Llama-2-13b_clean-mc4-it / trainer_state.json
g8a9's picture
Upload folder using huggingface_hub
2f14001
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.006297236406637901,
"global_step": 10000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 4.3689,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 3.0166,
"step": 20
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.6587,
"step": 30
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.7002,
"step": 40
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.8247,
"step": 50
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.7709,
"step": 60
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5964,
"step": 70
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5285,
"step": 80
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.6166,
"step": 90
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.7509,
"step": 100
},
{
"epoch": 0.0,
"eval_loss": 2.828864097595215,
"eval_runtime": 25015.5353,
"eval_samples_per_second": 4.048,
"eval_steps_per_second": 2.024,
"step": 100
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.6819,
"step": 110
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5314,
"step": 120
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4678,
"step": 130
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5079,
"step": 140
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.6501,
"step": 150
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.6981,
"step": 160
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5262,
"step": 170
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4819,
"step": 180
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4657,
"step": 190
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.6072,
"step": 200
},
{
"epoch": 0.0,
"eval_loss": 2.7019286155700684,
"eval_runtime": 25020.9542,
"eval_samples_per_second": 4.048,
"eval_steps_per_second": 2.024,
"step": 200
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5656,
"step": 210
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5185,
"step": 220
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4271,
"step": 230
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4286,
"step": 240
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5728,
"step": 250
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5597,
"step": 260
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4337,
"step": 270
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4491,
"step": 280
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4494,
"step": 290
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5075,
"step": 300
},
{
"epoch": 0.0,
"eval_loss": 2.6475937366485596,
"eval_runtime": 25026.694,
"eval_samples_per_second": 4.047,
"eval_steps_per_second": 2.023,
"step": 300
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5654,
"step": 310
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.445,
"step": 320
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4604,
"step": 330
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4279,
"step": 340
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.545,
"step": 350
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.579,
"step": 360
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4052,
"step": 370
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3807,
"step": 380
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4444,
"step": 390
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4991,
"step": 400
},
{
"epoch": 0.0,
"eval_loss": 2.606245279312134,
"eval_runtime": 25030.0633,
"eval_samples_per_second": 4.046,
"eval_steps_per_second": 2.023,
"step": 400
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.6451,
"step": 410
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4054,
"step": 420
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4127,
"step": 430
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3986,
"step": 440
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4556,
"step": 450
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.531,
"step": 460
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4173,
"step": 470
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4098,
"step": 480
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3917,
"step": 490
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5342,
"step": 500
},
{
"epoch": 0.0,
"eval_loss": 2.553729772567749,
"eval_runtime": 25028.6332,
"eval_samples_per_second": 4.046,
"eval_steps_per_second": 2.023,
"step": 500
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5335,
"step": 510
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4117,
"step": 520
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3891,
"step": 530
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3963,
"step": 540
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4859,
"step": 550
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5574,
"step": 560
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4218,
"step": 570
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3816,
"step": 580
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3866,
"step": 590
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4992,
"step": 600
},
{
"epoch": 0.0,
"eval_loss": 2.5366227626800537,
"eval_runtime": 25013.3524,
"eval_samples_per_second": 4.049,
"eval_steps_per_second": 2.024,
"step": 600
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5315,
"step": 610
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4261,
"step": 620
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3737,
"step": 630
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.385,
"step": 640
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.405,
"step": 650
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5182,
"step": 660
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3498,
"step": 670
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3539,
"step": 680
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3276,
"step": 690
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4602,
"step": 700
},
{
"epoch": 0.0,
"eval_loss": 2.5101232528686523,
"eval_runtime": 25025.24,
"eval_samples_per_second": 4.047,
"eval_steps_per_second": 2.023,
"step": 700
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5107,
"step": 710
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3919,
"step": 720
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3818,
"step": 730
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3866,
"step": 740
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4079,
