tasky / checkpoint-1200 /trainer_state.json
jordiclive's picture
Upload folder using huggingface_hub
9c8df94 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.8586640851887706,
"eval_steps": 600,
"global_step": 1200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.015488867376573089,
"grad_norm": 421527552.0,
"learning_rate": 1.0000000000000002e-06,
"loss": 61.1175,
"step": 10
},
{
"epoch": 0.030977734753146177,
"grad_norm": 337641472.0,
"learning_rate": 2.0000000000000003e-06,
"loss": 60.1666,
"step": 20
},
{
"epoch": 0.046466602129719266,
"grad_norm": 413138944.0,
"learning_rate": 3e-06,
"loss": 60.9036,
"step": 30
},
{
"epoch": 0.061955469506292354,
"grad_norm": 1367343104.0,
"learning_rate": 4.000000000000001e-06,
"loss": 61.7597,
"step": 40
},
{
"epoch": 0.07744433688286544,
"grad_norm": 57933824.0,
"learning_rate": 5e-06,
"loss": 61.2844,
"step": 50
},
{
"epoch": 0.09293320425943853,
"grad_norm": 94371840.0,
"learning_rate": 6e-06,
"loss": 60.3878,
"step": 60
},
{
"epoch": 0.10842207163601161,
"grad_norm": 40632320.0,
"learning_rate": 7.000000000000001e-06,
"loss": 59.0391,
"step": 70
},
{
"epoch": 0.12391093901258471,
"grad_norm": 20971520.0,
"learning_rate": 8.000000000000001e-06,
"loss": 61.2704,
"step": 80
},
{
"epoch": 0.1393998063891578,
"grad_norm": 110624768.0,
"learning_rate": 9e-06,
"loss": 59.6674,
"step": 90
},
{
"epoch": 0.15488867376573087,
"grad_norm": 66584576.0,
"learning_rate": 1e-05,
"loss": 59.4588,
"step": 100
},
{
"epoch": 0.17037754114230397,
"grad_norm": 89653248.0,
"learning_rate": 1.1000000000000001e-05,
"loss": 58.9144,
"step": 110
},
{
"epoch": 0.18586640851887706,
"grad_norm": 56360960.0,
"learning_rate": 1.2e-05,
"loss": 58.3093,
"step": 120
},
{
"epoch": 0.20135527589545016,
"grad_norm": 19791872.0,
"learning_rate": 1.3000000000000001e-05,
"loss": 58.0143,
"step": 130
},
{
"epoch": 0.21684414327202323,
"grad_norm": 5242880.0,
"learning_rate": 1.4000000000000001e-05,
"loss": 56.9984,
"step": 140
},
{
"epoch": 0.23233301064859632,
"grad_norm": 55050240.0,
"learning_rate": 1.5e-05,
"loss": 57.6238,
"step": 150
},
{
"epoch": 0.24782187802516942,
"grad_norm": 118489088.0,
"learning_rate": 1.6000000000000003e-05,
"loss": 55.2309,
"step": 160
},
{
"epoch": 0.2633107454017425,
"grad_norm": 61865984.0,
"learning_rate": 1.7000000000000003e-05,
"loss": 54.6207,
"step": 170
},
{
"epoch": 0.2787996127783156,
"grad_norm": 13041664.0,
"learning_rate": 1.8e-05,
"loss": 52.8616,
"step": 180
},
{
"epoch": 0.2942884801548887,
"grad_norm": 87031808.0,
"learning_rate": 1.9e-05,
"loss": 52.4976,
"step": 190
},
{
"epoch": 0.30977734753146174,
"grad_norm": 3129344.0,
"learning_rate": 2e-05,
"loss": 52.6041,
"step": 200
},
{
"epoch": 0.32526621490803487,
"grad_norm": 99090432.0,
"learning_rate": 2.1e-05,
"loss": 54.6559,
"step": 210
},
{
"epoch": 0.34075508228460794,
"grad_norm": 3238002688.0,
"learning_rate": 2.2000000000000003e-05,
"loss": 52.2666,
"step": 220
},
{
"epoch": 0.356243949661181,
"grad_norm": 8454144.0,
"learning_rate": 2.3000000000000003e-05,
"loss": 51.7553,
"step": 230
},
