nerui-pt-pl20-1 / trainer_state.json
apwic's picture
End of training
07453c0 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 100.0,
"eval_steps": 500,
"global_step": 9600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 1.1176737546920776,
"learning_rate": 4.9500000000000004e-05,
"loss": 0.8553,
"step": 96
},
{
"epoch": 1.0,
"eval_LOCATION_f1": 0.0,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.0,
"eval_LOCATION_recall": 0.0,
"eval_ORGANIZATION_f1": 0.26451612903225813,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.26973684210526316,
"eval_ORGANIZATION_recall": 0.25949367088607594,
"eval_PERSON_f1": 0.270042194092827,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.2831858407079646,
"eval_PERSON_recall": 0.25806451612903225,
"eval_loss": 0.4029257297515869,
"eval_overall_accuracy": 0.8643974746088389,
"eval_overall_f1": 0.21921921921921922,
"eval_overall_precision": 0.27238805970149255,
"eval_overall_recall": 0.18341708542713567,
"eval_runtime": 0.2909,
"eval_samples_per_second": 584.444,
"eval_steps_per_second": 10.314,
"step": 96
},
{
"epoch": 2.0,
"grad_norm": 0.8155122995376587,
"learning_rate": 4.9e-05,
"loss": 0.3858,
"step": 192
},
{
"epoch": 2.0,
"eval_LOCATION_f1": 0.3628318584070796,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.37272727272727274,
"eval_LOCATION_recall": 0.35344827586206895,
"eval_ORGANIZATION_f1": 0.5016949152542373,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.5401459854014599,
"eval_ORGANIZATION_recall": 0.46835443037974683,
"eval_PERSON_f1": 0.4904458598726114,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.4052631578947368,
"eval_PERSON_recall": 0.6209677419354839,
"eval_loss": 0.2568744122982025,
"eval_overall_accuracy": 0.9162777930277244,
"eval_overall_f1": 0.4598802395209581,
"eval_overall_precision": 0.43935926773455375,
"eval_overall_recall": 0.4824120603015075,
"eval_runtime": 0.2935,
"eval_samples_per_second": 579.245,
"eval_steps_per_second": 10.222,
"step": 192
},
{
"epoch": 3.0,
"grad_norm": 0.8273248672485352,
"learning_rate": 4.85e-05,
"loss": 0.2184,
"step": 288
},
{
"epoch": 3.0,
"eval_LOCATION_f1": 0.7364016736401673,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.7154471544715447,
"eval_LOCATION_recall": 0.7586206896551724,
"eval_ORGANIZATION_f1": 0.7433628318584071,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.6961325966850829,
"eval_ORGANIZATION_recall": 0.7974683544303798,
"eval_PERSON_f1": 0.9531249999999999,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9242424242424242,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.10997601598501205,
"eval_overall_accuracy": 0.9654131210540763,
"eval_overall_f1": 0.8057553956834533,
"eval_overall_precision": 0.7706422018348624,
"eval_overall_recall": 0.8442211055276382,
"eval_runtime": 0.2976,
"eval_samples_per_second": 571.159,
"eval_steps_per_second": 10.079,
"step": 288
},
{
"epoch": 4.0,
"grad_norm": 0.7750449180603027,
"learning_rate": 4.8e-05,
"loss": 0.1431,
"step": 384
},
{
"epoch": 4.0,
"eval_LOCATION_f1": 0.8278688524590164,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.7890625,
"eval_LOCATION_recall": 0.8706896551724138,
"eval_ORGANIZATION_f1": 0.8484848484848485,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.813953488372093,
"eval_ORGANIZATION_recall": 0.8860759493670886,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.0817088708281517,
"eval_overall_accuracy": 0.975020587427944,
"eval_overall_f1": 0.8824242424242424,
"eval_overall_precision": 0.8524590163934426,
"eval_overall_recall": 0.914572864321608,
"eval_runtime": 0.2944,
"eval_samples_per_second": 577.362,
"eval_steps_per_second": 10.189,
"step": 384
},
{
"epoch": 5.0,
"grad_norm": 0.6839625239372253,
"learning_rate": 4.75e-05,
"loss": 0.1164,
"step": 480
},
{
"epoch": 5.0,
"eval_LOCATION_f1": 0.8148148148148148,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.88,
"eval_LOCATION_recall": 0.7586206896551724,
"eval_ORGANIZATION_f1": 0.8493975903614459,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.8103448275862069,
"eval_ORGANIZATION_recall": 0.8924050632911392,
"eval_PERSON_f1": 0.9799196787148594,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.976,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.0709914118051529,
"eval_overall_accuracy": 0.9777655778204777,
"eval_overall_f1": 0.8808030112923463,
"eval_overall_precision": 0.8796992481203008,
"eval_overall_recall": 0.8819095477386935,
"eval_runtime": 0.2953,
"eval_samples_per_second": 575.645,
"eval_steps_per_second": 10.158,
"step": 480
},
{
"epoch": 6.0,
"grad_norm": 1.6261128187179565,
"learning_rate": 4.7e-05,
"loss": 0.1025,
"step": 576
},
{
"epoch": 6.0,
"eval_LOCATION_f1": 0.8770491803278688,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.8359375,
"eval_LOCATION_recall": 0.9224137931034483,
"eval_ORGANIZATION_f1": 0.8930817610062892,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.8875,
"eval_ORGANIZATION_recall": 0.8987341772151899,
"eval_PERSON_f1": 0.9723320158102766,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9534883720930233,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05246200039982796,
"eval_overall_accuracy": 0.984079055723305,
"eval_overall_f1": 0.9128834355828221,
"eval_overall_precision": 0.8920863309352518,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2975,
"eval_samples_per_second": 571.516,
"eval_steps_per_second": 10.086,
"step": 576
},
{
"epoch": 7.0,
"grad_norm": 0.8234473466873169,
"learning_rate": 4.6500000000000005e-05,
"loss": 0.089,
"step": 672
},
{
"epoch": 7.0,
"eval_LOCATION_f1": 0.9051724137931035,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9051724137931034,
"eval_LOCATION_recall": 0.9051724137931034,
"eval_ORGANIZATION_f1": 0.9051987767584098,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.8757396449704142,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04289942979812622,
"eval_overall_accuracy": 0.9868240461158386,
"eval_overall_f1": 0.928395061728395,
"eval_overall_precision": 0.912621359223301,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2949,
"eval_samples_per_second": 576.544,
"eval_steps_per_second": 10.174,
"step": 672
},
{
"epoch": 8.0,
"grad_norm": 0.4638328552246094,
"learning_rate": 4.600000000000001e-05,
"loss": 0.0784,
"step": 768
},
{
"epoch": 8.0,
"eval_LOCATION_f1": 0.8925619834710743,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.8571428571428571,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.8846153846153846,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.8961038961038961,
"eval_ORGANIZATION_recall": 0.8734177215189873,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.046066585928201675,
"eval_overall_accuracy": 0.9846280538018117,
"eval_overall_f1": 0.9190535491905356,
"eval_overall_precision": 0.9111111111111111,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.2922,
"eval_samples_per_second": 581.746,
"eval_steps_per_second": 10.266,
"step": 768
},
{
"epoch": 9.0,
"grad_norm": 0.521353006362915,
"learning_rate": 4.55e-05,
"loss": 0.0736,
"step": 864
},
{
"epoch": 9.0,
"eval_LOCATION_f1": 0.9282700421940928,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.91875,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9074074074074074,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9799196787148594,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.976,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.03669111058115959,
"eval_overall_accuracy": 0.9887455393906122,
"eval_overall_f1": 0.9404466501240695,
"eval_overall_precision": 0.928921568627451,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2965,
"eval_samples_per_second": 573.331,
"eval_steps_per_second": 10.118,
"step": 864
},
{
"epoch": 10.0,
"grad_norm": 0.8245035409927368,
"learning_rate": 4.5e-05,
"loss": 0.0645,
"step": 960
},
{
"epoch": 10.0,
"eval_LOCATION_f1": 0.9180327868852458,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.875,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.9294871794871796,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9415584415584416,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.038304075598716736,
"eval_overall_accuracy": 0.9879220422728521,
"eval_overall_f1": 0.9417596034696406,
"eval_overall_precision": 0.9290953545232273,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2926,
"eval_samples_per_second": 580.921,
"eval_steps_per_second": 10.252,
"step": 960
},
{
"epoch": 11.0,
"grad_norm": 0.5553610920906067,
"learning_rate": 4.4500000000000004e-05,
"loss": 0.0601,
"step": 1056
},
{
"epoch": 11.0,
"eval_LOCATION_f1": 0.9495798319327732,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9262295081967213,
"eval_LOCATION_recall": 0.9741379310344828,
"eval_ORGANIZATION_f1": 0.9433962264150944,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9375,
"eval_ORGANIZATION_recall": 0.9493670886075949,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03511735051870346,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9590062111801241,
