File size: 1,685 Bytes
f52379d |
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 64 65 66 67 68 |
{
"best_metric": 0.6523297491039427,
"best_model_checkpoint": "distilbert-base-multilingual-cased-hyper-matt/run-m4sjb92w/checkpoint-25",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 25,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.4,
"grad_norm": 1.5911545753479004,
"learning_rate": 3.072424541935991e-05,
"loss": 0.5559,
"step": 10
},
{
"epoch": 0.8,
"grad_norm": 2.1426916122436523,
"learning_rate": 1.0241415139786638e-05,
"loss": 0.4676,
"step": 20
},
{
"epoch": 1.0,
"eval_accuracy": 0.7575,
"eval_f1": 0.6523297491039427,
"eval_loss": 0.45884665846824646,
"eval_precision": 0.5833333333333334,
"eval_recall": 0.7398373983739838,
"eval_runtime": 1.5883,
"eval_samples_per_second": 251.842,
"eval_steps_per_second": 15.74,
"step": 25
}
],
"logging_steps": 10,
"max_steps": 25,
"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": 169558270279680.0,
"train_batch_size": 64,
"trial_name": null,
"trial_params": {
"_wandb": {},
"assignments": {},
"learning_rate": 5.1207075698933185e-05,
"metric": "eval/loss",
"num_train_epochs": 1,
"per_device_train_batch_size": 64,
"seed": 18
}
}
|