121 lines
2.9 KiB
JSON
121 lines
2.9 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 58,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.08620689655172414,
|
||
|
|
"grad_norm": 2.4018161296844482,
|
||
|
|
"learning_rate": 1.3333333333333333e-05,
|
||
|
|
"loss": 0.4234,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.1724137931034483,
|
||
|
|
"grad_norm": 1.6455100774765015,
|
||
|
|
"learning_rate": 1.983619906947144e-05,
|
||
|
|
"loss": 0.0817,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.25862068965517243,
|
||
|
|
"grad_norm": 0.3768883943557739,
|
||
|
|
"learning_rate": 1.8854560256532098e-05,
|
||
|
|
"loss": 0.0811,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3448275862068966,
|
||
|
|
"grad_norm": 0.7822470664978027,
|
||
|
|
"learning_rate": 1.7071067811865477e-05,
|
||
|
|
"loss": 0.0808,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.43103448275862066,
|
||
|
|
"grad_norm": 0.18719947338104248,
|
||
|
|
"learning_rate": 1.4647231720437687e-05,
|
||
|
|
"loss": 0.078,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5172413793103449,
|
||
|
|
"grad_norm": 0.009137788787484169,
|
||
|
|
"learning_rate": 1.180255037813906e-05,
|
||
|
|
"loss": 0.0781,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.603448275862069,
|
||
|
|
"grad_norm": 0.19379863142967224,
|
||
|
|
"learning_rate": 8.79463319744677e-06,
|
||
|
|
"loss": 0.0779,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6896551724137931,
|
||
|
|
"grad_norm": 0.265879362821579,
|
||
|
|
"learning_rate": 5.895871945472434e-06,
|
||
|
|
"loss": 0.0772,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7758620689655172,
|
||
|
|
"grad_norm": 0.38630935549736023,
|
||
|
|
"learning_rate": 3.3687734175920505e-06,
|
||
|
|
"loss": 0.0776,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8620689655172413,
|
||
|
|
"grad_norm": 0.533342182636261,
|
||
|
|
"learning_rate": 1.4421872769855262e-06,
|
||
|
|
"loss": 0.0779,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9482758620689655,
|
||
|
|
"grad_norm": 0.6314339637756348,
|
||
|
|
"learning_rate": 2.905818257394799e-07,
|
||
|
|
"loss": 0.0776,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"step": 58,
|
||
|
|
"total_flos": 2.1110553137958093e+17,
|
||
|
|
"train_loss": 0.10852315148402905,
|
||
|
|
"train_runtime": 1273.7115,
|
||
|
|
"train_samples_per_second": 2.893,
|
||
|
|
"train_steps_per_second": 0.046
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 58,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"save_steps": 500,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": true
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 2.1110553137958093e+17,
|
||
|
|
"train_batch_size": 8,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|