"eval_overall_precision": 0.9484029484029484,
"eval_overall_recall": 0.9698492462311558,
"eval_runtime": 0.2958,
"eval_samples_per_second": 574.68,
"eval_steps_per_second": 10.141,
"step": 1056
},
{
"epoch": 12.0,
"grad_norm": 0.501647412776947,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.059,
"step": 1152
},
{
"epoch": 12.0,
"eval_LOCATION_f1": 0.9059829059829059,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.8983050847457628,
"eval_LOCATION_recall": 0.9137931034482759,
"eval_ORGANIZATION_f1": 0.9363057324840764,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9423076923076923,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9761904761904763,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9609375,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.035545725375413895,
"eval_overall_accuracy": 0.9892945374691189,
"eval_overall_f1": 0.94,
"eval_overall_precision": 0.9353233830845771,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.293,
"eval_samples_per_second": 580.275,
"eval_steps_per_second": 10.24,
"step": 1152
},
{
"epoch": 13.0,
"grad_norm": 0.7835653424263,
"learning_rate": 4.35e-05,
"loss": 0.0534,
"step": 1248
},
{
"epoch": 13.0,
"eval_LOCATION_f1": 0.9184549356223175,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9145299145299145,
"eval_LOCATION_recall": 0.9224137931034483,
"eval_ORGANIZATION_f1": 0.9587301587301587,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9617834394904459,
"eval_ORGANIZATION_recall": 0.9556962025316456,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03767260164022446,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9536921151439299,
"eval_overall_precision": 0.9501246882793017,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.294,
"eval_samples_per_second": 578.238,
"eval_steps_per_second": 10.204,
"step": 1248
},
{
"epoch": 14.0,
"grad_norm": 0.17031921446323395,
"learning_rate": 4.3e-05,
"loss": 0.0502,
"step": 1344
},
{
"epoch": 14.0,
"eval_LOCATION_f1": 0.935064935064935,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9391304347826087,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9523809523809524,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9554140127388535,
"eval_ORGANIZATION_recall": 0.9493670886075949,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.030799932777881622,
"eval_overall_accuracy": 0.9912160307438924,
"eval_overall_f1": 0.9560853199498118,
"eval_overall_precision": 0.9548872180451128,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2948,
"eval_samples_per_second": 576.723,
"eval_steps_per_second": 10.177,
"step": 1344
},
{
"epoch": 15.0,
"grad_norm": 0.7071172595024109,
"learning_rate": 4.25e-05,
"loss": 0.0454,
"step": 1440
},
{
"epoch": 15.0,
"eval_LOCATION_f1": 0.9106382978723405,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.8991596638655462,
"eval_LOCATION_recall": 0.9224137931034483,
"eval_ORGANIZATION_f1": 0.9363057324840764,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9423076923076923,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03468826413154602,
"eval_overall_accuracy": 0.9895690365083722,
"eval_overall_f1": 0.9425,
"eval_overall_precision": 0.9378109452736318,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.3007,
"eval_samples_per_second": 565.302,
"eval_steps_per_second": 9.976,
"step": 1440
},
{
"epoch": 16.0,
"grad_norm": 0.8529306650161743,
"learning_rate": 4.2e-05,
"loss": 0.0451,
"step": 1536
},
{
"epoch": 16.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9453376205787781,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9607843137254902,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.030224068090319633,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9547738693467337,
"eval_overall_precision": 0.9547738693467337,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2919,
"eval_samples_per_second": 582.295,
"eval_steps_per_second": 10.276,
"step": 1536
},
{
"epoch": 17.0,
"grad_norm": 0.579302191734314,
"learning_rate": 4.15e-05,
"loss": 0.0436,
"step": 1632
},
{
"epoch": 17.0,
"eval_LOCATION_f1": 0.9282700421940928,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9389067524115756,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.954248366013072,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03300878405570984,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9498746867167919,
"eval_overall_precision": 0.9475,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2934,
"eval_samples_per_second": 579.322,
"eval_steps_per_second": 10.223,
"step": 1632
},
{
"epoch": 18.0,
"grad_norm": 0.5171939134597778,
"learning_rate": 4.1e-05,
"loss": 0.0407,
"step": 1728
},
{
"epoch": 18.0,
"eval_LOCATION_f1": 0.9322033898305084,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9389067524115756,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.954248366013072,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03554491698741913,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9522613065326633,
"eval_overall_precision": 0.9522613065326633,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.293,
"eval_samples_per_second": 580.291,
"eval_steps_per_second": 10.24,
"step": 1728
},
{
"epoch": 19.0,
"grad_norm": 0.7743630409240723,
"learning_rate": 4.05e-05,
"loss": 0.0385,
"step": 1824
},
{
"epoch": 19.0,
"eval_LOCATION_f1": 0.9184549356223175,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9145299145299145,
"eval_LOCATION_recall": 0.9224137931034483,
"eval_ORGANIZATION_f1": 0.9358974358974359,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.948051948051948,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03621438145637512,
"eval_overall_accuracy": 0.9887455393906122,
"eval_overall_f1": 0.9459119496855346,
"eval_overall_precision": 0.947103274559194,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.291,
"eval_samples_per_second": 584.136,
"eval_steps_per_second": 10.308,
"step": 1824
},
{
"epoch": 20.0,
"grad_norm": 0.5671931505203247,
"learning_rate": 4e-05,
"loss": 0.0351,
"step": 1920
},
{
"epoch": 20.0,
"eval_LOCATION_f1": 0.944206008583691,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9401709401709402,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9367088607594937,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9367088607594937,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.0372651182115078,
"eval_overall_accuracy": 0.9895690365083722,
"eval_overall_f1": 0.9536921151439299,
"eval_overall_precision": 0.9501246882793017,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2953,
"eval_samples_per_second": 575.595,
"eval_steps_per_second": 10.158,
"step": 1920
},
{
"epoch": 21.0,
"grad_norm": 0.7632231712341309,
"learning_rate": 3.9500000000000005e-05,
"loss": 0.0353,
"step": 2016
},
{
"epoch": 21.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9517684887459807,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9673202614379085,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.0339834988117218,
"eval_overall_accuracy": 0.9912160307438924,
"eval_overall_f1": 0.957286432160804,
"eval_overall_precision": 0.957286432160804,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2941,
"eval_samples_per_second": 577.983,
"eval_steps_per_second": 10.2,
"step": 2016
},
{
"epoch": 22.0,
"grad_norm": 0.43302038311958313,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.0332,
"step": 2112
},
{
"epoch": 22.0,
"eval_LOCATION_f1": 0.927038626609442,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9230769230769231,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9329073482428115,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9419354838709677,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03514440357685089,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9472361809045227,
"eval_overall_precision": 0.9472361809045227,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2934,
"eval_samples_per_second": 579.37,
"eval_steps_per_second": 10.224,
"step": 2112
},
{
"epoch": 23.0,
"grad_norm": 0.608894944190979,
"learning_rate": 3.85e-05,
"loss": 0.0329,
"step": 2208
},
{
"epoch": 23.0,
"eval_LOCATION_f1": 0.9356223175965666,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9316239316239316,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.952076677316294,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9612903225806452,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.031062569469213486,
"eval_overall_accuracy": 0.9912160307438924,
"eval_overall_f1": 0.957286432160804,
"eval_overall_precision": 0.957286432160804,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2923,
"eval_samples_per_second": 581.67,
"eval_steps_per_second": 10.265,
"step": 2208
},
{
"epoch": 24.0,
"grad_norm": 0.40360790491104126,
"learning_rate": 3.8e-05,
"loss": 0.0332,
"step": 2304
},
{
"epoch": 24.0,
