FT_3 / checkpoint-4800 /trainer_state.json
sheepy928's picture
Training in progress, step 4800, checkpoint
92de8ff
raw
history blame
61.2 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 25.53191489361702,
"eval_steps": 300,
"global_step": 4800,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05,
"learning_rate": 5e-07,
"loss": 1.0874,
"step": 10
},
{
"epoch": 0.11,
"learning_rate": 1e-06,
"loss": 0.9487,
"step": 20
},
{
"epoch": 0.16,
"learning_rate": 1.5e-06,
"loss": 0.7586,
"step": 30
},
{
"epoch": 0.21,
"learning_rate": 2e-06,
"loss": 0.7225,
"step": 40
},
{
"epoch": 0.27,
"learning_rate": 2.5e-06,
"loss": 0.7364,
"step": 50
},
{
"epoch": 0.32,
"learning_rate": 3e-06,
"loss": 0.7265,
"step": 60
},
{
"epoch": 0.37,
"learning_rate": 3.5e-06,
"loss": 0.7267,
"step": 70
},
{
"epoch": 0.43,
"learning_rate": 4e-06,
"loss": 0.5697,
"step": 80
},
{
"epoch": 0.48,
"learning_rate": 4.5e-06,
"loss": 1.018,
"step": 90
},
{
"epoch": 0.53,
"learning_rate": 5e-06,
"loss": 0.7875,
"step": 100
},
{
"epoch": 0.59,
"learning_rate": 5.5e-06,
"loss": 0.8242,
"step": 110
},
{
"epoch": 0.64,
"learning_rate": 6e-06,
"loss": 0.8034,
"step": 120
},
{
"epoch": 0.69,
"learning_rate": 6.5e-06,
"loss": 0.7717,
"step": 130
},
{
"epoch": 0.74,
"learning_rate": 7e-06,
"loss": 0.8337,
"step": 140
},
{
"epoch": 0.8,
"learning_rate": 7.5e-06,
"loss": 0.6884,
"step": 150
},
{
"epoch": 0.85,
"learning_rate": 8e-06,
"loss": 0.9129,
"step": 160
},
{
"epoch": 0.9,
"learning_rate": 8.500000000000002e-06,
"loss": 0.5637,
"step": 170
},
{
"epoch": 0.96,
"learning_rate": 9e-06,
"loss": 1.0458,
"step": 180
},
{
"epoch": 1.01,
"learning_rate": 9.5e-06,
"loss": 0.9414,
"step": 190
},
{
"epoch": 1.06,
"learning_rate": 1e-05,
"loss": 0.6379,
"step": 200
},
{
"epoch": 1.12,
"learning_rate": 1.0500000000000001e-05,
"loss": 0.9249,
"step": 210
},
{
"epoch": 1.17,
"learning_rate": 1.1e-05,
"loss": 0.6944,
"step": 220
},
{
"epoch": 1.22,
"learning_rate": 1.15e-05,
"loss": 0.9221,
"step": 230
},
{
"epoch": 1.28,
"learning_rate": 1.2e-05,
"loss": 0.6475,
"step": 240
},
{
"epoch": 1.33,
"learning_rate": 1.25e-05,
"loss": 0.7748,
"step": 250
},
{
"epoch": 1.38,
"learning_rate": 1.3e-05,
"loss": 0.8705,
"step": 260
},
{
"epoch": 1.44,
"learning_rate": 1.35e-05,
"loss": 0.7737,
"step": 270
},
{
"epoch": 1.49,
"learning_rate": 1.4e-05,
"loss": 0.8643,
"step": 280
},
{
"epoch": 1.54,
"learning_rate": 1.4500000000000002e-05,
"loss": 0.8428,
"step": 290
},
{
"epoch": 1.6,
"learning_rate": 1.5e-05,
"loss": 0.6785,
"step": 300
},
{
"epoch": 1.6,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.7930460572242737,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 6.0663,
"eval_samples_per_second": 247.266,
"eval_steps_per_second": 7.748,
"step": 300
},
{
"epoch": 1.65,
"learning_rate": 1.55e-05,
"loss": 0.6076,
"step": 310
},
{
"epoch": 1.7,
"learning_rate": 1.6e-05,
"loss": 0.5963,
"step": 320
},
{
"epoch": 1.76,
"learning_rate": 1.65e-05,
"loss": 0.6626,
"step": 330
},
{
"epoch": 1.81,
"learning_rate": 1.7000000000000003e-05,
"loss": 0.8379,
"step": 340
},
{
"epoch": 1.86,
"learning_rate": 1.7500000000000002e-05,
"loss": 0.8851,
"step": 350
},
{
"epoch": 1.91,
"learning_rate": 1.8e-05,
"loss": 0.7489,
"step": 360
},
{
"epoch": 1.97,
"learning_rate": 1.85e-05,
"loss": 0.7573,
"step": 370
},
{
"epoch": 2.02,
"learning_rate": 1.9e-05,
"loss": 0.8018,
"step": 380
},
{
"epoch": 2.07,
"learning_rate": 1.95e-05,
"loss": 0.6645,
"step": 390
},
{
"epoch": 2.13,
"learning_rate": 2e-05,
"loss": 0.8677,
"step": 400
},
{
"epoch": 2.18,
"learning_rate": 2.05e-05,
"loss": 0.7478,
"step": 410
},
{
"epoch": 2.23,
"learning_rate": 2.1000000000000002e-05,
"loss": 0.8551,
"step": 420
},
{
"epoch": 2.29,
"learning_rate": 2.1499999999999997e-05,
"loss": 0.9323,
"step": 430
},
{
"epoch": 2.34,
"learning_rate": 2.2e-05,
"loss": 0.7536,
"step": 440
},
{
"epoch": 2.39,
"learning_rate": 2.2499999999999998e-05,
"loss": 0.5336,
"step": 450
},
{
"epoch": 2.45,
"learning_rate": 2.3e-05,
"loss": 0.8955,
"step": 460
},
{
"epoch": 2.5,
"learning_rate": 2.3500000000000002e-05,
"loss": 0.7926,
"step": 470
},
{
"epoch": 2.55,
"learning_rate": 2.4e-05,
"loss": 0.5713,
"step": 480
},
{
"epoch": 2.61,
"learning_rate": 2.4500000000000003e-05,
"loss": 0.8568,
"step": 490
},
{
"epoch": 2.66,
"learning_rate": 2.5e-05,
"loss": 0.6348,
"step": 500
},
{
"epoch": 2.71,
"learning_rate": 2.55e-05,
"loss": 0.6223,
"step": 510
},
{
"epoch": 2.77,
"learning_rate": 2.6e-05,
"loss": 0.7579,
"step": 520
},
{
"epoch": 2.82,
"learning_rate": 2.65e-05,
"loss": 0.6325,
"step": 530
},
{
"epoch": 2.87,
"learning_rate": 2.7e-05,
"loss": 0.7276,
"step": 540
},
{
"epoch": 2.93,
"learning_rate": 2.75e-05,
"loss": 0.8766,
"step": 550
},
{
"epoch": 2.98,
"learning_rate": 2.8e-05,
"loss": 0.7107,
"step": 560
},
{
"epoch": 3.03,
"learning_rate": 2.85e-05,
"loss": 0.5904,
"step": 570
},
{
"epoch": 3.09,
"learning_rate": 2.9000000000000004e-05,
"loss": 0.7125,
"step": 580
},
{
"epoch": 3.14,
"learning_rate": 2.95e-05,
"loss": 0.755,
"step": 590
},
{
"epoch": 3.19,
"learning_rate": 3e-05,
"loss": 0.5583,
"step": 600
},
{
"epoch": 3.19,
"eval_accuracy": 0.7613333333333333,
"eval_combined_score": 0.7403762607674487,
"eval_f1": 0.7316181693637903,
"eval_loss": 0.6910097599029541,
"eval_precision": 0.7072202070393374,
"eval_recall": 0.7613333333333333,
"eval_runtime": 6.0882,
"eval_samples_per_second": 246.376,
"eval_steps_per_second": 7.72,
"step": 600
},
{
"epoch": 3.24,
"learning_rate": 3.05e-05,
"loss": 0.6527,
"step": 610
},
{
"epoch": 3.3,
"learning_rate": 3.1e-05,
