tofu_grad-diff_1e-05_8_600_183 / trainer_state.json
advit's picture
Upload folder using huggingface_hub
3f5ac8b 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": 1.0295407709529605,
"learning_rate": 9.59731543624161e-06,
"loss": -0.0013,
"step": 7
},
{
"epoch": 14.0,
"grad_norm": 1.6101380262999287,
"learning_rate": 9.12751677852349e-06,
"loss": -0.0058,
"step": 14
},
{
"epoch": 21.0,
"grad_norm": 2.5587235082879776,
"learning_rate": 8.65771812080537e-06,
"loss": -0.0312,
"step": 21
},
{
"epoch": 28.0,
"grad_norm": 3.0893433725673454,
"learning_rate": 8.18791946308725e-06,
"loss": -0.0788,
"step": 28
},
{
"epoch": 35.0,
"grad_norm": 3.5293163473047855,
"learning_rate": 7.718120805369127e-06,
"loss": -0.1452,
"step": 35
},
{
"epoch": 42.0,
"grad_norm": 5.547655411769822,
"learning_rate": 7.248322147651007e-06,
"loss": -0.2301,
"step": 42
},
{
"epoch": 49.0,
"grad_norm": 6.267911262269076,
"learning_rate": 6.778523489932887e-06,
"loss": -0.3565,
"step": 49
},
{
"epoch": 56.0,
"grad_norm": 6.378474139857179,
"learning_rate": 6.308724832214766e-06,
"loss": -0.4772,
"step": 56
},
{
"epoch": 63.0,
"grad_norm": 7.004648466723094,
"learning_rate": 5.8389261744966455e-06,
"loss": -0.6215,
"step": 63
},
{
"epoch": 70.0,
"grad_norm": 7.793761360598229,
"learning_rate": 5.369127516778524e-06,
"loss": -0.7594,
"step": 70
},
{
"epoch": 77.0,
"grad_norm": 8.262674888938404,
"learning_rate": 4.899328859060403e-06,
"loss": -0.9162,
"step": 77
},
{
"epoch": 84.0,
"grad_norm": 8.759817078561511,
"learning_rate": 4.429530201342283e-06,
"loss": -1.0719,
"step": 84
},
{
"epoch": 91.0,
"grad_norm": 8.974379267405835,
"learning_rate": 3.959731543624161e-06,
"loss": -1.2296,
"step": 91
},
{
"epoch": 98.0,
"grad_norm": 8.512101866353056,
"learning_rate": 3.4899328859060407e-06,
"loss": -1.3786,
"step": 98
},
{
"epoch": 105.0,
"grad_norm": 14.171190279456566,
"learning_rate": 3.02013422818792e-06,
"loss": -1.5287,
"step": 105
},
{
"epoch": 112.0,
"grad_norm": 24.98075124263089,
"learning_rate": 2.5503355704697992e-06,
"loss": -1.7145,
"step": 112
},
{
"epoch": 119.0,
"grad_norm": 24.356176616593,
"learning_rate": 2.080536912751678e-06,
"loss": -1.9954,
"step": 119
},
{
"epoch": 126.0,
"grad_norm": 21.64072093604211,
"learning_rate": 1.6107382550335572e-06,
"loss": -2.2458,
"step": 126
},
{
"epoch": 133.0,
"grad_norm": 23.479147717645056,
"learning_rate": 1.1409395973154363e-06,
"loss": -2.4623,
"step": 133
},
{
"epoch": 140.0,
"grad_norm": 23.31261623994507,
"learning_rate": 6.711409395973155e-07,
"loss": -2.5786,
"step": 140
},
{
"epoch": 147.0,
"grad_norm": 22.7183002708223,
"learning_rate": 2.0134228187919465e-07,
"loss": -2.6816,
"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
}