tofu_grad-diff_1e-05_8_500_45 / trainer_state.json
advit's picture
Upload folder using huggingface_hub
ba88bd3 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 125.0,
"eval_steps": 0,
"global_step": 125,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 12.0,
"grad_norm": 0.09067032312404616,
"learning_rate": 9.558232931726908e-06,
"loss": 0.0072,
"step": 12
},
{
"epoch": 24.0,
"grad_norm": 0.06763341570399517,
"learning_rate": 9.076305220883535e-06,
"loss": 0.0043,
"step": 24
},
{
"epoch": 36.0,
"grad_norm": 0.15398053264897768,
"learning_rate": 8.594377510040161e-06,
"loss": 0.0029,
"step": 36
},
{
"epoch": 48.0,
"grad_norm": 1.1000194510831982,
"learning_rate": 8.112449799196788e-06,
"loss": -0.0006,
"step": 48
},
{
"epoch": 60.0,
"grad_norm": 6.584712321431927,
"learning_rate": 7.630522088353415e-06,
"loss": -0.0587,
"step": 60
},
{
"epoch": 72.0,
"grad_norm": 11.775876675062765,
"learning_rate": 7.148594377510041e-06,
"loss": -0.3513,
"step": 72
},
{
"epoch": 84.0,
"grad_norm": 12.433636936001625,
"learning_rate": 6.666666666666667e-06,
"loss": -0.884,
"step": 84
},
{
"epoch": 96.0,
"grad_norm": 11.218853545023476,
"learning_rate": 6.184738955823294e-06,
"loss": -1.3655,
"step": 96
},
{
"epoch": 108.0,
"grad_norm": 9.40429887044656,
"learning_rate": 5.70281124497992e-06,
"loss": -1.8017,
"step": 108
},
{
"epoch": 120.0,
"grad_norm": 9.99393860896854,
"learning_rate": 5.220883534136547e-06,
"loss": -2.1427,
"step": 120
}
],
"logging_steps": 12,
"max_steps": 250,
"num_input_tokens_seen": 0,
"num_train_epochs": 250,
"save_steps": 25,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}