UltimoUno's picture
Uploaded checkpoint-1000
c73a8e4 verified
raw
history blame
14.7 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.05,
"eval_steps": 500,
"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": 83.0,
"learning_rate": 2e-08,
"loss": 7.8413,
"step": 10
},
{
"epoch": 0.0,
"grad_norm": 82.0,
"learning_rate": 4e-08,
"loss": 7.8305,
"step": 20
},
{
"epoch": 0.0,
"grad_norm": 84.0,
"learning_rate": 6e-08,
"loss": 7.8515,
"step": 30
},
{
"epoch": 0.0,
"grad_norm": 83.5,
"learning_rate": 8e-08,
"loss": 7.8284,
"step": 40
},
{
"epoch": 0.0,
"grad_norm": 82.0,
"learning_rate": 1e-07,
"loss": 7.8162,
"step": 50
},
{
"epoch": 0.0,
"grad_norm": 83.5,
"learning_rate": 1.2e-07,
"loss": 7.8523,
"step": 60
},
{
"epoch": 0.0,
"grad_norm": 81.0,
"learning_rate": 1.4e-07,
"loss": 7.8326,
"step": 70
},
{
"epoch": 0.0,
"grad_norm": 83.0,
"learning_rate": 1.6e-07,
"loss": 7.8242,
"step": 80
},
{
"epoch": 0.0,
"grad_norm": 81.5,
"learning_rate": 1.8e-07,
"loss": 7.8319,
"step": 90
},
{
"epoch": 0.01,
"grad_norm": 81.5,
"learning_rate": 2e-07,
"loss": 7.8175,
"step": 100
},
{
"epoch": 0.01,
"grad_norm": 83.0,
"learning_rate": 2.1999999999999998e-07,
"loss": 7.8136,
"step": 110
},
{
"epoch": 0.01,
"grad_norm": 81.5,
"learning_rate": 2.4e-07,
"loss": 7.846,
"step": 120
},
{
"epoch": 0.01,
"grad_norm": 82.5,
"learning_rate": 2.6e-07,
"loss": 7.8039,
"step": 130
},
{
"epoch": 0.01,
"grad_norm": 82.5,
"learning_rate": 2.8e-07,
"loss": 7.8113,
"step": 140
},
{
"epoch": 0.01,
"grad_norm": 82.5,
"learning_rate": 3e-07,
"loss": 7.7837,
"step": 150
},
{
"epoch": 0.01,
"grad_norm": 80.5,
"learning_rate": 3.2e-07,
"loss": 7.7796,
"step": 160
},
{
"epoch": 0.01,
"grad_norm": 82.0,
"learning_rate": 3.4000000000000003e-07,
"loss": 7.8044,
"step": 170
},
{
"epoch": 0.01,
"grad_norm": 81.5,
"learning_rate": 3.6e-07,
"loss": 7.7643,
"step": 180
},
{
"epoch": 0.01,
"grad_norm": 82.0,
"learning_rate": 3.7999999999999996e-07,
"loss": 7.7304,
"step": 190
},
{
"epoch": 0.01,
"grad_norm": 82.0,
"learning_rate": 4e-07,
"loss": 7.7071,
"step": 200
},
{
"epoch": 0.01,
"grad_norm": 80.5,
"learning_rate": 4.1999999999999995e-07,
"loss": 7.7164,
"step": 210
},
{
"epoch": 0.01,
"grad_norm": 82.5,
"learning_rate": 4.3999999999999997e-07,
"loss": 7.7243,
"step": 220
},
{
"epoch": 0.01,
"grad_norm": 80.5,
"learning_rate": 4.6e-07,
"loss": 7.6916,
"step": 230
},
{
"epoch": 0.01,
"grad_norm": 81.0,
"learning_rate": 4.8e-07,
"loss": 7.6749,
"step": 240
},
{
"epoch": 0.01,
"grad_norm": 80.5,
"learning_rate": 5e-07,
"loss": 7.6817,
"step": 250
},
{
"epoch": 0.01,
"grad_norm": 81.0,
"learning_rate": 5.2e-07,
"loss": 7.6871,
"step": 260
},
{
"epoch": 0.01,
"grad_norm": 80.5,