{
"epoch": 0.3717328170377541,
"grad_norm": 81264640.0,
"learning_rate": 2.4e-05,
"loss": 49.4186,
"step": 240
},
{
"epoch": 0.3872216844143272,
"grad_norm": 1531904.0,
"learning_rate": 2.5e-05,
"loss": 48.724,
"step": 250
},
{
"epoch": 0.4027105517909003,
"grad_norm": 6782976.0,
"learning_rate": 2.6000000000000002e-05,
"loss": 47.4897,
"step": 260
},
{
"epoch": 0.4181994191674734,
"grad_norm": 462848.0,
"learning_rate": 2.7000000000000002e-05,
"loss": 46.1025,
"step": 270
},
{
"epoch": 0.43368828654404645,
"grad_norm": 227328.0,
"learning_rate": 2.8000000000000003e-05,
"loss": 43.953,
"step": 280
},
{
"epoch": 0.4491771539206196,
"grad_norm": 212992.0,
"learning_rate": 2.9e-05,
"loss": 42.786,
"step": 290
},
{
"epoch": 0.46466602129719264,
"grad_norm": 40704.0,
"learning_rate": 3e-05,
"loss": 41.3757,
"step": 300
},
{
"epoch": 0.4801548886737657,
"grad_norm": 42991616.0,
"learning_rate": 3.1e-05,
"loss": 42.0031,
"step": 310
},
{
"epoch": 0.49564375605033884,
"grad_norm": 21102592.0,
"learning_rate": 3.2000000000000005e-05,
"loss": 41.9207,
"step": 320
},
{
"epoch": 0.5111326234269119,
"grad_norm": 16187392.0,
"learning_rate": 3.3e-05,
"loss": 42.2336,
"step": 330
},
{
"epoch": 0.526621490803485,
"grad_norm": 164864.0,
"learning_rate": 3.4000000000000007e-05,
"loss": 40.6817,
"step": 340
},
{
"epoch": 0.542110358180058,
"grad_norm": 517996544.0,
"learning_rate": 3.5e-05,
"loss": 44.9866,
"step": 350
},
{
"epoch": 0.5575992255566312,
"grad_norm": 87556096.0,
"learning_rate": 3.6e-05,
"loss": 47.7577,
"step": 360
},
{
"epoch": 0.5730880929332043,
"grad_norm": 29753344.0,
"learning_rate": 3.7e-05,
"loss": 50.8352,
"step": 370
},
{
"epoch": 0.5885769603097774,
"grad_norm": 38273024.0,
"learning_rate": 3.8e-05,
"loss": 50.4585,
"step": 380
},
{
"epoch": 0.6040658276863504,
"grad_norm": 24248320.0,
"learning_rate": 3.9000000000000006e-05,
"loss": 53.4794,
"step": 390
},
{
"epoch": 0.6195546950629235,
"grad_norm": 637534208.0,
"learning_rate": 4e-05,
"loss": 53.7074,
"step": 400
},
{
"epoch": 0.6350435624394967,
"grad_norm": 679477248.0,
"learning_rate": 4.1e-05,
"loss": 57.4144,
"step": 410
},
{
"epoch": 0.6505324298160697,
"grad_norm": 583008256.0,
"learning_rate": 4.2e-05,
"loss": 53.7095,
"step": 420
},
{
"epoch": 0.6660212971926428,
"grad_norm": 57933824.0,
"learning_rate": 4.3e-05,
"loss": 54.9929,
"step": 430
},
{
"epoch": 0.6815101645692159,
"grad_norm": 61079552.0,
"learning_rate": 4.4000000000000006e-05,
"loss": 59.2993,
"step": 440
},
{
"epoch": 0.6969990319457889,
"grad_norm": 227540992.0,
"learning_rate": 4.5e-05,
"loss": 60.4038,
"step": 450
},
{
"epoch": 0.712487899322362,
"grad_norm": 190840832.0,
"learning_rate": 4.600000000000001e-05,
"loss": 63.1003,
"step": 460
},
{
"epoch": 0.7279767666989352,
"grad_norm": 327155712.0,
"learning_rate": 4.7e-05,
"loss": 64.5368,
"step": 470
},
{
"epoch": 0.7434656340755083,
"grad_norm": 679477248.0,
"learning_rate": 4.8e-05,
"loss": 61.6716,
"step": 480
},
{
"epoch": 0.7589545014520813,
"grad_norm": 276824064.0,
"learning_rate": 4.9e-05,
"loss": 62.8625,
