UltimoUno's picture
Uploaded checkpoint-1000
a4e5f52 verified
raw
history blame
14.7 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.05,
"eval_steps": 1000,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"grad_norm": 118.0,
"learning_rate": 2.2000000000000002e-08,
"loss": 8.296,
"step": 10
},
{
"epoch": 0.0,
"grad_norm": 120.0,
"learning_rate": 4.4000000000000004e-08,
"loss": 8.3152,
"step": 20
},
{
"epoch": 0.0,
"grad_norm": 120.0,
"learning_rate": 6.6e-08,
"loss": 8.3217,
"step": 30
},
{
"epoch": 0.0,
"grad_norm": 117.0,
"learning_rate": 8.800000000000001e-08,
"loss": 8.3192,
"step": 40
},
{
"epoch": 0.0,
"grad_norm": 121.5,
"learning_rate": 1.1e-07,
"loss": 8.3432,
"step": 50
},
{
"epoch": 0.0,
"grad_norm": 120.5,
"learning_rate": 1.32e-07,
"loss": 8.3085,
"step": 60
},
{
"epoch": 0.0,
"grad_norm": 120.0,
"learning_rate": 1.5400000000000003e-07,
"loss": 8.3136,
"step": 70
},
{
"epoch": 0.0,
"grad_norm": 116.5,
"learning_rate": 1.7600000000000001e-07,
"loss": 8.3053,
"step": 80
},
{
"epoch": 0.0,
"grad_norm": 119.0,
"learning_rate": 1.98e-07,
"loss": 8.3401,
"step": 90
},
{
"epoch": 0.01,
"grad_norm": 119.0,
"learning_rate": 2.2e-07,
"loss": 8.2908,
"step": 100
},
{
"epoch": 0.01,
"grad_norm": 119.5,
"learning_rate": 2.42e-07,
"loss": 8.3283,
"step": 110
},
{
"epoch": 0.01,
"grad_norm": 119.5,
"learning_rate": 2.64e-07,
"loss": 8.2985,
"step": 120
},
{
"epoch": 0.01,
"grad_norm": 117.0,
"learning_rate": 2.8600000000000005e-07,
"loss": 8.2882,
"step": 130
},
{
"epoch": 0.01,
"grad_norm": 115.5,
"learning_rate": 3.0800000000000006e-07,
"loss": 8.2644,
"step": 140
},
{
"epoch": 0.01,
"grad_norm": 114.5,
"learning_rate": 3.3e-07,
"loss": 8.2033,
"step": 150
},
{
"epoch": 0.01,
"grad_norm": 115.5,
"learning_rate": 3.5200000000000003e-07,
"loss": 8.1953,
"step": 160
},
{
"epoch": 0.01,
"grad_norm": 113.5,
"learning_rate": 3.7400000000000004e-07,
"loss": 8.1654,
"step": 170
},
{
"epoch": 0.01,
"grad_norm": 116.5,
"learning_rate": 3.96e-07,
"loss": 8.1758,
"step": 180
},
{
"epoch": 0.01,
"grad_norm": 116.5,
"learning_rate": 4.18e-07,
"loss": 8.1881,
"step": 190
},
{
"epoch": 0.01,
"grad_norm": 111.0,
"learning_rate": 4.4e-07,
"loss": 8.0965,
"step": 200
},
{
"epoch": 0.01,
"grad_norm": 112.0,
"learning_rate": 4.62e-07,
"loss": 8.1027,
"step": 210
},
{
"epoch": 0.01,
"grad_norm": 112.0,
"learning_rate": 4.84e-07,
"loss": 8.0656,
"step": 220
},
{
"epoch": 0.01,
"grad_norm": 113.0,
"learning_rate": 5.06e-07,
"loss": 8.0485,
"step": 230
},
{
"epoch": 0.01,
"grad_norm": 113.0,
"learning_rate": 5.28e-07,
"loss": 8.0212,
"step": 240
},
{
"epoch": 0.01,
"grad_norm": 110.0,
"learning_rate": 5.5e-07,
"loss": 7.9518,
"step": 250
},
{
"epoch": 0.01,