"learning_rate": 5.4e-07,
"loss": 7.6558,
"step": 270
},
{
"epoch": 0.01,
"grad_norm": 80.5,
"learning_rate": 5.6e-07,
"loss": 7.5715,
"step": 280
},
{
"epoch": 0.01,
"grad_norm": 79.0,
"learning_rate": 5.8e-07,
"loss": 7.5422,
"step": 290
},
{
"epoch": 0.01,
"grad_norm": 80.0,
"learning_rate": 6e-07,
"loss": 7.4936,
"step": 300
},
{
"epoch": 0.02,
"grad_norm": 78.5,
"learning_rate": 6.2e-07,
"loss": 7.4695,
"step": 310
},
{
"epoch": 0.02,
"grad_norm": 79.0,
"learning_rate": 6.4e-07,
"loss": 7.4154,
"step": 320
},
{
"epoch": 0.02,
"grad_norm": 78.0,
"learning_rate": 6.6e-07,
"loss": 7.3668,
"step": 330
},
{
"epoch": 0.02,
"grad_norm": 79.0,
"learning_rate": 6.800000000000001e-07,
"loss": 7.3532,
"step": 340
},
{
"epoch": 0.02,
"grad_norm": 77.5,
"learning_rate": 7e-07,
"loss": 7.2727,
"step": 350
},
{
"epoch": 0.02,
"grad_norm": 77.5,
"learning_rate": 7.2e-07,
"loss": 7.2473,
"step": 360
},
{
"epoch": 0.02,
"grad_norm": 78.0,
"learning_rate": 7.4e-07,
"loss": 7.236,
"step": 370
},
{
"epoch": 0.02,
"grad_norm": 77.5,
"learning_rate": 7.599999999999999e-07,
"loss": 7.1711,
"step": 380
},
{
"epoch": 0.02,
"grad_norm": 77.5,
"learning_rate": 7.799999999999999e-07,
"loss": 7.1217,
"step": 390
},
{
"epoch": 0.02,
"grad_norm": 77.5,
"learning_rate": 8e-07,
"loss": 7.1038,
"step": 400
},
{
"epoch": 0.02,
"grad_norm": 78.0,
"learning_rate": 8.199999999999999e-07,
"loss": 7.0849,
"step": 410
},
{
"epoch": 0.02,
"grad_norm": 78.0,
"learning_rate": 8.399999999999999e-07,
"loss": 7.0331,
"step": 420
},
{
"epoch": 0.02,
"grad_norm": 77.0,
"learning_rate": 8.599999999999999e-07,
"loss": 6.9839,
"step": 430
},
{
"epoch": 0.02,
"grad_norm": 77.0,
"learning_rate": 8.799999999999999e-07,
"loss": 6.962,
"step": 440
},
{
"epoch": 0.02,
"grad_norm": 77.0,
"learning_rate": 9e-07,
"loss": 6.9108,
"step": 450
},
{
"epoch": 0.02,
"grad_norm": 77.5,
"learning_rate": 9.2e-07,
"loss": 6.8641,
"step": 460
},
{
"epoch": 0.02,
"grad_norm": 77.5,
"learning_rate": 9.399999999999999e-07,
"loss": 6.7994,
"step": 470
},
{
"epoch": 0.02,
"grad_norm": 77.0,
"learning_rate": 9.6e-07,
"loss": 6.7141,
"step": 480
},
{
"epoch": 0.02,
"grad_norm": 77.0,
"learning_rate": 9.8e-07,
"loss": 6.6188,
"step": 490
},
{
"epoch": 0.03,
"grad_norm": 77.5,
"learning_rate": 1e-06,
"loss": 6.4929,
"step": 500
},
{
"epoch": 0.03,
"eval_loss": 6.463568210601807,
"eval_runtime": 65.3176,
"eval_samples_per_second": 15.31,
"eval_steps_per_second": 15.31,
"step": 500
},
{
"epoch": 0.03,
"grad_norm": 77.5,
"learning_rate": 9.933333333333333e-07,
"loss": 6.4003,
"step": 510
},
{
"epoch": 0.03,
"grad_norm": 77.5,
"learning_rate": 9.866666666666666e-07,
"loss": 6.2969,
"step": 520
},
