File size: 1,510 Bytes
27aa9e0 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.4390243902439024,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_loss": 0.2154720425605774,
"eval_runtime": 17.0977,
"eval_samples_per_second": 64.219,
"eval_steps_per_second": 4.036,
"step": 410
},
{
"epoch": 1.2195121951219512,
"grad_norm": 2.2100486755371094,
"learning_rate": 1.1869918699186992e-05,
"loss": 0.4673,
"step": 500
},
{
"epoch": 2.0,
"eval_loss": 0.10782822966575623,
"eval_runtime": 17.1231,
"eval_samples_per_second": 64.124,
"eval_steps_per_second": 4.03,
"step": 820
},
{
"epoch": 2.4390243902439024,
"grad_norm": 0.8097894787788391,
"learning_rate": 3.7398373983739838e-06,
"loss": 0.1029,
"step": 1000
}
],
"logging_steps": 500,
"max_steps": 1230,
"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": 4184868077568000.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}
|