"loss": 0.7676,
"step": 620
},
{
"epoch": 3.35,
"learning_rate": 3.15e-05,
"loss": 0.766,
"step": 630
},
{
"epoch": 3.4,
"learning_rate": 3.2e-05,
"loss": 0.6217,
"step": 640
},
{
"epoch": 3.46,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.5405,
"step": 650
},
{
"epoch": 3.51,
"learning_rate": 3.3e-05,
"loss": 0.7951,
"step": 660
},
{
"epoch": 3.56,
"learning_rate": 3.35e-05,
"loss": 0.552,
"step": 670
},
{
"epoch": 3.62,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.6521,
"step": 680
},
{
"epoch": 3.67,
"learning_rate": 3.4500000000000005e-05,
"loss": 0.6814,
"step": 690
},
{
"epoch": 3.72,
"learning_rate": 3.5000000000000004e-05,
"loss": 0.3992,
"step": 700
},
{
"epoch": 3.78,
"learning_rate": 3.5499999999999996e-05,
"loss": 0.7018,
"step": 710
},
{
"epoch": 3.83,
"learning_rate": 3.6e-05,
"loss": 0.664,
"step": 720
},
{
"epoch": 3.88,
"learning_rate": 3.65e-05,
"loss": 0.6891,
"step": 730
},
{
"epoch": 3.94,
"learning_rate": 3.7e-05,
"loss": 0.6063,
"step": 740
},
{
"epoch": 3.99,
"learning_rate": 3.75e-05,
"loss": 0.6543,
"step": 750
},
{
"epoch": 4.04,
"learning_rate": 3.8e-05,
"loss": 0.5638,
"step": 760
},
{
"epoch": 4.1,
"learning_rate": 3.85e-05,
"loss": 0.6984,
"step": 770
},
{
"epoch": 4.15,
"learning_rate": 3.9e-05,
"loss": 0.7148,
"step": 780
},
{
"epoch": 4.2,
"learning_rate": 3.95e-05,
"loss": 0.4915,
"step": 790
},
{
"epoch": 4.26,
"learning_rate": 4e-05,
"loss": 0.648,
"step": 800
},
{
"epoch": 4.31,
"learning_rate": 4.05e-05,
"loss": 0.4527,
"step": 810
},
{
"epoch": 4.36,
"learning_rate": 4.1e-05,
"loss": 0.551,
"step": 820
},
{
"epoch": 4.41,
"learning_rate": 4.1500000000000006e-05,
"loss": 0.5909,
"step": 830
},
{
"epoch": 4.47,
"learning_rate": 4.2000000000000004e-05,
"loss": 0.603,
"step": 840
},
{
"epoch": 4.52,
"learning_rate": 4.25e-05,
"loss": 1.0745,
"step": 850
},
{
"epoch": 4.57,
"learning_rate": 4.2999999999999995e-05,
"loss": 0.6697,
"step": 860
},
{
"epoch": 4.63,
"learning_rate": 4.35e-05,
"loss": 0.8374,
"step": 870
},
{
"epoch": 4.68,
"learning_rate": 4.4e-05,
"loss": 0.4891,
"step": 880
},
{
"epoch": 4.73,
"learning_rate": 4.45e-05,
"loss": 0.5956,
"step": 890
},
{
"epoch": 4.79,
"learning_rate": 4.4999999999999996e-05,
"loss": 0.7857,
"step": 900
},
{
"epoch": 4.79,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.6514685153961182,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 5.9473,
"eval_samples_per_second": 252.216,
"eval_steps_per_second": 7.903,
"step": 900
},
{
"epoch": 4.84,
"learning_rate": 4.55e-05,
"loss": 0.8566,
"step": 910
},
{
"epoch": 4.89,
"learning_rate": 4.6e-05,
"loss": 0.4698,
"step": 920
},
{
"epoch": 4.95,
"learning_rate": 4.65e-05,
"loss": 0.7224,
"step": 930
},
{
"epoch": 5.0,
"learning_rate": 4.7000000000000004e-05,
"loss": 0.5879,
"step": 940
},
{
"epoch": 5.05,
"learning_rate": 4.75e-05,
"loss": 0.3592,
"step": 950
},
{
"epoch": 5.11,
"learning_rate": 4.8e-05,
"loss": 0.513,
"step": 960
},
{
"epoch": 5.16,
"learning_rate": 4.85e-05,
"loss": 0.6167,
"step": 970
},
{
"epoch": 5.21,
"learning_rate": 4.9000000000000005e-05,
"loss": 0.5706,
"step": 980
},
{
"epoch": 5.27,
"learning_rate": 4.9500000000000004e-05,
"loss": 0.5523,
"step": 990
},
{
"epoch": 5.32,
"learning_rate": 5e-05,
"loss": 0.6565,
"step": 1000
},
{
"epoch": 5.37,
"learning_rate": 5.05e-05,
"loss": 0.4634,
"step": 1010
},
{
"epoch": 5.43,
"learning_rate": 5.1e-05,
"loss": 0.634,
"step": 1020
},
{
"epoch": 5.48,
"learning_rate": 5.15e-05,
"loss": 0.5472,
"step": 1030
},
{
"epoch": 5.53,
"learning_rate": 5.2e-05,
"loss": 0.595,
"step": 1040
},
{
"epoch": 5.59,
"learning_rate": 5.25e-05,
"loss": 0.4889,
"step": 1050
},
{
"epoch": 5.64,
"learning_rate": 5.3e-05,
"loss": 0.5884,
"step": 1060
},
{
"epoch": 5.69,
"learning_rate": 5.35e-05,
"loss": 0.4149,
"step": 1070
},
{
"epoch": 5.74,
"learning_rate": 5.4e-05,
"loss": 0.7573,
"step": 1080
},
{
"epoch": 5.8,
"learning_rate": 5.45e-05,
"loss": 0.599,
"step": 1090
},
{
"epoch": 5.85,
"learning_rate": 5.5e-05,
"loss": 0.366,
"step": 1100
},
{
"epoch": 5.9,
"learning_rate": 5.55e-05,
"loss": 0.4906,
"step": 1110
},
{
"epoch": 5.96,
"learning_rate": 5.6e-05,
"loss": 0.4378,
"step": 1120
},
{
"epoch": 6.01,
"learning_rate": 5.6500000000000005e-05,
"loss": 0.4886,
"step": 1130
},
{
"epoch": 6.06,
"learning_rate": 5.7e-05,
"loss": 0.342,
"step": 1140
},
{
"epoch": 6.12,
"learning_rate": 5.75e-05,
"loss": 0.7803,
"step": 1150
},
{
"epoch": 6.17,
"learning_rate": 5.800000000000001e-05,
"loss": 0.3435,
"step": 1160
},
{
"epoch": 6.22,
"learning_rate": 5.8500000000000006e-05,
"loss": 0.6149,
"step": 1170
},
{
"epoch": 6.28,
"learning_rate": 5.9e-05,
"loss": 0.3026,
"step": 1180
},
{
"epoch": 6.33,
"learning_rate": 5.9499999999999996e-05,
"loss": 0.9387,
"step": 1190
},
{
"epoch": 6.38,
"learning_rate": 6e-05,
"loss": 0.6309,
"step": 1200
},
{
"epoch": 6.38,
"eval_accuracy": 0.848,
"eval_combined_score": 0.8403047916631027,
"eval_f1": 0.8270449473875959,
"eval_loss": 0.5592399835586548,
"eval_precision": 0.8381742192648148,
"eval_recall": 0.848,
"eval_runtime": 5.9701,
"eval_samples_per_second": 251.251,
"eval_steps_per_second": 7.873,
"step": 1200
},
{
"epoch": 6.44,
"learning_rate": 6.05e-05,
"loss": 0.4672,
"step": 1210
},
{
"epoch": 6.49,
"learning_rate": 6.1e-05,
"loss": 0.4909,
"step": 1220
},
{
"epoch": 6.54,
"learning_rate": 6.15e-05,
"loss": 0.5007,
"step": 1230
},
{
"epoch": 6.6,
"learning_rate": 6.2e-05,
"loss": 0.4318,
"step": 1240
},
{
"epoch": 6.65,
"learning_rate": 6.25e-05,
"loss": 0.3623,
"step": 1250
},
{
"epoch": 6.7,
"learning_rate": 6.3e-05,