{
"epoch": 0.03,
"grad_norm": 78.5,
"learning_rate": 9.8e-07,
"loss": 6.19,
"step": 530
},
{
"epoch": 0.03,
"grad_norm": 78.0,
"learning_rate": 9.733333333333333e-07,
"loss": 6.0401,
"step": 540
},
{
"epoch": 0.03,
"grad_norm": 79.0,
"learning_rate": 9.666666666666666e-07,
"loss": 5.9727,
"step": 550
},
{
"epoch": 0.03,
"grad_norm": 80.0,
"learning_rate": 9.6e-07,
"loss": 5.821,
"step": 560
},
{
"epoch": 0.03,
"grad_norm": 80.5,
"learning_rate": 9.533333333333333e-07,
"loss": 5.6864,
"step": 570
},
{
"epoch": 0.03,
"grad_norm": 80.5,
"learning_rate": 9.466666666666666e-07,
"loss": 5.5677,
"step": 580
},
{
"epoch": 0.03,
"grad_norm": 81.5,
"learning_rate": 9.399999999999999e-07,
"loss": 5.4587,
"step": 590
},
{
"epoch": 0.03,
"grad_norm": 82.0,
"learning_rate": 9.333333333333333e-07,
"loss": 5.3674,
"step": 600
},
{
"epoch": 0.03,
"grad_norm": 83.5,
"learning_rate": 9.266666666666665e-07,
"loss": 5.2343,
"step": 610
},
{
"epoch": 0.03,
"grad_norm": 83.5,
"learning_rate": 9.2e-07,
"loss": 5.1118,
"step": 620
},
{
"epoch": 0.03,
"grad_norm": 83.5,
"learning_rate": 9.133333333333333e-07,
"loss": 5.0416,
"step": 630
},
{
"epoch": 0.03,
"grad_norm": 85.5,
"learning_rate": 9.066666666666665e-07,
"loss": 4.9311,
"step": 640
},
{
"epoch": 0.03,
"grad_norm": 86.0,
"learning_rate": 9e-07,
"loss": 4.8409,
"step": 650
},
{
"epoch": 0.03,
"grad_norm": 86.5,
"learning_rate": 8.933333333333333e-07,
"loss": 4.7077,
"step": 660
},
{
"epoch": 0.03,
"grad_norm": 87.5,
"learning_rate": 8.866666666666667e-07,
"loss": 4.6436,
"step": 670
},
{
"epoch": 0.03,
"grad_norm": 86.0,
"learning_rate": 8.799999999999999e-07,
"loss": 4.5543,
"step": 680
},
{
"epoch": 0.03,
"grad_norm": 87.0,
"learning_rate": 8.733333333333333e-07,
"loss": 4.473,
"step": 690
},
{
"epoch": 0.04,
"grad_norm": 87.0,
"learning_rate": 8.666666666666667e-07,
"loss": 4.373,
"step": 700
},
{
"epoch": 0.04,
"grad_norm": 88.5,
"learning_rate": 8.599999999999999e-07,
"loss": 4.3226,
"step": 710
},
{
"epoch": 0.04,
"grad_norm": 87.5,
"learning_rate": 8.533333333333334e-07,
"loss": 4.2063,
"step": 720
},
{
"epoch": 0.04,
"grad_norm": 87.5,
"learning_rate": 8.466666666666667e-07,
"loss": 4.1628,
"step": 730
},
{
"epoch": 0.04,
"grad_norm": 86.5,
"learning_rate": 8.399999999999999e-07,
"loss": 4.0588,
"step": 740
},
{
"epoch": 0.04,
"grad_norm": 88.0,
"learning_rate": 8.333333333333333e-07,
"loss": 4.0117,
"step": 750
},
{
"epoch": 0.04,
"grad_norm": 88.0,
"learning_rate": 8.266666666666667e-07,
"loss": 3.9443,
"step": 760
},
{
"epoch": 0.04,
"grad_norm": 88.5,
"learning_rate": 8.199999999999999e-07,
"loss": 3.8509,
"step": 770
},
{
"epoch": 0.04,
"grad_norm": 88.0,
"learning_rate": 8.133333333333333e-07,
