131 lines
3.3 KiB
JSON
131 lines
3.3 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.005996509843879929,
|
||
|
|
"eval_steps": 99999999,
|
||
|
|
"global_step": 32,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.0001873909326212478,
|
||
|
|
"grad_norm": 245.6398468017578,
|
||
|
|
"learning_rate": 5e-05,
|
||
|
|
"loss": 175.7636,
|
||
|
|
"step": 1
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.0001873909326212478,
|
||
|
|
"eval_accuracy": 0.015452299171252725,
|
||
|
|
"eval_loss": 10.732580184936523,
|
||
|
|
"eval_runtime": 219.7551,
|
||
|
|
"eval_samples_per_second": 35.922,
|
||
|
|
"eval_steps_per_second": 4.491,
|
||
|
|
"step": 1
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.0003747818652424956,
|
||
|
|
"grad_norm": 113.21331024169922,
|
||
|
|
"learning_rate": 4.9990631440884397e-05,
|
||
|
|
"loss": 161.0339,
|
||
|
|
"step": 2
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.0003747818652424956,
|
||
|
|
"eval_accuracy": 0.015452299171252725,
|
||
|
|
"eval_loss": 10.66187572479248,
|
||
|
|
"eval_runtime": 137.4523,
|
||
|
|
"eval_samples_per_second": 57.431,
|
||
|
|
"eval_steps_per_second": 7.181,
|
||
|
|
"step": 2
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.0007495637304849911,
|
||
|
|
"grad_norm": 65.50191497802734,
|
||
|
|
"learning_rate": 4.997189432265318e-05,
|
||
|
|
"loss": 156.102,
|
||
|
|
"step": 4
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.0007495637304849911,
|
||
|
|
"eval_accuracy": 0.015464063058397669,
|
||
|
|
"eval_loss": 10.59908676147461,
|
||
|
|
"eval_runtime": 188.7788,
|
||
|
|
"eval_samples_per_second": 41.816,
|
||
|
|
"eval_steps_per_second": 5.228,
|
||
|
|
"step": 4
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.0014991274609699823,
|
||
|
|
"grad_norm": 38.306678771972656,
|
||
|
|
"learning_rate": 4.993442008619075e-05,
|
||
|
|
"loss": 152.2921,
|
||
|
|
"step": 8
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.0014991274609699823,
|
||
|
|
"eval_accuracy": 0.015459481333930691,
|
||
|
|
"eval_loss": 10.50749397277832,
|
||
|
|
"eval_runtime": 140.9589,
|
||
|
|
"eval_samples_per_second": 56.002,
|
||
|
|
"eval_steps_per_second": 7.002,
|
||
|
|
"step": 8
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.0029982549219399646,
|
||
|
|
"grad_norm": 33.0531005859375,
|
||
|
|
"learning_rate": 4.985947161326589e-05,
|
||
|
|
"loss": 148.7237,
|
||
|
|
"step": 16
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.0029982549219399646,
|
||
|
|
"eval_accuracy": 0.018715353804478252,
|
||
|
|
"eval_loss": 10.448219299316406,
|
||
|
|
"eval_runtime": 215.51,
|
||
|
|
"eval_samples_per_second": 36.629,
|
||
|
|
"eval_steps_per_second": 4.58,
|
||
|
|
"step": 16
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.005996509843879929,
|
||
|
|
"grad_norm": 33.14303207397461,
|
||
|
|
"learning_rate": 4.970957466741615e-05,
|
||
|
|
"loss": 141.2197,
|
||
|
|
"step": 32
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.005996509843879929,
|
||
|
|
"eval_accuracy": 0.02386372614066984,
|
||
|
|
"eval_loss": 10.312174797058105,
|
||
|
|
"eval_runtime": 201.4605,
|
||
|
|
"eval_samples_per_second": 39.184,
|
||
|
|
"eval_steps_per_second": 4.899,
|
||
|
|
"step": 32
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 99999999,
|
||
|
|
"max_steps": 5337,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"save_steps": 99999999,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 2140504326144000.0,
|
||
|
|
"train_batch_size": 8,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|