File size: 1,366 Bytes
f51cdbd |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0011090494166826625,
"eval_steps": 13,
"global_step": 13,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 8.531149359097404e-05,
"eval_loss": 3.899817705154419,
"eval_runtime": 66.4454,
"eval_samples_per_second": 74.287,
"eval_steps_per_second": 37.143,
"step": 1
},
{
"epoch": 0.0008531149359097404,
"grad_norm": 11.559722900390625,
"learning_rate": 0.00019396926207859084,
"loss": 14.6898,
"step": 10
},
{
"epoch": 0.0011090494166826625,
"eval_loss": 3.0394980907440186,
"eval_runtime": 64.5588,
"eval_samples_per_second": 76.457,
"eval_steps_per_second": 38.229,
"step": 13
}
],
"logging_steps": 10,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 13,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 463086746075136.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|