File size: 2,341 Bytes
b1e4085 5d07de2 b1e4085 5d07de2 b1e4085 5d07de2 b1e4085 5d07de2 b1e4085 5d07de2 b1e4085 5d07de2 b1e4085 5d07de2 b1e4085 5d07de2 b1e4085 5d07de2 b1e4085 5d07de2 b1e4085 |
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 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.716981132075472,
"eval_steps": 500,
"global_step": 1500,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.5741935483870968,
"eval_loss": 0.21353885531425476,
"eval_runtime": 5.4329,
"eval_samples_per_second": 570.601,
"eval_steps_per_second": 11.964,
"step": 318
},
{
"epoch": 1.5723270440251573,
"grad_norm": 0.553505003452301,
"learning_rate": 1.371069182389937e-05,
"loss": 0.3345,
"step": 500
},
{
"epoch": 2.0,
"eval_accuracy": 0.8087096774193548,
"eval_loss": 0.10993640869855881,
"eval_runtime": 6.0275,
"eval_samples_per_second": 514.313,
"eval_steps_per_second": 10.784,
"step": 636
},
{
"epoch": 3.0,
"eval_accuracy": 0.8596774193548387,
"eval_loss": 0.0786653459072113,
"eval_runtime": 5.5267,
"eval_samples_per_second": 560.911,
"eval_steps_per_second": 11.761,
"step": 954
},
{
"epoch": 3.1446540880503147,
"grad_norm": 0.48568108677864075,
"learning_rate": 7.421383647798742e-06,
"loss": 0.1269,
"step": 1000
},
{
"epoch": 4.0,
"eval_accuracy": 0.8790322580645161,
"eval_loss": 0.06603369116783142,
"eval_runtime": 5.5422,
"eval_samples_per_second": 559.348,
"eval_steps_per_second": 11.728,
"step": 1272
},
{
"epoch": 4.716981132075472,
"grad_norm": 0.3628057539463043,
"learning_rate": 1.1320754716981133e-06,
"loss": 0.0909,
"step": 1500
}
],
"logging_steps": 500,
"max_steps": 1590,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"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": 391368939443328.0,
"train_batch_size": 48,
"trial_name": null,
"trial_params": {
"alpha": 0.5191171844972077,
"num_train_epochs": 5,
"temperature": 9
}
}
|