"eval_LOCATION_f1": 0.9491525423728815,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9333333333333333,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.9358974358974359,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.948051948051948,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03414417803287506,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9560853199498118,
"eval_overall_precision": 0.9548872180451128,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2937,
"eval_samples_per_second": 578.766,
"eval_steps_per_second": 10.214,
"step": 2304
},
{
"epoch": 25.0,
"grad_norm": 0.6055574417114258,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.0302,
"step": 2400
},
{
"epoch": 25.0,
"eval_LOCATION_f1": 0.927038626609442,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9230769230769231,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9426751592356688,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9487179487179487,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.035754989832639694,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9510664993726474,
"eval_overall_precision": 0.949874686716792,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2927,
"eval_samples_per_second": 580.808,
"eval_steps_per_second": 10.25,
"step": 2400
},
{
"epoch": 26.0,
"grad_norm": 0.19510036706924438,
"learning_rate": 3.7e-05,
"loss": 0.0314,
"step": 2496
},
{
"epoch": 26.0,
"eval_LOCATION_f1": 0.944206008583691,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9401709401709402,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9523809523809524,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9554140127388535,
"eval_ORGANIZATION_recall": 0.9493670886075949,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.031882982701063156,
"eval_overall_accuracy": 0.9912160307438924,
"eval_overall_f1": 0.9586983729662076,
"eval_overall_precision": 0.9551122194513716,
"eval_overall_recall": 0.9623115577889447,
"eval_runtime": 0.2931,
"eval_samples_per_second": 579.939,
"eval_steps_per_second": 10.234,
"step": 2496
},
{
"epoch": 27.0,
"grad_norm": 1.498604655265808,
"learning_rate": 3.65e-05,
"loss": 0.0297,
"step": 2592
},
{
"epoch": 27.0,
"eval_LOCATION_f1": 0.94017094017094,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9322033898305084,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9423076923076923,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9545454545454546,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03271141275763512,
"eval_overall_accuracy": 0.9912160307438924,
"eval_overall_f1": 0.9559748427672956,
"eval_overall_precision": 0.9571788413098237,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2913,
"eval_samples_per_second": 583.592,
"eval_steps_per_second": 10.299,
"step": 2592
},
{
"epoch": 28.0,
"grad_norm": 0.28998106718063354,
"learning_rate": 3.6e-05,
"loss": 0.0265,
"step": 2688
},
{
"epoch": 28.0,
"eval_LOCATION_f1": 0.9282700421940928,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9299363057324842,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9358974358974359,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03875914216041565,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9475,
"eval_overall_precision": 0.9427860696517413,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2945,
"eval_samples_per_second": 577.226,
"eval_steps_per_second": 10.186,
"step": 2688
},
{
"epoch": 29.0,
"grad_norm": 0.5255737900733948,
"learning_rate": 3.55e-05,
"loss": 0.027,
"step": 2784
},
{
"epoch": 29.0,
"eval_LOCATION_f1": 0.9282700421940928,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9354838709677419,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9539473684210527,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04041021689772606,
"eval_overall_accuracy": 0.9898435355476256,
"eval_overall_f1": 0.9485570890840652,
"eval_overall_precision": 0.9473684210526315,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2938,
"eval_samples_per_second": 578.693,
"eval_steps_per_second": 10.212,
"step": 2784
},
{
"epoch": 30.0,
"grad_norm": 0.8123347759246826,
"learning_rate": 3.5e-05,
"loss": 0.0273,
"step": 2880
},
{
"epoch": 30.0,
"eval_LOCATION_f1": 0.9344978165938865,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9469026548672567,
"eval_LOCATION_recall": 0.9224137931034483,
"eval_ORGANIZATION_f1": 0.9490445859872612,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9551282051282052,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04018845781683922,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9558638083228247,
"eval_overall_precision": 0.959493670886076,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2935,
"eval_samples_per_second": 579.147,
"eval_steps_per_second": 10.22,
"step": 2880
},
{
"epoch": 31.0,
"grad_norm": 0.6206621527671814,
"learning_rate": 3.45e-05,
"loss": 0.0245,
"step": 2976
},
{
"epoch": 31.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9419354838709677,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9605263157894737,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03476196154952049,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9559748427672956,
"eval_overall_precision": 0.9571788413098237,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.293,
"eval_samples_per_second": 580.143,
"eval_steps_per_second": 10.238,
"step": 2976
},
{
"epoch": 32.0,
"grad_norm": 0.42933395504951477,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.0221,
"step": 3072
},
{
"epoch": 32.0,
"eval_LOCATION_f1": 0.9356223175965666,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9316239316239316,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9358974358974359,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.948051948051948,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.036590754985809326,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9521410579345088,
"eval_overall_precision": 0.9545454545454546,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2911,
"eval_samples_per_second": 584.037,
"eval_steps_per_second": 10.307,
"step": 3072
},
{
"epoch": 33.0,
"grad_norm": 0.31581228971481323,
"learning_rate": 3.35e-05,
"loss": 0.023,
"step": 3168
},
{
"epoch": 33.0,
"eval_LOCATION_f1": 0.944206008583691,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9401709401709402,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9511400651465798,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9798657718120806,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.040129464119672775,
"eval_overall_accuracy": 0.9892945374691189,
"eval_overall_f1": 0.959493670886076,
"eval_overall_precision": 0.9668367346938775,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2918,
"eval_samples_per_second": 582.631,
"eval_steps_per_second": 10.282,
"step": 3168
},
{
"epoch": 34.0,
"grad_norm": 0.04073067754507065,
"learning_rate": 3.3e-05,
"loss": 0.0219,
"step": 3264
},
{
"epoch": 34.0,
"eval_LOCATION_f1": 0.9487179487179486,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.940677966101695,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9490445859872612,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9551282051282052,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03480677306652069,
"eval_overall_accuracy": 0.9914905297831458,
"eval_overall_f1": 0.9586983729662076,
"eval_overall_precision": 0.9551122194513716,
"eval_overall_recall": 0.9623115577889447,
"eval_runtime": 0.2934,
"eval_samples_per_second": 579.369,
"eval_steps_per_second": 10.224,
"step": 3264
},
{
"epoch": 35.0,
"grad_norm": 1.3052045106887817,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.0227,
"step": 3360
},
{
"epoch": 35.0,
"eval_LOCATION_f1": 0.9310344827586207,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9310344827586207,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9419354838709677,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9605263157894737,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03988682106137276,
"eval_overall_accuracy": 0.9881965413121054,
"eval_overall_f1": 0.9508196721311476,
"eval_overall_precision": 0.9544303797468354,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2895,
"eval_samples_per_second": 587.159,
"eval_steps_per_second": 10.362,
"step": 3360
},
{
"epoch": 36.0,
"grad_norm": 0.5851593613624573,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.0194,
"step": 3456
},
{
"epoch": 36.0,
"eval_LOCATION_f1": 0.9543568464730291,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.92,
"eval_LOCATION_recall": 0.9913793103448276,
"eval_ORGANIZATION_f1": 0.9548387096774194,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9736842105263158,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.0369725376367569,
"eval_overall_accuracy": 0.9914905297831458,
"eval_overall_f1": 0.965,
"eval_overall_precision": 0.9601990049751243,
"eval_overall_recall": 0.9698492462311558,
"eval_runtime": 0.2925,
"eval_samples_per_second": 581.213,
"eval_steps_per_second": 10.257,
"step": 3456
},
{
"epoch": 37.0,
"grad_norm": 0.9545831084251404,
"learning_rate": 3.15e-05,
"loss": 0.0204,
"step": 3552
},
{
"epoch": 37.0,
