FT_3 / checkpoint-1500 /trainer_state.json
sheepy928's picture
Training in progress, step 1500, checkpoint
2bdf59d
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 7.9787234042553195,
"eval_steps": 20,
"global_step": 1500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05,
"learning_rate": 0.0004995563442768412,
"loss": 1.3139,
"step": 10
},
{
"epoch": 0.11,
"learning_rate": 0.0004986690328305235,
"loss": 1.2812,
"step": 20
},
{
"epoch": 0.11,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.8499402403831482,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 125.9807,
"eval_samples_per_second": 11.907,
"eval_steps_per_second": 0.373,
"step": 20
},
{
"epoch": 0.16,
"learning_rate": 0.0004977817213842058,
"loss": 0.832,
"step": 30
},
{
"epoch": 0.21,
"learning_rate": 0.0004968944099378882,
"loss": 0.8156,
"step": 40
},
{
"epoch": 0.21,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.8848057985305786,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 46.3365,
"eval_samples_per_second": 32.372,
"eval_steps_per_second": 1.014,
"step": 40
},
{
"epoch": 0.27,
"learning_rate": 0.0004960070984915705,
"loss": 0.7475,
"step": 50
},
{
"epoch": 0.32,
"learning_rate": 0.0004951197870452529,
"loss": 0.7478,
"step": 60
},
{
"epoch": 0.32,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7691774964332581,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0551,
"eval_samples_per_second": 247.726,
"eval_steps_per_second": 7.762,
"step": 60
},
{
"epoch": 0.37,
"learning_rate": 0.0004942324755989353,
"loss": 0.7663,
"step": 70
},
{
"epoch": 0.43,
"learning_rate": 0.0004933451641526176,
"loss": 0.6034,
"step": 80
},
{
"epoch": 0.43,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7553095817565918,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.025,
"eval_samples_per_second": 248.962,
"eval_steps_per_second": 7.801,
"step": 80
},
{
"epoch": 0.48,
"learning_rate": 0.0004924578527063,
"loss": 0.9511,
"step": 90
},
{
"epoch": 0.53,
"learning_rate": 0.0004915705412599822,
"loss": 0.7548,
"step": 100
},
{
"epoch": 0.53,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7768574357032776,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 5.9796,
"eval_samples_per_second": 250.851,
"eval_steps_per_second": 7.86,
"step": 100
},
{
"epoch": 0.59,
"learning_rate": 0.0004906832298136646,
"loss": 0.858,
"step": 110
},
{
"epoch": 0.64,
"learning_rate": 0.0004897959183673469,
"loss": 0.8452,
"step": 120
},
{
"epoch": 0.64,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.745326817035675,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.1179,
"eval_samples_per_second": 245.183,
"eval_steps_per_second": 7.682,
"step": 120
},
{
"epoch": 0.69,
"learning_rate": 0.0004889086069210293,
"loss": 0.8152,
"step": 130
},
{
"epoch": 0.74,
"learning_rate": 0.00048802129547471164,
"loss": 0.8972,
"step": 140
},
{
"epoch": 0.74,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7610827088356018,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0456,
"eval_samples_per_second": 248.113,
"eval_steps_per_second": 7.774,
"step": 140
},
{
"epoch": 0.8,
"learning_rate": 0.000487133984028394,
"loss": 0.7226,
"step": 150
},
{
"epoch": 0.85,
"learning_rate": 0.0004862466725820763,
"loss": 0.9377,
"step": 160
},
{
"epoch": 0.85,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7714303135871887,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 5.9995,
"eval_samples_per_second": 250.022,
"eval_steps_per_second": 7.834,
"step": 160
},
{
"epoch": 0.9,
"learning_rate": 0.0004853593611357587,
"loss": 0.594,
"step": 170
},
{
"epoch": 0.96,
"learning_rate": 0.00048447204968944104,
"loss": 1.0968,
"step": 180
},
{
"epoch": 0.96,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.9954016804695129,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 5.9871,
"eval_samples_per_second": 250.537,
