bounti / trainer_state.json
akoksal's picture
Upload trainer_state.json
6bb720d
raw
history blame
30.5 kB
{
"best_metric": 0.7303927466978029,
"best_model_checkpoint": "transformer_results/checkpoint-1195",
"epoch": 5.0,
"global_step": 1195,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 1.6666666666666668e-07,
"loss": 1.1199,
"step": 5
},
{
"epoch": 0.04,
"learning_rate": 3.3333333333333335e-07,
"loss": 1.1559,
"step": 10
},
{
"epoch": 0.06,
"learning_rate": 5.000000000000001e-07,
"loss": 1.1063,
"step": 15
},
{
"epoch": 0.08,
"learning_rate": 6.666666666666667e-07,
"loss": 1.1422,
"step": 20
},
{
"epoch": 0.1,
"learning_rate": 8.333333333333333e-07,
"loss": 1.1437,
"step": 25
},
{
"epoch": 0.13,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.1165,
"step": 30
},
{
"epoch": 0.15,
"learning_rate": 1.1666666666666668e-06,
"loss": 1.1732,
"step": 35
},
{
"epoch": 0.17,
"learning_rate": 1.3333333333333334e-06,
"loss": 1.1104,
"step": 40
},
{
"epoch": 0.19,
"learning_rate": 1.5e-06,
"loss": 1.1014,
"step": 45
},
{
"epoch": 0.21,
"learning_rate": 1.6666666666666667e-06,
"loss": 1.1026,
"step": 50
},
{
"epoch": 0.23,
"learning_rate": 1.8333333333333333e-06,
"loss": 1.1506,
"step": 55
},
{
"epoch": 0.25,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.1242,
"step": 60
},
{
"epoch": 0.27,
"learning_rate": 2.166666666666667e-06,
"loss": 1.1027,
"step": 65
},
{
"epoch": 0.29,
"learning_rate": 2.3333333333333336e-06,
"loss": 1.0989,
"step": 70
},
{
"epoch": 0.31,
"learning_rate": 2.5e-06,
"loss": 1.1215,
"step": 75
},
{
"epoch": 0.33,
"learning_rate": 2.666666666666667e-06,
"loss": 1.0996,
"step": 80
},
{
"epoch": 0.36,
"learning_rate": 2.8333333333333335e-06,
"loss": 1.0873,
"step": 85
},
{
"epoch": 0.38,
"learning_rate": 3e-06,
"loss": 1.0888,
"step": 90
},
{
"epoch": 0.4,
"learning_rate": 3.1666666666666667e-06,
"loss": 1.0732,
"step": 95
},
{
"epoch": 0.42,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.058,
"step": 100
},
{
"epoch": 0.44,
"learning_rate": 3.5e-06,
"loss": 1.0841,
"step": 105
},
{
"epoch": 0.46,
"learning_rate": 3.6666666666666666e-06,
"loss": 1.0668,
"step": 110
},
{
"epoch": 0.48,
"learning_rate": 3.833333333333334e-06,
"loss": 1.055,
"step": 115
},
{
"epoch": 0.5,
"learning_rate": 4.000000000000001e-06,
"loss": 1.0782,
"step": 120
},
{
"epoch": 0.52,
"learning_rate": 4.166666666666667e-06,
"loss": 1.0832,
"step": 125
},
{
"epoch": 0.54,
"learning_rate": 4.333333333333334e-06,
"loss": 1.0822,
"step": 130
},
{
"epoch": 0.56,
"learning_rate": 4.5e-06,
"loss": 1.1047,
"step": 135
},
{
"epoch": 0.59,
"learning_rate": 4.666666666666667e-06,
"loss": 1.0143,
"step": 140
},
{
"epoch": 0.61,
"learning_rate": 4.833333333333333e-06,
"loss": 1.0536,
"step": 145
},
{
"epoch": 0.63,
"learning_rate": 5e-06,
"loss": 0.9694,
"step": 150
},
{
"epoch": 0.65,
