nerui-pt-pl50-0 / trainer_state.json
apwic's picture
End of training
0c6d606 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": 1.0303987264633179,
"learning_rate": 4.9500000000000004e-05,
"loss": 0.8736,
"step": 96
},
{
"epoch": 1.0,
"eval_LOCATION_f1": 0.0,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.0,
"eval_LOCATION_recall": 0.0,
"eval_ORGANIZATION_f1": 0.13599999999999998,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.20481927710843373,
"eval_ORGANIZATION_recall": 0.10179640718562874,
"eval_PERSON_f1": 0.16842105263157892,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.3018867924528302,
"eval_PERSON_recall": 0.11678832116788321,
"eval_loss": 0.4344855844974518,
"eval_overall_accuracy": 0.8453038674033149,
"eval_overall_f1": 0.1233644859813084,
"eval_overall_precision": 0.24087591240875914,
"eval_overall_recall": 0.0829145728643216,
"eval_runtime": 0.2663,
"eval_samples_per_second": 638.371,
"eval_steps_per_second": 11.265,
"step": 96
},
{
"epoch": 2.0,
"grad_norm": 0.7377827763557434,
"learning_rate": 4.9e-05,
"loss": 0.3697,
"step": 192
},
{
"epoch": 2.0,
"eval_LOCATION_f1": 0.4,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.3287671232876712,
"eval_LOCATION_recall": 0.5106382978723404,
"eval_ORGANIZATION_f1": 0.5840220385674931,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.5408163265306123,
"eval_ORGANIZATION_recall": 0.6347305389221557,
"eval_PERSON_f1": 0.8439716312056738,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.8206896551724138,
"eval_PERSON_recall": 0.8686131386861314,
"eval_loss": 0.22115051746368408,
"eval_overall_accuracy": 0.9312154696132596,
"eval_overall_f1": 0.6169491525423729,
"eval_overall_precision": 0.5605749486652978,
"eval_overall_recall": 0.6859296482412061,
"eval_runtime": 0.2614,
"eval_samples_per_second": 650.261,
"eval_steps_per_second": 11.475,
"step": 192
},
{
"epoch": 3.0,
"grad_norm": 1.2577224969863892,
"learning_rate": 4.85e-05,
"loss": 0.203,
"step": 288
},
{
"epoch": 3.0,
"eval_LOCATION_f1": 0.7999999999999999,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.7722772277227723,
"eval_LOCATION_recall": 0.8297872340425532,
"eval_ORGANIZATION_f1": 0.7787114845938377,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.7315789473684211,
"eval_ORGANIZATION_recall": 0.8323353293413174,
"eval_PERSON_f1": 0.9507042253521126,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9183673469387755,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.11514607816934586,
"eval_overall_accuracy": 0.9660220994475138,
"eval_overall_f1": 0.8421052631578947,
"eval_overall_precision": 0.8036529680365296,
"eval_overall_recall": 0.8844221105527639,
"eval_runtime": 0.2609,
"eval_samples_per_second": 651.517,
"eval_steps_per_second": 11.497,
"step": 288
},
{
"epoch": 4.0,
"grad_norm": 0.6511440277099609,
"learning_rate": 4.8e-05,
"loss": 0.1351,
"step": 384
},
{
"epoch": 4.0,
"eval_LOCATION_f1": 0.8056872037914692,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.7264957264957265,
"eval_LOCATION_recall": 0.9042553191489362,
"eval_ORGANIZATION_f1": 0.8012232415902141,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.81875,
"eval_ORGANIZATION_recall": 0.7844311377245509,
"eval_PERSON_f1": 0.9747292418772563,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9642857142857143,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.08147778362035751,
"eval_overall_accuracy": 0.9718232044198895,
"eval_overall_f1": 0.8613496932515338,
"eval_overall_precision": 0.841726618705036,
"eval_overall_recall": 0.8819095477386935,
"eval_runtime": 0.2613,
"eval_samples_per_second": 650.654,
"eval_steps_per_second": 11.482,
"step": 384
},
{
"epoch": 5.0,
"grad_norm": 0.6455439329147339,
"learning_rate": 4.75e-05,
"loss": 0.1121,
"step": 480
},
{
"epoch": 5.0,
"eval_LOCATION_f1": 0.900523560209424,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8865979381443299,
"eval_LOCATION_recall": 0.9148936170212766,
"eval_ORGANIZATION_f1": 0.8630952380952381,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8579881656804734,
"eval_ORGANIZATION_recall": 0.8682634730538922,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.06132228672504425,
"eval_overall_accuracy": 0.9806629834254144,
"eval_overall_f1": 0.9149999999999999,
"eval_overall_precision": 0.9104477611940298,
"eval_overall_recall": 0.9195979899497487,
"eval_runtime": 0.2612,
"eval_samples_per_second": 650.948,
"eval_steps_per_second": 11.487,
"step": 480
},
{
"epoch": 6.0,
"grad_norm": 0.7582173943519592,
"learning_rate": 4.7e-05,
"loss": 0.0964,
"step": 576
},
{
"epoch": 6.0,
"eval_LOCATION_f1": 0.8878048780487804,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8198198198198198,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.8734939759036144,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8787878787878788,
"eval_ORGANIZATION_recall": 0.8682634730538922,
"eval_PERSON_f1": 0.9818181818181817,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9782608695652174,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05840582028031349,
"eval_overall_accuracy": 0.9820441988950276,
"eval_overall_f1": 0.9137931034482758,
"eval_overall_precision": 0.8961352657004831,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2601,
"eval_samples_per_second": 653.579,
"eval_steps_per_second": 11.534,
"step": 576
},
{
"epoch": 7.0,
"grad_norm": 0.6419504284858704,
"learning_rate": 4.6500000000000005e-05,
"loss": 0.0832,
"step": 672
},
{
"epoch": 7.0,
"eval_LOCATION_f1": 0.898989898989899,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8557692307692307,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8475609756097561,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8633540372670807,
"eval_ORGANIZATION_recall": 0.8323353293413174,
"eval_PERSON_f1": 0.9602888086642599,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.95,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.05497827008366585,
"eval_overall_accuracy": 0.9814917127071823,
"eval_overall_f1": 0.8991282689912827,
"eval_overall_precision": 0.891358024691358,
"eval_overall_recall": 0.907035175879397,
"eval_runtime": 0.262,
"eval_samples_per_second": 648.859,
"eval_steps_per_second": 11.45,
"step": 672
},
{
"epoch": 8.0,
"grad_norm": 0.5451741218566895,
"learning_rate": 4.600000000000001e-05,
"loss": 0.078,
"step": 768
},
{
"epoch": 8.0,
"eval_LOCATION_f1": 0.8768472906403939,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8165137614678899,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8527607361963191,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8742138364779874,
"eval_ORGANIZATION_recall": 0.8323353293413174,
"eval_PERSON_f1": 0.9708029197080292,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9708029197080292,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.04951971769332886,
"eval_overall_accuracy": 0.9823204419889503,
"eval_overall_f1": 0.8991282689912827,
"eval_overall_precision": 0.891358024691358,
"eval_overall_recall": 0.907035175879397,
"eval_runtime": 0.2611,
"eval_samples_per_second": 651.062,
"eval_steps_per_second": 11.489,
"step": 768
},
{
"epoch": 9.0,
"grad_norm": 0.7684198617935181,
"learning_rate": 4.55e-05,
"loss": 0.0701,
"step": 864
},
{
"epoch": 9.0,
"eval_LOCATION_f1": 0.878048780487805,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8108108108108109,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8562500000000001,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8954248366013072,
"eval_ORGANIZATION_recall": 0.8203592814371258,
"eval_PERSON_f1": 0.9745454545454545,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9710144927536232,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.047906920313835144,
"eval_overall_accuracy": 0.9831491712707182,
"eval_overall_f1": 0.9025,
"eval_overall_precision": 0.8980099502487562,
"eval_overall_recall": 0.907035175879397,
"eval_runtime": 0.2634,
"eval_samples_per_second": 645.438,
"eval_steps_per_second": 11.39,
"step": 864
},
{
"epoch": 10.0,
"grad_norm": 0.8079931735992432,
"learning_rate": 4.5e-05,
"loss": 0.0639,
"step": 960
},
{
"epoch": 10.0,
"eval_LOCATION_f1": 0.9175257731958764,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.89,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8973607038123166,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8793103448275862,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.9672727272727273,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9637681159420289,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.04653667286038399,
"eval_overall_accuracy": 0.9853591160220995,
"eval_overall_f1": 0.9259259259259259,
"eval_overall_precision": 0.9101941747572816,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.2608,
"eval_samples_per_second": 651.861,
"eval_steps_per_second": 11.503,
"step": 960
},
{
"epoch": 11.0,
"grad_norm": 0.642991840839386,
"learning_rate": 4.4500000000000004e-05,
"loss": 0.0619,
"step": 1056
},
{
"epoch": 11.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9244712990936556,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9329268292682927,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.9854014598540146,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9854014598540146,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04115524888038635,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9450000000000001,
