|
{ |
|
"best_metric": 1.0984796285629272, |
|
"best_model_checkpoint": "/kaggle/output/checkpoint-4000", |
|
"epoch": 0.16297262059973924, |
|
"eval_steps": 1000, |
|
"global_step": 4000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 2.7777777777777777e-11, |
|
"loss": 1.05, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 2.7750000000000004e-08, |
|
"loss": 1.1403, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"eval_accuracy": 0.33712574850299404, |
|
"eval_loss": 1.1030837297439575, |
|
"eval_runtime": 29.7882, |
|
"eval_samples_per_second": 168.187, |
|
"eval_steps_per_second": 21.049, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 5.5527777777777784e-08, |
|
"loss": 1.1194, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"eval_accuracy": 0.34331337325349304, |
|
"eval_loss": 1.1002165079116821, |
|
"eval_runtime": 29.8685, |
|
"eval_samples_per_second": 167.735, |
|
"eval_steps_per_second": 20.992, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 8.327777777777778e-08, |
|
"loss": 1.1194, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"eval_accuracy": 0.3471057884231537, |
|
"eval_loss": 1.101266622543335, |
|
"eval_runtime": 29.709, |
|
"eval_samples_per_second": 168.636, |
|
"eval_steps_per_second": 21.105, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 1.1105555555555557e-07, |
|
"loss": 1.1166, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"eval_accuracy": 0.34311377245508984, |
|
"eval_loss": 1.0984796285629272, |
|
"eval_runtime": 29.9401, |
|
"eval_samples_per_second": 167.334, |
|
"eval_steps_per_second": 20.942, |
|
"step": 4000 |
|
} |
|
], |
|
"logging_steps": 1000, |
|
"max_steps": 10000000, |
|
"num_train_epochs": 408, |
|
"save_steps": 1000, |
|
"total_flos": 4180823506944000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|