"loss": 0.3294,
"step": 1260
},
{
"epoch": 6.76,
"learning_rate": 6.35e-05,
"loss": 0.7501,
"step": 1270
},
{
"epoch": 6.81,
"learning_rate": 6.4e-05,
"loss": 0.6436,
"step": 1280
},
{
"epoch": 6.86,
"learning_rate": 6.450000000000001e-05,
"loss": 0.525,
"step": 1290
},
{
"epoch": 6.91,
"learning_rate": 6.500000000000001e-05,
"loss": 0.6047,
"step": 1300
},
{
"epoch": 6.97,
"learning_rate": 6.55e-05,
"loss": 0.3636,
"step": 1310
},
{
"epoch": 7.02,
"learning_rate": 6.6e-05,
"loss": 0.5634,
"step": 1320
},
{
"epoch": 7.07,
"learning_rate": 6.65e-05,
"loss": 0.3846,
"step": 1330
},
{
"epoch": 7.13,
"learning_rate": 6.7e-05,
"loss": 0.8436,
"step": 1340
},
{
"epoch": 7.18,
"learning_rate": 6.75e-05,
"loss": 0.4762,
"step": 1350
},
{
"epoch": 7.23,
"learning_rate": 6.800000000000001e-05,
"loss": 0.5856,
"step": 1360
},
{
"epoch": 7.29,
"learning_rate": 6.850000000000001e-05,
"loss": 0.4042,
"step": 1370
},
{
"epoch": 7.34,
"learning_rate": 6.900000000000001e-05,
"loss": 0.475,
"step": 1380
},
{
"epoch": 7.39,
"learning_rate": 6.950000000000001e-05,
"loss": 0.3535,
"step": 1390
},
{
"epoch": 7.45,
"learning_rate": 7.000000000000001e-05,
"loss": 0.2399,
"step": 1400
},
{
"epoch": 7.5,
"learning_rate": 7.049999999999999e-05,
"loss": 0.316,
"step": 1410
},
{
"epoch": 7.55,
"learning_rate": 7.095e-05,
"loss": 0.438,
"step": 1420
},
{
"epoch": 7.61,
"learning_rate": 7.145e-05,
"loss": 0.2673,
"step": 1430
},
{
"epoch": 7.66,
"learning_rate": 7.195e-05,
"loss": 0.4286,
"step": 1440
},
{
"epoch": 7.71,
"learning_rate": 7.245e-05,
"loss": 0.3655,
"step": 1450
},
{
"epoch": 7.77,
"learning_rate": 7.295e-05,
"loss": 0.434,
"step": 1460
},
{
"epoch": 7.82,
"learning_rate": 7.345e-05,
"loss": 0.6143,
"step": 1470
},
{
"epoch": 7.87,
"learning_rate": 7.395000000000001e-05,
"loss": 0.5471,
"step": 1480
},
{
"epoch": 7.93,
"learning_rate": 7.445000000000001e-05,
"loss": 0.299,
"step": 1490
},
{
"epoch": 7.98,
"learning_rate": 7.495e-05,
"loss": 0.2216,
"step": 1500
},
{
"epoch": 7.98,
"eval_accuracy": 0.8773333333333333,
"eval_combined_score": 0.8618647537688802,
"eval_f1": 0.8431508113173474,
"eval_loss": 0.5708244442939758,
"eval_precision": 0.8496415370915067,
"eval_recall": 0.8773333333333333,
"eval_runtime": 6.0286,
"eval_samples_per_second": 248.816,
"eval_steps_per_second": 7.796,
"step": 1500
},
{
"epoch": 8.03,
"learning_rate": 7.545e-05,
"loss": 0.5517,
"step": 1510
},
{
"epoch": 8.09,
"learning_rate": 7.595e-05,
"loss": 0.3237,
"step": 1520
},
{
"epoch": 8.14,
"learning_rate": 7.645e-05,
"loss": 0.3945,
"step": 1530
},
{
"epoch": 8.19,
"learning_rate": 7.695e-05,
"loss": 0.3996,
"step": 1540
},
{
"epoch": 8.24,
"learning_rate": 7.745000000000001e-05,
"loss": 0.3644,
"step": 1550
},
{
"epoch": 8.3,
"learning_rate": 7.795000000000001e-05,
"loss": 0.6767,
"step": 1560
},
{
"epoch": 8.35,
"learning_rate": 7.845000000000001e-05,
"loss": 0.434,
"step": 1570
},
{
"epoch": 8.4,
"learning_rate": 7.895000000000001e-05,
"loss": 0.4047,
"step": 1580
},
{
"epoch": 8.46,
"learning_rate": 7.945e-05,
"loss": 0.3844,
"step": 1590
},
{
"epoch": 8.51,
"learning_rate": 7.994999999999999e-05,
"loss": 0.2656,
"step": 1600
},
{
"epoch": 8.56,
"learning_rate": 8.044999999999999e-05,
"loss": 0.3318,
"step": 1610
},
{
"epoch": 8.62,
"learning_rate": 8.095e-05,
"loss": 0.4627,
"step": 1620
},
{
"epoch": 8.67,
"learning_rate": 8.145e-05,
"loss": 0.6657,
"step": 1630
},
{
"epoch": 8.72,
"learning_rate": 8.195e-05,
"loss": 0.353,
"step": 1640
},
{
"epoch": 8.78,
"learning_rate": 8.245e-05,
"loss": 0.4543,
"step": 1650
},
{
"epoch": 8.83,
"learning_rate": 8.295e-05,
"loss": 0.4121,
"step": 1660
},
{
"epoch": 8.88,
"learning_rate": 8.340000000000001e-05,
"loss": 0.2792,
"step": 1670
},
{
"epoch": 8.94,
"learning_rate": 8.39e-05,
"loss": 0.3618,
"step": 1680
},
{
"epoch": 8.99,
"learning_rate": 8.44e-05,
"loss": 0.4922,
"step": 1690
},
{
"epoch": 9.04,
"learning_rate": 8.49e-05,
"loss": 0.6822,
"step": 1700
},
{
"epoch": 9.1,
"learning_rate": 8.54e-05,
"loss": 0.4936,
"step": 1710
},
{
"epoch": 9.15,
"learning_rate": 8.59e-05,
"loss": 0.4652,
"step": 1720
},
{
"epoch": 9.2,
"learning_rate": 8.640000000000001e-05,
"loss": 0.3529,
"step": 1730
},
{
"epoch": 9.26,
"learning_rate": 8.690000000000001e-05,
"loss": 0.5115,
"step": 1740
},
{
"epoch": 9.31,
"learning_rate": 8.740000000000001e-05,
"loss": 0.5859,
"step": 1750
},
{
"epoch": 9.36,
"learning_rate": 8.790000000000001e-05,
"loss": 0.5069,
"step": 1760
},
{
"epoch": 9.41,
"learning_rate": 8.840000000000001e-05,
"loss": 0.2584,
"step": 1770
},
{
"epoch": 9.47,
"learning_rate": 8.885e-05,
"loss": 0.313,
"step": 1780
},
{
"epoch": 9.52,
"learning_rate": 8.935e-05,
"loss": 0.4103,
"step": 1790
},
{
"epoch": 9.57,
"learning_rate": 8.985e-05,
"loss": 0.3214,
"step": 1800
},
{
"epoch": 9.57,
"eval_accuracy": 0.896,
"eval_combined_score": 0.8819938675326909,
"eval_f1": 0.8583787127091727,
"eval_loss": 0.45495954155921936,
"eval_precision": 0.8775967574215913,
"eval_recall": 0.896,
"eval_runtime": 6.1706,
"eval_samples_per_second": 243.087,
"eval_steps_per_second": 7.617,
"step": 1800
},
{
"epoch": 9.63,
"learning_rate": 9.035e-05,
"loss": 0.5097,
"step": 1810
},
{
"epoch": 9.68,
"learning_rate": 9.085e-05,
"loss": 0.4306,
"step": 1820
},
{
"epoch": 9.73,
"learning_rate": 9.135e-05,
"loss": 0.2573,
"step": 1830
},
{
"epoch": 9.79,
"learning_rate": 9.185e-05,
"loss": 0.3534,
"step": 1840
},
{
"epoch": 9.84,
"learning_rate": 9.235000000000001e-05,
"loss": 0.5012,
"step": 1850
},
{
"epoch": 9.89,
"learning_rate": 9.285000000000001e-05,
