|
{ |
|
"best_metric": 0.2816188870151771, |
|
"best_model_checkpoint": "logs/indian_build_rr/roberta-base/seed_1/checkpoint-434", |
|
"epoch": 10.0, |
|
"eval_steps": 500, |
|
"global_step": 620, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.8779947916666667, |
|
"eval_f1": 0.09680365296803654, |
|
"eval_loss": 0.4225575029850006, |
|
"eval_micro-f1": 0.09680365296803654, |
|
"eval_precision": 0.08346456692913386, |
|
"eval_recall": 0.11521739130434783, |
|
"eval_runtime": 1.5383, |
|
"eval_samples_per_second": 19.503, |
|
"eval_steps_per_second": 5.201, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.8930989583333333, |
|
"eval_f1": 0.19573796369376484, |
|
"eval_loss": 0.34750670194625854, |
|
"eval_micro-f1": 0.19573796369376484, |
|
"eval_precision": 0.1536555142503098, |
|
"eval_recall": 0.26956521739130435, |
|
"eval_runtime": 1.537, |
|
"eval_samples_per_second": 19.519, |
|
"eval_steps_per_second": 5.205, |
|
"step": 124 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9052083333333333, |
|
"eval_f1": 0.24148606811145507, |
|
"eval_loss": 0.2912306487560272, |
|
"eval_micro-f1": 0.24148606811145507, |
|
"eval_precision": 0.1875, |
|
"eval_recall": 0.3391304347826087, |
|
"eval_runtime": 1.5375, |
|
"eval_samples_per_second": 19.512, |
|
"eval_steps_per_second": 5.203, |
|
"step": 186 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.9002604166666667, |
|
"eval_f1": 0.24856909239574815, |
|
"eval_loss": 0.29914453625679016, |
|
"eval_micro-f1": 0.24856909239574815, |
|
"eval_precision": 0.19921363040629095, |
|
"eval_recall": 0.33043478260869563, |
|
"eval_runtime": 1.5402, |
|
"eval_samples_per_second": 19.478, |
|
"eval_steps_per_second": 5.194, |
|
"step": 248 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_accuracy": 0.906640625, |
|
"eval_f1": 0.24417009602194786, |
|
"eval_loss": 0.2833251357078552, |
|
"eval_micro-f1": 0.24417009602194786, |
|
"eval_precision": 0.17835671342685372, |
|
"eval_recall": 0.3869565217391304, |
|
"eval_runtime": 1.5382, |
|
"eval_samples_per_second": 19.504, |
|
"eval_steps_per_second": 5.201, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_accuracy": 0.91484375, |
|
"eval_f1": 0.2718932443703086, |
|
"eval_loss": 0.26417481899261475, |
|
"eval_micro-f1": 0.2718932443703086, |
|
"eval_precision": 0.22056833558863329, |
|
"eval_recall": 0.35434782608695653, |
|
"eval_runtime": 1.5353, |
|
"eval_samples_per_second": 19.54, |
|
"eval_steps_per_second": 5.211, |
|
"step": 372 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_accuracy": 0.9177083333333333, |
|
"eval_f1": 0.2816188870151771, |
|
"eval_loss": 0.2584071457386017, |
|
"eval_micro-f1": 0.2816188870151771, |
|
"eval_precision": 0.23002754820936638, |
|
"eval_recall": 0.3630434782608696, |
|
"eval_runtime": 1.5473, |
|
"eval_samples_per_second": 19.388, |
|
"eval_steps_per_second": 5.17, |
|
"step": 434 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_accuracy": 0.9177083333333333, |
|
"eval_f1": 0.27419354838709675, |
|
"eval_loss": 0.25232046842575073, |
|
"eval_micro-f1": 0.27419354838709675, |
|
"eval_precision": 0.21794871794871795, |
|
"eval_recall": 0.3695652173913043, |
|
"eval_runtime": 1.5341, |
|
"eval_samples_per_second": 19.556, |
|
"eval_steps_per_second": 5.215, |
|
"step": 496 |
|
}, |
|
{ |
|
"epoch": 8.064516129032258, |
|
"grad_norm": 2.654693603515625, |
|
"learning_rate": 1.7975806451612903e-05, |
|
"loss": 0.4245, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_accuracy": 0.9166666666666666, |
|
"eval_f1": 0.25278810408921937, |
|
"eval_loss": 0.26304513216018677, |
|
"eval_micro-f1": 0.25278810408921937, |
|
"eval_precision": 0.192090395480226, |
|
"eval_recall": 0.3695652173913043, |
|
"eval_runtime": 2.1137, |
|
"eval_samples_per_second": 14.193, |
|
"eval_steps_per_second": 3.785, |
|
"step": 558 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"eval_accuracy": 0.919140625, |
|
"eval_f1": 0.25541795665634676, |
|
"eval_loss": 0.2640175521373749, |
|
"eval_micro-f1": 0.25541795665634676, |
|
"eval_precision": 0.19831730769230768, |
|
"eval_recall": 0.358695652173913, |
|
"eval_runtime": 1.5363, |
|
"eval_samples_per_second": 19.527, |
|
"eval_steps_per_second": 5.207, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"step": 620, |
|
"total_flos": 4.819469484490752e+16, |
|
"train_loss": 0.3849165085823305, |
|
"train_runtime": 337.1781, |
|
"train_samples_per_second": 14.651, |
|
"train_steps_per_second": 3.678 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 1240, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 20, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 3, |
|
"early_stopping_threshold": 0.0 |
|
}, |
|
"attributes": { |
|
"early_stopping_patience_counter": 0 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4.819469484490752e+16, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|