"step": 750
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4908,
"step": 760
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3965,
"step": 770
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.323,
"step": 780
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3136,
"step": 790
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3786,
"step": 800
},
{
"epoch": 0.0,
"eval_loss": 2.50821590423584,
"eval_runtime": 25013.6917,
"eval_samples_per_second": 4.049,
"eval_steps_per_second": 2.024,
"step": 800
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5106,
"step": 810
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3971,
"step": 820
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3305,
"step": 830
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3711,
"step": 840
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4803,
"step": 850
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4738,
"step": 860
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3712,
"step": 870
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3463,
"step": 880
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2843,
"step": 890
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3725,
"step": 900
},
{
"epoch": 0.0,
"eval_loss": 2.494638204574585,
"eval_runtime": 25014.3413,
"eval_samples_per_second": 4.049,
"eval_steps_per_second": 2.024,
"step": 900
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5215,
"step": 910
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3802,
"step": 920
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3499,
"step": 930
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3199,
"step": 940
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3491,
"step": 950
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4885,
"step": 960
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3633,
"step": 970
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3226,
"step": 980
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2587,
"step": 990
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3803,
"step": 1000
},
{
"epoch": 0.0,
"eval_loss": 2.458460807800293,
"eval_runtime": 25021.0121,
"eval_samples_per_second": 4.048,
"eval_steps_per_second": 2.024,
"step": 1000
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3921,
"step": 1010
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3305,
"step": 1020
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2907,
"step": 1030
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.319,
"step": 1040
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4507,
"step": 1050
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.467,
"step": 1060
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3639,
"step": 1070
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3189,
"step": 1080
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2974,
"step": 1090
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3331,
"step": 1100
},
{
"epoch": 0.0,
"eval_loss": 2.454998254776001,
"eval_runtime": 25014.8749,
"eval_samples_per_second": 4.049,
"eval_steps_per_second": 2.024,
"step": 1100
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4715,
"step": 1110
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3549,
"step": 1120
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3196,
"step": 1130
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2633,
"step": 1140
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3661,
"step": 1150
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4783,
"step": 1160
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3531,
"step": 1170
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2943,
"step": 1180
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2409,
"step": 1190
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3605,
"step": 1200
},
{
"epoch": 0.0,
"eval_loss": 2.448063611984253,
"eval_runtime": 25013.9619,
"eval_samples_per_second": 4.049,
"eval_steps_per_second": 2.024,
"step": 1200
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4612,
"step": 1210
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3746,
"step": 1220
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.304,
"step": 1230
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2925,
"step": 1240
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2926,
"step": 1250
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4145,
"step": 1260
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3593,
"step": 1270
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2417,
"step": 1280
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.301,
"step": 1290
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3336,
"step": 1300
},
{
"epoch": 0.0,
"eval_loss": 2.424609661102295,
"eval_runtime": 25025.8125,
"eval_samples_per_second": 4.047,
"eval_steps_per_second": 2.023,
"step": 1300
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4126,
"step": 1310
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.308,
"step": 1320
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3052,
"step": 1330
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2798,
"step": 1340
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3208,
"step": 1350
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3309,
"step": 1360
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.331,
"step": 1370
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3068,
"step": 1380
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1971,
"step": 1390
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3114,
"step": 1400
},
{
"epoch": 0.0,
"eval_loss": 2.4197137355804443,
"eval_runtime": 25013.8484,
"eval_samples_per_second": 4.049,
"eval_steps_per_second": 2.024,
"step": 1400
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4611,
"step": 1410
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2463,
"step": 1420
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2844,
"step": 1430
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2544,
"step": 1440
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3002,
"step": 1450
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4263,
"step": 1460
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.328,
"step": 1470
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2609,
"step": 1480
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2854,
"step": 1490
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3257,
"step": 1500
},
{
"epoch": 0.0,
"eval_loss": 2.407323122024536,
"eval_runtime": 25024.2416,
"eval_samples_per_second": 4.047,