"eval_overall_precision": 0.9402985074626866,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2609,
"eval_samples_per_second": 651.484,
"eval_steps_per_second": 11.497,
"step": 1056
},
{
"epoch": 12.0,
"grad_norm": 0.36129075288772583,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.056,
"step": 1152
},
{
"epoch": 12.0,
"eval_LOCATION_f1": 0.9137055837563451,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8737864077669902,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8854489164086686,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9166666666666666,
"eval_ORGANIZATION_recall": 0.8562874251497006,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04775137081742287,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9292929292929293,
"eval_overall_precision": 0.934010152284264,
"eval_overall_recall": 0.9246231155778895,
"eval_runtime": 0.2618,
"eval_samples_per_second": 649.419,
"eval_steps_per_second": 11.46,
"step": 1152
},
{
"epoch": 13.0,
"grad_norm": 0.8001056909561157,
"learning_rate": 4.35e-05,
"loss": 0.0502,
"step": 1248
},
{
"epoch": 13.0,
"eval_LOCATION_f1": 0.9081632653061226,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8725490196078431,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8957055214723927,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9182389937106918,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.043771468102931976,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9257861635220125,
"eval_overall_precision": 0.9269521410579346,
"eval_overall_recall": 0.9246231155778895,
"eval_runtime": 0.2608,
"eval_samples_per_second": 651.889,
"eval_steps_per_second": 11.504,
"step": 1248
},
{
"epoch": 14.0,
"grad_norm": 0.7112703919410706,
"learning_rate": 4.3e-05,
"loss": 0.0495,
"step": 1344
},
{
"epoch": 14.0,
"eval_LOCATION_f1": 0.9054726368159204,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8504672897196262,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.896969696969697,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9079754601226994,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04413843899965286,
"eval_overall_accuracy": 0.9853591160220995,
"eval_overall_f1": 0.927860696517413,
"eval_overall_precision": 0.9187192118226601,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2614,
"eval_samples_per_second": 650.445,
"eval_steps_per_second": 11.478,
"step": 1344
},
{
"epoch": 15.0,
"grad_norm": 0.3894376754760742,
"learning_rate": 4.25e-05,
"loss": 0.0465,
"step": 1440
},
{
"epoch": 15.0,
"eval_LOCATION_f1": 0.9214659685863875,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9072164948453608,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9041916167664671,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9041916167664671,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.0423913300037384,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9323308270676693,
"eval_overall_precision": 0.93,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.261,
"eval_samples_per_second": 651.374,
"eval_steps_per_second": 11.495,
"step": 1440
},
{
"epoch": 16.0,
"grad_norm": 0.9584354758262634,
"learning_rate": 4.2e-05,
"loss": 0.045,
"step": 1536
},
{
"epoch": 16.0,
"eval_LOCATION_f1": 0.9109947643979057,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8969072164948454,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9149560117302054,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.896551724137931,
"eval_ORGANIZATION_recall": 0.9341317365269461,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.044694896787405014,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9341614906832298,
"eval_overall_precision": 0.9238329238329238,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2612,
"eval_samples_per_second": 650.934,
"eval_steps_per_second": 11.487,
"step": 1536
},
{
"epoch": 17.0,
"grad_norm": 0.21413855254650116,
"learning_rate": 4.15e-05,
"loss": 0.0427,
"step": 1632
},
{
"epoch": 17.0,
"eval_LOCATION_f1": 0.9119170984455959,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8888888888888888,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9063444108761329,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9146341463414634,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.04704223573207855,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9309912170639899,
"eval_overall_precision": 0.9298245614035088,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2612,
"eval_samples_per_second": 650.958,
"eval_steps_per_second": 11.487,
"step": 1632
},
{
"epoch": 18.0,
"grad_norm": 0.48273587226867676,
"learning_rate": 4.1e-05,
"loss": 0.04,
"step": 1728
},
{
"epoch": 18.0,
"eval_LOCATION_f1": 0.9081632653061226,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8725490196078431,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8562691131498471,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.875,
"eval_ORGANIZATION_recall": 0.8383233532934131,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.052333418279886246,
"eval_overall_accuracy": 0.9825966850828729,
"eval_overall_f1": 0.9120603015075377,
"eval_overall_precision": 0.9120603015075377,
"eval_overall_recall": 0.9120603015075377,
"eval_runtime": 0.2606,
"eval_samples_per_second": 652.228,
"eval_steps_per_second": 11.51,
"step": 1728
},
{
"epoch": 19.0,
"grad_norm": 0.6569631099700928,
"learning_rate": 4.05e-05,
"loss": 0.0402,
"step": 1824
},
{
"epoch": 19.0,
"eval_LOCATION_f1": 0.9157894736842105,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.90625,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9003021148036255,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9085365853658537,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.050052743405103683,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.929471032745592,
"eval_overall_precision": 0.9318181818181818,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.2621,
"eval_samples_per_second": 648.687,
"eval_steps_per_second": 11.447,
"step": 1824
},
{
"epoch": 20.0,
"grad_norm": 0.8777341842651367,
"learning_rate": 4e-05,
"loss": 0.0382,
"step": 1920
},
{
"epoch": 20.0,
"eval_LOCATION_f1": 0.9270833333333334,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9081632653061225,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9129129129129129,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9156626506024096,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9708029197080292,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9708029197080292,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.05085308849811554,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9361702127659574,
"eval_overall_precision": 0.9326683291770573,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.261,
"eval_samples_per_second": 651.395,
"eval_steps_per_second": 11.495,
"step": 1920
},
{
"epoch": 21.0,
"grad_norm": 0.710879921913147,
"learning_rate": 3.9500000000000005e-05,
"loss": 0.0356,
"step": 2016
},
{
"epoch": 21.0,
"eval_LOCATION_f1": 0.9270833333333334,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9081632653061225,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9161676646706587,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9161676646706587,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04502540081739426,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9411764705882354,
"eval_overall_precision": 0.9376558603491272,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2616,
"eval_samples_per_second": 649.958,
"eval_steps_per_second": 11.47,
"step": 2016
},
{
"epoch": 22.0,
"grad_norm": 0.12565217912197113,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.0352,
"step": 2112
},
{
"epoch": 22.0,
"eval_LOCATION_f1": 0.9326424870466321,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9156626506024097,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9212121212121213,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05098550394177437,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9435382685069008,
"eval_overall_precision": 0.9423558897243107,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2609,
"eval_samples_per_second": 651.594,
"eval_steps_per_second": 11.499,
"step": 2112
},
{
"epoch": 23.0,
"grad_norm": 0.3223367929458618,
"learning_rate": 3.85e-05,
"loss": 0.0316,
"step": 2208
},
{
"epoch": 23.0,
"eval_LOCATION_f1": 0.9175257731958764,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.89,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9151515151515152,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9263803680981595,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.04805075749754906,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9360100376411543,
"eval_overall_precision": 0.9348370927318296,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2618,
"eval_samples_per_second": 649.41,
"eval_steps_per_second": 11.46,
"step": 2208
},
{
"epoch": 24.0,
"grad_norm": 0.4155941903591156,
"learning_rate": 3.8e-05,
"loss": 0.03,
"step": 2304
},
{
"epoch": 24.0,
"eval_LOCATION_f1": 0.8934010152284263,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8543689320388349,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9179331306990882,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9320987654320988,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9781021897810219,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9781021897810219,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05030519887804985,