"eval_LOCATION_f1": 0.9491525423728815,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9333333333333333,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.9545454545454545,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.98,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03820004314184189,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9622166246851386,
"eval_overall_precision": 0.9646464646464646,
"eval_overall_recall": 0.9597989949748744,
"eval_runtime": 0.2903,
"eval_samples_per_second": 585.68,
"eval_steps_per_second": 10.336,
"step": 3552
},
{
"epoch": 38.0,
"grad_norm": 0.330364465713501,
"learning_rate": 3.1e-05,
"loss": 0.0193,
"step": 3648
},
{
"epoch": 38.0,
"eval_LOCATION_f1": 0.9316239316239315,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.923728813559322,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9453376205787781,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9607843137254902,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.040419697761535645,
"eval_overall_accuracy": 0.9895690365083722,
"eval_overall_f1": 0.9534591194968555,
"eval_overall_precision": 0.9546599496221663,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.291,
"eval_samples_per_second": 584.249,
"eval_steps_per_second": 10.31,
"step": 3648
},
{
"epoch": 39.0,
"grad_norm": 0.21704113483428955,
"learning_rate": 3.05e-05,
"loss": 0.0193,
"step": 3744
},
{
"epoch": 39.0,
"eval_LOCATION_f1": 0.9527896995708154,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9487179487179487,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9551282051282052,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9675324675324676,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.035935286432504654,
"eval_overall_accuracy": 0.9923140269009059,
"eval_overall_f1": 0.964735516372796,
"eval_overall_precision": 0.9671717171717171,
"eval_overall_recall": 0.9623115577889447,
"eval_runtime": 0.2913,
"eval_samples_per_second": 583.529,
"eval_steps_per_second": 10.298,
"step": 3744
},
{
"epoch": 40.0,
"grad_norm": 0.8457311391830444,
"learning_rate": 3e-05,
"loss": 0.0191,
"step": 3840
},
{
"epoch": 40.0,
"eval_LOCATION_f1": 0.935064935064935,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9391304347826087,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9490445859872612,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9551282051282052,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.034387268126010895,
"eval_overall_accuracy": 0.9920395278616525,
"eval_overall_f1": 0.9559748427672956,
"eval_overall_precision": 0.9571788413098237,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.293,
"eval_samples_per_second": 580.141,
"eval_steps_per_second": 10.238,
"step": 3840
},
{
"epoch": 41.0,
"grad_norm": 0.07256820797920227,
"learning_rate": 2.95e-05,
"loss": 0.0183,
"step": 3936
},
{
"epoch": 41.0,
"eval_LOCATION_f1": 0.9198312236286921,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9008264462809917,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9329073482428115,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9419354838709677,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03764977306127548,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9450000000000001,
"eval_overall_precision": 0.9402985074626866,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2905,
"eval_samples_per_second": 585.15,
"eval_steps_per_second": 10.326,
"step": 3936
},
{
"epoch": 42.0,
"grad_norm": 0.05384012311697006,
"learning_rate": 2.9e-05,
"loss": 0.0181,
"step": 4032
},
{
"epoch": 42.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9463722397476341,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9433962264150944,
"eval_ORGANIZATION_recall": 0.9493670886075949,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.033380769193172455,
"eval_overall_accuracy": 0.9923140269009059,
"eval_overall_f1": 0.9564134495641344,
"eval_overall_precision": 0.9481481481481482,
"eval_overall_recall": 0.964824120603015,
"eval_runtime": 0.2894,
"eval_samples_per_second": 587.499,
"eval_steps_per_second": 10.368,
"step": 4032
},
{
"epoch": 43.0,
"grad_norm": 0.08901520073413849,
"learning_rate": 2.8499999999999998e-05,
"loss": 0.016,
"step": 4128
},
{
"epoch": 43.0,
"eval_LOCATION_f1": 0.9437229437229439,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9478260869565217,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9430379746835443,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9430379746835443,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.033028494566679,
"eval_overall_accuracy": 0.9917650288223991,
"eval_overall_f1": 0.9560853199498118,
"eval_overall_precision": 0.9548872180451128,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2906,
"eval_samples_per_second": 584.929,
"eval_steps_per_second": 10.322,
"step": 4128
},
{
"epoch": 44.0,
"grad_norm": 1.2836157083511353,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.0173,
"step": 4224
},
{
"epoch": 44.0,
"eval_LOCATION_f1": 0.9356223175965666,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9316239316239316,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.948051948051948,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9733333333333334,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04676896706223488,
"eval_overall_accuracy": 0.9879220422728521,
"eval_overall_f1": 0.9545454545454546,
"eval_overall_precision": 0.9593908629441624,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2905,
"eval_samples_per_second": 585.288,
"eval_steps_per_second": 10.329,
"step": 4224
},
{
"epoch": 45.0,
"grad_norm": 0.5232208371162415,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.0154,
"step": 4320
},
{
"epoch": 45.0,
"eval_LOCATION_f1": 0.94017094017094,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9322033898305084,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9354838709677419,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9539473684210527,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04091142490506172,
"eval_overall_accuracy": 0.9892945374691189,
"eval_overall_f1": 0.9521410579345088,
"eval_overall_precision": 0.9545454545454546,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2919,
"eval_samples_per_second": 582.298,
"eval_steps_per_second": 10.276,
"step": 4320
},
{
"epoch": 46.0,
"grad_norm": 0.6845114827156067,
"learning_rate": 2.7000000000000002e-05,
"loss": 0.0155,
"step": 4416
},
{
"epoch": 46.0,
"eval_LOCATION_f1": 0.9527896995708154,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9487179487179487,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9389067524115756,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.954248366013072,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03788773715496063,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9571788413098236,
"eval_overall_precision": 0.9595959595959596,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2893,
"eval_samples_per_second": 587.525,
"eval_steps_per_second": 10.368,
"step": 4416
},
{
"epoch": 47.0,
"grad_norm": 0.6623640060424805,
"learning_rate": 2.6500000000000004e-05,
"loss": 0.0145,
"step": 4512
},
{
"epoch": 47.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9389067524115756,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.954248366013072,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.042641639709472656,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9547738693467337,
"eval_overall_precision": 0.9547738693467337,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2925,
"eval_samples_per_second": 581.166,
"eval_steps_per_second": 10.256,
"step": 4512
},
{
"epoch": 48.0,
"grad_norm": 0.6918525695800781,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.0154,
"step": 4608
},
{
"epoch": 48.0,
"eval_LOCATION_f1": 0.94017094017094,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9322033898305084,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.932475884244373,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9477124183006536,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03981786221265793,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9521410579345088,
"eval_overall_precision": 0.9545454545454546,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2923,
"eval_samples_per_second": 581.646,
"eval_steps_per_second": 10.264,
"step": 4608
},
{
"epoch": 49.0,
"grad_norm": 0.04483887180685997,
"learning_rate": 2.5500000000000003e-05,
"loss": 0.0151,
"step": 4704
},
{
"epoch": 49.0,
"eval_LOCATION_f1": 0.94017094017094,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9322033898305084,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9449838187702266,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9668874172185431,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04250122979283333,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9570707070707072,
"eval_overall_precision": 0.9619289340101523,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2896,