"learning_rate": 5.1666666666666675e-06,
"loss": 0.9849,
"step": 155
},
{
"epoch": 0.67,
"learning_rate": 5.333333333333334e-06,
"loss": 1.056,
"step": 160
},
{
"epoch": 0.69,
"learning_rate": 5.500000000000001e-06,
"loss": 0.9908,
"step": 165
},
{
"epoch": 0.71,
"learning_rate": 5.666666666666667e-06,
"loss": 0.9972,
"step": 170
},
{
"epoch": 0.73,
"learning_rate": 5.833333333333334e-06,
"loss": 1.0025,
"step": 175
},
{
"epoch": 0.75,
"learning_rate": 6e-06,
"loss": 0.9894,
"step": 180
},
{
"epoch": 0.77,
"learning_rate": 6.166666666666667e-06,
"loss": 0.978,
"step": 185
},
{
"epoch": 0.79,
"learning_rate": 6.333333333333333e-06,
"loss": 0.9075,
"step": 190
},
{
"epoch": 0.82,
"learning_rate": 6.5000000000000004e-06,
"loss": 0.9821,
"step": 195
},
{
"epoch": 0.84,
"learning_rate": 6.666666666666667e-06,
"loss": 0.9892,
"step": 200
},
{
"epoch": 0.86,
"learning_rate": 6.833333333333334e-06,
"loss": 0.9589,
"step": 205
},
{
"epoch": 0.88,
"learning_rate": 7e-06,
"loss": 0.9523,
"step": 210
},
{
"epoch": 0.9,
"learning_rate": 7.166666666666667e-06,
"loss": 0.906,
"step": 215
},
{
"epoch": 0.92,
"learning_rate": 7.333333333333333e-06,
"loss": 0.9008,
"step": 220
},
{
"epoch": 0.94,
"learning_rate": 7.500000000000001e-06,
"loss": 0.8558,
"step": 225
},
{
"epoch": 0.96,
"learning_rate": 7.666666666666667e-06,
"loss": 0.8816,
"step": 230
},
{
"epoch": 0.98,
"learning_rate": 7.833333333333333e-06,
"loss": 0.8673,
"step": 235
},
{
"epoch": 1.0,
"eval_accuracy": 0.6118935837245696,
"eval_f1": 0.5585520526450062,
"eval_loss": 0.8446471691131592,
"eval_precision": 0.5895093083399559,
"eval_recall": 0.5934430679951587,
"eval_runtime": 1.3785,
"eval_samples_per_second": 463.547,
"step": 239
},
{
"epoch": 1.0,
"learning_rate": 8.000000000000001e-06,
"loss": 0.9194,
"step": 240
},
{
"epoch": 1.03,
"learning_rate": 8.166666666666668e-06,
"loss": 0.8337,
"step": 245
},
{
"epoch": 1.05,
"learning_rate": 8.333333333333334e-06,
"loss": 0.8408,
"step": 250
},
{
"epoch": 1.07,
"learning_rate": 8.5e-06,
"loss": 0.8691,
"step": 255
},
{
"epoch": 1.09,
"learning_rate": 8.666666666666668e-06,
"loss": 0.8203,
"step": 260
},
{
"epoch": 1.11,
"learning_rate": 8.833333333333334e-06,
"loss": 0.8385,
"step": 265
},
{
"epoch": 1.13,
"learning_rate": 9e-06,
"loss": 0.8129,
"step": 270
},
{
"epoch": 1.15,
"learning_rate": 9.166666666666666e-06,
"loss": 0.8152,
"step": 275
},
{
"epoch": 1.17,
"learning_rate": 9.333333333333334e-06,
"loss": 0.8545,
"step": 280
},
{
"epoch": 1.19,
"learning_rate": 9.5e-06,
"loss": 0.7112,
"step": 285
},
{
"epoch": 1.21,
"learning_rate": 9.666666666666667e-06,
"loss": 0.7656,
"step": 290
},
{
"epoch": 1.23,
"learning_rate": 9.833333333333333e-06,
"loss": 0.7246,
"step": 295
},
{
"epoch": 1.26,
"learning_rate": 1e-05,
"loss": 0.8573,
"step": 300
},
{
"epoch": 1.28,