"loss": 0.7057,
"step": 1860
},
{
"epoch": 9.95,
"learning_rate": 9.335e-05,
"loss": 0.5385,
"step": 1870
},
{
"epoch": 10.0,
"learning_rate": 9.385e-05,
"loss": 0.2633,
"step": 1880
},
{
"epoch": 10.05,
"learning_rate": 9.435e-05,
"loss": 0.3853,
"step": 1890
},
{
"epoch": 10.11,
"learning_rate": 9.485e-05,
"loss": 0.4354,
"step": 1900
},
{
"epoch": 10.16,
"learning_rate": 9.535e-05,
"loss": 0.7459,
"step": 1910
},
{
"epoch": 10.21,
"learning_rate": 9.585000000000001e-05,
"loss": 0.2937,
"step": 1920
},
{
"epoch": 10.27,
"learning_rate": 9.635000000000001e-05,
"loss": 0.2932,
"step": 1930
},
{
"epoch": 10.32,
"learning_rate": 9.685000000000001e-05,
"loss": 0.4256,
"step": 1940
},
{
"epoch": 10.37,
"learning_rate": 9.735000000000001e-05,
"loss": 0.4336,
"step": 1950
},
{
"epoch": 10.43,
"learning_rate": 9.785e-05,
"loss": 0.4684,
"step": 1960
},
{
"epoch": 10.48,
"learning_rate": 9.835e-05,
"loss": 0.5437,
"step": 1970
},
{
"epoch": 10.53,
"learning_rate": 9.884999999999999e-05,
"loss": 0.3036,
"step": 1980
},
{
"epoch": 10.59,
"learning_rate": 9.935e-05,
"loss": 0.1528,
"step": 1990
},
{
"epoch": 10.64,
"learning_rate": 9.985e-05,
"loss": 0.8779,
"step": 2000
},
{
"epoch": 10.69,
"learning_rate": 0.00010035,
"loss": 0.53,
"step": 2010
},
{
"epoch": 10.74,
"learning_rate": 0.00010085,
"loss": 0.2656,
"step": 2020
},
{
"epoch": 10.8,
"learning_rate": 0.00010135,
"loss": 0.3895,
"step": 2030
},
{
"epoch": 10.85,
"learning_rate": 0.00010185,
"loss": 0.5943,
"step": 2040
},
{
"epoch": 10.9,
"learning_rate": 0.00010235,
"loss": 0.5021,
"step": 2050
},
{
"epoch": 10.96,
"learning_rate": 0.00010284999999999999,
"loss": 0.3804,
"step": 2060
},
{
"epoch": 11.01,
"learning_rate": 0.00010335,
"loss": 0.2204,
"step": 2070
},
{
"epoch": 11.06,
"learning_rate": 0.00010385,
"loss": 0.4421,
"step": 2080
},
{
"epoch": 11.12,
"learning_rate": 0.0001043,
"loss": 1.0409,
"step": 2090
},
{
"epoch": 11.17,
"learning_rate": 0.00010480000000000001,
"loss": 0.7521,
"step": 2100
},
{
"epoch": 11.17,
"eval_accuracy": 0.884,
"eval_combined_score": 0.8540521114926303,
"eval_f1": 0.8422803386258884,
"eval_loss": 0.3819296956062317,
"eval_precision": 0.8059281073446327,
"eval_recall": 0.884,
"eval_runtime": 6.0267,
"eval_samples_per_second": 248.894,
"eval_steps_per_second": 7.799,
"step": 2100
},
{
"epoch": 11.22,
"learning_rate": 0.00010530000000000001,
"loss": 0.3117,
"step": 2110
},
{
"epoch": 11.28,
"learning_rate": 0.00010580000000000001,
"loss": 0.4548,
"step": 2120
},
{
"epoch": 11.33,
"learning_rate": 0.00010630000000000001,
"loss": 0.484,
"step": 2130
},
{
"epoch": 11.38,
"learning_rate": 0.00010680000000000001,
"loss": 0.4479,
"step": 2140
},
{
"epoch": 11.44,
"learning_rate": 0.0001073,
"loss": 0.3099,
"step": 2150
},
{
"epoch": 11.49,
"learning_rate": 0.0001078,
"loss": 0.4728,
"step": 2160
},
{
"epoch": 11.54,
"learning_rate": 0.00010829999999999999,
"loss": 0.5189,
"step": 2170
},
{
"epoch": 11.6,
"learning_rate": 0.0001088,
"loss": 0.5615,
"step": 2180
},
{
"epoch": 11.65,
"learning_rate": 0.0001093,
"loss": 0.536,
"step": 2190
},
{
"epoch": 11.7,
"learning_rate": 0.0001098,
"loss": 0.4329,
"step": 2200
},
{
"epoch": 11.76,
"learning_rate": 0.0001103,
"loss": 0.2304,
"step": 2210
},
{
"epoch": 11.81,
"learning_rate": 0.0001108,
"loss": 0.5139,
"step": 2220
},
{
"epoch": 11.86,
"learning_rate": 0.0001113,
"loss": 0.3353,
"step": 2230
},
{
"epoch": 11.91,
"learning_rate": 0.0001118,
"loss": 0.7493,
"step": 2240
},
{
"epoch": 11.97,
"learning_rate": 0.0001123,
"loss": 1.0483,
"step": 2250
},
{
"epoch": 12.02,
"learning_rate": 0.0001128,
"loss": 0.5422,
"step": 2260
},
{
"epoch": 12.07,
"learning_rate": 0.0001133,
"loss": 0.771,
"step": 2270
},
{
"epoch": 12.13,
"learning_rate": 0.0001138,
"loss": 0.841,
"step": 2280
},
{
"epoch": 12.18,
"learning_rate": 0.0001143,
"loss": 0.7316,
"step": 2290
},
{
"epoch": 12.23,
"learning_rate": 0.0001148,
"loss": 0.7394,
"step": 2300
},
{
"epoch": 12.29,
"learning_rate": 0.0001153,
"loss": 0.7084,
"step": 2310
},
{
"epoch": 12.34,
"learning_rate": 0.0001158,
"loss": 0.8033,
"step": 2320
},
{
"epoch": 12.39,
"learning_rate": 0.00011630000000000001,
"loss": 0.6616,
"step": 2330
},
{
"epoch": 12.45,
"learning_rate": 0.0001168,
"loss": 0.7601,
"step": 2340
},
{
"epoch": 12.5,
"learning_rate": 0.0001173,
"loss": 0.7986,
"step": 2350
},
{
"epoch": 12.55,
"learning_rate": 0.0001178,
"loss": 0.673,
"step": 2360
},
{
"epoch": 12.61,
"learning_rate": 0.0001183,
"loss": 0.6354,
"step": 2370
},
{
"epoch": 12.66,
"learning_rate": 0.0001188,
"loss": 0.617,
"step": 2380
},
{
"epoch": 12.71,
"learning_rate": 0.0001193,
"loss": 0.5532,
"step": 2390
},
{
"epoch": 12.77,
"learning_rate": 0.00011980000000000001,
"loss": 0.5048,
"step": 2400
},
{
"epoch": 12.77,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6626504648943422,
"eval_f1": 0.6276400817995911,
"eval_loss": 0.6582097411155701,
"eval_precision": 0.5456284444444445,
"eval_recall": 0.7386666666666667,
"eval_runtime": 5.7153,
"eval_samples_per_second": 262.451,
"eval_steps_per_second": 8.223,
"step": 2400
},
{
"epoch": 12.82,
"learning_rate": 0.00012030000000000001,
"loss": 0.7655,
"step": 2410
},
{
"epoch": 12.87,
"learning_rate": 0.00012080000000000001,
"loss": 0.5875,
"step": 2420
},
{
"epoch": 12.93,
"learning_rate": 0.00012130000000000001,
"loss": 0.6008,
"step": 2430
},
{
"epoch": 12.98,
"learning_rate": 0.0001218,
"loss": 0.612,
"step": 2440
},
{
"epoch": 13.03,
"learning_rate": 0.00012230000000000002,
"loss": 0.6436,
"step": 2450
},
{
"epoch": 13.09,
"learning_rate": 0.00012275,