"eval_steps_per_second": 7.85,
"step": 180
},
{
"epoch": 1.01,
"learning_rate": 0.00048358473824312333,
"loss": 0.9644,
"step": 190
},
{
"epoch": 1.06,
"learning_rate": 0.00048269742679680566,
"loss": 0.7502,
"step": 200
},
{
"epoch": 1.06,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7544593214988708,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0077,
"eval_samples_per_second": 249.679,
"eval_steps_per_second": 7.823,
"step": 200
},
{
"epoch": 1.12,
"learning_rate": 0.000481810115350488,
"loss": 0.7231,
"step": 210
},
{
"epoch": 1.17,
"learning_rate": 0.0004809228039041704,
"loss": 0.7902,
"step": 220
},
{
"epoch": 1.17,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7758567929267883,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0531,
"eval_samples_per_second": 247.806,
"eval_steps_per_second": 7.765,
"step": 220
},
{
"epoch": 1.22,
"learning_rate": 0.00048003549245785273,
"loss": 0.7591,
"step": 230
},
{
"epoch": 1.28,
"learning_rate": 0.00047914818101153507,
"loss": 0.817,
"step": 240
},
{
"epoch": 1.28,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.767899751663208,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.1711,
"eval_samples_per_second": 243.067,
"eval_steps_per_second": 7.616,
"step": 240
},
{
"epoch": 1.33,
"learning_rate": 0.0004782608695652174,
"loss": 0.6681,
"step": 250
},
{
"epoch": 1.38,
"learning_rate": 0.00047737355811889974,
"loss": 0.9199,
"step": 260
},
{
"epoch": 1.38,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7462519407272339,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0331,
"eval_samples_per_second": 248.63,
"eval_steps_per_second": 7.79,
"step": 260
},
{
"epoch": 1.44,
"learning_rate": 0.00047648624667258213,
"loss": 0.7409,
"step": 270
},
{
"epoch": 1.49,
"learning_rate": 0.0004755989352262644,
"loss": 0.7246,
"step": 280
},
{
"epoch": 1.49,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7581822872161865,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.1558,
"eval_samples_per_second": 243.673,
"eval_steps_per_second": 7.635,
"step": 280
},
{
"epoch": 1.54,
"learning_rate": 0.00047471162377994675,
"loss": 0.6876,
"step": 290
},
{
"epoch": 1.6,
"learning_rate": 0.0004738243123336291,
"loss": 0.7508,
"step": 300
},
{
"epoch": 1.6,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7464602589607239,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.1548,
"eval_samples_per_second": 243.711,
"eval_steps_per_second": 7.636,
"step": 300
},
{
"epoch": 1.65,
"learning_rate": 0.0004729370008873114,
"loss": 0.8539,
"step": 310
},
{
"epoch": 1.7,
"learning_rate": 0.0004720496894409938,
"loss": 0.7011,
"step": 320
},
{
"epoch": 1.7,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.788334310054779,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.1655,
"eval_samples_per_second": 243.289,
"eval_steps_per_second": 7.623,
"step": 320
},
{
"epoch": 1.76,
"learning_rate": 0.00047116237799467615,
"loss": 0.9111,
"step": 330
},
{
"epoch": 1.81,
"learning_rate": 0.0004702750665483585,
"loss": 0.8442,
"step": 340
},
{
"epoch": 1.81,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7656621336936951,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.2177,
"eval_samples_per_second": 241.249,
"eval_steps_per_second": 7.559,
"step": 340
},
{
"epoch": 1.86,
"learning_rate": 0.00046938775510204083,
"loss": 0.7179,
"step": 350
},
{
"epoch": 1.91,
"learning_rate": 0.00046850044365572317,
"loss": 1.0021,
"step": 360
},
{
"epoch": 1.91,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7755117416381836,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0871,
"eval_samples_per_second": 246.422,
"eval_steps_per_second": 7.721,
"step": 360
},
{
"epoch": 1.97,
"learning_rate": 0.0004676131322094055,
"loss": 0.8331,
"step": 370
},
{
"epoch": 2.02,
"learning_rate": 0.00046672582076308784,
"loss": 0.7982,