"eval_overall_accuracy": 0.9856353591160221,
"eval_overall_f1": 0.9325,
"eval_overall_precision": 0.927860696517413,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2609,
"eval_samples_per_second": 651.702,
"eval_steps_per_second": 11.501,
"step": 2304
},
{
"epoch": 25.0,
"grad_norm": 0.3500244617462158,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.0304,
"step": 2400
},
{
"epoch": 25.0,
"eval_LOCATION_f1": 0.9072164948453608,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.88,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9101796407185628,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9101796407185628,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04637878015637398,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9338327091136079,
"eval_overall_precision": 0.9280397022332506,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.26,
"eval_samples_per_second": 653.938,
"eval_steps_per_second": 11.54,
"step": 2400
},
{
"epoch": 26.0,
"grad_norm": 0.3021068572998047,
"learning_rate": 3.7e-05,
"loss": 0.0292,
"step": 2496
},
{
"epoch": 26.0,
"eval_LOCATION_f1": 0.9175257731958764,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.89,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9156626506024097,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9212121212121213,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04712934046983719,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9386733416770965,
"eval_overall_precision": 0.9351620947630923,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.261,
"eval_samples_per_second": 651.446,
"eval_steps_per_second": 11.496,
"step": 2496
},
{
"epoch": 27.0,
"grad_norm": 0.5916212797164917,
"learning_rate": 3.65e-05,
"loss": 0.0279,
"step": 2592
},
{
"epoch": 27.0,
"eval_LOCATION_f1": 0.9128205128205128,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8811881188118812,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8902439024390244,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.906832298136646,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04792354255914688,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9271356783919598,
"eval_overall_precision": 0.9271356783919598,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.2607,
"eval_samples_per_second": 652.033,
"eval_steps_per_second": 11.506,
"step": 2592
},
{
"epoch": 28.0,
"grad_norm": 0.263266384601593,
"learning_rate": 3.6e-05,
"loss": 0.028,
"step": 2688
},
{
"epoch": 28.0,
"eval_LOCATION_f1": 0.9,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8490566037735849,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9046153846153847,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.930379746835443,
"eval_ORGANIZATION_recall": 0.8802395209580839,
"eval_PERSON_f1": 0.9781021897810219,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9781021897810219,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05301225185394287,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9286608260325407,
"eval_overall_precision": 0.9251870324189526,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2608,
"eval_samples_per_second": 651.797,
"eval_steps_per_second": 11.502,
"step": 2688
},
{
"epoch": 29.0,
"grad_norm": 0.4376133978366852,
"learning_rate": 3.55e-05,
"loss": 0.0266,
"step": 2784
},
{
"epoch": 29.0,
"eval_LOCATION_f1": 0.9137055837563451,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8737864077669902,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9107692307692307,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9367088607594937,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.053360432386398315,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9358490566037736,
"eval_overall_precision": 0.9370277078085643,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.26,
"eval_samples_per_second": 653.89,
"eval_steps_per_second": 11.539,
"step": 2784
},
{
"epoch": 30.0,
"grad_norm": 0.30625322461128235,
"learning_rate": 3.5e-05,
"loss": 0.0247,
"step": 2880
},
{
"epoch": 30.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9096385542168675,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9151515151515152,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9854014598540146,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9854014598540146,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.049321241676807404,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9388264669163546,
"eval_overall_precision": 0.9330024813895782,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2611,
"eval_samples_per_second": 651.118,
"eval_steps_per_second": 11.49,
"step": 2880
},
{
"epoch": 31.0,
"grad_norm": 0.09783239662647247,
"learning_rate": 3.45e-05,
"loss": 0.0232,
"step": 2976
},
{
"epoch": 31.0,
"eval_LOCATION_f1": 0.9270833333333334,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9081632653061225,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9123867069486405,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9207317073170732,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05281314253807068,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9396984924623115,
"eval_overall_precision": 0.9396984924623115,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2612,
"eval_samples_per_second": 650.73,
"eval_steps_per_second": 11.483,
"step": 2976
},
{
"epoch": 32.0,
"grad_norm": 0.8584625124931335,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.0249,
"step": 3072
},
{
"epoch": 32.0,
"eval_LOCATION_f1": 0.9222797927461138,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.898989898989899,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9107142857142857,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9053254437869822,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.056144535541534424,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9376558603491272,
"eval_overall_precision": 0.9306930693069307,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2604,
"eval_samples_per_second": 652.803,
"eval_steps_per_second": 11.52,
"step": 3072
},
{
"epoch": 33.0,
"grad_norm": 0.1327567994594574,
"learning_rate": 3.35e-05,
"loss": 0.0235,
"step": 3168
},
{
"epoch": 33.0,
"eval_LOCATION_f1": 0.9270833333333334,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9081632653061225,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9207317073170732,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.937888198757764,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05539720132946968,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9444444444444445,
"eval_overall_precision": 0.949238578680203,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2616,
"eval_samples_per_second": 649.903,
"eval_steps_per_second": 11.469,
"step": 3168
},
{
"epoch": 34.0,
"grad_norm": 0.9002353549003601,
"learning_rate": 3.3e-05,
"loss": 0.0226,
"step": 3264
},
{
"epoch": 34.0,
"eval_LOCATION_f1": 0.9081632653061226,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8725490196078431,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9051987767584098,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.925,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06008733808994293,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9296482412060302,
"eval_overall_precision": 0.9296482412060302,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2605,
"eval_samples_per_second": 652.615,
"eval_steps_per_second": 11.517,
"step": 3264
},
{
"epoch": 35.0,
"grad_norm": 0.08030929416418076,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.0216,
"step": 3360
},
{
"epoch": 35.0,
"eval_LOCATION_f1": 0.9045226130653266,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8571428571428571,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9102167182662538,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9423076923076923,
"eval_ORGANIZATION_recall": 0.8802395209580839,
"eval_PERSON_f1": 0.9781021897810219,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9781021897810219,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.06106843799352646,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9321608040201005,
"eval_overall_precision": 0.9321608040201005,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2606,
"eval_samples_per_second": 652.421,
"eval_steps_per_second": 11.513,
"step": 3360
},
{
"epoch": 36.0,
"grad_norm": 0.30918025970458984,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.0211,
"step": 3456
},
{
"epoch": 36.0,
"eval_LOCATION_f1": 0.8944723618090452,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8476190476190476,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9221183800623053,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.961038961038961,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.054767195135354996,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9331651954602774,
"eval_overall_precision": 0.9367088607594937,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2621,
"eval_samples_per_second": 648.616,
"eval_steps_per_second": 11.446,
"step": 3456
},
{
"epoch": 37.0,
"grad_norm": 0.5124485492706299,
"learning_rate": 3.15e-05,