"loss": 0.3595,
"step": 2460
},
{
"epoch": 13.14,
"learning_rate": 0.00012325000000000001,
"loss": 0.4373,
"step": 2470
},
{
"epoch": 13.19,
"learning_rate": 0.00012375,
"loss": 0.8131,
"step": 2480
},
{
"epoch": 13.24,
"learning_rate": 0.00012425,
"loss": 0.7109,
"step": 2490
},
{
"epoch": 13.3,
"learning_rate": 0.00012475,
"loss": 0.5552,
"step": 2500
},
{
"epoch": 13.35,
"learning_rate": 0.00012525,
"loss": 0.4912,
"step": 2510
},
{
"epoch": 13.4,
"learning_rate": 0.00012575,
"loss": 0.5125,
"step": 2520
},
{
"epoch": 13.46,
"learning_rate": 0.00012625,
"loss": 0.5537,
"step": 2530
},
{
"epoch": 13.51,
"learning_rate": 0.00012675,
"loss": 0.6721,
"step": 2540
},
{
"epoch": 13.56,
"learning_rate": 0.00012725,
"loss": 0.5703,
"step": 2550
},
{
"epoch": 13.62,
"learning_rate": 0.00012775000000000002,
"loss": 0.4654,
"step": 2560
},
{
"epoch": 13.67,
"learning_rate": 0.00012825,
"loss": 0.4402,
"step": 2570
},
{
"epoch": 13.72,
"learning_rate": 0.00012875,
"loss": 0.4534,
"step": 2580
},
{
"epoch": 13.78,
"learning_rate": 0.00012925,
"loss": 0.5178,
"step": 2590
},
{
"epoch": 13.83,
"learning_rate": 0.00012975,
"loss": 0.5167,
"step": 2600
},
{
"epoch": 13.88,
"learning_rate": 0.00013025,
"loss": 0.4782,
"step": 2610
},
{
"epoch": 13.94,
"learning_rate": 0.00013075,
"loss": 0.4171,
"step": 2620
},
{
"epoch": 13.99,
"learning_rate": 0.00013125000000000002,
"loss": 0.3338,
"step": 2630
},
{
"epoch": 14.04,
"learning_rate": 0.00013175,
"loss": 0.523,
"step": 2640
},
{
"epoch": 14.1,
"learning_rate": 0.00013225000000000002,
"loss": 0.5211,
"step": 2650
},
{
"epoch": 14.15,
"learning_rate": 0.00013275,
"loss": 0.3958,
"step": 2660
},
{
"epoch": 14.2,
"learning_rate": 0.00013325,
"loss": 0.3883,
"step": 2670
},
{
"epoch": 14.26,
"learning_rate": 0.00013375,
"loss": 0.466,
"step": 2680
},
{
"epoch": 14.31,
"learning_rate": 0.00013425,
"loss": 0.563,
"step": 2690
},
{
"epoch": 14.36,
"learning_rate": 0.00013475000000000002,
"loss": 0.6435,
"step": 2700
},
{
"epoch": 14.36,
"eval_accuracy": 0.8466666666666667,
"eval_combined_score": 0.820593120110759,
"eval_f1": 0.8092415776379762,
"eval_loss": 0.5365216135978699,
"eval_precision": 0.7797975694717267,
"eval_recall": 0.8466666666666667,
"eval_runtime": 5.7927,
"eval_samples_per_second": 258.944,
"eval_steps_per_second": 8.114,
"step": 2700
},
{
"epoch": 14.41,
"learning_rate": 0.00013525,
"loss": 0.4351,
"step": 2710
},
{
"epoch": 14.47,
"learning_rate": 0.00013575000000000002,
"loss": 0.9678,
"step": 2720
},
{
"epoch": 14.52,
"learning_rate": 0.00013625,
"loss": 0.3769,
"step": 2730
},
{
"epoch": 14.57,
"learning_rate": 0.00013675000000000002,
"loss": 0.6706,
"step": 2740
},
{
"epoch": 14.63,
"learning_rate": 0.00013725,
"loss": 0.6711,
"step": 2750
},
{
"epoch": 14.68,
"learning_rate": 0.00013775000000000001,
"loss": 0.5355,
"step": 2760
},
{
"epoch": 14.73,
"learning_rate": 0.00013825000000000003,
"loss": 0.6193,
"step": 2770
},
{
"epoch": 14.79,
"learning_rate": 0.00013875,
"loss": 0.6431,
"step": 2780
},
{
"epoch": 14.84,
"learning_rate": 0.00013925000000000002,
"loss": 0.6239,
"step": 2790
},
{
"epoch": 14.89,
"learning_rate": 0.00013975,
"loss": 0.4647,
"step": 2800
},
{
"epoch": 14.95,
"learning_rate": 0.00014025000000000002,
"loss": 0.2059,
"step": 2810
},
{
"epoch": 15.0,
"learning_rate": 0.00014074999999999998,
"loss": 0.6128,
"step": 2820
},
{
"epoch": 15.05,
"learning_rate": 0.00014125,
"loss": 0.9306,
"step": 2830
},
{
"epoch": 15.11,
"learning_rate": 0.00014175,
"loss": 0.4907,
"step": 2840
},
{
"epoch": 15.16,
"learning_rate": 0.00014225,
"loss": 0.4597,
"step": 2850
},
{
"epoch": 15.21,
"learning_rate": 0.00014275,
"loss": 0.7004,
"step": 2860
},
{
"epoch": 15.27,
"learning_rate": 0.00014324999999999999,
"loss": 0.4713,
"step": 2870
},
{
"epoch": 15.32,
"learning_rate": 0.00014375,
"loss": 0.5127,
"step": 2880
},
{
"epoch": 15.37,
"learning_rate": 0.00014424999999999998,
"loss": 0.7406,
"step": 2890
},
{
"epoch": 15.43,
"learning_rate": 0.00014475,
"loss": 0.5231,
"step": 2900
},
{
"epoch": 15.48,
"learning_rate": 0.00014524999999999998,
"loss": 0.5013,
"step": 2910
},
{
"epoch": 15.53,
"learning_rate": 0.00014575,
"loss": 0.4772,
"step": 2920
},
{
"epoch": 15.59,
"learning_rate": 0.00014625,
"loss": 0.5269,
"step": 2930
},
{
"epoch": 15.64,
"learning_rate": 0.00014675,
"loss": 0.7292,
"step": 2940
},
{
"epoch": 15.69,
"learning_rate": 0.00014725,
"loss": 0.5534,
"step": 2950
},
{
"epoch": 15.74,
"learning_rate": 0.00014774999999999999,
"loss": 0.7513,
"step": 2960
},
{
"epoch": 15.8,
"learning_rate": 0.00014825,
"loss": 0.661,
"step": 2970
},
{
"epoch": 15.85,
"learning_rate": 0.00014874999999999998,
"loss": 0.8045,
"step": 2980
},
{
"epoch": 15.9,
"learning_rate": 0.00014925,
"loss": 0.8469,
"step": 2990
},
{
"epoch": 15.96,
"learning_rate": 0.00014975,
"loss": 0.9304,
"step": 3000
},
{
"epoch": 15.96,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6841020585693436,
"eval_f1": 0.6288777491861415,
"eval_loss": 0.757703959941864,
"eval_precision": 0.6301971517578995,
"eval_recall": 0.7386666666666667,
"eval_runtime": 5.7335,
"eval_samples_per_second": 261.622,
"eval_steps_per_second": 8.197,
"step": 3000
},
{
"epoch": 16.01,
"learning_rate": 0.00015025,
"loss": 0.6005,
"step": 3010
},
{
"epoch": 16.06,
"learning_rate": 0.00015075,
"loss": 0.9853,
"step": 3020
},
{
"epoch": 16.12,
"learning_rate": 0.00015125,
"loss": 0.9841,
"step": 3030
},
{
"epoch": 16.17,
"learning_rate": 0.00015175,
"loss": 0.8429,
"step": 3040
},
{
"epoch": 16.22,
"learning_rate": 0.00015225,
"loss": 0.5311,