"step": 380
},
{
"epoch": 2.02,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.8436231017112732,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0719,
"eval_samples_per_second": 247.04,
"eval_steps_per_second": 7.741,
"step": 380
},
{
"epoch": 2.07,
"learning_rate": 0.0004658385093167702,
"loss": 0.8408,
"step": 390
},
{
"epoch": 2.13,
"learning_rate": 0.0004649511978704525,
"loss": 0.8299,
"step": 400
},
{
"epoch": 2.13,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7582988142967224,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.2274,
"eval_samples_per_second": 240.873,
"eval_steps_per_second": 7.547,
"step": 400
},
{
"epoch": 2.18,
"learning_rate": 0.0004640638864241349,
"loss": 0.7852,
"step": 410
},
{
"epoch": 2.23,
"learning_rate": 0.00046317657497781724,
"loss": 0.8789,
"step": 420
},
{
"epoch": 2.23,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7546933889389038,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.3059,
"eval_samples_per_second": 237.872,
"eval_steps_per_second": 7.453,
"step": 420
},
{
"epoch": 2.29,
"learning_rate": 0.0004622892635314996,
"loss": 0.6384,
"step": 430
},
{
"epoch": 2.34,
"learning_rate": 0.0004614019520851819,
"loss": 0.8853,
"step": 440
},
{
"epoch": 2.34,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7661357522010803,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.3477,
"eval_samples_per_second": 236.306,
"eval_steps_per_second": 7.404,
"step": 440
},
{
"epoch": 2.39,
"learning_rate": 0.0004605146406388642,
"loss": 0.7721,
"step": 450
},
{
"epoch": 2.45,
"learning_rate": 0.0004596273291925466,
"loss": 0.7522,
"step": 460
},
{
"epoch": 2.45,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7484121322631836,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.2677,
"eval_samples_per_second": 239.321,
"eval_steps_per_second": 7.499,
"step": 460
},
{
"epoch": 2.5,
"learning_rate": 0.0004587400177462289,
"loss": 0.8076,
"step": 470
},
{
"epoch": 2.55,
"learning_rate": 0.00045785270629991126,
"loss": 0.9035,
"step": 480
},
{
"epoch": 2.55,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7667799592018127,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.4501,
"eval_samples_per_second": 232.554,
"eval_steps_per_second": 7.287,
"step": 480
},
{
"epoch": 2.61,
"learning_rate": 0.0004569653948535936,
"loss": 0.7544,
"step": 490
},
{
"epoch": 2.66,
"learning_rate": 0.000456078083407276,
"loss": 0.8717,
"step": 500
},
{
"epoch": 2.66,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7541614770889282,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.4865,
"eval_samples_per_second": 231.251,
"eval_steps_per_second": 7.246,
"step": 500
},
{
"epoch": 2.71,
"learning_rate": 0.00045519077196095833,
"loss": 0.6823,
"step": 510
},
{
"epoch": 2.77,
"learning_rate": 0.00045430346051464067,
"loss": 0.8903,
"step": 520
},
{
"epoch": 2.77,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.801760733127594,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.3567,
"eval_samples_per_second": 235.972,
"eval_steps_per_second": 7.394,
"step": 520
},
{
"epoch": 2.82,
"learning_rate": 0.000453416149068323,
"loss": 0.7565,
"step": 530
},
{
"epoch": 2.87,
"learning_rate": 0.0004525288376220053,
"loss": 0.7392,
"step": 540
},
{
"epoch": 2.87,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7826161980628967,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.5294,
"eval_samples_per_second": 229.731,
"eval_steps_per_second": 7.198,
"step": 540
},
{
"epoch": 2.93,
"learning_rate": 0.0004516415261756877,
"loss": 0.629,
"step": 550
},
{
"epoch": 2.98,
"learning_rate": 0.00045075421472937,
"loss": 0.8626,
"step": 560
},
{
"epoch": 2.98,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7489452958106995,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.3521,
"eval_samples_per_second": 236.143,
"eval_steps_per_second": 7.399,