"learning_rate": 9.976076555023924e-06,
"loss": 0.8283,
"step": 305
},
{
"epoch": 1.3,
"learning_rate": 9.952153110047848e-06,
"loss": 0.8442,
"step": 310
},
{
"epoch": 1.32,
"learning_rate": 9.928229665071771e-06,
"loss": 0.8681,
"step": 315
},
{
"epoch": 1.34,
"learning_rate": 9.904306220095695e-06,
"loss": 0.7913,
"step": 320
},
{
"epoch": 1.36,
"learning_rate": 9.880382775119618e-06,
"loss": 0.7516,
"step": 325
},
{
"epoch": 1.38,
"learning_rate": 9.856459330143542e-06,
"loss": 0.7396,
"step": 330
},
{
"epoch": 1.4,
"learning_rate": 9.832535885167465e-06,
"loss": 0.7783,
"step": 335
},
{
"epoch": 1.42,
"learning_rate": 9.808612440191389e-06,
"loss": 0.6969,
"step": 340
},
{
"epoch": 1.44,
"learning_rate": 9.784688995215312e-06,
"loss": 0.6135,
"step": 345
},
{
"epoch": 1.46,
"learning_rate": 9.760765550239236e-06,
"loss": 0.6747,
"step": 350
},
{
"epoch": 1.49,
"learning_rate": 9.736842105263159e-06,
"loss": 0.7245,
"step": 355
},
{
"epoch": 1.51,
"learning_rate": 9.712918660287082e-06,
"loss": 0.8613,
"step": 360
},
{
"epoch": 1.53,
"learning_rate": 9.688995215311006e-06,
"loss": 0.6747,
"step": 365
},
{
"epoch": 1.55,
"learning_rate": 9.66507177033493e-06,
"loss": 0.5984,
"step": 370
},
{
"epoch": 1.57,
"learning_rate": 9.641148325358853e-06,
"loss": 0.7647,
"step": 375
},
{
"epoch": 1.59,
"learning_rate": 9.617224880382776e-06,
"loss": 0.8218,
"step": 380
},
{
"epoch": 1.61,
"learning_rate": 9.593301435406698e-06,
"loss": 0.6774,
"step": 385
},
{
"epoch": 1.63,
"learning_rate": 9.569377990430623e-06,
"loss": 0.7308,
"step": 390
},
{
"epoch": 1.65,
"learning_rate": 9.545454545454547e-06,
"loss": 0.7043,
"step": 395
},
{
"epoch": 1.67,
"learning_rate": 9.52153110047847e-06,
"loss": 0.6552,
"step": 400
},
{
"epoch": 1.69,
"learning_rate": 9.497607655502394e-06,
"loss": 0.7811,
"step": 405
},
{
"epoch": 1.72,
"learning_rate": 9.473684210526315e-06,
"loss": 0.7064,
"step": 410
},
{
"epoch": 1.74,
"learning_rate": 9.44976076555024e-06,
"loss": 0.7103,
"step": 415
},
{
"epoch": 1.76,
"learning_rate": 9.425837320574164e-06,
"loss": 0.6587,
"step": 420
},
{
"epoch": 1.78,
"learning_rate": 9.401913875598086e-06,
"loss": 0.6484,
"step": 425
},
{
"epoch": 1.8,
"learning_rate": 9.377990430622011e-06,
"loss": 0.8353,
"step": 430
},
{
"epoch": 1.82,
"learning_rate": 9.354066985645935e-06,
"loss": 0.7396,
"step": 435
},
{
"epoch": 1.84,
"learning_rate": 9.330143540669856e-06,
"loss": 0.5923,
"step": 440
},
{
"epoch": 1.86,
"learning_rate": 9.306220095693781e-06,
"loss": 0.7663,
"step": 445
},
{
"epoch": 1.88,
"learning_rate": 9.282296650717703e-06,
"loss": 0.8757,
"step": 450
},
{
"epoch": 1.9,
"learning_rate": 9.258373205741627e-06,
"loss": 0.7992,
"step": 455
},
{
"epoch": 1.92,
"learning_rate": 9.234449760765552e-06,
"loss": 0.5915,
"step": 460
},
{
"epoch": 1.95,