"loss": 0.0209,
"step": 3552
},
{
"epoch": 37.0,
"eval_LOCATION_f1": 0.898989898989899,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8557692307692307,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9107692307692307,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9367088607594937,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05310112610459328,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9346733668341709,
"eval_overall_precision": 0.9346733668341709,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2596,
"eval_samples_per_second": 654.755,
"eval_steps_per_second": 11.554,
"step": 3552
},
{
"epoch": 38.0,
"grad_norm": 0.3233339786529541,
"learning_rate": 3.1e-05,
"loss": 0.0178,
"step": 3648
},
{
"epoch": 38.0,
"eval_LOCATION_f1": 0.9175257731958764,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.89,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9179331306990882,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9320987654320988,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05196001008152962,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9396984924623115,
"eval_overall_precision": 0.9396984924623115,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2608,
"eval_samples_per_second": 651.895,
"eval_steps_per_second": 11.504,
"step": 3648
},
{
"epoch": 39.0,
"grad_norm": 0.33664995431900024,
"learning_rate": 3.05e-05,
"loss": 0.019,
"step": 3744
},
{
"epoch": 39.0,
"eval_LOCATION_f1": 0.9090909090909091,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8653846153846154,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9158878504672898,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9545454545454546,
"eval_ORGANIZATION_recall": 0.8802395209580839,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05798303335905075,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9393939393939393,
"eval_overall_precision": 0.9441624365482234,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2602,
"eval_samples_per_second": 653.372,
"eval_steps_per_second": 11.53,
"step": 3744
},
{
"epoch": 40.0,
"grad_norm": 0.9574192762374878,
"learning_rate": 3e-05,
"loss": 0.0182,
"step": 3840
},
{
"epoch": 40.0,
"eval_LOCATION_f1": 0.91,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8584905660377359,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9068322981366459,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9419354838709677,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.05943457782268524,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9308176100628931,
"eval_overall_precision": 0.9319899244332494,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2603,
"eval_samples_per_second": 653.007,
"eval_steps_per_second": 11.524,
"step": 3840
},
{
"epoch": 41.0,
"grad_norm": 0.8977973461151123,
"learning_rate": 2.95e-05,
"loss": 0.0175,
"step": 3936
},
{
"epoch": 41.0,
"eval_LOCATION_f1": 0.9285714285714286,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8921568627450981,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9212121212121211,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9325153374233128,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04987391456961632,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9461827284105131,
"eval_overall_precision": 0.942643391521197,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2607,
"eval_samples_per_second": 652.043,
"eval_steps_per_second": 11.507,
"step": 3936
},
{
"epoch": 42.0,
"grad_norm": 0.45573097467422485,
"learning_rate": 2.9e-05,
"loss": 0.017,
"step": 4032
},
{
"epoch": 42.0,
"eval_LOCATION_f1": 0.9175257731958764,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.89,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9118541033434651,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9259259259259259,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.05312899500131607,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9346733668341709,
"eval_overall_precision": 0.9346733668341709,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2608,
"eval_samples_per_second": 651.716,
"eval_steps_per_second": 11.501,
"step": 4032
},
{
"epoch": 43.0,
"grad_norm": 0.21106405556201935,
"learning_rate": 2.8499999999999998e-05,
"loss": 0.016,
"step": 4128
},
{
"epoch": 43.0,
"eval_LOCATION_f1": 0.9137055837563451,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8737864077669902,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9179331306990882,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9320987654320988,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05849442631006241,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9386733416770965,
"eval_overall_precision": 0.9351620947630923,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.2602,
"eval_samples_per_second": 653.361,
"eval_steps_per_second": 11.53,
"step": 4128
},
{
"epoch": 44.0,
"grad_norm": 0.3944805860519409,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.0176,
"step": 4224
},
{
"epoch": 44.0,
"eval_LOCATION_f1": 0.9090909090909091,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8653846153846154,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8984615384615384,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9240506329113924,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.06286009401082993,
"eval_overall_accuracy": 0.9856353591160221,
"eval_overall_f1": 0.9308176100628931,
"eval_overall_precision": 0.9319899244332494,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2619,
"eval_samples_per_second": 649.103,
"eval_steps_per_second": 11.455,
"step": 4224
},
{
"epoch": 45.0,
"grad_norm": 1.5326480865478516,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.0183,
"step": 4320
},
{
"epoch": 45.0,
"eval_LOCATION_f1": 0.9222797927461138,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.898989898989899,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9024390243902439,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9192546583850931,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9705882352941176,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9777777777777777,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.05268233269453049,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9306431273644388,
"eval_overall_precision": 0.9341772151898734,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.2615,
"eval_samples_per_second": 650.06,
"eval_steps_per_second": 11.472,
"step": 4320
},
{
"epoch": 46.0,
"grad_norm": 0.6381075382232666,
"learning_rate": 2.7000000000000002e-05,
"loss": 0.0154,
"step": 4416
},
{
"epoch": 46.0,
"eval_LOCATION_f1": 0.898989898989899,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8557692307692307,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9096573208722741,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.948051948051948,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9705882352941176,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9777777777777777,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.06112867221236229,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9279393173198482,
"eval_overall_precision": 0.9338422391857506,
"eval_overall_recall": 0.9221105527638191,
"eval_runtime": 0.2606,
"eval_samples_per_second": 652.36,
"eval_steps_per_second": 11.512,
"step": 4416
},
{
"epoch": 47.0,
"grad_norm": 0.29776057600975037,
"learning_rate": 2.6500000000000004e-05,
"loss": 0.0133,
"step": 4512
},
{
"epoch": 47.0,
"eval_LOCATION_f1": 0.9081632653061226,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8725490196078431,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8982035928143712,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8982035928143712,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.06605502218008041,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9301745635910225,
"eval_overall_precision": 0.9232673267326733,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2607,
"eval_samples_per_second": 652.15,
"eval_steps_per_second": 11.509,
"step": 4512
},
{
"epoch": 48.0,
"grad_norm": 0.4508885145187378,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.0153,
"step": 4608
},
{
"epoch": 48.0,
"eval_LOCATION_f1": 0.9035532994923857,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8640776699029126,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.892966360856269,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9125,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.06266425549983978,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9259723964868257,
"eval_overall_precision": 0.924812030075188,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.2607,
"eval_samples_per_second": 652.071,
"eval_steps_per_second": 11.507,
"step": 4608
},
{
"epoch": 49.0,
"grad_norm": 1.1082617044448853,
"learning_rate": 2.5500000000000003e-05,
"loss": 0.0152,
"step": 4704
},
{
"epoch": 49.0,
"eval_LOCATION_f1": 0.9035532994923857,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8640776699029126,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9046153846153847,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.930379746835443,
"eval_ORGANIZATION_recall": 0.8802395209580839,
