tofu_grad-diff_1e-05_8_600_1883 / trainer_state.json
advit's picture
Upload folder using huggingface_hub
d62f697 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": 0.6107874579526225,
"learning_rate": 9.59731543624161e-06,
"loss": 0.0002,
"step": 7
},
{
"epoch": 14.0,
"grad_norm": 1.8362841815977748,
"learning_rate": 9.12751677852349e-06,
"loss": -0.0076,
"step": 14
},
{
"epoch": 21.0,
"grad_norm": 3.2374627346013236,
"learning_rate": 8.65771812080537e-06,
"loss": -0.0412,
"step": 21
},
{
"epoch": 28.0,
"grad_norm": 4.622968153267193,
"learning_rate": 8.18791946308725e-06,
"loss": -0.1087,
"step": 28
},
{
"epoch": 35.0,
"grad_norm": 5.641018081333198,
"learning_rate": 7.718120805369127e-06,
"loss": -0.2239,
"step": 35
},
{
"epoch": 42.0,
"grad_norm": 5.606092401750038,
"learning_rate": 7.248322147651007e-06,
"loss": -0.3627,
"step": 42
},
{
"epoch": 49.0,
"grad_norm": 6.5853437590918,
"learning_rate": 6.778523489932887e-06,
"loss": -0.529,
"step": 49
},
{
"epoch": 56.0,
"grad_norm": 7.206903412278825,
"learning_rate": 6.308724832214766e-06,
"loss": -0.6741,
"step": 56
},
{
"epoch": 63.0,
"grad_norm": 7.6024521024219345,
"learning_rate": 5.8389261744966455e-06,
"loss": -0.851,
"step": 63
},
{
"epoch": 70.0,
"grad_norm": 8.315299788205518,
"learning_rate": 5.369127516778524e-06,
"loss": -1.0112,
"step": 70
},
{
"epoch": 77.0,
"grad_norm": 9.00404875274923,
"learning_rate": 4.899328859060403e-06,
"loss": -1.1947,
"step": 77
},
{
"epoch": 84.0,
"grad_norm": 10.130676403138883,
"learning_rate": 4.429530201342283e-06,
"loss": -1.3739,
"step": 84
},
{
"epoch": 91.0,
"grad_norm": 12.908375105735518,
"learning_rate": 3.959731543624161e-06,
"loss": -1.5594,
"step": 91
},
{
"epoch": 98.0,
"grad_norm": 14.681669468186767,
"learning_rate": 3.4899328859060407e-06,
"loss": -1.7764,
"step": 98
},
{
"epoch": 105.0,
"grad_norm": 16.20082654123523,
"learning_rate": 3.02013422818792e-06,
"loss": -2.0193,
"step": 105
},
{
"epoch": 112.0,
"grad_norm": 15.988354700411382,
"learning_rate": 2.5503355704697992e-06,
"loss": -2.2288,
"step": 112
},
{
"epoch": 119.0,
"grad_norm": 15.760785964878352,
"learning_rate": 2.080536912751678e-06,
"loss": -2.4097,
"step": 119
},
{
"epoch": 126.0,
"grad_norm": 14.411480189628838,
"learning_rate": 1.6107382550335572e-06,
"loss": -2.5561,
"step": 126
},
{
"epoch": 133.0,
"grad_norm": 15.337007526277898,
"learning_rate": 1.1409395973154363e-06,
"loss": -2.6913,
"step": 133
},
{
"epoch": 140.0,
"grad_norm": 15.293177432264137,
"learning_rate": 6.711409395973155e-07,
"loss": -2.7731,
"step": 140
},
{
"epoch": 147.0,
"grad_norm": 15.353543008399216,
"learning_rate": 2.0134228187919465e-07,
"loss": -2.8297,
"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
}