"eval_samples_per_second": 586.918,
"eval_steps_per_second": 10.357,
"step": 4704
},
{
"epoch": 50.0,
"grad_norm": 0.44632968306541443,
"learning_rate": 2.5e-05,
"loss": 0.0138,
"step": 4800
},
{
"epoch": 50.0,
"eval_LOCATION_f1": 0.9372384937238494,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9105691056910569,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.9290322580645162,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9473684210526315,
"eval_ORGANIZATION_recall": 0.9113924050632911,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.042706288397312164,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9486858573216519,
"eval_overall_precision": 0.9451371571072319,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2932,
"eval_samples_per_second": 579.773,
"eval_steps_per_second": 10.231,
"step": 4800
},
{
"epoch": 51.0,
"grad_norm": 0.37510067224502563,
"learning_rate": 2.45e-05,
"loss": 0.015,
"step": 4896
},
{
"epoch": 51.0,
"eval_LOCATION_f1": 0.9539748953974895,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.926829268292683,
"eval_LOCATION_recall": 0.9827586206896551,
"eval_ORGANIZATION_f1": 0.9514563106796117,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9735099337748344,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03982841223478317,
"eval_overall_accuracy": 0.9917650288223991,
"eval_overall_f1": 0.9624060150375939,
"eval_overall_precision": 0.96,
"eval_overall_recall": 0.964824120603015,
"eval_runtime": 0.2906,
"eval_samples_per_second": 585.061,
"eval_steps_per_second": 10.325,
"step": 4896
},
{
"epoch": 52.0,
"grad_norm": 1.2106904983520508,
"learning_rate": 2.4e-05,
"loss": 0.0146,
"step": 4992
},
{
"epoch": 52.0,
"eval_LOCATION_f1": 0.944206008583691,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9401709401709402,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.939297124600639,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9483870967741935,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.037753116339445114,
"eval_overall_accuracy": 0.9912160307438924,
"eval_overall_f1": 0.9547738693467337,
"eval_overall_precision": 0.9547738693467337,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2911,
"eval_samples_per_second": 584.021,
"eval_steps_per_second": 10.306,
"step": 4992
},
{
"epoch": 53.0,
"grad_norm": 0.6939998865127563,
"learning_rate": 2.35e-05,
"loss": 0.0121,
"step": 5088
},
{
"epoch": 53.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9389067524115756,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.954248366013072,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.045009445399045944,
"eval_overall_accuracy": 0.9898435355476256,
"eval_overall_f1": 0.9547738693467337,
"eval_overall_precision": 0.9547738693467337,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2909,
"eval_samples_per_second": 584.294,
"eval_steps_per_second": 10.311,
"step": 5088
},
{
"epoch": 54.0,
"grad_norm": 0.7895837426185608,
"learning_rate": 2.3000000000000003e-05,
"loss": 0.0136,
"step": 5184
},
{
"epoch": 54.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9389067524115756,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.954248366013072,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04220401495695114,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9547738693467337,
"eval_overall_precision": 0.9547738693467337,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.291,
"eval_samples_per_second": 584.273,
"eval_steps_per_second": 10.311,
"step": 5184
},
{
"epoch": 55.0,
"grad_norm": 0.10359565168619156,
"learning_rate": 2.25e-05,
"loss": 0.0135,
"step": 5280
},
{
"epoch": 55.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9290322580645162,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9473684210526315,
"eval_ORGANIZATION_recall": 0.9113924050632911,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.043841563165187836,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9521410579345088,
"eval_overall_precision": 0.9545454545454546,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2919,
"eval_samples_per_second": 582.472,
"eval_steps_per_second": 10.279,
"step": 5280
},
{
"epoch": 56.0,
"grad_norm": 0.36767861247062683,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.012,
"step": 5376
},
{
"epoch": 56.0,
"eval_LOCATION_f1": 0.9487179487179486,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.940677966101695,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9358974358974359,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.948051948051948,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04247433319687843,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9547738693467337,
"eval_overall_precision": 0.9547738693467337,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2903,
"eval_samples_per_second": 585.526,
"eval_steps_per_second": 10.333,
"step": 5376
},
{
"epoch": 57.0,
"grad_norm": 0.39423635601997375,
"learning_rate": 2.15e-05,
"loss": 0.0136,
"step": 5472
},
{
"epoch": 57.0,
"eval_LOCATION_f1": 0.944206008583691,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9401709401709402,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9290322580645162,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9473684210526315,
"eval_ORGANIZATION_recall": 0.9113924050632911,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.042152438312768936,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9508196721311476,
"eval_overall_precision": 0.9544303797468354,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2897,
"eval_samples_per_second": 586.851,
"eval_steps_per_second": 10.356,
"step": 5472
},
{
"epoch": 58.0,
"grad_norm": 0.2699180543422699,
"learning_rate": 2.1e-05,
"loss": 0.0133,
"step": 5568
},
{
"epoch": 58.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9354838709677419,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9539473684210527,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.045361388474702835,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9534591194968555,
"eval_overall_precision": 0.9546599496221663,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2898,
"eval_samples_per_second": 586.678,
"eval_steps_per_second": 10.353,
"step": 5568
},
{
"epoch": 59.0,
"grad_norm": 0.13147902488708496,
"learning_rate": 2.05e-05,
"loss": 0.0119,
"step": 5664
},
{
"epoch": 59.0,
"eval_LOCATION_f1": 0.9535864978902953,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9338842975206612,
"eval_LOCATION_recall": 0.9741379310344828,
"eval_ORGANIZATION_f1": 0.9449838187702266,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9668874172185431,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04451941326260567,
"eval_overall_accuracy": 0.9914905297831458,
"eval_overall_f1": 0.9597989949748744,
"eval_overall_precision": 0.9597989949748744,
"eval_overall_recall": 0.9597989949748744,
"eval_runtime": 0.2898,
"eval_samples_per_second": 586.581,
"eval_steps_per_second": 10.351,
"step": 5664
},
{
"epoch": 60.0,
"grad_norm": 0.1671062409877777,
"learning_rate": 2e-05,
"loss": 0.0112,
"step": 5760
},
{
"epoch": 60.0,
"eval_LOCATION_f1": 0.9576271186440678,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9416666666666667,
"eval_LOCATION_recall": 0.9741379310344828,
"eval_ORGANIZATION_f1": 0.9354838709677419,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9539473684210527,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04959705471992493,
"eval_overall_accuracy": 0.9898435355476256,
"eval_overall_f1": 0.957286432160804,
"eval_overall_precision": 0.957286432160804,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2911,
"eval_samples_per_second": 584.075,
"eval_steps_per_second": 10.307,
"step": 5760
},
{
"epoch": 61.0,
"grad_norm": 0.44050949811935425,
"learning_rate": 1.9500000000000003e-05,
"loss": 0.0116,
"step": 5856
},
{
"epoch": 61.0,
"eval_LOCATION_f1": 0.9576271186440678,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9416666666666667,
"eval_LOCATION_recall": 0.9741379310344828,
"eval_ORGANIZATION_f1": 0.9453376205787781,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9607843137254902,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04536319151520729,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9611041405269761,
"eval_overall_precision": 0.9598997493734336,
"eval_overall_recall": 0.9623115577889447,
"eval_runtime": 0.29,
"eval_samples_per_second": 586.299,
"eval_steps_per_second": 10.346,
"step": 5856
},
{
"epoch": 62.0,
"grad_norm": 0.820795476436615,
"learning_rate": 1.9e-05,
"loss": 0.0128,
"step": 5952
},
{
"epoch": 62.0,
"eval_LOCATION_f1": 0.9372384937238494,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9105691056910569,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.9385113268608414,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9602649006622517,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.049761563539505005,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.9523809523809523,