"learning_rate": 9.210526315789474e-06,
"loss": 0.72,
"step": 465
},
{
"epoch": 1.97,
"learning_rate": 9.186602870813399e-06,
"loss": 0.7812,
"step": 470
},
{
"epoch": 1.99,
"learning_rate": 9.16267942583732e-06,
"loss": 0.6364,
"step": 475
},
{
"epoch": 2.0,
"eval_accuracy": 0.6885758998435054,
"eval_f1": 0.656770150887798,
"eval_loss": 0.7154723405838013,
"eval_precision": 0.6491329545325667,
"eval_recall": 0.6740555031294136,
"eval_runtime": 1.3791,
"eval_samples_per_second": 463.34,
"step": 478
},
{
"epoch": 2.01,
"learning_rate": 9.138755980861244e-06,
"loss": 0.5847,
"step": 480
},
{
"epoch": 2.03,
"learning_rate": 9.11483253588517e-06,
"loss": 0.5516,
"step": 485
},
{
"epoch": 2.05,
"learning_rate": 9.090909090909091e-06,
"loss": 0.6028,
"step": 490
},
{
"epoch": 2.07,
"learning_rate": 9.066985645933015e-06,
"loss": 0.6717,
"step": 495
},
{
"epoch": 2.09,
"learning_rate": 9.043062200956938e-06,
"loss": 0.5282,
"step": 500
},
{
"epoch": 2.11,
"learning_rate": 9.019138755980861e-06,
"loss": 0.611,
"step": 505
},
{
"epoch": 2.13,
"learning_rate": 8.995215311004785e-06,
"loss": 0.5825,
"step": 510
},
{
"epoch": 2.15,
"learning_rate": 8.971291866028708e-06,
"loss": 0.6462,
"step": 515
},
{
"epoch": 2.18,
"learning_rate": 8.947368421052632e-06,
"loss": 0.5069,
"step": 520
},
{
"epoch": 2.2,
"learning_rate": 8.923444976076557e-06,
"loss": 0.5475,
"step": 525
},
{
"epoch": 2.22,
"learning_rate": 8.899521531100479e-06,
"loss": 0.4481,
"step": 530
},
{
"epoch": 2.24,
"learning_rate": 8.875598086124402e-06,
"loss": 0.6493,
"step": 535
},
{
"epoch": 2.26,
"learning_rate": 8.851674641148326e-06,
"loss": 0.6118,
"step": 540
},
{
"epoch": 2.28,
"learning_rate": 8.82775119617225e-06,
"loss": 0.5763,
"step": 545
},
{
"epoch": 2.3,
"learning_rate": 8.803827751196173e-06,
"loss": 0.623,
"step": 550
},
{
"epoch": 2.32,
"learning_rate": 8.779904306220096e-06,
"loss": 0.6462,
"step": 555
},
{
"epoch": 2.34,
"learning_rate": 8.75598086124402e-06,
"loss": 0.5816,
"step": 560
},
{
"epoch": 2.36,
"learning_rate": 8.732057416267943e-06,
"loss": 0.5347,
"step": 565
},
{
"epoch": 2.38,
"learning_rate": 8.708133971291867e-06,
"loss": 0.5908,
"step": 570
},
{
"epoch": 2.41,
"learning_rate": 8.68421052631579e-06,
"loss": 0.5647,
"step": 575
},
{
"epoch": 2.43,
"learning_rate": 8.660287081339714e-06,
"loss": 0.5552,
"step": 580
},
{
"epoch": 2.45,
"learning_rate": 8.636363636363637e-06,
"loss": 0.6036,
"step": 585
},
{
"epoch": 2.47,
"learning_rate": 8.61244019138756e-06,
"loss": 0.6157,
"step": 590
},
{
"epoch": 2.49,
"learning_rate": 8.588516746411484e-06,
"loss": 0.6226,
"step": 595
},
{
"epoch": 2.51,
"learning_rate": 8.564593301435407e-06,
"loss": 0.6381,
"step": 600
},
{
"epoch": 2.53,
"learning_rate": 8.540669856459331e-06,
"loss": 0.5427,
"step": 605
},
{
"epoch": 2.55,
"learning_rate": 8.516746411483254e-06,