"step": 560
},
{
"epoch": 3.03,
"learning_rate": 0.00044986690328305235,
"loss": 0.7379,
"step": 570
},
{
"epoch": 3.09,
"learning_rate": 0.0004489795918367347,
"loss": 0.6063,
"step": 580
},
{
"epoch": 3.09,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.9793464541435242,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.3272,
"eval_samples_per_second": 237.071,
"eval_steps_per_second": 7.428,
"step": 580
},
{
"epoch": 3.14,
"learning_rate": 0.000448092280390417,
"loss": 0.9408,
"step": 590
},
{
"epoch": 3.19,
"learning_rate": 0.0004472049689440994,
"loss": 0.8703,
"step": 600
},
{
"epoch": 3.19,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7475989460945129,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.3253,
"eval_samples_per_second": 237.143,
"eval_steps_per_second": 7.43,
"step": 600
},
{
"epoch": 3.24,
"learning_rate": 0.00044631765749778175,
"loss": 0.8594,
"step": 610
},
{
"epoch": 3.3,
"learning_rate": 0.0004454303460514641,
"loss": 0.797,
"step": 620
},
{
"epoch": 3.3,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7692281603813171,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.6464,
"eval_samples_per_second": 225.686,
"eval_steps_per_second": 7.071,
"step": 620
},
{
"epoch": 3.35,
"learning_rate": 0.0004445430346051464,
"loss": 0.8531,
"step": 630
},
{
"epoch": 3.4,
"learning_rate": 0.00044365572315882877,
"loss": 0.7526,
"step": 640
},
{
"epoch": 3.4,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7548736929893494,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.5723,
"eval_samples_per_second": 228.23,
"eval_steps_per_second": 7.151,
"step": 640
},
{
"epoch": 3.46,
"learning_rate": 0.0004427684117125111,
"loss": 0.8442,
"step": 650
},
{
"epoch": 3.51,
"learning_rate": 0.00044188110026619344,
"loss": 0.9005,
"step": 660
},
{
"epoch": 3.51,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.8103847503662109,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.4776,
"eval_samples_per_second": 231.566,
"eval_steps_per_second": 7.256,
"step": 660
},
{
"epoch": 3.56,
"learning_rate": 0.0004409937888198758,
"loss": 0.8343,
"step": 670
},
{
"epoch": 3.62,
"learning_rate": 0.0004401064773735581,
"loss": 0.7993,
"step": 680
},
{
"epoch": 3.62,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.8053144812583923,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.3285,
"eval_samples_per_second": 237.021,
"eval_steps_per_second": 7.427,
"step": 680
},
{
"epoch": 3.67,
"learning_rate": 0.0004392191659272405,
"loss": 0.8369,
"step": 690
},
{
"epoch": 3.72,
"learning_rate": 0.00043833185448092284,
"loss": 0.7966,
"step": 700
},
{
"epoch": 3.72,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7448229193687439,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.3865,
"eval_samples_per_second": 234.871,
"eval_steps_per_second": 7.359,
"step": 700
},
{
"epoch": 3.78,
"learning_rate": 0.0004374445430346052,
"loss": 0.7612,
"step": 710
},
{
"epoch": 3.83,
"learning_rate": 0.00043655723158828746,
"loss": 0.7656,
"step": 720
},
{
"epoch": 3.83,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7586243748664856,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.3473,
"eval_samples_per_second": 236.32,
"eval_steps_per_second": 7.405,
"step": 720
},
{
"epoch": 3.88,
"learning_rate": 0.0004356699201419698,
"loss": 0.6469,
"step": 730
},
{
"epoch": 3.94,
"learning_rate": 0.0004347826086956522,
"loss": 0.6889,
"step": 740
},
{
"epoch": 3.94,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7640272378921509,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.3581,
"eval_samples_per_second": 235.92,
"eval_steps_per_second": 7.392,
"step": 740
},
{
"epoch": 3.99,
"learning_rate": 0.0004338952972493345,
"loss": 0.7086,
"step": 750
},
{
"epoch": 4.04,
"learning_rate": 0.00043300798580301686,
"loss": 0.8226,
"step": 760
},
{
