File size: 1,428 Bytes
0b5c2b8 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.2653061224489797,
"eval_steps": 20,
"global_step": 40,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.82,
"grad_norm": 0.1748005896806717,
"learning_rate": 2.1e-05,
"loss": 4.8309,
"step": 10
},
{
"epoch": 1.63,
"grad_norm": 0.19310609996318817,
"learning_rate": 3.2999999999999996e-05,
"loss": 5.0159,
"step": 20
},
{
"epoch": 1.63,
"eval_loss": NaN,
"eval_runtime": 53.474,
"eval_samples_per_second": 7.237,
"eval_steps_per_second": 0.916,
"step": 20
},
{
"epoch": 2.45,
"grad_norm": NaN,
"learning_rate": 4.2e-05,
"loss": 4.8025,
"step": 30
},
{
"epoch": 3.27,
"grad_norm": NaN,
"learning_rate": 5.399999999999999e-05,
"loss": 4.1014,
"step": 40
},
{
"epoch": 3.27,
"eval_loss": NaN,
"eval_runtime": 53.4777,
"eval_samples_per_second": 7.237,
"eval_steps_per_second": 0.916,
"step": 40
}
],
"logging_steps": 10,
"max_steps": 400,
"num_input_tokens_seen": 0,
"num_train_epochs": 34,
"save_steps": 20,
"total_flos": 1.0133225920167936e+17,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}
|