File size: 1,662 Bytes
e30beec 53ddeb5 7aeaae7 53ddeb5 e30beec 53ddeb5 7aeaae7 53ddeb5 e30beec 53ddeb5 e30beec 7aeaae7 53ddeb5 7aeaae7 53ddeb5 7aeaae7 53ddeb5 7aeaae7 53ddeb5 7aeaae7 8d3381d 53ddeb5 e30beec 7aeaae7 e30beec 7aeaae7 e30beec 53ddeb5 e30beec 53ddeb5 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": 0.0033651149747616375,
"eval_steps": 3,
"global_step": 3,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0011217049915872126,
"grad_norm": 0.010464487597346306,
"learning_rate": 2e-05,
"loss": 11.9305,
"step": 1
},
{
"epoch": 0.0011217049915872126,
"eval_loss": 11.931302070617676,
"eval_runtime": 1.6109,
"eval_samples_per_second": 466.206,
"eval_steps_per_second": 116.707,
"step": 1
},
{
"epoch": 0.002243409983174425,
"grad_norm": 0.012750067748129368,
"learning_rate": 4e-05,
"loss": 11.9324,
"step": 2
},
{
"epoch": 0.0033651149747616375,
"grad_norm": 0.01111360639333725,
"learning_rate": 6e-05,
"loss": 11.9253,
"step": 3
},
{
"epoch": 0.0033651149747616375,
"eval_loss": 11.931297302246094,
"eval_runtime": 1.6294,
"eval_samples_per_second": 460.916,
"eval_steps_per_second": 115.382,
"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": 738508800.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|