"epoch": 4.04,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.8118994235992432,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.3396,
"eval_samples_per_second": 236.61,
"eval_steps_per_second": 7.414,
"step": 760
},
{
"epoch": 4.1,
"learning_rate": 0.0004321206743566992,
"loss": 1.0159,
"step": 770
},
{
"epoch": 4.15,
"learning_rate": 0.0004312333629103816,
"loss": 0.8907,
"step": 780
},
{
"epoch": 4.15,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7906585335731506,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.4149,
"eval_samples_per_second": 233.829,
"eval_steps_per_second": 7.327,
"step": 780
},
{
"epoch": 4.2,
"learning_rate": 0.00043034605146406393,
"loss": 0.6486,
"step": 790
},
{
"epoch": 4.26,
"learning_rate": 0.00042945874001774627,
"loss": 0.8749,
"step": 800
},
{
"epoch": 4.26,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7677525877952576,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.3008,
"eval_samples_per_second": 238.066,
"eval_steps_per_second": 7.459,
"step": 800
},
{
"epoch": 4.31,
"learning_rate": 0.00042857142857142855,
"loss": 0.6891,
"step": 810
},
{
"epoch": 4.36,
"learning_rate": 0.0004276841171251109,
"loss": 0.749,
"step": 820
},
{
"epoch": 4.36,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7736731767654419,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.384,
"eval_samples_per_second": 234.964,
"eval_steps_per_second": 7.362,
"step": 820
},
{
"epoch": 4.41,
"learning_rate": 0.0004267968056787933,
"loss": 0.7781,
"step": 830
},
{
"epoch": 4.47,
"learning_rate": 0.0004259094942324756,
"loss": 0.7333,
"step": 840
},
{
"epoch": 4.47,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.8354427218437195,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.1708,
"eval_samples_per_second": 243.081,
"eval_steps_per_second": 7.617,
"step": 840
},
{
"epoch": 4.52,
"learning_rate": 0.00042502218278615795,
"loss": 1.1763,
"step": 850
},
{
"epoch": 4.57,
"learning_rate": 0.0004241348713398403,
"loss": 0.9287,
"step": 860
},
{
"epoch": 4.57,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7903938889503479,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.1862,
"eval_samples_per_second": 242.475,
"eval_steps_per_second": 7.598,
"step": 860
},
{
"epoch": 4.63,
"learning_rate": 0.0004232475598935226,
"loss": 0.7707,
"step": 870
},
{
"epoch": 4.68,
"learning_rate": 0.000422360248447205,
"loss": 0.8231,
"step": 880
},
{
"epoch": 4.68,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7689003944396973,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0616,
"eval_samples_per_second": 247.459,
"eval_steps_per_second": 7.754,
"step": 880
},
{
"epoch": 4.73,
"learning_rate": 0.00042147293700088735,
"loss": 0.723,
"step": 890
},
{
"epoch": 4.79,
"learning_rate": 0.00042058562555456964,
"loss": 0.7486,
"step": 900
},
{
"epoch": 4.79,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7458215951919556,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0863,
"eval_samples_per_second": 246.454,
"eval_steps_per_second": 7.722,
"step": 900
},
{
"epoch": 4.84,
"learning_rate": 0.000419698314108252,
"loss": 0.6488,
"step": 910
},
{
"epoch": 4.89,
"learning_rate": 0.0004188110026619343,
"loss": 0.8551,
"step": 920
},
{
"epoch": 4.89,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7851412892341614,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 5.9684,
"eval_samples_per_second": 251.326,
"eval_steps_per_second": 7.875,
"step": 920
},
{
"epoch": 4.95,
"learning_rate": 0.0004179236912156167,
"loss": 0.7437,
"step": 930
},
{
"epoch": 5.0,
"learning_rate": 0.00041703637976929904,
"loss": 0.7452,
"step": 940
},
{
"epoch": 5.0,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7961435317993164,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0838,
"eval_samples_per_second": 246.558,
"eval_steps_per_second": 7.725,