"eval_steps_per_second": 2.024,
"step": 1500
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4174,
"step": 1510
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2817,
"step": 1520
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2796,
"step": 1530
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2834,
"step": 1540
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2803,
"step": 1550
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.39,
"step": 1560
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2672,
"step": 1570
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3054,
"step": 1580
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2576,
"step": 1590
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3099,
"step": 1600
},
{
"epoch": 0.0,
"eval_loss": 2.401474952697754,
"eval_runtime": 25023.95,
"eval_samples_per_second": 4.047,
"eval_steps_per_second": 2.024,
"step": 1600
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4225,
"step": 1610
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3135,
"step": 1620
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2705,
"step": 1630
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2075,
"step": 1640
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3811,
"step": 1650
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4239,
"step": 1660
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3319,
"step": 1670
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3106,
"step": 1680
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2231,
"step": 1690
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.311,
"step": 1700
},
{
"epoch": 0.0,
"eval_loss": 2.3863916397094727,
"eval_runtime": 25021.8392,
"eval_samples_per_second": 4.047,
"eval_steps_per_second": 2.024,
"step": 1700
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4332,
"step": 1710
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3183,
"step": 1720
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2177,
"step": 1730
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3045,
"step": 1740
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2627,
"step": 1750
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4087,
"step": 1760
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3026,
"step": 1770
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3316,
"step": 1780
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.256,
"step": 1790
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3276,
"step": 1800
},
{
"epoch": 0.0,
"eval_loss": 2.3831562995910645,
"eval_runtime": 25030.8877,
"eval_samples_per_second": 4.046,
"eval_steps_per_second": 2.023,
"step": 1800
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3993,
"step": 1810
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3138,
"step": 1820
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2652,
"step": 1830
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2848,
"step": 1840
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3009,
"step": 1850
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3942,
"step": 1860
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2951,
"step": 1870
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2457,
"step": 1880
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2514,
"step": 1890
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2656,
"step": 1900
},
{
"epoch": 0.0,
"eval_loss": 2.3777658939361572,
"eval_runtime": 25024.5627,
"eval_samples_per_second": 4.047,
"eval_steps_per_second": 2.023,
"step": 1900
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3702,
"step": 1910
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2896,
"step": 1920
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2635,
"step": 1930
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2506,
"step": 1940
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2108,
"step": 1950
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3469,
"step": 1960
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2863,
"step": 1970
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3095,
"step": 1980
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2594,
"step": 1990
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3124,
"step": 2000
},
{
"epoch": 0.0,
"eval_loss": 2.3710832595825195,
"eval_runtime": 25009.9377,
"eval_samples_per_second": 4.049,
"eval_steps_per_second": 2.025,
"step": 2000
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.42,
"step": 2010
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2725,
"step": 2020
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.243,
"step": 2030
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1696,
"step": 2040
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2764,
"step": 2050
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.4149,
"step": 2060
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3201,
"step": 2070
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2489,
"step": 2080
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1856,
"step": 2090
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.295,
"step": 2100
},
{
"epoch": 0.0,
"eval_loss": 2.3622617721557617,
"eval_runtime": 25023.6158,
"eval_samples_per_second": 4.047,
"eval_steps_per_second": 2.024,
"step": 2100
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3851,
"step": 2110
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2984,
"step": 2120
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.189,
"step": 2130
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2425,
"step": 2140
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.312,
"step": 2150
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3269,
"step": 2160
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3006,
"step": 2170
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2974,
"step": 2180
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1995,
"step": 2190
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3021,
"step": 2200
},
{
"epoch": 0.0,
"eval_loss": 2.356457471847534,
"eval_runtime": 25014.0777,
"eval_samples_per_second": 4.049,
"eval_steps_per_second": 2.024,
"step": 2200
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3836,
"step": 2210
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2795,
"step": 2220
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.196,
"step": 2230
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2284,
"step": 2240
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2464,
"step": 2250
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.406,
