rwku_grad-diff_1e-05_8_600_362 / trainer_state.json
advit's picture
Upload folder using huggingface_hub
4b7d9fe verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 150.0,
"eval_steps": 0,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 7.0,
"grad_norm": 48.4139042121476,
"learning_rate": 9.59731543624161e-06,
"loss": -1.7565,
"step": 7
},
{
"epoch": 14.0,
"grad_norm": 52.59146449904736,
"learning_rate": 9.12751677852349e-06,
"loss": -1.7613,
"step": 14
},
{
"epoch": 21.0,
"grad_norm": 47.26514678968975,
"learning_rate": 8.65771812080537e-06,
"loss": -3.3713,
"step": 21
},
{
"epoch": 28.0,
"grad_norm": 46.58180426373221,
"learning_rate": 8.18791946308725e-06,
"loss": -3.2182,
"step": 28
},
{
"epoch": 35.0,
"grad_norm": 49.96836818031308,
"learning_rate": 7.718120805369127e-06,
"loss": -4.3871,
"step": 35
},
{
"epoch": 42.0,
"grad_norm": 51.36942343142531,
"learning_rate": 7.248322147651007e-06,
"loss": -6.0204,
"step": 42
},
{
"epoch": 49.0,
"grad_norm": 57.98074681502372,
"learning_rate": 6.778523489932887e-06,
"loss": -7.6868,
"step": 49
},
{
"epoch": 56.0,
"grad_norm": 63.94053871326419,
"learning_rate": 6.308724832214766e-06,
"loss": -8.3268,
"step": 56
},
{
"epoch": 63.0,
"grad_norm": 69.6805815155802,
"learning_rate": 5.8389261744966455e-06,
"loss": -10.5719,
"step": 63
},
{
"epoch": 70.0,
"grad_norm": 67.34407931241151,
"learning_rate": 5.369127516778524e-06,
"loss": -11.0897,
"step": 70
},
{
"epoch": 77.0,
"grad_norm": 67.18560177039734,
"learning_rate": 4.899328859060403e-06,
"loss": -12.9657,
"step": 77
},
{
"epoch": 84.0,
"grad_norm": 65.05528975579614,
"learning_rate": 4.429530201342283e-06,
"loss": -13.5019,
"step": 84
},
{
"epoch": 91.0,
"grad_norm": 68.36811466181042,
"learning_rate": 3.959731543624161e-06,
"loss": -14.4435,
"step": 91
},
{
"epoch": 98.0,
"grad_norm": 61.60167621847075,
"learning_rate": 3.4899328859060407e-06,
"loss": -15.6623,
"step": 98
},
{
"epoch": 105.0,
"grad_norm": 64.00094153911085,
"learning_rate": 3.02013422818792e-06,
"loss": -17.1393,
"step": 105
},
{
"epoch": 112.0,
"grad_norm": 63.87128213160341,
"learning_rate": 2.5503355704697992e-06,
"loss": -17.6534,
"step": 112
},
{
"epoch": 119.0,
"grad_norm": 64.38897540669797,
"learning_rate": 2.080536912751678e-06,
"loss": -18.0848,
"step": 119
},
{
"epoch": 126.0,
"grad_norm": 69.13070299837193,
"learning_rate": 1.6107382550335572e-06,
"loss": -18.2882,
"step": 126
},
{
"epoch": 133.0,
"grad_norm": 77.86614653780259,
"learning_rate": 1.1409395973154363e-06,
"loss": -18.8161,
"step": 133
},
{
"epoch": 140.0,
"grad_norm": 71.46054590772218,
"learning_rate": 6.711409395973155e-07,
"loss": -19.1841,
"step": 140
},
{
"epoch": 147.0,
"grad_norm": 69.2287092573417,
"learning_rate": 2.0134228187919465e-07,
"loss": -19.8017,
"step": 147
}
],
"logging_steps": 7,
"max_steps": 150,
"num_input_tokens_seen": 0,
"num_train_epochs": 150,
"save_steps": 15,
"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": 1,
"trial_name": null,
"trial_params": null
}