File size: 1,738 Bytes
67e0246 74bc8e0 67e0246 74bc8e0 67e0246 74bc8e0 67e0246 74bc8e0 67e0246 74bc8e0 67e0246 | 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 69 70 71 72 | {
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9959839357429718,
"eval_steps": 30,
"global_step": 31,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.321285140562249,
"grad_norm": 0.5042463327687016,
"learning_rate": 8.83022221559489e-05,
"loss": 0.668,
"step": 10
},
{
"epoch": 0.642570281124498,
"grad_norm": 0.4073430870409904,
"learning_rate": 3.5659838364445505e-05,
"loss": 0.4073,
"step": 20
},
{
"epoch": 0.963855421686747,
"grad_norm": 0.3439649236092943,
"learning_rate": 3.380821129028489e-07,
"loss": 0.3531,
"step": 30
},
{
"epoch": 0.963855421686747,
"eval_loss": 0.32887399196624756,
"eval_runtime": 16.2654,
"eval_samples_per_second": 5.041,
"eval_steps_per_second": 0.676,
"step": 30
},
{
"epoch": 0.9959839357429718,
"step": 31,
"total_flos": 2886883717677056.0,
"train_loss": 0.46779590124084103,
"train_runtime": 2530.0595,
"train_samples_per_second": 1.575,
"train_steps_per_second": 0.012
}
],
"logging_steps": 10,
"max_steps": 31,
"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": 2886883717677056.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|