"step": 3050
},
{
"epoch": 16.28,
"learning_rate": 0.00015275,
"loss": 0.8929,
"step": 3060
},
{
"epoch": 16.33,
"learning_rate": 0.00015325,
"loss": 0.6568,
"step": 3070
},
{
"epoch": 16.38,
"learning_rate": 0.00015375,
"loss": 0.7808,
"step": 3080
},
{
"epoch": 16.44,
"learning_rate": 0.00015425,
"loss": 0.8071,
"step": 3090
},
{
"epoch": 16.49,
"learning_rate": 0.00015475,
"loss": 0.6082,
"step": 3100
},
{
"epoch": 16.54,
"learning_rate": 0.00015525,
"loss": 0.8183,
"step": 3110
},
{
"epoch": 16.6,
"learning_rate": 0.00015575,
"loss": 0.8457,
"step": 3120
},
{
"epoch": 16.65,
"learning_rate": 0.00015625,
"loss": 0.8111,
"step": 3130
},
{
"epoch": 16.7,
"learning_rate": 0.00015675000000000002,
"loss": 0.8024,
"step": 3140
},
{
"epoch": 16.76,
"learning_rate": 0.00015725,
"loss": 0.5843,
"step": 3150
},
{
"epoch": 16.81,
"learning_rate": 0.00015775,
"loss": 0.7493,
"step": 3160
},
{
"epoch": 16.86,
"learning_rate": 0.00015825,
"loss": 0.6283,
"step": 3170
},
{
"epoch": 16.91,
"learning_rate": 0.00015875,
"loss": 0.7267,
"step": 3180
},
{
"epoch": 16.97,
"learning_rate": 0.00015925,
"loss": 0.8913,
"step": 3190
},
{
"epoch": 17.02,
"learning_rate": 0.00015975,
"loss": 0.8809,
"step": 3200
},
{
"epoch": 17.07,
"learning_rate": 0.00016025000000000002,
"loss": 0.7423,
"step": 3210
},
{
"epoch": 17.13,
"learning_rate": 0.00016075,
"loss": 0.7022,
"step": 3220
},
{
"epoch": 17.18,
"learning_rate": 0.00016125000000000002,
"loss": 0.672,
"step": 3230
},
{
"epoch": 17.23,
"learning_rate": 0.00016175,
"loss": 0.7071,
"step": 3240
},
{
"epoch": 17.29,
"learning_rate": 0.00016225000000000001,
"loss": 0.7613,
"step": 3250
},
{
"epoch": 17.34,
"learning_rate": 0.00016275,
"loss": 0.7014,
"step": 3260
},
{
"epoch": 17.39,
"learning_rate": 0.00016325,
"loss": 0.7322,
"step": 3270
},
{
"epoch": 17.45,
"learning_rate": 0.00016375000000000002,
"loss": 0.8469,
"step": 3280
},
{
"epoch": 17.5,
"learning_rate": 0.00016425,
"loss": 0.647,
"step": 3290
},
{
"epoch": 17.55,
"learning_rate": 0.00016475000000000002,
"loss": 0.7902,
"step": 3300
},
{
"epoch": 17.55,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6841020585693436,
"eval_f1": 0.6288777491861415,
"eval_loss": 0.7684083580970764,
"eval_precision": 0.6301971517578995,
"eval_recall": 0.7386666666666667,
"eval_runtime": 5.6811,
"eval_samples_per_second": 264.032,
"eval_steps_per_second": 8.273,
"step": 3300
},
{
"epoch": 17.61,
"learning_rate": 0.00016525,
"loss": 0.7717,
"step": 3310
},
{
"epoch": 17.66,
"learning_rate": 0.00016575000000000002,
"loss": 0.8894,
"step": 3320
},
{
"epoch": 17.71,
"learning_rate": 0.00016625,
"loss": 0.9062,
"step": 3330
},
{
"epoch": 17.77,
"learning_rate": 0.00016675000000000001,
"loss": 0.755,
"step": 3340
},
{
"epoch": 17.82,
"learning_rate": 0.00016725000000000003,
"loss": 0.6708,
"step": 3350
},
{
"epoch": 17.87,
"learning_rate": 0.00016775,
"loss": 0.8674,
"step": 3360
},
{
"epoch": 17.93,
"learning_rate": 0.00016825000000000002,
"loss": 0.7541,
"step": 3370
},
{
"epoch": 17.98,
"learning_rate": 0.00016875,
"loss": 0.8417,
"step": 3380
},
{
"epoch": 18.03,
"learning_rate": 0.00016925000000000002,
"loss": 0.8044,
"step": 3390
},
{
"epoch": 18.09,
"learning_rate": 0.00016975,
"loss": 0.7059,
"step": 3400
},
{
"epoch": 18.14,
"learning_rate": 0.00017025000000000002,
"loss": 0.7291,
"step": 3410
},
{
"epoch": 18.19,
"learning_rate": 0.00017075,
"loss": 0.8393,
"step": 3420
},
{
"epoch": 18.24,
"learning_rate": 0.00017125000000000002,
"loss": 0.6944,
"step": 3430
},
{
"epoch": 18.3,
"learning_rate": 0.00017175000000000003,
"loss": 0.7587,
"step": 3440
},
{
"epoch": 18.35,
"learning_rate": 0.00017224999999999999,
"loss": 0.8562,
"step": 3450
},
{
"epoch": 18.4,
"learning_rate": 0.00017275,
"loss": 0.8328,
"step": 3460
},
{
"epoch": 18.46,
"learning_rate": 0.00017324999999999998,
"loss": 0.7379,
"step": 3470
},
{
"epoch": 18.51,
"learning_rate": 0.00017375,
"loss": 0.8784,
"step": 3480
},
{
"epoch": 18.56,
"learning_rate": 0.00017424999999999998,
"loss": 0.8329,
"step": 3490
},
{
"epoch": 18.62,
"learning_rate": 0.00017475,
"loss": 0.6559,
"step": 3500
},
{
"epoch": 18.67,
"learning_rate": 0.00017525,
"loss": 0.8082,
"step": 3510
},
{
"epoch": 18.72,
"learning_rate": 0.00017575,
"loss": 0.7626,
"step": 3520
},
{
"epoch": 18.78,
"learning_rate": 0.00017625,
"loss": 0.7877,
"step": 3530
},
{
"epoch": 18.83,
"learning_rate": 0.00017675,
"loss": 0.7847,
"step": 3540
},
{
"epoch": 18.88,
"learning_rate": 0.00017725,
"loss": 0.5692,
"step": 3550
},
{
"epoch": 18.94,
"learning_rate": 0.00017774999999999998,
"loss": 0.8115,
"step": 3560
},
{
"epoch": 18.99,
"learning_rate": 0.00017825,
"loss": 0.7631,
"step": 3570
},
{
"epoch": 19.04,
"learning_rate": 0.00017875,
"loss": 0.7847,
"step": 3580
},
{
"epoch": 19.1,
"learning_rate": 0.00017925,
"loss": 0.7622,
"step": 3590
},
{
"epoch": 19.15,
"learning_rate": 0.00017975,
"loss": 0.6364,
"step": 3600
},
{
"epoch": 19.15,
"eval_accuracy": 0.7386666666666667,
"eval_combined_score": 0.6841020585693436,
"eval_f1": 0.6288777491861415,
"eval_loss": 0.7637550234794617,
"eval_precision": 0.6301971517578995,
"eval_recall": 0.7386666666666667,
"eval_runtime": 5.9956,
"eval_samples_per_second": 250.184,
"eval_steps_per_second": 7.839,
"step": 3600
},
{
"epoch": 19.2,
"learning_rate": 0.00018025,
"loss": 0.8643,
"step": 3610
},
{
"epoch": 19.26,
"learning_rate": 0.00018075,
"loss": 0.656,
"step": 3620
},
{
"epoch": 19.31,
"learning_rate": 0.00018125,
"loss": 0.6252,
"step": 3630
},
{
"epoch": 19.36,
"learning_rate": 0.00018175,
"loss": 0.8049,
"step": 3640
