File size: 1,473 Bytes
29616b0 |
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 63 |
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.7694527267481004,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1923631816870251,
"grad_norm": 70.2215347290039,
"learning_rate": 8.080769230769231e-06,
"loss": -100.6029,
"step": 500
},
{
"epoch": 0.3847263633740502,
"grad_norm": 1890.31591796875,
"learning_rate": 6.157692307692308e-06,
"loss": -151.516,
"step": 1000
},
{
"epoch": 0.5770895450610753,
"grad_norm": 258.2842102050781,
"learning_rate": 4.234615384615385e-06,
"loss": -154.422,
"step": 1500
},
{
"epoch": 0.7694527267481004,
"grad_norm": 101.9043197631836,
"learning_rate": 2.3115384615384617e-06,
"loss": -157.1482,
"step": 2000
}
],
"logging_steps": 500,
"max_steps": 2600,
"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": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|