File size: 1,637 Bytes
2b86ebd |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.2727272727272725,
"eval_steps": 500,
"global_step": 6,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.7272727272727273,
"eval_loss": 1.2520767450332642,
"eval_runtime": 3.3961,
"eval_samples_per_second": 21.201,
"eval_steps_per_second": 0.589,
"step": 2
},
{
"epoch": 1.8636363636363638,
"eval_loss": 1.2290809154510498,
"eval_runtime": 3.2611,
"eval_samples_per_second": 22.078,
"eval_steps_per_second": 0.613,
"step": 5
},
{
"epoch": 2.2727272727272725,
"eval_loss": 1.1983939409255981,
"eval_runtime": 3.281,
"eval_samples_per_second": 21.945,
"eval_steps_per_second": 0.61,
"step": 6
},
{
"epoch": 2.2727272727272725,
"step": 6,
"total_flos": 9840843816960.0,
"train_loss": 1.4369689623514812,
"train_runtime": 552.6919,
"train_samples_per_second": 7.322,
"train_steps_per_second": 0.011
}
],
"logging_steps": 10,
"max_steps": 6,
"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": true
},
"attributes": {}
}
},
"total_flos": 9840843816960.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|