tofu_grad-diff_1e-05_8_600_265 / trainer_state.json
advit's picture
Upload folder using huggingface_hub
fba6ae9 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": 0.8417389912494785,
"learning_rate": 9.59731543624161e-06,
"loss": 0.0045,
"step": 7
},
{
"epoch": 14.0,
"grad_norm": 0.4786471444985482,
"learning_rate": 9.12751677852349e-06,
"loss": 0.006,
"step": 14
},
{
"epoch": 21.0,
"grad_norm": 1.5881157316852257,
"learning_rate": 8.65771812080537e-06,
"loss": -0.0027,
"step": 21
},
{
"epoch": 28.0,
"grad_norm": 4.09206151385278,
"learning_rate": 8.18791946308725e-06,
"loss": -0.0348,
"step": 28
},
{
"epoch": 35.0,
"grad_norm": 5.01122840357199,
"learning_rate": 7.718120805369127e-06,
"loss": -0.1156,
"step": 35
},
{
"epoch": 42.0,
"grad_norm": 7.461285597467877,
"learning_rate": 7.248322147651007e-06,
"loss": -0.237,
"step": 42
},
{
"epoch": 49.0,
"grad_norm": 11.284996451666391,
"learning_rate": 6.778523489932887e-06,
"loss": -0.467,
"step": 49
},
{
"epoch": 56.0,
"grad_norm": 11.157239551789843,
"learning_rate": 6.308724832214766e-06,
"loss": -0.7162,
"step": 56
},
{
"epoch": 63.0,
"grad_norm": 10.809964246247898,
"learning_rate": 5.8389261744966455e-06,
"loss": -0.9948,
"step": 63
},
{
"epoch": 70.0,
"grad_norm": 11.305731350943853,
"learning_rate": 5.369127516778524e-06,
"loss": -1.2487,
"step": 70
},
{
"epoch": 77.0,
"grad_norm": 11.511427251209193,
"learning_rate": 4.899328859060403e-06,
"loss": -1.4888,
"step": 77
},
{
"epoch": 84.0,
"grad_norm": 11.051168991221283,
"learning_rate": 4.429530201342283e-06,
"loss": -1.7204,
"step": 84
},
{
"epoch": 91.0,
"grad_norm": 10.505646710728744,
"learning_rate": 3.959731543624161e-06,
"loss": -1.9089,
"step": 91
},
{
"epoch": 98.0,
"grad_norm": 9.219832421561724,
"learning_rate": 3.4899328859060407e-06,
"loss": -2.0656,
"step": 98
},
{
"epoch": 105.0,
"grad_norm": 10.008549145486828,
"learning_rate": 3.02013422818792e-06,
"loss": -2.2141,
"step": 105
},
{
"epoch": 112.0,
"grad_norm": 10.12067182034686,
"learning_rate": 2.5503355704697992e-06,
"loss": -2.3313,
"step": 112
},
{
"epoch": 119.0,
"grad_norm": 10.55600167069203,
"learning_rate": 2.080536912751678e-06,
"loss": -2.4331,
"step": 119
},
{
"epoch": 126.0,
"grad_norm": 10.283950245380707,
"learning_rate": 1.6107382550335572e-06,
"loss": -2.5125,
"step": 126
},
{
"epoch": 133.0,
"grad_norm": 11.69963455753479,
"learning_rate": 1.1409395973154363e-06,
"loss": -2.5995,
"step": 133
},
{
"epoch": 140.0,
"grad_norm": 12.463511811653747,
"learning_rate": 6.711409395973155e-07,
"loss": -2.6652,
"step": 140
},
{
"epoch": 147.0,
"grad_norm": 12.631801542285586,
"learning_rate": 2.0134228187919465e-07,
"loss": -2.6958,
"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
}