},
{
"epoch": 19.41,
"learning_rate": 0.00018225,
"loss": 0.8622,
"step": 3650
},
{
"epoch": 19.47,
"learning_rate": 0.00018275,
"loss": 0.8585,
"step": 3660
},
{
"epoch": 19.52,
"learning_rate": 0.00018325,
"loss": 0.7333,
"step": 3670
},
{
"epoch": 19.57,
"learning_rate": 0.00018375,
"loss": 0.7186,
"step": 3680
},
{
"epoch": 19.63,
"learning_rate": 0.00018425,
"loss": 0.7759,
"step": 3690
},
{
"epoch": 19.68,
"learning_rate": 0.00018475,
"loss": 0.7912,
"step": 3700
},
{
"epoch": 19.73,
"learning_rate": 0.00018525,
"loss": 0.8636,
"step": 3710
},
{
"epoch": 19.79,
"learning_rate": 0.00018575000000000002,
"loss": 0.8167,
"step": 3720
},
{
"epoch": 19.84,
"learning_rate": 0.00018625,
"loss": 0.5816,
"step": 3730
},
{
"epoch": 19.89,
"learning_rate": 0.00018675,
"loss": 0.8881,
"step": 3740
},
{
"epoch": 19.95,
"learning_rate": 0.00018725,
"loss": 0.8232,
"step": 3750
},
{
"epoch": 20.0,
"learning_rate": 0.00018775,
"loss": 0.7109,
"step": 3760
},
{
"epoch": 20.05,
"learning_rate": 0.00018825,
"loss": 0.8016,
"step": 3770
},
{
"epoch": 20.11,
"learning_rate": 0.00018875,
"loss": 0.6983,
"step": 3780
},
{
"epoch": 20.16,
"learning_rate": 0.00018925,
"loss": 0.9032,
"step": 3790
},
{
"epoch": 20.21,
"learning_rate": 0.00018975,
"loss": 0.839,
"step": 3800
},
{
"epoch": 20.27,
"learning_rate": 0.00019025000000000002,
"loss": 0.8061,
"step": 3810
},
{
"epoch": 20.32,
"learning_rate": 0.00019075,
"loss": 0.7371,
"step": 3820
},
{
"epoch": 20.37,
"learning_rate": 0.00019125000000000001,
"loss": 0.7358,
"step": 3830
},
{
"epoch": 20.43,
"learning_rate": 0.00019175,
"loss": 0.6059,
"step": 3840
},
{
"epoch": 20.48,
"learning_rate": 0.00019225,
"loss": 0.8188,
"step": 3850
},
{
"epoch": 20.53,
"learning_rate": 0.00019275,
"loss": 0.7803,
"step": 3860
},
{
"epoch": 20.59,
"learning_rate": 0.00019325,
"loss": 0.7161,
"step": 3870
},
{
"epoch": 20.64,
"learning_rate": 0.00019375000000000002,
"loss": 0.6724,
"step": 3880
},
{
"epoch": 20.69,
"learning_rate": 0.00019425,
"loss": 0.7061,
"step": 3890
},
{
"epoch": 20.74,
"learning_rate": 0.00019475000000000002,
"loss": 0.6738,
"step": 3900
},
{
"epoch": 20.74,
"eval_accuracy": 0.7393333333333333,
"eval_combined_score": 0.7056336725949668,
"eval_f1": 0.6292089176424869,
"eval_loss": 0.7768693566322327,
"eval_precision": 0.7146591060707139,
"eval_recall": 0.7393333333333333,
"eval_runtime": 5.8568,
"eval_samples_per_second": 256.113,
"eval_steps_per_second": 8.025,
"step": 3900
},
{
"epoch": 20.8,
"learning_rate": 0.00019525,
"loss": 0.694,
"step": 3910
},
{
"epoch": 20.85,
"learning_rate": 0.00019575000000000001,
"loss": 1.0223,
"step": 3920
},
{
"epoch": 20.9,
"learning_rate": 0.00019625,
"loss": 0.7801,
"step": 3930
},
{
"epoch": 20.96,
"learning_rate": 0.00019675,
"loss": 0.6794,
"step": 3940
},
{
"epoch": 21.01,
"learning_rate": 0.00019725000000000002,
"loss": 0.8515,
"step": 3950
},
{
"epoch": 21.06,
"learning_rate": 0.00019775,
"loss": 0.8019,
"step": 3960
},
{
"epoch": 21.12,
"learning_rate": 0.00019825000000000002,
"loss": 0.8918,
"step": 3970
},
{
"epoch": 21.17,
"learning_rate": 0.00019875,
"loss": 0.7041,
"step": 3980
},
{
"epoch": 21.22,
"learning_rate": 0.00019925000000000002,
"loss": 0.7506,
"step": 3990
},
{
"epoch": 21.28,
"learning_rate": 0.00019975,
"loss": 0.9895,
"step": 4000
},
{
"epoch": 21.33,
"learning_rate": 0.00020025000000000002,
"loss": 0.6327,
"step": 4010
},
{
"epoch": 21.38,
"learning_rate": 0.00020075000000000003,
"loss": 0.7891,
"step": 4020
},
{
"epoch": 21.44,
"learning_rate": 0.00020125,
"loss": 0.6668,
"step": 4030
},
{
"epoch": 21.49,
"learning_rate": 0.00020175000000000003,
"loss": 0.7532,
"step": 4040
},
{
"epoch": 21.54,
"learning_rate": 0.00020225,
"loss": 0.7809,
"step": 4050
},
{
"epoch": 21.6,
"learning_rate": 0.00020275000000000002,
"loss": 0.6936,
"step": 4060
},
{
"epoch": 21.65,
"learning_rate": 0.00020324999999999998,
"loss": 0.7121,
"step": 4070
},
{
"epoch": 21.7,
"learning_rate": 0.00020375,
"loss": 0.9925,
"step": 4080
},
{
"epoch": 21.76,
"learning_rate": 0.00020425,
"loss": 0.8201,
"step": 4090
},
{
"epoch": 21.81,
"learning_rate": 0.00020475,
"loss": 0.6287,
"step": 4100
},
{
"epoch": 21.86,
"learning_rate": 0.00020525,
"loss": 0.8232,
"step": 4110
},
{
"epoch": 21.91,
"learning_rate": 0.00020575,
"loss": 0.7285,
"step": 4120
},
{
"epoch": 21.97,
"learning_rate": 0.00020625,
"loss": 0.7564,
"step": 4130
},
{
"epoch": 22.02,
"learning_rate": 0.00020674999999999998,
"loss": 0.8331,
"step": 4140
},
{
"epoch": 22.07,
"learning_rate": 0.00020725,
"loss": 0.7732,
"step": 4150
},
{
"epoch": 22.13,
"learning_rate": 0.00020774999999999998,
"loss": 0.7252,
"step": 4160
},
{
"epoch": 22.18,
"learning_rate": 0.00020825,
"loss": 0.6347,
"step": 4170
},
{
"epoch": 22.23,
"learning_rate": 0.00020875,
"loss": 0.7721,
"step": 4180
},
{
"epoch": 22.29,
"learning_rate": 0.00020925,
"loss": 0.7649,
"step": 4190
},
{
"epoch": 22.34,
"learning_rate": 0.00020975,
"loss": 0.8142,
"step": 4200
},
{
"epoch": 22.34,
"eval_accuracy": 0.7393333333333333,
"eval_combined_score": 0.7056336725949668,
"eval_f1": 0.6292089176424869,
"eval_loss": 0.744327962398529,
"eval_precision": 0.7146591060707139,
"eval_recall": 0.7393333333333333,
"eval_runtime": 5.7187,
"eval_samples_per_second": 262.296,
"eval_steps_per_second": 8.219,
"step": 4200
},
{
"epoch": 22.39,
"learning_rate": 0.00021025,
"loss": 0.7605,
"step": 4210
},
{
"epoch": 22.45,
"learning_rate": 0.00021075,
"loss": 0.7106,
"step": 4220
},
{
"epoch": 22.5,
"learning_rate": 0.00021124999999999998,
"loss": 0.7094,
"step": 4230
},
