File size: 1,648 Bytes
503d527 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.18181818181818182,
"eval_steps": 9,
"global_step": 9,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.020202020202020204,
"eval_loss": 4.9802985191345215,
"eval_runtime": 2.3092,
"eval_samples_per_second": 36.376,
"eval_steps_per_second": 4.764,
"step": 1
},
{
"epoch": 0.06060606060606061,
"grad_norm": 3.5151710510253906,
"learning_rate": 1.5e-05,
"loss": 4.8465,
"step": 3
},
{
"epoch": 0.12121212121212122,
"grad_norm": 3.6303155422210693,
"learning_rate": 3e-05,
"loss": 4.8307,
"step": 6
},
{
"epoch": 0.18181818181818182,
"grad_norm": 3.675507068634033,
"learning_rate": 4.5e-05,
"loss": 4.7838,
"step": 9
},
{
"epoch": 0.18181818181818182,
"eval_loss": 4.756908893585205,
"eval_runtime": 2.3145,
"eval_samples_per_second": 36.293,
"eval_steps_per_second": 4.753,
"step": 9
}
],
"logging_steps": 3,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 9,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2351283906281472.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|