"eval_PERSON_f1": 0.9779411764705882,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9851851851851852,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06184014678001404,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.929471032745592,
"eval_overall_precision": 0.9318181818181818,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.2609,
"eval_samples_per_second": 651.698,
"eval_steps_per_second": 11.501,
"step": 4704
},
{
"epoch": 50.0,
"grad_norm": 0.8354146480560303,
"learning_rate": 2.5e-05,
"loss": 0.0139,
"step": 4800
},
{
"epoch": 50.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9141104294478527,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9371069182389937,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.967032967032967,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9705882352941176,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.06013813987374306,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9345088161209069,
"eval_overall_precision": 0.9368686868686869,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2619,
"eval_samples_per_second": 649.019,
"eval_steps_per_second": 11.453,
"step": 4800
},
{
"epoch": 51.0,
"grad_norm": 0.19659610092639923,
"learning_rate": 2.45e-05,
"loss": 0.0127,
"step": 4896
},
{
"epoch": 51.0,
"eval_LOCATION_f1": 0.9128205128205128,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8811881188118812,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9024390243902439,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9192546583850931,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.060121648013591766,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9296482412060302,
"eval_overall_precision": 0.9296482412060302,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2619,
"eval_samples_per_second": 649.015,
"eval_steps_per_second": 11.453,
"step": 4896
},
{
"epoch": 52.0,
"grad_norm": 0.4250730872154236,
"learning_rate": 2.4e-05,
"loss": 0.0121,
"step": 4992
},
{
"epoch": 52.0,
"eval_LOCATION_f1": 0.9222797927461138,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.898989898989899,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9118541033434651,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9259259259259259,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06659343093633652,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9358490566037736,
"eval_overall_precision": 0.9370277078085643,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.261,
"eval_samples_per_second": 651.316,
"eval_steps_per_second": 11.494,
"step": 4992
},
{
"epoch": 53.0,
"grad_norm": 0.2273990660905838,
"learning_rate": 2.35e-05,
"loss": 0.0126,
"step": 5088
},
{
"epoch": 53.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9118541033434651,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9259259259259259,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05864882096648216,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9396984924623115,
"eval_overall_precision": 0.9396984924623115,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2595,
"eval_samples_per_second": 655.149,
"eval_steps_per_second": 11.561,
"step": 5088
},
{
"epoch": 54.0,
"grad_norm": 0.8456025123596191,
"learning_rate": 2.3000000000000003e-05,
"loss": 0.0124,
"step": 5184
},
{
"epoch": 54.0,
"eval_LOCATION_f1": 0.9411764705882354,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.946236559139785,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9281437125748502,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9281437125748503,
"eval_ORGANIZATION_recall": 0.9281437125748503,
"eval_PERSON_f1": 0.9708029197080292,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9708029197080292,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06092650443315506,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.9459119496855346,
"eval_overall_precision": 0.947103274559194,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2606,
"eval_samples_per_second": 652.429,
"eval_steps_per_second": 11.513,
"step": 5184
},
{
"epoch": 55.0,
"grad_norm": 1.4310436248779297,
"learning_rate": 2.25e-05,
"loss": 0.0131,
"step": 5280
},
{
"epoch": 55.0,
"eval_LOCATION_f1": 0.9270833333333334,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9081632653061225,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9146341463414633,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9316770186335404,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.06136379390954971,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9407313997477933,
"eval_overall_precision": 0.9443037974683545,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2627,
"eval_samples_per_second": 647.247,
"eval_steps_per_second": 11.422,
"step": 5280
},
{
"epoch": 56.0,
"grad_norm": 0.32882949709892273,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.013,
"step": 5376
},
{
"epoch": 56.0,
"eval_LOCATION_f1": 0.9326424870466321,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9212121212121211,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9325153374233128,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06318280845880508,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9422110552763819,
"eval_overall_precision": 0.9422110552763819,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.2609,
"eval_samples_per_second": 651.565,
"eval_steps_per_second": 11.498,
"step": 5376
},
{
"epoch": 57.0,
"grad_norm": 0.06369222700595856,
"learning_rate": 2.15e-05,
"loss": 0.0119,
"step": 5472
},
{
"epoch": 57.0,
"eval_LOCATION_f1": 0.9183673469387754,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8823529411764706,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9063444108761329,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9146341463414634,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06446920335292816,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9325,
"eval_overall_precision": 0.927860696517413,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.26,
"eval_samples_per_second": 653.78,
"eval_steps_per_second": 11.537,
"step": 5472
},
{
"epoch": 58.0,
"grad_norm": 0.19622349739074707,
"learning_rate": 2.1e-05,
"loss": 0.0121,
"step": 5568
},
{
"epoch": 58.0,
"eval_LOCATION_f1": 0.9081632653061226,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8725490196078431,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9051987767584098,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.925,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.06313645839691162,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9321608040201005,
"eval_overall_precision": 0.9321608040201005,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.261,
"eval_samples_per_second": 651.319,
"eval_steps_per_second": 11.494,
"step": 5568
},
{
"epoch": 59.0,
"grad_norm": 0.9658548831939697,
"learning_rate": 2.05e-05,
"loss": 0.0109,
"step": 5664
},
{
"epoch": 59.0,
"eval_LOCATION_f1": 0.9222797927461138,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.898989898989899,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9174311926605505,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9375,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06376946717500687,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9382093316519546,
"eval_overall_precision": 0.9417721518987342,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2601,
"eval_samples_per_second": 653.576,
"eval_steps_per_second": 11.534,
"step": 5664
},
{
"epoch": 60.0,
"grad_norm": 0.1680481880903244,
"learning_rate": 2e-05,
"loss": 0.0117,
"step": 5760
},
{
"epoch": 60.0,
"eval_LOCATION_f1": 0.9128205128205128,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8811881188118812,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9141104294478527,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9371069182389937,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9672727272727273,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9637681159420289,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06653210520744324,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9321608040201005,
"eval_overall_precision": 0.9321608040201005,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.262,
"eval_samples_per_second": 648.745,
"eval_steps_per_second": 11.448,
"step": 5760
},
{
"epoch": 61.0,
"grad_norm": 0.20809078216552734,
"learning_rate": 1.9500000000000003e-05,
"loss": 0.01,
"step": 5856
},
{
"epoch": 61.0,
"eval_LOCATION_f1": 0.9183673469387754,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8823529411764706,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9030303030303031,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9141104294478528,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9708029197080292,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9708029197080292,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06468936055898666,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.93,
"eval_overall_precision": 0.9253731343283582,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2634,
"eval_samples_per_second": 645.473,
"eval_steps_per_second": 11.391,
"step": 5856
},
{
"epoch": 62.0,
"grad_norm": 0.3894479274749756,
"learning_rate": 1.9e-05,
"loss": 0.0108,
"step": 5952
},
{
"epoch": 62.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9146341463414633,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9316770186335404,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06007487326860428,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9383647798742139,