"grad_norm": 107.5,
"learning_rate": 5.720000000000001e-07,
"loss": 7.9086,
"step": 260
},
{
"epoch": 0.01,
"grad_norm": 106.0,
"learning_rate": 5.94e-07,
"loss": 7.8287,
"step": 270
},
{
"epoch": 0.01,
"grad_norm": 105.0,
"learning_rate": 6.160000000000001e-07,
"loss": 7.7678,
"step": 280
},
{
"epoch": 0.01,
"grad_norm": 108.5,
"learning_rate": 6.38e-07,
"loss": 7.7167,
"step": 290
},
{
"epoch": 0.01,
"grad_norm": 102.0,
"learning_rate": 6.6e-07,
"loss": 7.6403,
"step": 300
},
{
"epoch": 0.02,
"grad_norm": 100.0,
"learning_rate": 6.82e-07,
"loss": 7.5792,
"step": 310
},
{
"epoch": 0.02,
"grad_norm": 100.0,
"learning_rate": 7.040000000000001e-07,
"loss": 7.5038,
"step": 320
},
{
"epoch": 0.02,
"grad_norm": 103.5,
"learning_rate": 7.260000000000001e-07,
"loss": 7.4563,
"step": 330
},
{
"epoch": 0.02,
"grad_norm": 99.5,
"learning_rate": 7.480000000000001e-07,
"loss": 7.3818,
"step": 340
},
{
"epoch": 0.02,
"grad_norm": 104.5,
"learning_rate": 7.7e-07,
"loss": 7.3034,
"step": 350
},
{
"epoch": 0.02,
"grad_norm": 103.0,
"learning_rate": 7.92e-07,
"loss": 7.2297,
"step": 360
},
{
"epoch": 0.02,
"grad_norm": 99.5,
"learning_rate": 8.140000000000001e-07,
"loss": 7.1394,
"step": 370
},
{
"epoch": 0.02,
"grad_norm": 103.0,
"learning_rate": 8.36e-07,
"loss": 7.0762,
"step": 380
},
{
"epoch": 0.02,
"grad_norm": 102.5,
"learning_rate": 8.580000000000001e-07,
"loss": 7.0122,
"step": 390
},
{
"epoch": 0.02,
"grad_norm": 104.5,
"learning_rate": 8.8e-07,
"loss": 6.8935,
"step": 400
},
{
"epoch": 0.02,
"grad_norm": 99.0,
"learning_rate": 9.02e-07,
"loss": 6.7687,
"step": 410
},
{
"epoch": 0.02,
"grad_norm": 94.0,
"learning_rate": 9.24e-07,
"loss": 6.6825,
"step": 420
},
{
"epoch": 0.02,
"grad_norm": 93.5,
"learning_rate": 9.46e-07,
"loss": 6.568,
"step": 430
},
{
"epoch": 0.02,
"grad_norm": 89.5,
"learning_rate": 9.68e-07,
"loss": 6.4486,
"step": 440
},
{
"epoch": 0.02,
"grad_norm": 88.0,
"learning_rate": 9.9e-07,
"loss": 6.3358,
"step": 450
},
{
"epoch": 0.02,
"grad_norm": 85.5,
"learning_rate": 1.012e-06,
"loss": 6.196,
"step": 460
},
{
"epoch": 0.02,
"grad_norm": 84.0,
"learning_rate": 1.034e-06,
"loss": 6.0811,
"step": 470
},
{
"epoch": 0.02,
"grad_norm": 82.0,
"learning_rate": 1.056e-06,
"loss": 5.9429,
"step": 480
},
{
"epoch": 0.02,
"grad_norm": 82.0,
"learning_rate": 1.078e-06,
"loss": 5.8245,
"step": 490
},
{
"epoch": 0.03,
"grad_norm": 81.0,
"learning_rate": 1.1e-06,
"loss": 5.6819,
"step": 500
},
{
"epoch": 0.03,
"grad_norm": 81.5,
"learning_rate": 1.0975555555555557e-06,
"loss": 5.539,
"step": 510
},
{
"epoch": 0.03,
"grad_norm": 81.5,
"learning_rate": 1.095111111111111e-06,
"loss": 5.4188,
"step": 520
},
{
"epoch": 0.03,
"grad_norm": 81.5,
