dnd-x4 / trainer_state.json
lodrick-the-lafted's picture
Upload folder using huggingface_hub
29819c9 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9309090909090909,
"eval_steps": 500,
"global_step": 16,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05818181818181818,
"grad_norm": 29.06173240606997,
"learning_rate": 6.666666666666667e-07,
"loss": 1.6056,
"step": 1
},
{
"epoch": 0.11636363636363636,
"grad_norm": 33.11539051626074,
"learning_rate": 1.3333333333333334e-06,
"loss": 1.6191,
"step": 2
},
{
"epoch": 0.17454545454545456,
"grad_norm": 26.63160827688533,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.5718,
"step": 3
},
{
"epoch": 0.23272727272727273,
"grad_norm": 14.191035966685748,
"learning_rate": 2.666666666666667e-06,
"loss": 1.3925,
"step": 4
},
{
"epoch": 0.2909090909090909,
"grad_norm": 7.533285764918969,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.2544,
"step": 5
},
{
"epoch": 0.3490909090909091,
"grad_norm": 5.548373808167863,
"learning_rate": 4.000000000000001e-06,
"loss": 1.323,
"step": 6
},
{
"epoch": 0.4072727272727273,
"grad_norm": 6.463847939558766,
"learning_rate": 4.666666666666667e-06,
"loss": 1.0632,
"step": 7
},
{
"epoch": 0.46545454545454545,
"grad_norm": 4.758530699604651,
"learning_rate": 5.333333333333334e-06,
"loss": 1.1021,
"step": 8
},
{
"epoch": 0.5236363636363637,
"grad_norm": 4.09443774321632,
"learning_rate": 6e-06,
"loss": 1.0727,
"step": 9
},
{
"epoch": 0.5818181818181818,
"grad_norm": 3.655837928622172,
"learning_rate": 6.666666666666667e-06,
"loss": 1.0485,
"step": 10
},
{
"epoch": 0.64,
"grad_norm": 2.559904495644721,
"learning_rate": 7.333333333333333e-06,
"loss": 1.0662,
"step": 11
},
{
"epoch": 0.6981818181818182,
"grad_norm": 2.7664462242928543,
"learning_rate": 8.000000000000001e-06,
"loss": 1.0107,
"step": 12
},
{
"epoch": 0.7563636363636363,
"grad_norm": 2.5753839738123783,
"learning_rate": 8.666666666666668e-06,
"loss": 0.9393,
"step": 13
},
{
"epoch": 0.8145454545454546,
"grad_norm": 2.8285590821566657,
"learning_rate": 9.333333333333334e-06,
"loss": 0.97,
"step": 14
},
{
"epoch": 0.8727272727272727,
"grad_norm": 2.588452638553932,
"learning_rate": 1e-05,
"loss": 0.9732,
"step": 15
},
{
"epoch": 0.9309090909090909,
"grad_norm": 2.5969098968062427,
"learning_rate": 5e-06,
"loss": 0.9705,
"step": 16
}
],
"logging_steps": 1,
"max_steps": 17,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 4,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 30366593187840.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}