"step": 490
},
{
"epoch": 0.7744433688286544,
"grad_norm": 78643200.0,
"learning_rate": 5e-05,
"loss": 63.9848,
"step": 500
},
{
"epoch": 0.7899322362052275,
"grad_norm": 224395264.0,
"learning_rate": 5.1000000000000006e-05,
"loss": 64.5113,
"step": 510
},
{
"epoch": 0.8054211035818006,
"grad_norm": 154140672.0,
"learning_rate": 5.2000000000000004e-05,
"loss": 64.9807,
"step": 520
},
{
"epoch": 0.8209099709583737,
"grad_norm": 805306368.0,
"learning_rate": 5.300000000000001e-05,
"loss": 65.7812,
"step": 530
},
{
"epoch": 0.8363988383349468,
"grad_norm": 339738624.0,
"learning_rate": 5.4000000000000005e-05,
"loss": 67.1272,
"step": 540
},
{
"epoch": 0.8518877057115198,
"grad_norm": 1002438656.0,
"learning_rate": 5.500000000000001e-05,
"loss": 66.3905,
"step": 550
},
{
"epoch": 0.8673765730880929,
"grad_norm": 2583691264.0,
"learning_rate": 5.6000000000000006e-05,
"loss": 66.0419,
"step": 560
},
{
"epoch": 0.882865440464666,
"grad_norm": 411041792.0,
"learning_rate": 5.6999999999999996e-05,
"loss": 62.0064,
"step": 570
},
{
"epoch": 0.8983543078412392,
"grad_norm": 70254592.0,
"learning_rate": 5.8e-05,
"loss": 63.6127,
"step": 580
},
{
"epoch": 0.9138431752178122,
"grad_norm": 191889408.0,
"learning_rate": 5.9e-05,
"loss": 63.481,
"step": 590
},
{
"epoch": 0.9293320425943853,
"grad_norm": 436207616.0,
"learning_rate": 6e-05,
"loss": 66.0833,
"step": 600
},
{
"epoch": 0.9293320425943853,
"eval_loss": 69.23383331298828,
"eval_runtime": 141.0364,
"eval_samples_per_second": 10.636,
"eval_steps_per_second": 2.659,
"step": 600
},
{
"epoch": 0.9448209099709584,
"grad_norm": 33161216.0,
"learning_rate": 6.1e-05,
"loss": 65.1055,
"step": 610
},
{
"epoch": 0.9603097773475314,
"grad_norm": 79167488.0,
"learning_rate": 6.2e-05,
"loss": 65.4074,
"step": 620
},
{
"epoch": 0.9757986447241046,
"grad_norm": 119013376.0,
"learning_rate": 6.3e-05,
"loss": 64.0661,
"step": 630
},
{
"epoch": 0.9912875121006777,
"grad_norm": 116391936.0,
"learning_rate": 6.400000000000001e-05,
"loss": 63.0841,
"step": 640
},
{
"epoch": 1.0067763794772506,
"grad_norm": 191889408.0,
"learning_rate": 6.500000000000001e-05,
"loss": 63.6633,
"step": 650
},
{
"epoch": 1.0222652468538238,
"grad_norm": 35389440.0,
"learning_rate": 6.6e-05,
"loss": 63.879,
"step": 660
},
{
"epoch": 1.037754114230397,
"grad_norm": 219152384.0,
"learning_rate": 6.7e-05,
"loss": 65.5105,
"step": 670
},
{
"epoch": 1.05324298160697,
"grad_norm": 476053504.0,
"learning_rate": 6.800000000000001e-05,
"loss": 66.3527,
"step": 680
},
{
"epoch": 1.0687318489835431,
"grad_norm": 2348810240.0,
"learning_rate": 6.9e-05,
"loss": 66.1827,
"step": 690
},
{
"epoch": 1.084220716360116,
"grad_norm": 452984832.0,
"learning_rate": 7e-05,
"loss": 67.8703,
"step": 700
},
{
"epoch": 1.0997095837366893,
"grad_norm": 46137344.0,
"learning_rate": 7.1e-05,
"loss": 67.2648,
"step": 710
},
{
"epoch": 1.1151984511132624,
"grad_norm": 70778880.0,
"learning_rate": 7.2e-05,
"loss": 62.0604,
"step": 720
},
{
"epoch": 1.1306873184898354,
"grad_norm": 283115520.0,
"learning_rate": 7.3e-05,
"loss": 60.8914,
"step": 730