"loss": 0.6935,
"step": 610
},
{
"epoch": 2.57,
"learning_rate": 8.492822966507178e-06,
"loss": 0.6107,
"step": 615
},
{
"epoch": 2.59,
"learning_rate": 8.468899521531101e-06,
"loss": 0.5913,
"step": 620
},
{
"epoch": 2.62,
"learning_rate": 8.444976076555025e-06,
"loss": 0.7105,
"step": 625
},
{
"epoch": 2.64,
"learning_rate": 8.421052631578948e-06,
"loss": 0.7886,
"step": 630
},
{
"epoch": 2.66,
"learning_rate": 8.397129186602872e-06,
"loss": 0.6322,
"step": 635
},
{
"epoch": 2.68,
"learning_rate": 8.373205741626795e-06,
"loss": 0.6138,
"step": 640
},
{
"epoch": 2.7,
"learning_rate": 8.349282296650719e-06,
"loss": 0.4859,
"step": 645
},
{
"epoch": 2.72,
"learning_rate": 8.325358851674642e-06,
"loss": 0.5193,
"step": 650
},
{
"epoch": 2.74,
"learning_rate": 8.301435406698564e-06,
"loss": 0.5186,
"step": 655
},
{
"epoch": 2.76,
"learning_rate": 8.277511961722489e-06,
"loss": 0.6264,
"step": 660
},
{
"epoch": 2.78,
"learning_rate": 8.253588516746413e-06,
"loss": 0.4961,
"step": 665
},
{
"epoch": 2.8,
"learning_rate": 8.229665071770336e-06,
"loss": 0.5501,
"step": 670
},
{
"epoch": 2.82,
"learning_rate": 8.20574162679426e-06,
"loss": 0.6095,
"step": 675
},
{
"epoch": 2.85,
"learning_rate": 8.181818181818183e-06,
"loss": 0.6167,
"step": 680
},
{
"epoch": 2.87,
"learning_rate": 8.157894736842106e-06,
"loss": 0.5376,
"step": 685
},
{
"epoch": 2.89,
"learning_rate": 8.13397129186603e-06,
"loss": 0.6622,
"step": 690
},
{
"epoch": 2.91,
"learning_rate": 8.110047846889952e-06,
"loss": 0.5905,
"step": 695
},
{
"epoch": 2.93,
"learning_rate": 8.086124401913877e-06,
"loss": 0.5377,
"step": 700
},
{
"epoch": 2.95,
"learning_rate": 8.0622009569378e-06,
"loss": 0.4796,
"step": 705
},
{
"epoch": 2.97,
"learning_rate": 8.038277511961722e-06,
"loss": 0.6476,
"step": 710
},
{
"epoch": 2.99,
"learning_rate": 8.014354066985647e-06,
"loss": 0.6019,
"step": 715
},
{
"epoch": 3.0,
"eval_accuracy": 0.7198748043818466,
"eval_f1": 0.6813571826149668,
"eval_loss": 0.731553316116333,
"eval_precision": 0.6802937538038156,
"eval_recall": 0.6984726537939752,
"eval_runtime": 1.3797,
"eval_samples_per_second": 463.146,
"step": 717
},
{
"epoch": 3.01,
"learning_rate": 7.990430622009569e-06,
"loss": 0.3467,
"step": 720
},
{
"epoch": 3.03,
"learning_rate": 7.966507177033494e-06,
"loss": 0.5747,
"step": 725
},
{
"epoch": 3.05,
"learning_rate": 7.942583732057418e-06,
"loss": 0.4857,
"step": 730
},
{
"epoch": 3.08,
"learning_rate": 7.91866028708134e-06,
"loss": 0.3488,
"step": 735
},
{
"epoch": 3.1,
"learning_rate": 7.894736842105265e-06,
"loss": 0.5139,
"step": 740
},
{
"epoch": 3.12,
"learning_rate": 7.870813397129188e-06,
"loss": 0.4459,
"step": 745
},
{
"epoch": 3.14,
"learning_rate": 7.84688995215311e-06,
"loss": 0.3908,
"step": 750
},
{
"epoch": 3.16,
"learning_rate": 7.822966507177035e-06,
