|
{ |
|
"best_metric": 0.9176467061042786, |
|
"best_model_checkpoint": "FinBERT_market_based/checkpoint-1432", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 1432, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 1.1162790697674418e-05, |
|
"loss": 1.4577, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 2.2325581395348837e-05, |
|
"loss": 1.0761, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 3.348837209302326e-05, |
|
"loss": 1.0211, |
|
"step": 144 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 4.465116279069767e-05, |
|
"loss": 1.0051, |
|
"step": 192 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 4.935333678220383e-05, |
|
"loss": 0.9814, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 4.811174340403518e-05, |
|
"loss": 0.9718, |
|
"step": 288 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 4.687015002586653e-05, |
|
"loss": 0.9401, |
|
"step": 336 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 4.562855664769788e-05, |
|
"loss": 0.9486, |
|
"step": 384 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 4.438696326952923e-05, |
|
"loss": 0.9477, |
|
"step": 432 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 4.3145369891360584e-05, |
|
"loss": 0.9236, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 4.190377651319193e-05, |
|
"loss": 0.9295, |
|
"step": 528 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 4.066218313502328e-05, |
|
"loss": 0.9388, |
|
"step": 576 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 3.942058975685463e-05, |
|
"loss": 0.9446, |
|
"step": 624 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 3.8178996378685985e-05, |
|
"loss": 0.9324, |
|
"step": 672 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.5537056232184504, |
|
"eval_f1_macro": 0.4530869728302888, |
|
"eval_f1_micro": 0.5537056232184504, |
|
"eval_f1_weighted": 0.49220984693785635, |
|
"eval_loss": 0.9287100434303284, |
|
"eval_precision_macro": 0.5454170327986705, |
|
"eval_precision_micro": 0.5537056232184504, |
|
"eval_precision_weighted": 0.5470355528203532, |
|
"eval_recall_macro": 0.49494460688671565, |
|
"eval_recall_micro": 0.5537056232184504, |
|
"eval_recall_weighted": 0.5537056232184504, |
|
"eval_runtime": 2411.8627, |
|
"eval_samples_per_second": 6.4, |
|
"eval_steps_per_second": 0.05, |
|
"step": 716 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 3.693740300051733e-05, |
|
"loss": 0.9273, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 3.569580962234868e-05, |
|
"loss": 0.901, |
|
"step": 768 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 3.445421624418003e-05, |
|
"loss": 0.8876, |
|
"step": 816 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 3.3212622866011386e-05, |
|
"loss": 0.8826, |
|
"step": 864 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 3.197102948784273e-05, |
|
"loss": 0.8802, |
|
"step": 912 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 3.072943610967408e-05, |
|
"loss": 0.8896, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 2.9487842731505433e-05, |
|
"loss": 0.885, |
|
"step": 1008 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 2.8246249353336783e-05, |
|
"loss": 0.8706, |
|
"step": 1056 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 2.7004655975168137e-05, |
|
"loss": 0.8925, |
|
"step": 1104 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"learning_rate": 2.5763062596999484e-05, |
|
"loss": 0.8952, |
|
"step": 1152 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 2.4521469218830834e-05, |
|
"loss": 0.8921, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 2.3279875840662184e-05, |
|
"loss": 0.8934, |
|
"step": 1248 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 2.2038282462493534e-05, |
|
"loss": 0.8923, |
|
"step": 1296 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 2.0796689084324885e-05, |
|
"loss": 0.8778, |
|
"step": 1344 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 1.9555095706156235e-05, |
|
"loss": 0.8738, |
|
"step": 1392 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.5627105467737756, |
|
"eval_f1_macro": 0.49749240436690023, |
|
"eval_f1_micro": 0.5627105467737756, |
|
"eval_f1_weighted": 0.5279720746084178, |
|
"eval_loss": 0.9176467061042786, |
|
"eval_precision_macro": 0.5386355574899088, |
|
"eval_precision_micro": 0.5627105467737756, |
|
"eval_precision_weighted": 0.5462149036191247, |
|
"eval_recall_macro": 0.517542664344306, |
|
"eval_recall_micro": 0.5627105467737756, |
|
"eval_recall_weighted": 0.5627105467737756, |
|
"eval_runtime": 2502.0236, |
|
"eval_samples_per_second": 6.169, |
|
"eval_steps_per_second": 0.048, |
|
"step": 1432 |
|
} |
|
], |
|
"logging_steps": 48, |
|
"max_steps": 2148, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"total_flos": 6027139059895296.0, |
|
"train_batch_size": 64, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|