"eval_overall_precision": 0.95,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2909,
"eval_samples_per_second": 584.353,
"eval_steps_per_second": 10.312,
"step": 5952
},
{
"epoch": 63.0,
"grad_norm": 0.02152247354388237,
"learning_rate": 1.85e-05,
"loss": 0.0103,
"step": 6048
},
{
"epoch": 63.0,
"eval_LOCATION_f1": 0.9576271186440678,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9416666666666667,
"eval_LOCATION_recall": 0.9741379310344828,
"eval_ORGANIZATION_f1": 0.9551282051282052,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9675324675324676,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.045038990676403046,
"eval_overall_accuracy": 0.9914905297831458,
"eval_overall_f1": 0.9649122807017544,
"eval_overall_precision": 0.9625,
"eval_overall_recall": 0.9673366834170855,
"eval_runtime": 0.2912,
"eval_samples_per_second": 583.753,
"eval_steps_per_second": 10.302,
"step": 6048
},
{
"epoch": 64.0,
"grad_norm": 0.05587596818804741,
"learning_rate": 1.8e-05,
"loss": 0.0121,
"step": 6144
},
{
"epoch": 64.0,
"eval_LOCATION_f1": 0.9527896995708154,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9487179487179487,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9354838709677419,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9539473684210527,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.045539844781160355,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9558638083228247,
"eval_overall_precision": 0.959493670886076,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2975,
"eval_samples_per_second": 571.502,
"eval_steps_per_second": 10.085,
"step": 6144
},
{
"epoch": 65.0,
"grad_norm": 0.5795026421546936,
"learning_rate": 1.75e-05,
"loss": 0.0122,
"step": 6240
},
{
"epoch": 65.0,
"eval_LOCATION_f1": 0.9495798319327732,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9262295081967213,
"eval_LOCATION_recall": 0.9741379310344828,
"eval_ORGANIZATION_f1": 0.9449838187702266,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9668874172185431,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04776795208454132,
"eval_overall_accuracy": 0.9898435355476256,
"eval_overall_f1": 0.958594730238394,
"eval_overall_precision": 0.9573934837092731,
"eval_overall_recall": 0.9597989949748744,
"eval_runtime": 0.2908,
"eval_samples_per_second": 584.601,
"eval_steps_per_second": 10.316,
"step": 6240
},
{
"epoch": 66.0,
"grad_norm": 0.2520827651023865,
"learning_rate": 1.7000000000000003e-05,
"loss": 0.0104,
"step": 6336
},
{
"epoch": 66.0,
"eval_LOCATION_f1": 0.9531914893617022,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9411764705882353,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.9333333333333332,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9363057324840764,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04898129776120186,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9550000000000001,
"eval_overall_precision": 0.9502487562189055,
"eval_overall_recall": 0.9597989949748744,
"eval_runtime": 0.2908,
"eval_samples_per_second": 584.546,
"eval_steps_per_second": 10.316,
"step": 6336
},
{
"epoch": 67.0,
"grad_norm": 0.05709691718220711,
"learning_rate": 1.65e-05,
"loss": 0.0092,
"step": 6432
},
{
"epoch": 67.0,
"eval_LOCATION_f1": 0.9617021276595743,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9495798319327731,
"eval_LOCATION_recall": 0.9741379310344828,
"eval_ORGANIZATION_f1": 0.9389067524115756,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.954248366013072,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.046496715396642685,
"eval_overall_accuracy": 0.9898435355476256,
"eval_overall_f1": 0.958594730238394,
"eval_overall_precision": 0.9573934837092731,
"eval_overall_recall": 0.9597989949748744,
"eval_runtime": 0.2904,
"eval_samples_per_second": 585.413,
"eval_steps_per_second": 10.331,
"step": 6432
},
{
"epoch": 68.0,
"grad_norm": 0.9552698135375977,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.0112,
"step": 6528
},
{
"epoch": 68.0,
"eval_LOCATION_f1": 0.9572649572649573,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9491525423728814,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.946031746031746,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9490445859872612,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04343028366565704,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9612015018773465,
"eval_overall_precision": 0.9576059850374065,
"eval_overall_recall": 0.964824120603015,
"eval_runtime": 0.2905,
"eval_samples_per_second": 585.298,
"eval_steps_per_second": 10.329,
"step": 6528
},
{
"epoch": 69.0,
"grad_norm": 0.16388903558254242,
"learning_rate": 1.55e-05,
"loss": 0.0104,
"step": 6624
},
{
"epoch": 69.0,
"eval_LOCATION_f1": 0.944206008583691,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9401709401709402,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9294871794871796,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9415584415584416,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04765097796916962,
"eval_overall_accuracy": 0.9892945374691189,
"eval_overall_f1": 0.950943396226415,
"eval_overall_precision": 0.9521410579345088,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2914,
"eval_samples_per_second": 583.313,
"eval_steps_per_second": 10.294,
"step": 6624
},
{
"epoch": 70.0,
"grad_norm": 0.7745044827461243,
"learning_rate": 1.5e-05,
"loss": 0.0095,
"step": 6720
},
{
"epoch": 70.0,
"eval_LOCATION_f1": 0.9576271186440678,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9416666666666667,
"eval_LOCATION_recall": 0.9741379310344828,
"eval_ORGANIZATION_f1": 0.9545454545454545,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.98,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04321495071053505,
"eval_overall_accuracy": 0.9917650288223991,
"eval_overall_f1": 0.964735516372796,
"eval_overall_precision": 0.9671717171717171,
"eval_overall_recall": 0.9623115577889447,
"eval_runtime": 0.2891,
"eval_samples_per_second": 587.955,
"eval_steps_per_second": 10.376,
"step": 6720
},
{
"epoch": 71.0,
"grad_norm": 0.415163516998291,
"learning_rate": 1.45e-05,
"loss": 0.0095,
"step": 6816
},
{
"epoch": 71.0,
"eval_LOCATION_f1": 0.9437229437229439,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9478260869565217,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9423076923076923,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9545454545454546,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04255209490656853,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9546599496221662,
"eval_overall_precision": 0.9570707070707071,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2893,
"eval_samples_per_second": 587.665,
"eval_steps_per_second": 10.371,
"step": 6816
},
{
"epoch": 72.0,
"grad_norm": 0.2266206294298172,
"learning_rate": 1.4000000000000001e-05,
"loss": 0.0086,
"step": 6912
},
{
"epoch": 72.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9354838709677419,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9539473684210527,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.043971460312604904,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9522613065326633,
"eval_overall_precision": 0.9522613065326633,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2913,
"eval_samples_per_second": 583.672,
"eval_steps_per_second": 10.3,
"step": 6912
},
{
"epoch": 73.0,
"grad_norm": 0.22036756575107574,
"learning_rate": 1.3500000000000001e-05,
"loss": 0.0091,
"step": 7008
},
{
"epoch": 73.0,
"eval_LOCATION_f1": 0.9491525423728815,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9333333333333333,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.9276315789473684,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9657534246575342,
"eval_ORGANIZATION_recall": 0.8924050632911392,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.050814829766750336,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.9531051964512041,
"eval_overall_precision": 0.9616368286445013,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2914,
"eval_samples_per_second": 583.291,
"eval_steps_per_second": 10.293,
"step": 7008
},
{
"epoch": 74.0,
"grad_norm": 0.1528637558221817,
"learning_rate": 1.3000000000000001e-05,
"loss": 0.0088,
"step": 7104
},
{
"epoch": 74.0,
"eval_LOCATION_f1": 0.944206008583691,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9401709401709402,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9419354838709677,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9605263157894737,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04793453961610794,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9558638083228247,
"eval_overall_precision": 0.959493670886076,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2908,
"eval_samples_per_second": 584.594,
"eval_steps_per_second": 10.316,
"step": 7104
},
{
"epoch": 75.0,
"grad_norm": 0.3548160791397095,
"learning_rate": 1.25e-05,
"loss": 0.0082,
"step": 7200
},
{
"epoch": 75.0,
