tofu_grad-diff_1e-05_8_600_2890 / trainer_state.json
advit's picture
Upload folder using huggingface_hub
08a4444 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": 0.25628022788974686,
"learning_rate": 9.59731543624161e-06,
"loss": 0.0074,
"step": 7
},
{
"epoch": 14.0,
"grad_norm": 0.8213893764378412,
"learning_rate": 9.12751677852349e-06,
"loss": 0.0035,
"step": 14
},
{
"epoch": 21.0,
"grad_norm": 3.146292715281867,
"learning_rate": 8.65771812080537e-06,
"loss": -0.0161,
"step": 21
},
{
"epoch": 28.0,
"grad_norm": 4.857079344482695,
"learning_rate": 8.18791946308725e-06,
"loss": -0.0724,
"step": 28
},
{
"epoch": 35.0,
"grad_norm": 5.031443674314287,
"learning_rate": 7.718120805369127e-06,
"loss": -0.1775,
"step": 35
},
{
"epoch": 42.0,
"grad_norm": 5.145416922127087,
"learning_rate": 7.248322147651007e-06,
"loss": -0.2899,
"step": 42
},
{
"epoch": 49.0,
"grad_norm": 6.581720364055563,
"learning_rate": 6.778523489932887e-06,
"loss": -0.4445,
"step": 49
},
{
"epoch": 56.0,
"grad_norm": 7.585066362427658,
"learning_rate": 6.308724832214766e-06,
"loss": -0.5908,
"step": 56
},
{
"epoch": 63.0,
"grad_norm": 9.4177403581883,
"learning_rate": 5.8389261744966455e-06,
"loss": -0.77,
"step": 63
},
{
"epoch": 70.0,
"grad_norm": 9.324274906321666,
"learning_rate": 5.369127516778524e-06,
"loss": -0.9715,
"step": 70
},
{
"epoch": 77.0,
"grad_norm": 9.902383056559504,
"learning_rate": 4.899328859060403e-06,
"loss": -1.1618,
"step": 77
},
{
"epoch": 84.0,
"grad_norm": 11.19757988214141,
"learning_rate": 4.429530201342283e-06,
"loss": -1.3546,
"step": 84
},
{
"epoch": 91.0,
"grad_norm": 11.43623948886692,
"learning_rate": 3.959731543624161e-06,
"loss": -1.533,
"step": 91
},
{
"epoch": 98.0,
"grad_norm": 10.582688185722402,
"learning_rate": 3.4899328859060407e-06,
"loss": -1.6989,
"step": 98
},
{
"epoch": 105.0,
"grad_norm": 13.279382764006586,
"learning_rate": 3.02013422818792e-06,
"loss": -1.891,
"step": 105
},
{
"epoch": 112.0,
"grad_norm": 14.948839812377317,
"learning_rate": 2.5503355704697992e-06,
"loss": -2.0501,
"step": 112
},
{
"epoch": 119.0,
"grad_norm": 15.741821959580664,
"learning_rate": 2.080536912751678e-06,
"loss": -2.2028,
"step": 119
},
{
"epoch": 126.0,
"grad_norm": 14.486664129387696,
"learning_rate": 1.6107382550335572e-06,
"loss": -2.3334,
"step": 126
},
{
"epoch": 133.0,
"grad_norm": 16.050469521299604,
"learning_rate": 1.1409395973154363e-06,
"loss": -2.4748,
"step": 133
},
{
"epoch": 140.0,
"grad_norm": 15.95606485295358,
"learning_rate": 6.711409395973155e-07,
"loss": -2.561,
"step": 140
},
{
"epoch": 147.0,
"grad_norm": 15.94923144352862,
"learning_rate": 2.0134228187919465e-07,
"loss": -2.6189,
"step": 147
}
],
"logging_steps": 7,
"max_steps": 150,
"num_input_tokens_seen": 0,
"num_train_epochs": 150,
"save_steps": 0,
"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
}