"loss": 0.5026,
"step": 755
},
{
"epoch": 3.18,
"learning_rate": 7.799043062200957e-06,
"loss": 0.386,
"step": 760
},
{
"epoch": 3.2,
"learning_rate": 7.77511961722488e-06,
"loss": 0.5769,
"step": 765
},
{
"epoch": 3.22,
"learning_rate": 7.751196172248805e-06,
"loss": 0.517,
"step": 770
},
{
"epoch": 3.24,
"learning_rate": 7.727272727272727e-06,
"loss": 0.4157,
"step": 775
},
{
"epoch": 3.26,
"learning_rate": 7.703349282296652e-06,
"loss": 0.5181,
"step": 780
},
{
"epoch": 3.28,
"learning_rate": 7.679425837320574e-06,
"loss": 0.4949,
"step": 785
},
{
"epoch": 3.31,
"learning_rate": 7.655502392344498e-06,
"loss": 0.5073,
"step": 790
},
{
"epoch": 3.33,
"learning_rate": 7.631578947368423e-06,
"loss": 0.3862,
"step": 795
},
{
"epoch": 3.35,
"learning_rate": 7.6076555023923446e-06,
"loss": 0.4249,
"step": 800
},
{
"epoch": 3.37,
"learning_rate": 7.583732057416269e-06,
"loss": 0.3961,
"step": 805
},
{
"epoch": 3.39,
"learning_rate": 7.5598086124401915e-06,
"loss": 0.4937,
"step": 810
},
{
"epoch": 3.41,
"learning_rate": 7.535885167464115e-06,
"loss": 0.4701,
"step": 815
},
{
"epoch": 3.43,
"learning_rate": 7.511961722488039e-06,
"loss": 0.4645,
"step": 820
},
{
"epoch": 3.45,
"learning_rate": 7.488038277511962e-06,
"loss": 0.4872,
"step": 825
},
{
"epoch": 3.47,
"learning_rate": 7.464114832535886e-06,
"loss": 0.3549,
"step": 830
},
{
"epoch": 3.49,
"learning_rate": 7.44019138755981e-06,
"loss": 0.4213,
"step": 835
},
{
"epoch": 3.51,
"learning_rate": 7.416267942583732e-06,
"loss": 0.4418,
"step": 840
},
{
"epoch": 3.54,
"learning_rate": 7.392344497607657e-06,
"loss": 0.5649,
"step": 845
},
{
"epoch": 3.56,
"learning_rate": 7.368421052631579e-06,
"loss": 0.4578,
"step": 850
},
{
"epoch": 3.58,
"learning_rate": 7.344497607655503e-06,
"loss": 0.5598,
"step": 855
},
{
"epoch": 3.6,
"learning_rate": 7.320574162679427e-06,
"loss": 0.6353,
"step": 860
},
{
"epoch": 3.62,
"learning_rate": 7.29665071770335e-06,
"loss": 0.4503,
"step": 865
},
{
"epoch": 3.64,
"learning_rate": 7.272727272727273e-06,
"loss": 0.4849,
"step": 870
},
{
"epoch": 3.66,
"learning_rate": 7.248803827751197e-06,
"loss": 0.3857,
"step": 875
},
{
"epoch": 3.68,
"learning_rate": 7.22488038277512e-06,
"loss": 0.3519,
"step": 880
},
{
"epoch": 3.7,
"learning_rate": 7.2009569377990444e-06,
"loss": 0.5901,
"step": 885
},
{
"epoch": 3.72,
"learning_rate": 7.177033492822967e-06,
"loss": 0.2847,
"step": 890
},
{
"epoch": 3.74,
"learning_rate": 7.1531100478468905e-06,
"loss": 0.3772,
"step": 895
},
{
"epoch": 3.77,
"learning_rate": 7.129186602870813e-06,
"loss": 0.457,
"step": 900
},
{
"epoch": 3.79,
"learning_rate": 7.1052631578947375e-06,
"loss": 0.4477,
"step": 905
},
{
"epoch": 3.81,
"learning_rate": 7.081339712918661e-06,
"loss": 0.396,
"step": 910
},
{
"epoch": 3.83,
"learning_rate": 7.0574162679425836e-06,