"loss": 3.7851,
"step": 780
},
{
"epoch": 0.04,
"grad_norm": 87.5,
"learning_rate": 8.066666666666666e-07,
"loss": 3.7559,
"step": 790
},
{
"epoch": 0.04,
"grad_norm": 87.0,
"learning_rate": 8e-07,
"loss": 3.6867,
"step": 800
},
{
"epoch": 0.04,
"grad_norm": 88.0,
"learning_rate": 7.933333333333333e-07,
"loss": 3.6217,
"step": 810
},
{
"epoch": 0.04,
"grad_norm": 86.5,
"learning_rate": 7.866666666666666e-07,
"loss": 3.5678,
"step": 820
},
{
"epoch": 0.04,
"grad_norm": 86.5,
"learning_rate": 7.799999999999999e-07,
"loss": 3.5387,
"step": 830
},
{
"epoch": 0.04,
"grad_norm": 86.5,
"learning_rate": 7.733333333333333e-07,
"loss": 3.4999,
"step": 840
},
{
"epoch": 0.04,
"grad_norm": 87.0,
"learning_rate": 7.666666666666667e-07,
"loss": 3.4263,
"step": 850
},
{
"epoch": 0.04,
"grad_norm": 87.0,
"learning_rate": 7.599999999999999e-07,
"loss": 3.4185,
"step": 860
},
{
"epoch": 0.04,
"grad_norm": 86.0,
"learning_rate": 7.533333333333332e-07,
"loss": 3.3753,
"step": 870
},
{
"epoch": 0.04,
"grad_norm": 86.0,
"learning_rate": 7.466666666666667e-07,
"loss": 3.318,
"step": 880
},
{
"epoch": 0.04,
"grad_norm": 85.5,
"learning_rate": 7.4e-07,
"loss": 3.2846,
"step": 890
},
{
"epoch": 0.04,
"grad_norm": 86.5,
"learning_rate": 7.333333333333332e-07,
"loss": 3.2757,
"step": 900
},
{
"epoch": 0.05,
"grad_norm": 85.0,
"learning_rate": 7.266666666666667e-07,
"loss": 3.2204,
"step": 910
},
{
"epoch": 0.05,
"grad_norm": 87.0,
"learning_rate": 7.2e-07,
"loss": 3.1933,
"step": 920
},
{
"epoch": 0.05,
"grad_norm": 85.0,
"learning_rate": 7.133333333333333e-07,
"loss": 3.1404,
"step": 930
},
{
"epoch": 0.05,
"grad_norm": 84.5,
"learning_rate": 7.066666666666666e-07,
"loss": 3.1084,
"step": 940
},
{
"epoch": 0.05,
"grad_norm": 83.5,
"learning_rate": 7e-07,
"loss": 3.0518,
"step": 950
},
{
"epoch": 0.05,
"grad_norm": 84.5,
"learning_rate": 6.933333333333333e-07,
"loss": 3.0331,
"step": 960
},
{
"epoch": 0.05,
"grad_norm": 84.0,
"learning_rate": 6.866666666666666e-07,
"loss": 3.0252,
"step": 970
},
{
"epoch": 0.05,
"grad_norm": 83.0,
"learning_rate": 6.800000000000001e-07,
"loss": 2.9718,
"step": 980
},
{
"epoch": 0.05,
"grad_norm": 84.0,
"learning_rate": 6.733333333333333e-07,
"loss": 2.9666,
"step": 990
},
{
"epoch": 0.05,
"grad_norm": 82.0,
"learning_rate": 6.666666666666666e-07,
"loss": 2.9071,
"step": 1000
},
{
"epoch": 0.05,
"eval_loss": 2.927218437194824,
"eval_runtime": 65.2971,
"eval_samples_per_second": 15.315,
"eval_steps_per_second": 15.315,
"step": 1000
}
],
"logging_steps": 10,
"max_steps": 2000,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"total_flos": 1.613922041856e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}