"step": 2260
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2814,
"step": 2270
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2595,
"step": 2280
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2578,
"step": 2290
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2471,
"step": 2300
},
{
"epoch": 0.0,
"eval_loss": 2.334439516067505,
"eval_runtime": 25021.2061,
"eval_samples_per_second": 4.048,
"eval_steps_per_second": 2.024,
"step": 2300
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3846,
"step": 2310
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2797,
"step": 2320
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2136,
"step": 2330
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2303,
"step": 2340
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3312,
"step": 2350
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3484,
"step": 2360
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3012,
"step": 2370
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2255,
"step": 2380
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1879,
"step": 2390
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2432,
"step": 2400
},
{
"epoch": 0.0,
"eval_loss": 2.3361294269561768,
"eval_runtime": 25017.0273,
"eval_samples_per_second": 4.048,
"eval_steps_per_second": 2.024,
"step": 2400
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3223,
"step": 2410
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2756,
"step": 2420
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2312,
"step": 2430
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2296,
"step": 2440
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2083,
"step": 2450
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3684,
"step": 2460
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2336,
"step": 2470
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2262,
"step": 2480
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1644,
"step": 2490
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3096,
"step": 2500
},
{
"epoch": 0.0,
"eval_loss": 2.336559772491455,
"eval_runtime": 25015.5454,
"eval_samples_per_second": 4.048,
"eval_steps_per_second": 2.024,
"step": 2500
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3185,
"step": 2510
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2768,
"step": 2520
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2151,
"step": 2530
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2017,
"step": 2540
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2616,
"step": 2550
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3333,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2404,
"step": 2570
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.25,
"step": 2580
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.22,
"step": 2590
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2884,
"step": 2600
},
{
"epoch": 0.0,
"eval_loss": 2.332972526550293,
"eval_runtime": 25018.5289,
"eval_samples_per_second": 4.048,
"eval_steps_per_second": 2.024,
"step": 2600
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3739,
"step": 2610
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2611,
"step": 2620
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2323,
"step": 2630
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1285,
"step": 2640
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2504,
"step": 2650
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3694,
"step": 2660
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2317,
"step": 2670
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2714,
"step": 2680
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1926,
"step": 2690
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2617,
"step": 2700
},
{
"epoch": 0.0,
"eval_loss": 2.325580596923828,
"eval_runtime": 25014.9463,
"eval_samples_per_second": 4.049,
"eval_steps_per_second": 2.024,
"step": 2700
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3665,
"step": 2710
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2604,
"step": 2720
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2129,
"step": 2730
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2166,
"step": 2740
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2418,
"step": 2750
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3793,
"step": 2760
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2684,
"step": 2770
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1758,
"step": 2780
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2116,
"step": 2790
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2753,
"step": 2800
},
{
"epoch": 0.0,
"eval_loss": 2.3111133575439453,
"eval_runtime": 25017.4138,
"eval_samples_per_second": 4.048,
"eval_steps_per_second": 2.024,
"step": 2800
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3754,
"step": 2810
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2508,
"step": 2820
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1793,
"step": 2830
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1444,
"step": 2840
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2093,
"step": 2850
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2917,
"step": 2860
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2487,
"step": 2870
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1931,
"step": 2880
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1862,
"step": 2890
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3007,
"step": 2900
},
{
"epoch": 0.0,
"eval_loss": 2.3113691806793213,
"eval_runtime": 25009.312,
"eval_samples_per_second": 4.049,
"eval_steps_per_second": 2.025,
"step": 2900
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3637,
"step": 2910
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2385,
"step": 2920
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2092,
"step": 2930
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1755,
"step": 2940
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2523,
"step": 2950
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3127,
"step": 2960
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2634,
"step": 2970
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2487,
"step": 2980
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1269,
"step": 2990
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1926,
"step": 3000
},
{
"epoch": 0.0,
"eval_loss": 2.2998297214508057,
"eval_runtime": 25014.9441,
"eval_samples_per_second": 4.049,
"eval_steps_per_second": 2.024,