"eval_LOCATION_f1": 0.9487179487179486,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.940677966101695,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9329073482428115,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9419354838709677,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04753913730382919,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9535759096612295,
"eval_overall_precision": 0.9523809523809523,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2919,
"eval_samples_per_second": 582.473,
"eval_steps_per_second": 10.279,
"step": 7200
},
{
"epoch": 76.0,
"grad_norm": 0.0739251896739006,
"learning_rate": 1.2e-05,
"loss": 0.0085,
"step": 7296
},
{
"epoch": 76.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9329073482428115,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9419354838709677,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04924161732196808,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9523809523809523,
"eval_overall_precision": 0.95,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2926,
"eval_samples_per_second": 581.041,
"eval_steps_per_second": 10.254,
"step": 7296
},
{
"epoch": 77.0,
"grad_norm": 0.41715970635414124,
"learning_rate": 1.1500000000000002e-05,
"loss": 0.0078,
"step": 7392
},
{
"epoch": 77.0,
"eval_LOCATION_f1": 0.9487179487179486,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.940677966101695,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9358974358974359,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.948051948051948,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05100114643573761,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9547738693467337,
"eval_overall_precision": 0.9547738693467337,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2914,
"eval_samples_per_second": 583.363,
"eval_steps_per_second": 10.295,
"step": 7392
},
{
"epoch": 78.0,
"grad_norm": 1.2218786478042603,
"learning_rate": 1.1000000000000001e-05,
"loss": 0.0092,
"step": 7488
},
{
"epoch": 78.0,
"eval_LOCATION_f1": 0.94017094017094,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9322033898305084,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.932475884244373,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9477124183006536,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.050010260194540024,
"eval_overall_accuracy": 0.9898435355476256,
"eval_overall_f1": 0.950943396226415,
"eval_overall_precision": 0.9521410579345088,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2924,
"eval_samples_per_second": 581.344,
"eval_steps_per_second": 10.259,
"step": 7488
},
{
"epoch": 79.0,
"grad_norm": 0.005696540232747793,
"learning_rate": 1.05e-05,
"loss": 0.0082,
"step": 7584
},
{
"epoch": 79.0,
"eval_LOCATION_f1": 0.9396551724137931,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9396551724137931,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9423076923076923,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9545454545454546,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.048680275678634644,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9534591194968555,
"eval_overall_precision": 0.9546599496221663,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2912,
"eval_samples_per_second": 583.859,
"eval_steps_per_second": 10.303,
"step": 7584
},
{
"epoch": 80.0,
"grad_norm": 0.3896704912185669,
"learning_rate": 1e-05,
"loss": 0.0087,
"step": 7680
},
{
"epoch": 80.0,
"eval_LOCATION_f1": 0.944206008583691,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9401709401709402,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9389067524115756,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.954248366013072,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04815710708498955,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9546599496221662,
"eval_overall_precision": 0.9570707070707071,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2888,
"eval_samples_per_second": 588.575,
"eval_steps_per_second": 10.387,
"step": 7680
},
{
"epoch": 81.0,
"grad_norm": 3.0765485763549805,
"learning_rate": 9.5e-06,
"loss": 0.0076,
"step": 7776
},
{
"epoch": 81.0,
"eval_LOCATION_f1": 0.944206008583691,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9401709401709402,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9389067524115756,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.954248366013072,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04572370648384094,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9546599496221662,
"eval_overall_precision": 0.9570707070707071,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2908,
"eval_samples_per_second": 584.504,
"eval_steps_per_second": 10.315,
"step": 7776
},
{
"epoch": 82.0,
"grad_norm": 0.06425667554140091,
"learning_rate": 9e-06,
"loss": 0.007,
"step": 7872
},
{
"epoch": 82.0,
"eval_LOCATION_f1": 0.944206008583691,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9401709401709402,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9419354838709677,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9605263157894737,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04720095545053482,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9558638083228247,
"eval_overall_precision": 0.959493670886076,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2931,
"eval_samples_per_second": 580.075,
"eval_steps_per_second": 10.237,
"step": 7872
},
{
"epoch": 83.0,
"grad_norm": 0.015088742598891258,
"learning_rate": 8.500000000000002e-06,
"loss": 0.0063,
"step": 7968
},
{
"epoch": 83.0,
"eval_LOCATION_f1": 0.944206008583691,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9401709401709402,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9483870967741935,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9671052631578947,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04591359943151474,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9583858764186632,
"eval_overall_precision": 0.9620253164556962,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2913,
"eval_samples_per_second": 583.649,
"eval_steps_per_second": 10.3,
"step": 7968
},
{
"epoch": 84.0,
"grad_norm": 0.09398268163204193,
"learning_rate": 8.000000000000001e-06,
"loss": 0.0075,
"step": 8064
},
{
"epoch": 84.0,
"eval_LOCATION_f1": 0.9487179487179486,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.940677966101695,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9389067524115756,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.954248366013072,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04623812064528465,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9559748427672956,
"eval_overall_precision": 0.9571788413098237,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2908,
"eval_samples_per_second": 584.611,
"eval_steps_per_second": 10.317,
"step": 8064
},
{
"epoch": 85.0,
"grad_norm": 0.33947882056236267,
"learning_rate": 7.5e-06,
"loss": 0.0077,
"step": 8160
},
{
"epoch": 85.0,
"eval_LOCATION_f1": 0.9356223175965666,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9316239316239316,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9419354838709677,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9605263157894737,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05004940181970596,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.953341740226986,
"eval_overall_precision": 0.9569620253164557,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2891,
"eval_samples_per_second": 588.008,
"eval_steps_per_second": 10.377,
"step": 8160
},
{
"epoch": 86.0,
"grad_norm": 0.27867794036865234,
"learning_rate": 7.000000000000001e-06,
"loss": 0.0084,
"step": 8256
},
{
"epoch": 86.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9449838187702266,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9668874172185431,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05041741579771042,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9571788413098236,
"eval_overall_precision": 0.9595959595959596,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2912,
"eval_samples_per_second": 583.811,
"eval_steps_per_second": 10.303,
"step": 8256
},
{
"epoch": 87.0,
"grad_norm": 0.27448999881744385,
"learning_rate": 6.5000000000000004e-06,
"loss": 0.0089,
"step": 8352
},
{
"epoch": 87.0,
"eval_LOCATION_f1": 0.9487179487179486,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.940677966101695,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9483870967741935,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9671052631578947,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.050721243023872375,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9596977329974811,
"eval_overall_precision": 0.9621212121212122,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2893,
"eval_samples_per_second": 587.602,
"eval_steps_per_second": 10.369,
"step": 8352
},
{
"epoch": 88.0,
"grad_norm": 0.22354625165462494,
"learning_rate": 6e-06,
"loss": 0.007,
"step": 8448
},
{
"epoch": 88.0,