"eval_overall_precision": 0.9395465994962217,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2616,
"eval_samples_per_second": 649.774,
"eval_steps_per_second": 11.467,
"step": 5952
},
{
"epoch": 63.0,
"grad_norm": 0.4755129814147949,
"learning_rate": 1.85e-05,
"loss": 0.0109,
"step": 6048
},
{
"epoch": 63.0,
"eval_LOCATION_f1": 0.9222797927461138,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.898989898989899,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9259259259259259,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9554140127388535,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.059221021831035614,
"eval_overall_accuracy": 0.988950276243094,
"eval_overall_f1": 0.9443037974683544,
"eval_overall_precision": 0.951530612244898,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2607,
"eval_samples_per_second": 652.215,
"eval_steps_per_second": 11.51,
"step": 6048
},
{
"epoch": 64.0,
"grad_norm": 0.05980967730283737,
"learning_rate": 1.8e-05,
"loss": 0.0101,
"step": 6144
},
{
"epoch": 64.0,
"eval_LOCATION_f1": 0.9081632653061226,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8725490196078431,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9156626506024097,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9212121212121213,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.060932304710149765,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9338327091136079,
"eval_overall_precision": 0.9280397022332506,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2617,
"eval_samples_per_second": 649.712,
"eval_steps_per_second": 11.466,
"step": 6144
},
{
"epoch": 65.0,
"grad_norm": 0.10981345921754837,
"learning_rate": 1.75e-05,
"loss": 0.0115,
"step": 6240
},
{
"epoch": 65.0,
"eval_LOCATION_f1": 0.9081632653061226,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8725490196078431,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9164086687306501,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9487179487179487,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06204293295741081,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9343434343434344,
"eval_overall_precision": 0.9390862944162437,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2625,
"eval_samples_per_second": 647.592,
"eval_steps_per_second": 11.428,
"step": 6240
},
{
"epoch": 66.0,
"grad_norm": 0.012435493990778923,
"learning_rate": 1.7000000000000003e-05,
"loss": 0.0093,
"step": 6336
},
{
"epoch": 66.0,
"eval_LOCATION_f1": 0.9175257731958764,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.89,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9096385542168675,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9151515151515152,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.061884891241788864,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9336670838548186,
"eval_overall_precision": 0.9301745635910225,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2615,
"eval_samples_per_second": 650.116,
"eval_steps_per_second": 11.473,
"step": 6336
},
{
"epoch": 67.0,
"grad_norm": 1.247888445854187,
"learning_rate": 1.65e-05,
"loss": 0.0105,
"step": 6432
},
{
"epoch": 67.0,
"eval_LOCATION_f1": 0.9222797927461138,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.898989898989899,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.920245398773006,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9433962264150944,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.05958583578467369,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9393939393939393,
"eval_overall_precision": 0.9441624365482234,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2616,
"eval_samples_per_second": 649.819,
"eval_steps_per_second": 11.467,
"step": 6432
},
{
"epoch": 68.0,
"grad_norm": 0.3255453407764435,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.0094,
"step": 6528
},
{
"epoch": 68.0,
"eval_LOCATION_f1": 0.9326424870466321,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9235474006116209,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.94375,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.060759324580430984,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.9457755359394704,
"eval_overall_precision": 0.9493670886075949,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.2616,
"eval_samples_per_second": 649.793,
"eval_steps_per_second": 11.467,
"step": 6528
},
{
"epoch": 69.0,
"grad_norm": 0.6159924864768982,
"learning_rate": 1.55e-05,
"loss": 0.0096,
"step": 6624
},
{
"epoch": 69.0,
"eval_LOCATION_f1": 0.9222797927461138,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.898989898989899,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9320987654320988,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9617834394904459,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9705882352941176,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9777777777777777,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.06378670781850815,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9429657794676807,
"eval_overall_precision": 0.9514066496163683,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2612,
"eval_samples_per_second": 650.728,
"eval_steps_per_second": 11.483,
"step": 6624
},
{
"epoch": 70.0,
"grad_norm": 0.006584213115274906,
"learning_rate": 1.5e-05,
"loss": 0.0089,
"step": 6720
},
{
"epoch": 70.0,
"eval_LOCATION_f1": 0.9222797927461138,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.898989898989899,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.934984520123839,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.967948717948718,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9705882352941176,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9777777777777777,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.06304128468036652,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.9441624365482234,
"eval_overall_precision": 0.9538461538461539,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2613,
"eval_samples_per_second": 650.475,
"eval_steps_per_second": 11.479,
"step": 6720
},
{
"epoch": 71.0,
"grad_norm": 0.11688349395990372,
"learning_rate": 1.45e-05,
"loss": 0.0097,
"step": 6816
},
{
"epoch": 71.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9151515151515152,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9263803680981595,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06276717782020569,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9385194479297366,
"eval_overall_precision": 0.9373433583959899,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2619,
"eval_samples_per_second": 649.085,
"eval_steps_per_second": 11.454,
"step": 6816
},
{
"epoch": 72.0,
"grad_norm": 0.11350841820240021,
"learning_rate": 1.4000000000000001e-05,
"loss": 0.0092,
"step": 6912
},
{
"epoch": 72.0,
"eval_LOCATION_f1": 0.9128205128205128,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8811881188118812,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.916923076923077,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9430379746835443,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06497593224048615,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.935687263556116,
"eval_overall_precision": 0.9392405063291139,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2617,
"eval_samples_per_second": 649.718,
"eval_steps_per_second": 11.466,
"step": 6912
},
{
"epoch": 73.0,
"grad_norm": 0.024633856490254402,
"learning_rate": 1.3500000000000001e-05,
"loss": 0.0089,
"step": 7008
},
{
"epoch": 73.0,
"eval_LOCATION_f1": 0.9222797927461138,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.898989898989899,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9179331306990882,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9320987654320988,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.967032967032967,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9705882352941176,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.06628074496984482,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9358490566037736,
"eval_overall_precision": 0.9370277078085643,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2612,
"eval_samples_per_second": 650.901,
"eval_steps_per_second": 11.486,
"step": 7008
},
{
"epoch": 74.0,
"grad_norm": 0.5928414463996887,
"learning_rate": 1.3000000000000001e-05,
"loss": 0.0088,
"step": 7104
},
{
"epoch": 74.0,
"eval_LOCATION_f1": 0.9175257731958764,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.89,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9118541033434651,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9259259259259259,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.967032967032967,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9705882352941176,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.06625661998987198,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9321608040201005,
"eval_overall_precision": 0.9321608040201005,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2604,
"eval_samples_per_second": 652.819,
"eval_steps_per_second": 11.52,
"step": 7104
},
{
"epoch": 75.0,
"grad_norm": 0.0615532249212265,
"learning_rate": 1.25e-05,
"loss": 0.0076,
"step": 7200
},
{