"step": 3000
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3595,
"step": 3010
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2325,
"step": 3020
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1953,
"step": 3030
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.184,
"step": 3040
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1961,
"step": 3050
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.3776,
"step": 3060
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2627,
"step": 3070
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2189,
"step": 3080
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1835,
"step": 3090
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.2283,
"step": 3100
},
{
"epoch": 0.0,
"eval_loss": 2.2964084148406982,
"eval_runtime": 25012.2645,
"eval_samples_per_second": 4.049,
"eval_steps_per_second": 2.024,
"step": 3100
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1955,
"step": 3150
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1781,
"step": 3200
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1431,
"step": 3250
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1395,
"step": 3300
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1339,
"step": 3350
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1488,
"step": 3400
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1246,
"step": 3450
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1307,
"step": 3500
},
{
"epoch": 0.0,
"eval_loss": 2.2042970657348633,
"eval_runtime": 34108.0847,
"eval_samples_per_second": 2.969,
"eval_steps_per_second": 0.742,
"step": 3500
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1207,
"step": 3550
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1247,
"step": 3600
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1225,
"step": 3650
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0978,
"step": 3700
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1168,
"step": 3750
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1122,
"step": 3800
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1046,
"step": 3850
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1208,
"step": 3900
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1206,
"step": 3950
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1128,
"step": 4000
},
{
"epoch": 0.0,
"eval_loss": 2.1652708053588867,
"eval_runtime": 34110.436,
"eval_samples_per_second": 2.969,
"eval_steps_per_second": 0.742,
"step": 4000
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0952,
"step": 4050
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0932,
"step": 4100
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0884,
"step": 4150
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0733,
"step": 4200
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0889,
"step": 4250
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0845,
"step": 4300
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0734,
"step": 4350
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0829,
"step": 4400
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0784,
"step": 4450
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0669,
"step": 4500
},
{
"epoch": 0.0,
"eval_loss": 2.144939661026001,
"eval_runtime": 34106.0495,
"eval_samples_per_second": 2.969,
"eval_steps_per_second": 0.742,
"step": 4500
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0678,
"step": 4550
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0704,
"step": 4600
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0714,
"step": 4650
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0661,
"step": 4700
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0707,
"step": 4750
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0685,
"step": 4800
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0706,
"step": 4850
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0753,
"step": 4900
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.056,
"step": 4950
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0646,
"step": 5000
},
{
"epoch": 0.0,
"eval_loss": 2.1237690448760986,
"eval_runtime": 34108.4877,
"eval_samples_per_second": 2.969,
"eval_steps_per_second": 0.742,
"step": 5000
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.053,
"step": 5050
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0622,
"step": 5100
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0415,
"step": 5150
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0561,
"step": 5200
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0517,
"step": 5250
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0559,
"step": 5300
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0417,
"step": 5350
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0435,
"step": 5400
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0533,
"step": 5450
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0388,
"step": 5500
},
{
"epoch": 0.0,
"eval_loss": 2.109766960144043,
"eval_runtime": 34100.9613,
"eval_samples_per_second": 2.97,
"eval_steps_per_second": 0.742,
"step": 5500
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0524,
"step": 5550
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0521,
"step": 5600
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0356,
"step": 5650
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0565,
"step": 5700
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0341,
"step": 5750
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.041,
"step": 5800
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0378,
"step": 5850
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0388,
"step": 5900
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0456,
"step": 5950
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0391,
"step": 6000
},
{
"epoch": 0.0,
"eval_loss": 2.0924971103668213,
"eval_runtime": 34094.327,
"eval_samples_per_second": 2.97,
"eval_steps_per_second": 0.743,
"step": 6000
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0364,
"step": 6050
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.028,
"step": 6100
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0255,
"step": 6150
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0049,
"step": 6200
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0214,
"step": 6250
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0303,
"step": 6300
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0216,
"step": 6350
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0278,
"step": 6400
