File size: 1,246 Bytes
3e44fed |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.2345679012345678,
"eval_steps": 500,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.37037037037037035,
"grad_norm": 69.9074478149414,
"learning_rate": 9.952e-06,
"loss": 4.4273,
"step": 30
},
{
"epoch": 0.7407407407407407,
"grad_norm": 96.12484741210938,
"learning_rate": 9.892000000000001e-06,
"loss": 2.6895,
"step": 60
},
{
"epoch": 1.1111111111111112,
"grad_norm": 43.14171600341797,
"learning_rate": 9.832e-06,
"loss": 2.4001,
"step": 90
}
],
"logging_steps": 30,
"max_steps": 5000,
"num_input_tokens_seen": 0,
"num_train_epochs": 62,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.82243166208e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|