"epoch": 75.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.920245398773006,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9433962264150944,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06464764475822449,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9407313997477933,
"eval_overall_precision": 0.9443037974683545,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.261,
"eval_samples_per_second": 651.288,
"eval_steps_per_second": 11.493,
"step": 7200
},
{
"epoch": 76.0,
"grad_norm": 0.1333237737417221,
"learning_rate": 1.2e-05,
"loss": 0.0084,
"step": 7296
},
{
"epoch": 76.0,
"eval_LOCATION_f1": 0.9175257731958764,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.89,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9207317073170732,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.937888198757764,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06337085366249084,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9383647798742139,
"eval_overall_precision": 0.9395465994962217,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2608,
"eval_samples_per_second": 651.747,
"eval_steps_per_second": 11.501,
"step": 7296
},
{
"epoch": 77.0,
"grad_norm": 0.46974897384643555,
"learning_rate": 1.1500000000000002e-05,
"loss": 0.0079,
"step": 7392
},
{
"epoch": 77.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9118541033434651,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9259259259259259,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.967032967032967,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9705882352941176,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.06465104967355728,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9346733668341709,
"eval_overall_precision": 0.9346733668341709,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2616,
"eval_samples_per_second": 649.782,
"eval_steps_per_second": 11.467,
"step": 7392
},
{
"epoch": 78.0,
"grad_norm": 0.6800858378410339,
"learning_rate": 1.1000000000000001e-05,
"loss": 0.0078,
"step": 7488
},
{
"epoch": 78.0,
"eval_LOCATION_f1": 0.9270833333333334,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9081632653061225,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9212121212121211,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9325153374233128,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.967032967032967,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9705882352941176,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.06692018359899521,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9383647798742139,
"eval_overall_precision": 0.9395465994962217,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2612,
"eval_samples_per_second": 650.756,
"eval_steps_per_second": 11.484,
"step": 7488
},
{
"epoch": 79.0,
"grad_norm": 0.10270219296216965,
"learning_rate": 1.05e-05,
"loss": 0.0082,
"step": 7584
},
{
"epoch": 79.0,
"eval_LOCATION_f1": 0.9128205128205128,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8811881188118812,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9113149847094801,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.93125,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.967032967032967,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9705882352941176,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.06794097274541855,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9308176100628931,
"eval_overall_precision": 0.9319899244332494,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2619,
"eval_samples_per_second": 649.002,
"eval_steps_per_second": 11.453,
"step": 7584
},
{
"epoch": 80.0,
"grad_norm": 0.17227163910865784,
"learning_rate": 1e-05,
"loss": 0.0075,
"step": 7680
},
{
"epoch": 80.0,
"eval_LOCATION_f1": 0.9326424870466321,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9096385542168675,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9151515151515152,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06505602598190308,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.93734335839599,
"eval_overall_precision": 0.935,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2616,
"eval_samples_per_second": 649.79,
"eval_steps_per_second": 11.467,
"step": 7680
},
{
"epoch": 81.0,
"grad_norm": 0.7876644134521484,
"learning_rate": 9.5e-06,
"loss": 0.0086,
"step": 7776
},
{
"epoch": 81.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9090909090909091,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9202453987730062,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06498304009437561,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9360100376411543,
"eval_overall_precision": 0.9348370927318296,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2605,
"eval_samples_per_second": 652.635,
"eval_steps_per_second": 11.517,
"step": 7776
},
{
"epoch": 82.0,
"grad_norm": 0.013782556168735027,
"learning_rate": 9e-06,
"loss": 0.0064,
"step": 7872
},
{
"epoch": 82.0,
"eval_LOCATION_f1": 0.9326424870466321,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9179331306990882,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9320987654320988,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06517800688743591,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9408805031446541,
"eval_overall_precision": 0.9420654911838791,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2606,
"eval_samples_per_second": 652.34,
"eval_steps_per_second": 11.512,
"step": 7872
},
{
"epoch": 83.0,
"grad_norm": 0.02583060786128044,
"learning_rate": 8.500000000000002e-06,
"loss": 0.006,
"step": 7968
},
{
"epoch": 83.0,
"eval_LOCATION_f1": 0.9326424870466321,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9151515151515152,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9263803680981595,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06762006878852844,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9396984924623115,
"eval_overall_precision": 0.9396984924623115,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2608,
"eval_samples_per_second": 651.854,
"eval_steps_per_second": 11.503,
"step": 7968
},
{
"epoch": 84.0,
"grad_norm": 0.03260604664683342,
"learning_rate": 8.000000000000001e-06,
"loss": 0.0079,
"step": 8064
},
{
"epoch": 84.0,
"eval_LOCATION_f1": 0.9326424870466321,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.918429003021148,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.926829268292683,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.967032967032967,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9705882352941176,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.06765930354595184,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9385194479297366,
"eval_overall_precision": 0.9373433583959899,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2614,
"eval_samples_per_second": 650.265,
"eval_steps_per_second": 11.475,
"step": 8064
},
{
"epoch": 85.0,
"grad_norm": 0.07081805914640427,
"learning_rate": 7.5e-06,
"loss": 0.0074,
"step": 8160
},
{
"epoch": 85.0,
"eval_LOCATION_f1": 0.9270833333333334,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9081632653061225,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9179331306990882,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9320987654320988,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9705882352941176,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9777777777777777,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.0699184387922287,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9382093316519546,
"eval_overall_precision": 0.9417721518987342,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2612,
"eval_samples_per_second": 650.911,
"eval_steps_per_second": 11.487,
"step": 8160
},
{
"epoch": 86.0,
"grad_norm": 1.070292353630066,
"learning_rate": 7.000000000000001e-06,
"loss": 0.0084,
"step": 8256
},
{
"epoch": 86.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9090909090909091,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9202453987730062,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06956853717565536,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9360100376411543,
"eval_overall_precision": 0.9348370927318296,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2606,
"eval_samples_per_second": 652.227,
"eval_steps_per_second": 11.51,
"step": 8256
},
{
"epoch": 87.0,
"grad_norm": 0.3695351481437683,
"learning_rate": 6.5000000000000004e-06,
"loss": 0.007,
"step": 8352
},
{
"epoch": 87.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9118541033434651,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9259259259259259,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06800873577594757,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9371859296482412,
"eval_overall_precision": 0.9371859296482412,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2626,
"eval_samples_per_second": 647.383,
"eval_steps_per_second": 11.424,
"step": 8352
},
{
"epoch": 88.0,
"grad_norm": 0.27165156602859497,
"learning_rate": 6e-06,
"loss": 0.0069,
"step": 8448
},
{
"epoch": 88.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.916923076923077,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9430379746835443,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06649405509233475,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9382093316519546,
