|
{ |
|
"best_metric": 0.3527472913265228, |
|
"best_model_checkpoint": "AmBig_Questions_v7/checkpoint-96", |
|
"epoch": 9.0, |
|
"eval_steps": 500, |
|
"global_step": 144, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.5934579439252337, |
|
"eval_loss": 0.641407310962677, |
|
"eval_runtime": 0.3064, |
|
"eval_samples_per_second": 698.428, |
|
"eval_steps_per_second": 13.055, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.7570093457943925, |
|
"eval_loss": 0.544841468334198, |
|
"eval_runtime": 0.2272, |
|
"eval_samples_per_second": 942.093, |
|
"eval_steps_per_second": 17.609, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.8271028037383178, |
|
"eval_loss": 0.44836297631263733, |
|
"eval_runtime": 0.1974, |
|
"eval_samples_per_second": 1083.98, |
|
"eval_steps_per_second": 20.261, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.8504672897196262, |
|
"eval_loss": 0.37522220611572266, |
|
"eval_runtime": 0.1833, |
|
"eval_samples_per_second": 1167.295, |
|
"eval_steps_per_second": 21.819, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_accuracy": 0.8551401869158879, |
|
"eval_loss": 0.36060166358947754, |
|
"eval_runtime": 0.2024, |
|
"eval_samples_per_second": 1057.568, |
|
"eval_steps_per_second": 19.768, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_accuracy": 0.8551401869158879, |
|
"eval_loss": 0.3527472913265228, |
|
"eval_runtime": 0.1689, |
|
"eval_samples_per_second": 1266.975, |
|
"eval_steps_per_second": 23.682, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_accuracy": 0.8598130841121495, |
|
"eval_loss": 0.35737448930740356, |
|
"eval_runtime": 0.1698, |
|
"eval_samples_per_second": 1260.253, |
|
"eval_steps_per_second": 23.556, |
|
"step": 112 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_accuracy": 0.8551401869158879, |
|
"eval_loss": 0.3698413670063019, |
|
"eval_runtime": 0.1727, |
|
"eval_samples_per_second": 1239.099, |
|
"eval_steps_per_second": 23.161, |
|
"step": 128 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_accuracy": 0.8551401869158879, |
|
"eval_loss": 0.3658725619316101, |
|
"eval_runtime": 0.1701, |
|
"eval_samples_per_second": 1257.934, |
|
"eval_steps_per_second": 23.513, |
|
"step": 144 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 160, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 10, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 57683860156152.0, |
|
"train_batch_size": 64, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|