"step": 940
},
{
"epoch": 5.05,
"learning_rate": 0.0004161490683229814,
"loss": 0.8069,
"step": 950
},
{
"epoch": 5.11,
"learning_rate": 0.0004152617568766637,
"loss": 0.7453,
"step": 960
},
{
"epoch": 5.11,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7462239861488342,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.1042,
"eval_samples_per_second": 245.731,
"eval_steps_per_second": 7.7,
"step": 960
},
{
"epoch": 5.16,
"learning_rate": 0.0004143744454303461,
"loss": 0.5743,
"step": 970
},
{
"epoch": 5.21,
"learning_rate": 0.00041348713398402844,
"loss": 0.7784,
"step": 980
},
{
"epoch": 5.21,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7713678479194641,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0898,
"eval_samples_per_second": 246.314,
"eval_steps_per_second": 7.718,
"step": 980
},
{
"epoch": 5.27,
"learning_rate": 0.0004125998225377107,
"loss": 0.7916,
"step": 990
},
{
"epoch": 5.32,
"learning_rate": 0.00041171251109139306,
"loss": 0.7943,
"step": 1000
},
{
"epoch": 5.32,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7590846419334412,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0172,
"eval_samples_per_second": 249.284,
"eval_steps_per_second": 7.811,
"step": 1000
},
{
"epoch": 5.37,
"learning_rate": 0.0004108251996450754,
"loss": 0.7477,
"step": 1010
},
{
"epoch": 5.43,
"learning_rate": 0.0004099378881987578,
"loss": 0.8187,
"step": 1020
},
{
"epoch": 5.43,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7467174530029297,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0527,
"eval_samples_per_second": 247.824,
"eval_steps_per_second": 7.765,
"step": 1020
},
{
"epoch": 5.48,
"learning_rate": 0.0004090505767524401,
"loss": 0.724,
"step": 1030
},
{
"epoch": 5.53,
"learning_rate": 0.00040816326530612246,
"loss": 0.82,
"step": 1040
},
{
"epoch": 5.53,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7653962969779968,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0631,
"eval_samples_per_second": 247.397,
"eval_steps_per_second": 7.752,
"step": 1040
},
{
"epoch": 5.59,
"learning_rate": 0.0004072759538598048,
"loss": 0.7251,
"step": 1050
},
{
"epoch": 5.64,
"learning_rate": 0.00040638864241348714,
"loss": 0.8369,
"step": 1060
},
{
"epoch": 5.64,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7671139240264893,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 5.9969,
"eval_samples_per_second": 250.128,
"eval_steps_per_second": 7.837,
"step": 1060
},
{
"epoch": 5.69,
"learning_rate": 0.0004055013309671695,
"loss": 0.8827,
"step": 1070
},
{
"epoch": 5.74,
"learning_rate": 0.0004046140195208518,
"loss": 0.8594,
"step": 1080
},
{
"epoch": 5.74,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7597693800926208,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.1035,
"eval_samples_per_second": 245.759,
"eval_steps_per_second": 7.7,
"step": 1080
},
{
"epoch": 5.8,
"learning_rate": 0.00040372670807453415,
"loss": 0.6991,
"step": 1090
},
{
"epoch": 5.85,
"learning_rate": 0.0004028393966282165,
"loss": 0.763,
"step": 1100
},
{
"epoch": 5.85,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7626741528511047,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.2099,
"eval_samples_per_second": 241.55,
"eval_steps_per_second": 7.569,
"step": 1100
},
{
"epoch": 5.9,
"learning_rate": 0.0004019520851818989,
"loss": 0.803,
"step": 1110
},
{
"epoch": 5.96,
"learning_rate": 0.0004010647737355812,
"loss": 0.8508,
"step": 1120
},
{
"epoch": 5.96,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7459200620651245,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.1055,
"eval_samples_per_second": 245.68,
"eval_steps_per_second": 7.698,
"step": 1120
},
{
"epoch": 6.01,
"learning_rate": 0.00040017746228926355,
"loss": 0.655,
"step": 1130
},
{
"epoch": 6.06,
"learning_rate": 0.0003992901508429459,
"loss": 0.67,
"step": 1140
},
{