"eval_overall_precision": 0.9417721518987342,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2592,
"eval_samples_per_second": 655.794,
"eval_steps_per_second": 11.573,
"step": 8448
},
{
"epoch": 89.0,
"grad_norm": 1.3479974269866943,
"learning_rate": 5.500000000000001e-06,
"loss": 0.0066,
"step": 8544
},
{
"epoch": 89.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9051987767584098,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.925,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.0673149898648262,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9358490566037736,
"eval_overall_precision": 0.9370277078085643,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2611,
"eval_samples_per_second": 650.979,
"eval_steps_per_second": 11.488,
"step": 8544
},
{
"epoch": 90.0,
"grad_norm": 0.015431804582476616,
"learning_rate": 5e-06,
"loss": 0.0072,
"step": 8640
},
{
"epoch": 90.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9164086687306501,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9487179487179487,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06866373121738434,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9380530973451328,
"eval_overall_precision": 0.9440203562340967,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2608,
"eval_samples_per_second": 651.841,
"eval_steps_per_second": 11.503,
"step": 8640
},
{
"epoch": 91.0,
"grad_norm": 0.18616460263729095,
"learning_rate": 4.5e-06,
"loss": 0.0067,
"step": 8736
},
{
"epoch": 91.0,
"eval_LOCATION_f1": 0.9183673469387754,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8823529411764706,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9085365853658537,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9254658385093167,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.967032967032967,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9705882352941176,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.06930830329656601,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9309912170639899,
"eval_overall_precision": 0.9298245614035088,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2607,
"eval_samples_per_second": 652.022,
"eval_steps_per_second": 11.506,
"step": 8736
},
{
"epoch": 92.0,
"grad_norm": 0.43256962299346924,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0064,
"step": 8832
},
{
"epoch": 92.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9179331306990882,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9320987654320988,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.967032967032967,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9705882352941176,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.0697290375828743,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9371859296482412,
"eval_overall_precision": 0.9371859296482412,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2616,
"eval_samples_per_second": 649.855,
"eval_steps_per_second": 11.468,
"step": 8832
},
{
"epoch": 93.0,
"grad_norm": 0.04950817674398422,
"learning_rate": 3.5000000000000004e-06,
"loss": 0.007,
"step": 8928
},
{
"epoch": 93.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9235474006116209,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.94375,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06825991719961166,
"eval_overall_accuracy": 0.988950276243094,
"eval_overall_f1": 0.9420654911838791,
"eval_overall_precision": 0.9444444444444444,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2613,
"eval_samples_per_second": 650.64,
"eval_steps_per_second": 11.482,
"step": 8928
},
{
"epoch": 94.0,
"grad_norm": 0.07757169753313065,
"learning_rate": 3e-06,
"loss": 0.0061,
"step": 9024
},
{
"epoch": 94.0,
"eval_LOCATION_f1": 0.9326424870466321,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9212121212121211,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9325153374233128,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.967032967032967,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9705882352941176,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.06755328923463821,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9396984924623115,
"eval_overall_precision": 0.9396984924623115,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2607,
"eval_samples_per_second": 652.053,
"eval_steps_per_second": 11.507,
"step": 9024
},
{
"epoch": 95.0,
"grad_norm": 0.27466660737991333,
"learning_rate": 2.5e-06,
"loss": 0.0066,
"step": 9120
},
{
"epoch": 95.0,
"eval_LOCATION_f1": 0.9183673469387754,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8823529411764706,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.916923076923077,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9430379746835443,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.967032967032967,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9705882352941176,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.07005652040243149,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9345088161209069,
"eval_overall_precision": 0.9368686868686869,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2613,
"eval_samples_per_second": 650.673,
"eval_steps_per_second": 11.482,
"step": 9120
},
{
"epoch": 96.0,
"grad_norm": 0.03098815307021141,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.0052,
"step": 9216
},
{
"epoch": 96.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9207317073170732,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.937888198757764,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.967032967032967,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9705882352941176,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.06894105672836304,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9383647798742139,
"eval_overall_precision": 0.9395465994962217,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2609,
"eval_samples_per_second": 651.656,
"eval_steps_per_second": 11.5,
"step": 9216
},
{
"epoch": 97.0,
"grad_norm": 0.7062220573425293,
"learning_rate": 1.5e-06,
"loss": 0.0052,
"step": 9312
},
{
"epoch": 97.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.920245398773006,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9433962264150944,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.967032967032967,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9705882352941176,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.0702434778213501,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9370277078085643,
"eval_overall_precision": 0.9393939393939394,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2611,
"eval_samples_per_second": 651.113,
"eval_steps_per_second": 11.49,
"step": 9312
},
{
"epoch": 98.0,
"grad_norm": 0.03454367071390152,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.0073,
"step": 9408
},
{
"epoch": 98.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9207317073170732,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.937888198757764,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.967032967032967,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9705882352941176,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.06922313570976257,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9383647798742139,
"eval_overall_precision": 0.9395465994962217,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2611,
"eval_samples_per_second": 650.973,
"eval_steps_per_second": 11.488,
"step": 9408
},
{
"epoch": 99.0,
"grad_norm": 0.059272103011608124,
"learning_rate": 5.000000000000001e-07,
"loss": 0.0052,
"step": 9504
},
{
"epoch": 99.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9207317073170732,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.937888198757764,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.967032967032967,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9705882352941176,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.06897852569818497,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9383647798742139,
"eval_overall_precision": 0.9395465994962217,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2608,
"eval_samples_per_second": 651.888,
"eval_steps_per_second": 11.504,
"step": 9504
},
{
"epoch": 100.0,
"grad_norm": 0.04698795825242996,
"learning_rate": 0.0,
"loss": 0.0063,
"step": 9600
},
{
"epoch": 100.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9207317073170732,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.937888198757764,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.967032967032967,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9705882352941176,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.06901910156011581,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9383647798742139,
"eval_overall_precision": 0.9395465994962217,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2611,
"eval_samples_per_second": 651.172,
"eval_steps_per_second": 11.491,
"step": 9600
},
{
"epoch": 100.0,
"step": 9600,
"total_flos": 4297274884593540.0,
"train_loss": 0.03668565873677532,
"train_runtime": 533.0622,
"train_samples_per_second": 287.021,
"train_steps_per_second": 18.009
}
],
"logging_steps": 500,
"max_steps": 9600,
"num_input_tokens_seen": 0,
"num_train_epochs": 100,
"save_steps": 500,
"total_flos": 4297274884593540.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}