"eval_LOCATION_f1": 0.944206008583691,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9401709401709402,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9385113268608414,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9602649006622517,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04851313307881355,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9545454545454546,
"eval_overall_precision": 0.9593908629441624,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2914,
"eval_samples_per_second": 583.485,
"eval_steps_per_second": 10.297,
"step": 8448
},
{
"epoch": 89.0,
"grad_norm": 0.5501545071601868,
"learning_rate": 5.500000000000001e-06,
"loss": 0.0075,
"step": 8544
},
{
"epoch": 89.0,
"eval_LOCATION_f1": 0.9356223175965666,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9316239316239316,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9419354838709677,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9605263157894737,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.047070857137441635,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.953341740226986,
"eval_overall_precision": 0.9569620253164557,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2898,
"eval_samples_per_second": 586.553,
"eval_steps_per_second": 10.351,
"step": 8544
},
{
"epoch": 90.0,
"grad_norm": 0.022565767168998718,
"learning_rate": 5e-06,
"loss": 0.0074,
"step": 8640
},
{
"epoch": 90.0,
"eval_LOCATION_f1": 0.9487179487179486,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.940677966101695,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9449838187702266,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9668874172185431,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.048480287194252014,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9583858764186632,
"eval_overall_precision": 0.9620253164556962,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2905,
"eval_samples_per_second": 585.145,
"eval_steps_per_second": 10.326,
"step": 8640
},
{
"epoch": 91.0,
"grad_norm": 0.11001965403556824,
"learning_rate": 4.5e-06,
"loss": 0.0067,
"step": 8736
},
{
"epoch": 91.0,
"eval_LOCATION_f1": 0.94017094017094,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9322033898305084,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9449838187702266,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9668874172185431,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04967214912176132,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9558638083228247,
"eval_overall_precision": 0.959493670886076,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2897,
"eval_samples_per_second": 586.774,
"eval_steps_per_second": 10.355,
"step": 8736
},
{
"epoch": 92.0,
"grad_norm": 1.1619187593460083,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0074,
"step": 8832
},
{
"epoch": 92.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9449838187702266,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9668874172185431,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.049173153936862946,
"eval_overall_accuracy": 0.9912160307438924,
"eval_overall_f1": 0.9571788413098236,
"eval_overall_precision": 0.9595959595959596,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2891,
"eval_samples_per_second": 588.059,
"eval_steps_per_second": 10.378,
"step": 8832
},
{
"epoch": 93.0,
"grad_norm": 0.05074794217944145,
"learning_rate": 3.5000000000000004e-06,
"loss": 0.0067,
"step": 8928
},
{
"epoch": 93.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9483870967741935,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9671052631578947,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.046569496393203735,
"eval_overall_accuracy": 0.9912160307438924,
"eval_overall_f1": 0.9584905660377357,
"eval_overall_precision": 0.9596977329974811,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2942,
"eval_samples_per_second": 577.833,
"eval_steps_per_second": 10.197,
"step": 8928
},
{
"epoch": 94.0,
"grad_norm": 0.08575073629617691,
"learning_rate": 3e-06,
"loss": 0.0076,
"step": 9024
},
{
"epoch": 94.0,
"eval_LOCATION_f1": 0.9487179487179486,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.940677966101695,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9483870967741935,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9671052631578947,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04603978246450424,
"eval_overall_accuracy": 0.9917650288223991,
"eval_overall_f1": 0.9596977329974811,
"eval_overall_precision": 0.9621212121212122,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2908,
"eval_samples_per_second": 584.521,
"eval_steps_per_second": 10.315,
"step": 9024
},
{
"epoch": 95.0,
"grad_norm": 0.026022328063845634,
"learning_rate": 2.5e-06,
"loss": 0.0063,
"step": 9120
},
{
"epoch": 95.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9449838187702266,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9668874172185431,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04672197997570038,
"eval_overall_accuracy": 0.9912160307438924,
"eval_overall_f1": 0.9571788413098236,
"eval_overall_precision": 0.9595959595959596,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2922,
"eval_samples_per_second": 581.789,
"eval_steps_per_second": 10.267,
"step": 9120
},
{
"epoch": 96.0,
"grad_norm": 0.07688921689987183,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.0064,
"step": 9216
},
{
"epoch": 96.0,
"eval_LOCATION_f1": 0.9531914893617022,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9411764705882353,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.9449838187702266,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9668874172185431,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.0466776117682457,
"eval_overall_accuracy": 0.9912160307438924,
"eval_overall_f1": 0.9596977329974811,
"eval_overall_precision": 0.9621212121212122,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.289,
"eval_samples_per_second": 588.324,
"eval_steps_per_second": 10.382,
"step": 9216
},
{
"epoch": 97.0,
"grad_norm": 0.8250861167907715,
"learning_rate": 1.5e-06,
"loss": 0.0068,
"step": 9312
},
{
"epoch": 97.0,
"eval_LOCATION_f1": 0.9531914893617022,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9411764705882353,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.9449838187702266,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9668874172185431,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.046966131776571274,
"eval_overall_accuracy": 0.9912160307438924,
"eval_overall_f1": 0.9596977329974811,
"eval_overall_precision": 0.9621212121212122,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2892,
"eval_samples_per_second": 587.744,
"eval_steps_per_second": 10.372,
"step": 9312
},
{
"epoch": 98.0,
"grad_norm": 0.16832178831100464,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.0061,
"step": 9408
},
{
"epoch": 98.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9449838187702266,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9668874172185431,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04705871641635895,
"eval_overall_accuracy": 0.9912160307438924,
"eval_overall_f1": 0.9571788413098236,
"eval_overall_precision": 0.9595959595959596,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2905,
"eval_samples_per_second": 585.26,
"eval_steps_per_second": 10.328,
"step": 9408
},
{
"epoch": 99.0,
"grad_norm": 0.0696122795343399,
"learning_rate": 5.000000000000001e-07,
"loss": 0.0068,
"step": 9504
},
{
"epoch": 99.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9449838187702266,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9668874172185431,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.046953875571489334,
"eval_overall_accuracy": 0.9912160307438924,
"eval_overall_f1": 0.9571788413098236,
"eval_overall_precision": 0.9595959595959596,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2888,
"eval_samples_per_second": 588.56,
"eval_steps_per_second": 10.386,
"step": 9504
},
{
"epoch": 100.0,
"grad_norm": 0.3352962136268616,
"learning_rate": 0.0,
"loss": 0.0068,
"step": 9600
},
{
"epoch": 100.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9449838187702266,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9668874172185431,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.0468829870223999,
"eval_overall_accuracy": 0.9912160307438924,
"eval_overall_f1": 0.9571788413098236,
"eval_overall_precision": 0.9595959595959596,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2886,
"eval_samples_per_second": 588.987,
"eval_steps_per_second": 10.394,
"step": 9600
},
{
"epoch": 100.0,
"step": 9600,
"total_flos": 4293597283743744.0,
"train_loss": 0.03746084541703264,
"train_runtime": 545.4697,
"train_samples_per_second": 280.676,
"train_steps_per_second": 17.6
}
],
"logging_steps": 500,
"max_steps": 9600,
"num_input_tokens_seen": 0,
"num_train_epochs": 100,
"save_steps": 500,
"total_flos": 4293597283743744.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}