120 lines
2.7 KiB (Stored with Git LFS)
JSON
120 lines
2.7 KiB (Stored with Git LFS)
JSON
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.9932279909706546,
|
|
"eval_steps": 500,
|
|
"global_step": 110,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.09029345372460497,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 9.921152889737985e-06,
|
|
"loss": 1.0434,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 0.18058690744920994,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 9.448285454973739e-06,
|
|
"loss": 1.0444,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.2708803611738149,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 8.587536285221656e-06,
|
|
"loss": 0.978,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 0.3611738148984199,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 7.413961013653725e-06,
|
|
"loss": 1.0049,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 0.45146726862302483,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 6.029893093705492e-06,
|
|
"loss": 0.972,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 0.5417607223476298,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 4.556020523385326e-06,
|
|
"loss": 0.9987,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 0.6320541760722348,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 3.1208620894288105e-06,
|
|
"loss": 0.988,
|
|
"step": 70
|
|
},
|
|
{
|
|
"epoch": 0.7223476297968398,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 1.8495607820914451e-06,
|
|
"loss": 0.9637,
|
|
"step": 80
|
|
},
|
|
{
|
|
"epoch": 0.8126410835214447,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 8.529715727489912e-07,
|
|
"loss": 0.9834,
|
|
"step": 90
|
|
},
|
|
{
|
|
"epoch": 0.9029345372460497,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 2.179950786173879e-07,
|
|
"loss": 1.012,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.9932279909706546,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0,
|
|
"loss": 1.0422,
|
|
"step": 110
|
|
},
|
|
{
|
|
"epoch": 0.9932279909706546,
|
|
"step": 110,
|
|
"total_flos": 1.1335431340058214e+17,
|
|
"train_loss": 1.0027889251708983,
|
|
"train_runtime": 1026.1033,
|
|
"train_samples_per_second": 3.455,
|
|
"train_steps_per_second": 0.107
|
|
}
|
|
],
|
|
"logging_steps": 10,
|
|
"max_steps": 110,
|
|
"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": 1.1335431340058214e+17,
|
|
"train_batch_size": 1,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|