File size: 1,455 Bytes
2f8c7b8 40e3ec3 2f8c7b8 40e3ec3 2f8c7b8 40e3ec3 2f8c7b8 40e3ec3 2f8c7b8 40e3ec3 2f8c7b8 40e3ec3 2f8c7b8 40e3ec3 2f8c7b8 40e3ec3 2f8c7b8 40e3ec3 2f8c7b8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 | {
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9997526589166461,
"eval_steps": 500,
"global_step": 2021,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.24734108335394508,
"grad_norm": 1.439273715019226,
"learning_rate": 7.535873330034637e-05,
"loss": 0.2317,
"step": 500
},
{
"epoch": 0.49468216670789017,
"grad_norm": 3.661175489425659,
"learning_rate": 5.061850569025235e-05,
"loss": 0.0951,
"step": 1000
},
{
"epoch": 0.7420232500618352,
"grad_norm": 2.657053232192993,
"learning_rate": 2.5878278080158342e-05,
"loss": 0.0719,
"step": 1500
},
{
"epoch": 0.9893643334157803,
"grad_norm": 4.781520843505859,
"learning_rate": 1.1380504700643246e-06,
"loss": 0.0668,
"step": 2000
}
],
"logging_steps": 500,
"max_steps": 2021,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 9.4486400434176e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|