},
{
"epoch": 1.1461761858664086,
"grad_norm": 78118912.0,
"learning_rate": 7.4e-05,
"loss": 60.0754,
"step": 740
},
{
"epoch": 1.1616650532429815,
"grad_norm": 120061952.0,
"learning_rate": 7.500000000000001e-05,
"loss": 63.6695,
"step": 750
},
{
"epoch": 1.1771539206195547,
"grad_norm": 90701824.0,
"learning_rate": 7.6e-05,
"loss": 65.6076,
"step": 760
},
{
"epoch": 1.1926427879961277,
"grad_norm": 23724032.0,
"learning_rate": 7.7e-05,
"loss": 64.6991,
"step": 770
},
{
"epoch": 1.2081316553727008,
"grad_norm": 22806528.0,
"learning_rate": 7.800000000000001e-05,
"loss": 64.4208,
"step": 780
},
{
"epoch": 1.223620522749274,
"grad_norm": 19529728.0,
"learning_rate": 7.900000000000001e-05,
"loss": 58.9719,
"step": 790
},
{
"epoch": 1.239109390125847,
"grad_norm": 154140672.0,
"learning_rate": 8e-05,
"loss": 58.4048,
"step": 800
},
{
"epoch": 1.2545982575024202,
"grad_norm": 4882432.0,
"learning_rate": 8.1e-05,
"loss": 63.3226,
"step": 810
},
{
"epoch": 1.2700871248789931,
"grad_norm": 4718592.0,
"learning_rate": 8.2e-05,
"loss": 62.6276,
"step": 820
},
{
"epoch": 1.2855759922555663,
"grad_norm": 56098816.0,
"learning_rate": 8.3e-05,
"loss": 57.6699,
"step": 830
},
{
"epoch": 1.3010648596321395,
"grad_norm": 2281701376.0,
"learning_rate": 8.4e-05,
"loss": 55.8831,
"step": 840
},
{
"epoch": 1.3165537270087124,
"grad_norm": 63963136.0,
"learning_rate": 8.5e-05,
"loss": 58.8188,
"step": 850
},
{
"epoch": 1.3320425943852856,
"grad_norm": 66322432.0,
"learning_rate": 8.6e-05,
"loss": 57.2062,
"step": 860
},
{
"epoch": 1.3475314617618586,
"grad_norm": 17956864.0,
"learning_rate": 8.7e-05,
"loss": 59.4092,
"step": 870
},
{
"epoch": 1.3630203291384317,
"grad_norm": 246415360.0,
"learning_rate": 8.800000000000001e-05,
"loss": 56.8145,
"step": 880
},
{
"epoch": 1.378509196515005,
"grad_norm": 205520896.0,
"learning_rate": 8.900000000000001e-05,
"loss": 56.4558,
"step": 890
},
{
"epoch": 1.3939980638915779,
"grad_norm": 90177536.0,
"learning_rate": 9e-05,
"loss": 54.4208,
"step": 900
},
{
"epoch": 1.409486931268151,
"grad_norm": 383778816.0,
"learning_rate": 9.1e-05,
"loss": 53.8711,
"step": 910
},
{
"epoch": 1.424975798644724,
"grad_norm": 23461888.0,
"learning_rate": 9.200000000000001e-05,
"loss": 52.0157,
"step": 920
},
{
"epoch": 1.4404646660212972,
"grad_norm": 27394048.0,
"learning_rate": 9.300000000000001e-05,
"loss": 48.0571,
"step": 930
},
{
"epoch": 1.4559535333978704,
"grad_norm": 8716288.0,
"learning_rate": 9.4e-05,
"loss": 43.4202,
"step": 940
},
{
"epoch": 1.4714424007744433,
"grad_norm": 5570560.0,
"learning_rate": 9.5e-05,
"loss": 40.7559,
"step": 950
},
{
"epoch": 1.4869312681510165,
"grad_norm": 20316160.0,
"learning_rate": 9.6e-05,
"loss": 39.1436,
"step": 960
},
{
"epoch": 1.5024201355275895,
"grad_norm": 15204352.0,
"learning_rate": 9.7e-05,
"loss": 36.618,
"step": 970
},
{
"epoch": 1.5179090029041626,
"grad_norm": 5832704.0,
"learning_rate": 9.8e-05,
"loss": 34.3857,
"step": 980
},
{
"epoch": 1.5333978702807358,
"grad_norm": 2293760.0,
"learning_rate": 9.900000000000001e-05,
"loss": 29.7184,
"step": 990