"epoch": 6.06,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7736058235168457,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0743,
"eval_samples_per_second": 246.941,
"eval_steps_per_second": 7.737,
"step": 1140
},
{
"epoch": 6.12,
"learning_rate": 0.0003984028393966282,
"loss": 0.9277,
"step": 1150
},
{
"epoch": 6.17,
"learning_rate": 0.00039751552795031056,
"loss": 0.7358,
"step": 1160
},
{
"epoch": 6.17,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7588059902191162,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0157,
"eval_samples_per_second": 249.349,
"eval_steps_per_second": 7.813,
"step": 1160
},
{
"epoch": 6.22,
"learning_rate": 0.0003966282165039929,
"loss": 0.6581,
"step": 1170
},
{
"epoch": 6.28,
"learning_rate": 0.00039574090505767524,
"loss": 0.6768,
"step": 1180
},
{
"epoch": 6.28,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7461269497871399,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0429,
"eval_samples_per_second": 248.226,
"eval_steps_per_second": 7.778,
"step": 1180
},
{
"epoch": 6.33,
"learning_rate": 0.0003948535936113576,
"loss": 0.6814,
"step": 1190
},
{
"epoch": 6.38,
"learning_rate": 0.0003939662821650399,
"loss": 0.7112,
"step": 1200
},
{
"epoch": 6.38,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7580690383911133,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 5.987,
"eval_samples_per_second": 250.543,
"eval_steps_per_second": 7.85,
"step": 1200
},
{
"epoch": 6.44,
"learning_rate": 0.0003930789707187223,
"loss": 0.78,
"step": 1210
},
{
"epoch": 6.49,
"learning_rate": 0.00039219165927240464,
"loss": 0.7991,
"step": 1220
},
{
"epoch": 6.49,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7527822256088257,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0389,
"eval_samples_per_second": 248.39,
"eval_steps_per_second": 7.783,
"step": 1220
},
{
"epoch": 6.54,
"learning_rate": 0.000391304347826087,
"loss": 0.833,
"step": 1230
},
{
"epoch": 6.6,
"learning_rate": 0.0003904170363797693,
"loss": 0.9258,
"step": 1240
},
{
"epoch": 6.6,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7517044544219971,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 5.9942,
"eval_samples_per_second": 250.24,
"eval_steps_per_second": 7.841,
"step": 1240
},
{
"epoch": 6.65,
"learning_rate": 0.00038952972493345165,
"loss": 0.6751,
"step": 1250
},
{
"epoch": 6.7,
"learning_rate": 0.000388642413487134,
"loss": 0.7574,
"step": 1260
},
{
"epoch": 6.7,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7456061244010925,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.1978,
"eval_samples_per_second": 242.023,
"eval_steps_per_second": 7.583,
"step": 1260
},
{
"epoch": 6.76,
"learning_rate": 0.0003877551020408163,
"loss": 0.8179,
"step": 1270
},
{
"epoch": 6.81,
"learning_rate": 0.00038686779059449866,
"loss": 0.7691,
"step": 1280
},
{
"epoch": 6.81,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7492356896400452,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0678,
"eval_samples_per_second": 247.208,
"eval_steps_per_second": 7.746,
"step": 1280
},
{
"epoch": 6.86,
"learning_rate": 0.000385980479148181,
"loss": 0.7528,
"step": 1290
},
{
"epoch": 6.91,
"learning_rate": 0.0003850931677018634,
"loss": 0.5853,
"step": 1300
},
{
"epoch": 6.91,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7996741533279419,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 5.9805,
"eval_samples_per_second": 250.815,
"eval_steps_per_second": 7.859,
"step": 1300
},
{
"epoch": 6.97,
"learning_rate": 0.0003842058562555457,
"loss": 1.0142,
"step": 1310
},
{
"epoch": 7.02,
"learning_rate": 0.00038331854480922806,
"loss": 0.9782,
"step": 1320
},
{
"epoch": 7.02,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7786191701889038,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.1561,
"eval_samples_per_second": 243.66,
"eval_steps_per_second": 7.635,