"learning_rate": 1.0926666666666667e-06,
"loss": 5.2885,
"step": 530
},
{
"epoch": 0.03,
"grad_norm": 82.0,
"learning_rate": 1.0902222222222224e-06,
"loss": 5.1496,
"step": 540
},
{
"epoch": 0.03,
"grad_norm": 81.5,
"learning_rate": 1.0877777777777778e-06,
"loss": 5.0336,
"step": 550
},
{
"epoch": 0.03,
"grad_norm": 82.0,
"learning_rate": 1.0853333333333334e-06,
"loss": 4.9006,
"step": 560
},
{
"epoch": 0.03,
"grad_norm": 81.5,
"learning_rate": 1.082888888888889e-06,
"loss": 4.7757,
"step": 570
},
{
"epoch": 0.03,
"grad_norm": 82.0,
"learning_rate": 1.0804444444444445e-06,
"loss": 4.6461,
"step": 580
},
{
"epoch": 0.03,
"grad_norm": 80.5,
"learning_rate": 1.078e-06,
"loss": 4.5267,
"step": 590
},
{
"epoch": 0.03,
"grad_norm": 82.0,
"learning_rate": 1.0755555555555555e-06,
"loss": 4.4198,
"step": 600
},
{
"epoch": 0.03,
"grad_norm": 83.0,
"learning_rate": 1.0731111111111111e-06,
"loss": 4.2895,
"step": 610
},
{
"epoch": 0.03,
"grad_norm": 83.5,
"learning_rate": 1.0706666666666668e-06,
"loss": 4.2099,
"step": 620
},
{
"epoch": 0.03,
"grad_norm": 84.0,
"learning_rate": 1.0682222222222224e-06,
"loss": 4.1181,
"step": 630
},
{
"epoch": 0.03,
"grad_norm": 82.0,
"learning_rate": 1.0657777777777778e-06,
"loss": 4.0069,
"step": 640
},
{
"epoch": 0.03,
"grad_norm": 82.0,
"learning_rate": 1.0633333333333335e-06,
"loss": 3.9045,
"step": 650
},
{
"epoch": 0.03,
"grad_norm": 82.0,
"learning_rate": 1.0608888888888889e-06,
"loss": 3.7913,
"step": 660
},
{
"epoch": 0.03,
"grad_norm": 82.5,
"learning_rate": 1.0584444444444445e-06,
"loss": 3.7172,
"step": 670
},
{
"epoch": 0.03,
"grad_norm": 82.5,
"learning_rate": 1.056e-06,
"loss": 3.6226,
"step": 680
},
{
"epoch": 0.03,
"grad_norm": 82.0,
"learning_rate": 1.0535555555555556e-06,
"loss": 3.5128,
"step": 690
},
{
"epoch": 0.04,
"grad_norm": 81.5,
"learning_rate": 1.0511111111111112e-06,
"loss": 3.4335,
"step": 700
},
{
"epoch": 0.04,
"grad_norm": 81.0,
"learning_rate": 1.0486666666666668e-06,
"loss": 3.3716,
"step": 710
},
{
"epoch": 0.04,
"grad_norm": 79.5,
"learning_rate": 1.0462222222222222e-06,
"loss": 3.2632,
"step": 720
},
{
"epoch": 0.04,
"grad_norm": 80.5,
"learning_rate": 1.0437777777777779e-06,
"loss": 3.2192,
"step": 730
},
{
"epoch": 0.04,
"grad_norm": 80.5,
"learning_rate": 1.0413333333333333e-06,
"loss": 3.1043,
"step": 740
},
{
"epoch": 0.04,
"grad_norm": 81.0,
"learning_rate": 1.038888888888889e-06,
"loss": 3.0207,
"step": 750
},
{
"epoch": 0.04,
"grad_norm": 80.0,
"learning_rate": 1.0364444444444445e-06,
"loss": 2.9501,
"step": 760
},
{
"epoch": 0.04,
"grad_norm": 79.5,
"learning_rate": 1.034e-06,
"loss": 2.9028,
"step": 770
},
{
"epoch": 0.04,
"grad_norm": 78.5,
"learning_rate": 1.0315555555555556e-06,
"loss": 2.8108,