},
{
"epoch": 1.5488867376573088,
"grad_norm": 22282240.0,
"learning_rate": 0.0001,
"loss": 24.8724,
"step": 1000
},
{
"epoch": 1.5643756050338817,
"grad_norm": 10682368.0,
"learning_rate": 9.98165137614679e-05,
"loss": 21.2392,
"step": 1010
},
{
"epoch": 1.579864472410455,
"grad_norm": 25690112.0,
"learning_rate": 9.963302752293578e-05,
"loss": 18.7594,
"step": 1020
},
{
"epoch": 1.595353339787028,
"grad_norm": 15400960.0,
"learning_rate": 9.944954128440368e-05,
"loss": 17.9276,
"step": 1030
},
{
"epoch": 1.6108422071636013,
"grad_norm": 2359296.0,
"learning_rate": 9.926605504587157e-05,
"loss": 16.505,
"step": 1040
},
{
"epoch": 1.6263310745401742,
"grad_norm": 19005440.0,
"learning_rate": 9.908256880733946e-05,
"loss": 15.258,
"step": 1050
},
{
"epoch": 1.6418199419167472,
"grad_norm": 9240576.0,
"learning_rate": 9.889908256880734e-05,
"loss": 13.9628,
"step": 1060
},
{
"epoch": 1.6573088092933204,
"grad_norm": 7012352.0,
"learning_rate": 9.871559633027525e-05,
"loss": 14.8131,
"step": 1070
},
{
"epoch": 1.6727976766698935,
"grad_norm": 8388608.0,
"learning_rate": 9.853211009174312e-05,
"loss": 13.4851,
"step": 1080
},
{
"epoch": 1.6882865440464667,
"grad_norm": 1286144.0,
"learning_rate": 9.834862385321102e-05,
"loss": 12.8225,
"step": 1090
},
{
"epoch": 1.7037754114230397,
"grad_norm": 2490368.0,
"learning_rate": 9.816513761467891e-05,
"loss": 11.7111,
"step": 1100
},
{
"epoch": 1.7192642787996126,
"grad_norm": 1064960.0,
"learning_rate": 9.79816513761468e-05,
"loss": 11.347,
"step": 1110
},
{
"epoch": 1.7347531461761858,
"grad_norm": 352256.0,
"learning_rate": 9.779816513761468e-05,
"loss": 10.6953,
"step": 1120
},
{
"epoch": 1.750242013552759,
"grad_norm": 4046848.0,
"learning_rate": 9.761467889908259e-05,
"loss": 10.3879,
"step": 1130
},
{
"epoch": 1.7657308809293322,
"grad_norm": 348160.0,
"learning_rate": 9.743119266055046e-05,
"loss": 10.5364,
"step": 1140
},
{
"epoch": 1.7812197483059051,
"grad_norm": 6193152.0,
"learning_rate": 9.724770642201836e-05,
"loss": 10.7673,
"step": 1150
},
{
"epoch": 1.796708615682478,
"grad_norm": 671744.0,
"learning_rate": 9.706422018348625e-05,
"loss": 10.0088,
"step": 1160
},
{
"epoch": 1.8121974830590513,
"grad_norm": 557056.0,
"learning_rate": 9.688073394495414e-05,
"loss": 10.1469,
"step": 1170
},
{
"epoch": 1.8276863504356244,
"grad_norm": 835584.0,
"learning_rate": 9.669724770642202e-05,
"loss": 10.2772,
"step": 1180
},
{
"epoch": 1.8431752178121976,
"grad_norm": 2277376.0,
"learning_rate": 9.651376146788991e-05,
"loss": 9.8019,
"step": 1190
},
{
"epoch": 1.8586640851887706,
"grad_norm": 307200.0,
"learning_rate": 9.63302752293578e-05,
"loss": 9.5204,
"step": 1200
},
{
"epoch": 1.8586640851887706,
"eval_loss": 9.286345481872559,
"eval_runtime": 140.9651,
"eval_samples_per_second": 10.641,
"eval_steps_per_second": 2.66,
"step": 1200
}
],
"logging_steps": 10,
"max_steps": 6450,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 600,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6.568007548325069e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}