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.04,
"step": 6450
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0146,
"step": 6500
},
{
"epoch": 0.0,
"eval_loss": 2.082850217819214,
"eval_runtime": 34130.627,
"eval_samples_per_second": 2.967,
"eval_steps_per_second": 0.742,
"step": 6500
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0299,
"step": 6550
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0249,
"step": 6600
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0169,
"step": 6650
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0043,
"step": 6700
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0169,
"step": 6750
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0146,
"step": 6800
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0178,
"step": 6850
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.017,
"step": 6900
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0011,
"step": 6950
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.9961,
"step": 7000
},
{
"epoch": 0.0,
"eval_loss": 2.0665175914764404,
"eval_runtime": 34103.0381,
"eval_samples_per_second": 2.97,
"eval_steps_per_second": 0.742,
"step": 7000
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0201,
"step": 7050
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0165,
"step": 7100
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0071,
"step": 7150
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0038,
"step": 7200
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0074,
"step": 7250
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0009,
"step": 7300
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.9877,
"step": 7350
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.006,
"step": 7400
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.9915,
"step": 7450
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.993,
"step": 7500
},
{
"epoch": 0.0,
"eval_loss": 2.0603718757629395,
"eval_runtime": 34086.5352,
"eval_samples_per_second": 2.971,
"eval_steps_per_second": 0.743,
"step": 7500
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.9975,
"step": 7550
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.994,
"step": 7600
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.007,
"step": 7650
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0034,
"step": 7700
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0081,
"step": 7750
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.9855,
"step": 7800
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0026,
"step": 7850
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.0022,
"step": 7900
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 2.0013,
"step": 7950
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 2.0073,
"step": 8000
},
{
"epoch": 0.01,
"eval_loss": 2.050844669342041,
"eval_runtime": 34104.8601,
"eval_samples_per_second": 2.969,
"eval_steps_per_second": 0.742,
"step": 8000
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9936,
"step": 8050
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9682,
"step": 8100
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 2.0048,
"step": 8150
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9783,
"step": 8200
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9703,
"step": 8250
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 2.0042,
"step": 8300
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9848,
"step": 8350
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9808,
"step": 8400
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9871,
"step": 8450
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9733,
"step": 8500
},
{
"epoch": 0.01,
"eval_loss": 2.0437986850738525,
"eval_runtime": 34093.5093,
"eval_samples_per_second": 2.97,
"eval_steps_per_second": 0.743,
"step": 8500
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9796,
"step": 8550
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9943,
"step": 8600
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9722,
"step": 8650
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9835,
"step": 8700
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.963,
"step": 8750
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 2.0058,
"step": 8800
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9804,
"step": 8850
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9729,
"step": 8900
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9867,
"step": 8950
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.976,
"step": 9000
},
{
"epoch": 0.01,
"eval_loss": 2.041231155395508,
"eval_runtime": 34089.8046,
"eval_samples_per_second": 2.971,
"eval_steps_per_second": 0.743,
"step": 9000
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9773,
"step": 9050
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.964,
"step": 9100
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9648,
"step": 9150
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9843,
"step": 9200
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9677,
"step": 9250
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.962,
"step": 9300
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9953,
"step": 9350
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9665,
"step": 9400
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9724,
"step": 9450
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9576,
"step": 9500
},
{
"epoch": 0.01,
"eval_loss": 2.0336899757385254,
"eval_runtime": 34110.7491,
"eval_samples_per_second": 2.969,
"eval_steps_per_second": 0.742,
"step": 9500
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9817,
"step": 9550
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.952,
"step": 9600
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9693,
"step": 9650
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9827,
"step": 9700
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.979,
"step": 9750
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9666,
"step": 9800
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.987,
"step": 9850
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9596,
"step": 9900
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9663,
"step": 9950
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.9783,
"step": 10000
},
{
"epoch": 0.01,
"eval_loss": 2.0236124992370605,
"eval_runtime": 34103.4942,
"eval_samples_per_second": 2.97,
"eval_steps_per_second": 0.742,
"step": 10000
}
],
"max_steps": 10000,
"num_train_epochs": 1,
"total_flos": 3.2626731178471956e+19,
"trial_name": null,
"trial_params": null
}