"loss": 0.4659,
"step": 915
},
{
"epoch": 3.85,
"learning_rate": 7.033492822966508e-06,
"loss": 0.3475,
"step": 920
},
{
"epoch": 3.87,
"learning_rate": 7.009569377990431e-06,
"loss": 0.6194,
"step": 925
},
{
"epoch": 3.89,
"learning_rate": 6.985645933014355e-06,
"loss": 0.6006,
"step": 930
},
{
"epoch": 3.91,
"learning_rate": 6.961722488038278e-06,
"loss": 0.4289,
"step": 935
},
{
"epoch": 3.93,
"learning_rate": 6.937799043062201e-06,
"loss": 0.415,
"step": 940
},
{
"epoch": 3.95,
"learning_rate": 6.913875598086125e-06,
"loss": 0.4557,
"step": 945
},
{
"epoch": 3.97,
"learning_rate": 6.889952153110049e-06,
"loss": 0.5737,
"step": 950
},
{
"epoch": 4.0,
"learning_rate": 6.866028708133971e-06,
"loss": 0.4552,
"step": 955
},
{
"epoch": 4.0,
"eval_accuracy": 0.7386541471048513,
"eval_f1": 0.6994009008729405,
"eval_loss": 0.7402008771896362,
"eval_precision": 0.7015953124331721,
"eval_recall": 0.7032879361319608,
"eval_runtime": 1.3798,
"eval_samples_per_second": 463.119,
"step": 956
},
{
"epoch": 4.02,
"learning_rate": 6.842105263157896e-06,
"loss": 0.3086,
"step": 960
},
{
"epoch": 4.04,
"learning_rate": 6.818181818181818e-06,
"loss": 0.3635,
"step": 965
},
{
"epoch": 4.06,
"learning_rate": 6.794258373205742e-06,
"loss": 0.4597,
"step": 970
},
{
"epoch": 4.08,
"learning_rate": 6.770334928229666e-06,
"loss": 0.3121,
"step": 975
},
{
"epoch": 4.1,
"learning_rate": 6.746411483253589e-06,
"loss": 0.3196,
"step": 980
},
{
"epoch": 4.12,
"learning_rate": 6.722488038277513e-06,
"loss": 0.3561,
"step": 985
},
{
"epoch": 4.14,
"learning_rate": 6.6985645933014365e-06,
"loss": 0.4719,
"step": 990
},
{
"epoch": 4.16,
"learning_rate": 6.674641148325359e-06,
"loss": 0.3962,
"step": 995
},
{
"epoch": 4.18,
"learning_rate": 6.6507177033492834e-06,
"loss": 0.4611,
"step": 1000
},
{
"epoch": 4.21,
"learning_rate": 6.626794258373206e-06,
"loss": 0.3683,
"step": 1005
},
{
"epoch": 4.23,
"learning_rate": 6.6028708133971295e-06,
"loss": 0.4804,
"step": 1010
},
{
"epoch": 4.25,
"learning_rate": 6.578947368421054e-06,
"loss": 0.4906,
"step": 1015
},
{
"epoch": 4.27,
"learning_rate": 6.5550239234449765e-06,
"loss": 0.3739,
"step": 1020
},
{
"epoch": 4.29,
"learning_rate": 6.5311004784689e-06,
"loss": 0.3931,
"step": 1025
},
{
"epoch": 4.31,
"learning_rate": 6.507177033492823e-06,
"loss": 0.3653,
"step": 1030
},
{
"epoch": 4.33,
"learning_rate": 6.483253588516747e-06,
"loss": 0.2901,
"step": 1035
},
{
"epoch": 4.35,
"learning_rate": 6.459330143540671e-06,
"loss": 0.3018,
"step": 1040
},
{
"epoch": 4.37,
"learning_rate": 6.435406698564594e-06,
"loss": 0.3269,
"step": 1045
},
{
"epoch": 4.39,
"learning_rate": 6.411483253588517e-06,
"loss": 0.3136,
"step": 1050
},
{
"epoch": 4.41,
"learning_rate": 6.38755980861244e-06,
"loss": 0.2619,
"step": 1055
},
{
"epoch": 4.44,
"learning_rate": 6.363636363636364e-06,
