File size: 1,664 Bytes
e30beec a569556 7aeaae7 a569556 e30beec da43db1 a569556 7aeaae7 da43db1 e30beec da43db1 a569556 e30beec 7aeaae7 da43db1 a569556 7aeaae7 da43db1 7aeaae7 da43db1 a569556 7aeaae7 da43db1 7aeaae7 8d3381d da43db1 a569556 53ddeb5 e30beec 7aeaae7 e30beec 7aeaae7 e30beec a569556 e30beec a569556 7aeaae7 e30beec |
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": 0.0016825574873808188,
"eval_steps": 3,
"global_step": 3,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0005608524957936063,
"grad_norm": 0.014755763113498688,
"learning_rate": 2e-05,
"loss": 11.9315,
"step": 1
},
{
"epoch": 0.0005608524957936063,
"eval_loss": 11.931306838989258,
"eval_runtime": 2.7544,
"eval_samples_per_second": 272.651,
"eval_steps_per_second": 136.507,
"step": 1
},
{
"epoch": 0.0011217049915872126,
"grad_norm": 0.008283632807433605,
"learning_rate": 4e-05,
"loss": 11.9304,
"step": 2
},
{
"epoch": 0.0016825574873808188,
"grad_norm": 0.016088014468550682,
"learning_rate": 6e-05,
"loss": 11.9319,
"step": 3
},
{
"epoch": 0.0016825574873808188,
"eval_loss": 11.931303977966309,
"eval_runtime": 2.8104,
"eval_samples_per_second": 267.223,
"eval_steps_per_second": 133.789,
"step": 3
}
],
"logging_steps": 1,
"max_steps": 10,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 3,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 384024576.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|