File size: 1,472 Bytes
6cabc50 cfae386 6cabc50 cfae386 6cabc50 184ce01 cfae386 6cabc50 cfae386 6cabc50 | 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_metric": null,
"best_model_checkpoint": null,
"epoch": 1.2468827930174564,
"eval_steps": 500,
"global_step": 1500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.41562759767248547,
"grad_norm": 56089.828125,
"learning_rate": 1.7229149348850097e-05,
"loss": 0.4691,
"step": 500
},
{
"epoch": 0.8312551953449709,
"grad_norm": 31839.919921875,
"learning_rate": 1.4458298697700195e-05,
"loss": 0.392,
"step": 1000
},
{
"epoch": 1.0,
"eval_loss": 0.31241247057914734,
"eval_runtime": 34.4517,
"eval_samples_per_second": 14.339,
"eval_steps_per_second": 1.8,
"step": 1203
},
{
"epoch": 1.2468827930174564,
"grad_norm": 29103.794921875,
"learning_rate": 1.1687448046550292e-05,
"loss": 0.3735,
"step": 1500
}
],
"logging_steps": 500,
"max_steps": 3609,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 7306885728829440.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|