{
"epoch": 22.55,
"learning_rate": 0.00021175,
"loss": 0.8416,
"step": 4240
},
{
"epoch": 22.61,
"learning_rate": 0.00021225,
"loss": 0.7271,
"step": 4250
},
{
"epoch": 22.66,
"learning_rate": 0.00021275,
"loss": 0.8397,
"step": 4260
},
{
"epoch": 22.71,
"learning_rate": 0.00021325,
"loss": 0.8801,
"step": 4270
},
{
"epoch": 22.77,
"learning_rate": 0.00021375,
"loss": 0.8683,
"step": 4280
},
{
"epoch": 22.82,
"learning_rate": 0.00021425,
"loss": 0.7017,
"step": 4290
},
{
"epoch": 22.87,
"learning_rate": 0.00021475,
"loss": 0.8673,
"step": 4300
},
{
"epoch": 22.93,
"learning_rate": 0.00021525,
"loss": 0.6106,
"step": 4310
},
{
"epoch": 22.98,
"learning_rate": 0.00021575,
"loss": 0.7888,
"step": 4320
},
{
"epoch": 23.03,
"learning_rate": 0.00021625,
"loss": 0.7133,
"step": 4330
},
{
"epoch": 23.09,
"learning_rate": 0.00021675,
"loss": 0.7322,
"step": 4340
},
{
"epoch": 23.14,
"learning_rate": 0.00021725,
"loss": 0.5461,
"step": 4350
},
{
"epoch": 23.19,
"learning_rate": 0.00021775,
"loss": 0.7274,
"step": 4360
},
{
"epoch": 23.24,
"learning_rate": 0.00021825,
"loss": 1.1518,
"step": 4370
},
{
"epoch": 23.3,
"learning_rate": 0.00021875,
"loss": 0.8713,
"step": 4380
},
{
"epoch": 23.35,
"learning_rate": 0.00021925000000000002,
"loss": 0.8016,
"step": 4390
},
{
"epoch": 23.4,
"learning_rate": 0.00021975,
"loss": 0.7848,
"step": 4400
},
{
"epoch": 23.46,
"learning_rate": 0.00022025000000000001,
"loss": 0.9202,
"step": 4410
},
{
"epoch": 23.51,
"learning_rate": 0.00022075,
"loss": 0.6641,
"step": 4420
},
{
"epoch": 23.56,
"learning_rate": 0.00022125,
"loss": 0.7703,
"step": 4430
},
{
"epoch": 23.62,
"learning_rate": 0.00022175,
"loss": 0.7311,
"step": 4440
},
{
"epoch": 23.67,
"learning_rate": 0.00022225,
"loss": 0.5956,
"step": 4450
},
{
"epoch": 23.72,
"learning_rate": 0.00022275000000000002,
"loss": 0.7111,
"step": 4460
},
{
"epoch": 23.78,
"learning_rate": 0.00022325,
"loss": 0.7672,
"step": 4470
},
{
"epoch": 23.83,
"learning_rate": 0.00022375000000000002,
"loss": 0.8842,
"step": 4480
},
{
"epoch": 23.88,
"learning_rate": 0.00022425,
"loss": 0.8225,
"step": 4490
},
{
"epoch": 23.94,
"learning_rate": 0.00022475000000000001,
"loss": 0.8184,
"step": 4500
},
{
"epoch": 23.94,
"eval_accuracy": 0.7393333333333333,
"eval_combined_score": 0.7056336725949668,
"eval_f1": 0.6292089176424869,
"eval_loss": 0.7635167837142944,
"eval_precision": 0.7146591060707139,
"eval_recall": 0.7393333333333333,
"eval_runtime": 6.1889,
"eval_samples_per_second": 242.371,
"eval_steps_per_second": 7.594,
"step": 4500
},
{
"epoch": 23.99,
"learning_rate": 0.00022525,
"loss": 0.8185,
"step": 4510
},
{
"epoch": 24.04,
"learning_rate": 0.00022575,
"loss": 0.7461,
"step": 4520
},
{
"epoch": 24.1,
"learning_rate": 0.00022625000000000002,
"loss": 0.6885,
"step": 4530
},
{
"epoch": 24.15,
"learning_rate": 0.00022675,
"loss": 0.8025,
"step": 4540
},
{
"epoch": 24.2,
"learning_rate": 0.00022725000000000002,
"loss": 0.6607,
"step": 4550
},
{
"epoch": 24.26,
"learning_rate": 0.00022775,
"loss": 0.7011,
"step": 4560
},
{
"epoch": 24.31,
"learning_rate": 0.00022825000000000002,
"loss": 0.6394,
"step": 4570
},
{
"epoch": 24.36,
"learning_rate": 0.00022875,
"loss": 0.8336,
"step": 4580
},
{
"epoch": 24.41,
"learning_rate": 0.00022925000000000002,
"loss": 0.8099,
"step": 4590
},
{
"epoch": 24.47,
"learning_rate": 0.00022975000000000003,
"loss": 0.6199,
"step": 4600
},
{
"epoch": 24.52,
"learning_rate": 0.00023025,
"loss": 0.8079,
"step": 4610
},
{
"epoch": 24.57,
"learning_rate": 0.00023075000000000003,
"loss": 0.9195,
"step": 4620
},
{
"epoch": 24.63,
"learning_rate": 0.00023125,
"loss": 0.8569,
"step": 4630
},
{
"epoch": 24.68,
"learning_rate": 0.00023175000000000002,
"loss": 0.7448,
"step": 4640
},
{
"epoch": 24.73,
"learning_rate": 0.00023225,
"loss": 0.7706,
"step": 4650
},
{
"epoch": 24.79,
"learning_rate": 0.00023275000000000002,
"loss": 0.6306,
"step": 4660
},
{
"epoch": 24.84,
"learning_rate": 0.00023325,
"loss": 0.6033,
"step": 4670
},
{
"epoch": 24.89,
"learning_rate": 0.00023375000000000002,
"loss": 0.9749,
"step": 4680
},
{
"epoch": 24.95,
"learning_rate": 0.00023425000000000003,
"loss": 0.7738,
"step": 4690
},
{
"epoch": 25.0,
"learning_rate": 0.00023475,
"loss": 0.8824,
"step": 4700
},
{
"epoch": 25.05,
"learning_rate": 0.00023525,
"loss": 0.8072,
"step": 4710
},
{
"epoch": 25.11,
"learning_rate": 0.00023574999999999998,
"loss": 0.7295,
"step": 4720
},
{
"epoch": 25.16,
"learning_rate": 0.00023625,
"loss": 0.8466,
"step": 4730
},
{
"epoch": 25.21,
"learning_rate": 0.00023674999999999998,
"loss": 0.7498,
"step": 4740
},
{
"epoch": 25.27,
"learning_rate": 0.00023725,
"loss": 0.7199,
"step": 4750
},
{
"epoch": 25.32,
"learning_rate": 0.00023775,
"loss": 0.7826,
"step": 4760
},
{
"epoch": 25.37,
"learning_rate": 0.00023825,
"loss": 0.7767,
"step": 4770
},
{
"epoch": 25.43,
"learning_rate": 0.00023875,
"loss": 0.71,
"step": 4780
},
{
"epoch": 25.48,
"learning_rate": 0.00023925,
"loss": 0.8495,
"step": 4790
},
{
"epoch": 25.53,
"learning_rate": 0.00023975,
"loss": 0.7562,
"step": 4800
},
{
"epoch": 25.53,
"eval_accuracy": 0.7393333333333333,
"eval_combined_score": 0.7056336725949668,
"eval_f1": 0.6292089176424869,
"eval_loss": 0.7467172741889954,
"eval_precision": 0.7146591060707139,
"eval_recall": 0.7393333333333333,
"eval_runtime": 5.7487,
"eval_samples_per_second": 260.927,
"eval_steps_per_second": 8.176,
"step": 4800
}
],
"logging_steps": 10,
"max_steps": 5640,
"num_train_epochs": 30,
"save_steps": 300,
"total_flos": 1.00772435460096e+16,
"trial_name": null,
"trial_params": null
}