"step": 780
},
{
"epoch": 0.04,
"grad_norm": 78.5,
"learning_rate": 1.0291111111111112e-06,
"loss": 2.7679,
"step": 790
},
{
"epoch": 0.04,
"grad_norm": 77.0,
"learning_rate": 1.0266666666666666e-06,
"loss": 2.6742,
"step": 800
},
{
"epoch": 0.04,
"grad_norm": 77.5,
"learning_rate": 1.0242222222222223e-06,
"loss": 2.6345,
"step": 810
},
{
"epoch": 0.04,
"grad_norm": 77.0,
"learning_rate": 1.021777777777778e-06,
"loss": 2.5581,
"step": 820
},
{
"epoch": 0.04,
"grad_norm": 77.0,
"learning_rate": 1.0193333333333333e-06,
"loss": 2.5076,
"step": 830
},
{
"epoch": 0.04,
"grad_norm": 77.0,
"learning_rate": 1.016888888888889e-06,
"loss": 2.4608,
"step": 840
},
{
"epoch": 0.04,
"grad_norm": 77.0,
"learning_rate": 1.0144444444444446e-06,
"loss": 2.3898,
"step": 850
},
{
"epoch": 0.04,
"grad_norm": 77.0,
"learning_rate": 1.012e-06,
"loss": 2.3806,
"step": 860
},
{
"epoch": 0.04,
"grad_norm": 76.5,
"learning_rate": 1.0095555555555556e-06,
"loss": 2.2935,
"step": 870
},
{
"epoch": 0.04,
"grad_norm": 75.5,
"learning_rate": 1.0071111111111113e-06,
"loss": 2.2645,
"step": 880
},
{
"epoch": 0.04,
"grad_norm": 75.0,
"learning_rate": 1.0046666666666667e-06,
"loss": 2.1927,
"step": 890
},
{
"epoch": 0.04,
"grad_norm": 75.5,
"learning_rate": 1.0022222222222223e-06,
"loss": 2.1659,
"step": 900
},
{
"epoch": 0.05,
"grad_norm": 74.0,
"learning_rate": 9.997777777777777e-07,
"loss": 2.1114,
"step": 910
},
{
"epoch": 0.05,
"grad_norm": 76.5,
"learning_rate": 9.973333333333334e-07,
"loss": 2.0784,
"step": 920
},
{
"epoch": 0.05,
"grad_norm": 74.0,
"learning_rate": 9.94888888888889e-07,
"loss": 2.0061,
"step": 930
},
{
"epoch": 0.05,
"grad_norm": 73.5,
"learning_rate": 9.924444444444446e-07,
"loss": 1.9691,
"step": 940
},
{
"epoch": 0.05,
"grad_norm": 73.0,
"learning_rate": 9.9e-07,
"loss": 1.8852,
"step": 950
},
{
"epoch": 0.05,
"grad_norm": 74.0,
"learning_rate": 9.875555555555557e-07,
"loss": 1.8666,
"step": 960
},
{
"epoch": 0.05,
"grad_norm": 72.0,
"learning_rate": 9.85111111111111e-07,
"loss": 1.8188,
"step": 970
},
{
"epoch": 0.05,
"grad_norm": 71.5,
"learning_rate": 9.826666666666667e-07,
"loss": 1.7199,
"step": 980
},
{
"epoch": 0.05,
"grad_norm": 73.0,
"learning_rate": 9.802222222222221e-07,
"loss": 1.7025,
"step": 990
},
{
"epoch": 0.05,
"grad_norm": 71.0,
"learning_rate": 9.777777777777778e-07,
"loss": 1.6182,
"step": 1000
},
{
"epoch": 0.05,
"eval_loss": 1.607034683227539,
"eval_runtime": 64.6423,
"eval_samples_per_second": 15.47,
"eval_steps_per_second": 15.47,
"step": 1000
}
],
"logging_steps": 10,
"max_steps": 5000,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 1000,
"total_flos": 1.613922041856e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}