{
"epoch": 0.7058823529411765,
"grad_norm": 16.97751235961914,
"learning_rate": 2.4000000000000003e-06,
"logits/chosen": -2.0030388832092285,
"logits/rejected": -2.02868914604187,
"logps/chosen": -176.69699096679688,
"logps/rejected": -73.69422912597656,
"loss": 0.2737,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.7846705913543701,
"rewards/margins": 1.3031082153320312,
"rewards/rejected": -0.5184376835823059,
"step": 15
},
{
"epoch": 0.9411764705882353,
"grad_norm": 12.779258728027344,
"learning_rate": 9e-07,
"logits/chosen": -1.9846420288085938,
"logits/rejected": -2.072688579559326,
"logps/chosen": -150.73324584960938,
"logps/rejected": -78.59916687011719,
"loss": 0.2197,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.8508585691452026,
"rewards/margins": 1.5887625217437744,
"rewards/rejected": -0.7379039525985718,
"step": 20
}
],
"logging_steps": 5,
"max_steps": 22,
"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": 2,
"trial_name": null,
"trial_params": null
}