"loss": 0.3609,
"step": 1060
},
{
"epoch": 4.46,
"learning_rate": 6.339712918660288e-06,
"loss": 0.3332,
"step": 1065
},
{
"epoch": 4.48,
"learning_rate": 6.31578947368421e-06,
"loss": 0.4103,
"step": 1070
},
{
"epoch": 4.5,
"learning_rate": 6.291866028708135e-06,
"loss": 0.3114,
"step": 1075
},
{
"epoch": 4.52,
"learning_rate": 6.267942583732058e-06,
"loss": 0.3378,
"step": 1080
},
{
"epoch": 4.54,
"learning_rate": 6.244019138755982e-06,
"loss": 0.2184,
"step": 1085
},
{
"epoch": 4.56,
"learning_rate": 6.220095693779905e-06,
"loss": 0.3536,
"step": 1090
},
{
"epoch": 4.58,
"learning_rate": 6.196172248803828e-06,
"loss": 0.3263,
"step": 1095
},
{
"epoch": 4.6,
"learning_rate": 6.172248803827752e-06,
"loss": 0.4233,
"step": 1100
},
{
"epoch": 4.62,
"learning_rate": 6.1483253588516755e-06,
"loss": 0.3299,
"step": 1105
},
{
"epoch": 4.64,
"learning_rate": 6.124401913875598e-06,
"loss": 0.4214,
"step": 1110
},
{
"epoch": 4.67,
"learning_rate": 6.100478468899522e-06,
"loss": 0.4293,
"step": 1115
},
{
"epoch": 4.69,
"learning_rate": 6.076555023923445e-06,
"loss": 0.2951,
"step": 1120
},
{
"epoch": 4.71,
"learning_rate": 6.0526315789473685e-06,
"loss": 0.348,
"step": 1125
},
{
"epoch": 4.73,
"learning_rate": 6.028708133971293e-06,
"loss": 0.375,
"step": 1130
},
{
"epoch": 4.75,
"learning_rate": 6.0047846889952155e-06,
"loss": 0.3462,
"step": 1135
},
{
"epoch": 4.77,
"learning_rate": 5.98086124401914e-06,
"loss": 0.4293,
"step": 1140
},
{
"epoch": 4.79,
"learning_rate": 5.956937799043063e-06,
"loss": 0.3565,
"step": 1145
},
{
"epoch": 4.81,
"learning_rate": 5.933014354066986e-06,
"loss": 0.4702,
"step": 1150
},
{
"epoch": 4.83,
"learning_rate": 5.90909090909091e-06,
"loss": 0.4045,
"step": 1155
},
{
"epoch": 4.85,
"learning_rate": 5.885167464114833e-06,
"loss": 0.2668,
"step": 1160
},
{
"epoch": 4.87,
"learning_rate": 5.861244019138756e-06,
"loss": 0.2465,
"step": 1165
},
{
"epoch": 4.9,
"learning_rate": 5.837320574162681e-06,
"loss": 0.4719,
"step": 1170
},
{
"epoch": 4.92,
"learning_rate": 5.813397129186603e-06,
"loss": 0.4193,
"step": 1175
},
{
"epoch": 4.94,
"learning_rate": 5.789473684210527e-06,
"loss": 0.2751,
"step": 1180
},
{
"epoch": 4.96,
"learning_rate": 5.76555023923445e-06,
"loss": 0.3353,
"step": 1185
},
{
"epoch": 4.98,
"learning_rate": 5.741626794258374e-06,
"loss": 0.4269,
"step": 1190
},
{
"epoch": 5.0,
"learning_rate": 5.717703349282297e-06,
"loss": 0.3446,
"step": 1195
},
{
"epoch": 5.0,
"eval_accuracy": 0.7449139280125195,
"eval_f1": 0.7148205862964074,
"eval_loss": 0.8129351735115051,
"eval_precision": 0.705887006955344,
"eval_recall": 0.7303927466978029,
"eval_runtime": 1.3814,
"eval_samples_per_second": 462.57,
"step": 1195
}
],
"max_steps": 2390,
"num_train_epochs": 10,
"total_flos": 1585297624774500.0,
"trial_name": null,
"trial_params": null
}