"step": 1320
},
{
"epoch": 7.07,
"learning_rate": 0.0003824312333629104,
"loss": 0.8774,
"step": 1330
},
{
"epoch": 7.13,
"learning_rate": 0.0003815439219165927,
"loss": 0.73,
"step": 1340
},
{
"epoch": 7.13,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7597090005874634,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.252,
"eval_samples_per_second": 239.925,
"eval_steps_per_second": 7.518,
"step": 1340
},
{
"epoch": 7.18,
"learning_rate": 0.0003806566104702751,
"loss": 0.6523,
"step": 1350
},
{
"epoch": 7.23,
"learning_rate": 0.0003797692990239574,
"loss": 0.5814,
"step": 1360
},
{
"epoch": 7.23,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.8069555759429932,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0437,
"eval_samples_per_second": 248.194,
"eval_steps_per_second": 7.777,
"step": 1360
},
{
"epoch": 7.29,
"learning_rate": 0.00037888198757763975,
"loss": 0.8547,
"step": 1370
},
{
"epoch": 7.34,
"learning_rate": 0.0003779946761313221,
"loss": 0.8289,
"step": 1380
},
{
"epoch": 7.34,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7525202035903931,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0147,
"eval_samples_per_second": 249.387,
"eval_steps_per_second": 7.814,
"step": 1380
},
{
"epoch": 7.39,
"learning_rate": 0.0003771073646850044,
"loss": 0.7157,
"step": 1390
},
{
"epoch": 7.45,
"learning_rate": 0.0003762200532386868,
"loss": 0.7269,
"step": 1400
},
{
"epoch": 7.45,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7548522353172302,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.1004,
"eval_samples_per_second": 245.886,
"eval_steps_per_second": 7.704,
"step": 1400
},
{
"epoch": 7.5,
"learning_rate": 0.00037533274179236915,
"loss": 0.8475,
"step": 1410
},
{
"epoch": 7.55,
"learning_rate": 0.0003744454303460515,
"loss": 0.7227,
"step": 1420
},
{
"epoch": 7.55,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7969293594360352,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0981,
"eval_samples_per_second": 245.98,
"eval_steps_per_second": 7.707,
"step": 1420
},
{
"epoch": 7.61,
"learning_rate": 0.00037355811889973377,
"loss": 0.9252,
"step": 1430
},
{
"epoch": 7.66,
"learning_rate": 0.00037267080745341616,
"loss": 0.71,
"step": 1440
},
{
"epoch": 7.66,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.8190247416496277,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0637,
"eval_samples_per_second": 247.376,
"eval_steps_per_second": 7.751,
"step": 1440
},
{
"epoch": 7.71,
"learning_rate": 0.0003717834960070985,
"loss": 0.8722,
"step": 1450
},
{
"epoch": 7.77,
"learning_rate": 0.00037089618456078084,
"loss": 1.0148,
"step": 1460
},
{
"epoch": 7.77,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7832964062690735,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.091,
"eval_samples_per_second": 246.267,
"eval_steps_per_second": 7.716,
"step": 1460
},
{
"epoch": 7.82,
"learning_rate": 0.0003700088731144632,
"loss": 0.772,
"step": 1470
},
{
"epoch": 7.87,
"learning_rate": 0.0003691215616681455,
"loss": 0.6867,
"step": 1480
},
{
"epoch": 7.87,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.8290088772773743,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.1496,
"eval_samples_per_second": 243.918,
"eval_steps_per_second": 7.643,
"step": 1480
},
{
"epoch": 7.93,
"learning_rate": 0.0003682342502218279,
"loss": 0.8245,
"step": 1490
},
{
"epoch": 7.98,
"learning_rate": 0.00036734693877551024,
"loss": 0.8665,
"step": 1500
},
{
"epoch": 7.98,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7548300623893738,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.2167,
"eval_samples_per_second": 241.285,
"eval_steps_per_second": 7.56,
"step": 1500
}
],
"logging_steps": 10,
"max_steps": 5640,
"num_train_epochs": 30,
"save_steps": 100,
"total_flos": 3149993726705664.0,
"trial_name": null,
"trial_params": null
}