tofu_grad-diff_1e-05_8_600_1000 / trainer_state.json
advit's picture
Upload folder using huggingface_hub
555edd8 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": 1.4699813338456935,
"learning_rate": 9.59731543624161e-06,
"loss": -0.0069,
"step": 7
},
{
"epoch": 14.0,
"grad_norm": 2.566041184048418,
"learning_rate": 9.12751677852349e-06,
"loss": -0.0223,
"step": 14
},
{
"epoch": 21.0,
"grad_norm": 3.9755727978224904,
"learning_rate": 8.65771812080537e-06,
"loss": -0.0701,
"step": 21
},
{
"epoch": 28.0,
"grad_norm": 5.259416437129205,
"learning_rate": 8.18791946308725e-06,
"loss": -0.1528,
"step": 28
},
{
"epoch": 35.0,
"grad_norm": 6.265130361541103,
"learning_rate": 7.718120805369127e-06,
"loss": -0.2856,
"step": 35
},
{
"epoch": 42.0,
"grad_norm": 7.190235408724265,
"learning_rate": 7.248322147651007e-06,
"loss": -0.4478,
"step": 42
},
{
"epoch": 49.0,
"grad_norm": 8.386072718169949,
"learning_rate": 6.778523489932887e-06,
"loss": -0.661,
"step": 49
},
{
"epoch": 56.0,
"grad_norm": 9.235590790539801,
"learning_rate": 6.308724832214766e-06,
"loss": -0.8643,
"step": 56
},
{
"epoch": 63.0,
"grad_norm": 9.838200514182319,
"learning_rate": 5.8389261744966455e-06,
"loss": -1.1025,
"step": 63
},
{
"epoch": 70.0,
"grad_norm": 10.706790904030157,
"learning_rate": 5.369127516778524e-06,
"loss": -1.2974,
"step": 70
},
{
"epoch": 77.0,
"grad_norm": 11.88970623267881,
"learning_rate": 4.899328859060403e-06,
"loss": -1.5504,
"step": 77
},
{
"epoch": 84.0,
"grad_norm": 12.550873695921803,
"learning_rate": 4.429530201342283e-06,
"loss": -1.787,
"step": 84
},
{
"epoch": 91.0,
"grad_norm": 12.71339801928843,
"learning_rate": 3.959731543624161e-06,
"loss": -2.0196,
"step": 91
},
{
"epoch": 98.0,
"grad_norm": 12.323045225577104,
"learning_rate": 3.4899328859060407e-06,
"loss": -2.2456,
"step": 98
},
{
"epoch": 105.0,
"grad_norm": 14.582427524923755,
"learning_rate": 3.02013422818792e-06,
"loss": -2.4526,
"step": 105
},
{
"epoch": 112.0,
"grad_norm": 18.031930253503727,
"learning_rate": 2.5503355704697992e-06,
"loss": -2.6399,
"step": 112
},
{
"epoch": 119.0,
"grad_norm": 20.96314616521406,
"learning_rate": 2.080536912751678e-06,
"loss": -2.7913,
"step": 119
},
{
"epoch": 126.0,
"grad_norm": 20.857768031534732,
"learning_rate": 1.6107382550335572e-06,
"loss": -3.0434,
"step": 126
},
{
"epoch": 133.0,
"grad_norm": 24.41375787013953,
"learning_rate": 1.1409395973154363e-06,
"loss": -3.2463,
"step": 133
},
{
"epoch": 140.0,
"grad_norm": 25.42343731327185,
"learning_rate": 6.711409395973155e-07,
"loss": -3.3968,
"step": 140
},
{
"epoch": 147.0,
"grad_norm": 25.6834807125128,
"learning_rate": 2.0134228187919465e-07,
"loss": -3.4758,
"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
}