BARTSumpson / trainer_state.json
de-Rodrigo's picture
Upload v1 model (10k samples, 2k steps)
f3651eb
{
"best_metric": 1.3787956237792969,
"best_model_checkpoint": "test-calls-summarization/checkpoint-1000",
"epoch": 25.579536370903277,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.06,
"learning_rate": 4.9999999999999996e-05,
"loss": 2.0533,
"step": 5
},
{
"epoch": 0.13,
"learning_rate": 9.999999999999999e-05,
"loss": 1.0512,
"step": 10
},
{
"epoch": 0.19,
"learning_rate": 0.00015,
"loss": 0.7919,
"step": 15
},
{
"epoch": 0.26,
"learning_rate": 0.00019999999999999998,
"loss": 0.6876,
"step": 20
},
{
"epoch": 0.32,
"learning_rate": 0.00025,
"loss": 0.6567,
"step": 25
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 0.6271,
"step": 30
},
{
"epoch": 0.45,
"learning_rate": 0.0002998495486459378,
"loss": 0.5943,
"step": 35
},
{
"epoch": 0.51,
"learning_rate": 0.00029969909729187557,
"loss": 0.5666,
"step": 40
},
{
"epoch": 0.58,
"learning_rate": 0.0002995486459378134,
"loss": 0.5603,
"step": 45
},
{
"epoch": 0.64,
"learning_rate": 0.0002993981945837512,
"loss": 0.5282,
"step": 50
},
{
"epoch": 0.7,
"learning_rate": 0.00029924774322968905,
"loss": 0.5173,
"step": 55
},
{
"epoch": 0.77,
"learning_rate": 0.00029909729187562687,
"loss": 0.5011,
"step": 60
},
{
"epoch": 0.83,
"learning_rate": 0.0002989468405215647,
"loss": 0.4926,
"step": 65
},
{
"epoch": 0.9,
"learning_rate": 0.00029879638916750247,
"loss": 0.478,
"step": 70
},
{
"epoch": 0.96,
"learning_rate": 0.0002986459378134403,
"loss": 0.4766,
"step": 75
},
{
"epoch": 1.02,
"learning_rate": 0.0002984954864593781,
"loss": 0.4756,
"step": 80
},
{
"epoch": 1.09,
"learning_rate": 0.0002983450351053159,
"loss": 0.4229,
"step": 85
},
{
"epoch": 1.15,
"learning_rate": 0.0002981945837512537,
"loss": 0.4239,
"step": 90
},
{
"epoch": 1.22,
"learning_rate": 0.00029804413239719154,
"loss": 0.431,
"step": 95
},
{
"epoch": 1.28,
"learning_rate": 0.00029789368104312936,
"loss": 0.4333,
"step": 100
},
{
"epoch": 1.34,
"learning_rate": 0.0002977432296890672,
"loss": 0.4218,
"step": 105
},
{
"epoch": 1.41,
"learning_rate": 0.000297592778335005,
"loss": 0.4357,
"step": 110
},
{
"epoch": 1.47,
"learning_rate": 0.0002974423269809428,
"loss": 0.4197,
"step": 115
},
{
"epoch": 1.53,
"learning_rate": 0.0002972918756268806,
"loss": 0.4213,
"step": 120
},
{
"epoch": 1.6,
"learning_rate": 0.00029714142427281844,
"loss": 0.4087,
"step": 125
},
{
"epoch": 1.66,
"learning_rate": 0.0002969909729187562,
"loss": 0.4041,
"step": 130
},
{
"epoch": 1.73,
"learning_rate": 0.00029684052156469403,
"loss": 0.4103,
"step": 135
},
{
"epoch": 1.79,
"learning_rate": 0.00029669007021063186,
"loss": 0.4009,
"step": 140
},
{
"epoch": 1.85,
"learning_rate": 0.0002965396188565697,
"loss": 0.4077,
"step": 145
},
{
"epoch": 1.92,
"learning_rate": 0.0002963891675025075,
"loss": 0.4257,
"step": 150
},
{
"epoch": 1.98,
"learning_rate": 0.00029623871614844533,
"loss": 0.4111,
"step": 155
},
{
"epoch": 2.05,
"learning_rate": 0.0002960882647943831,
"loss": 0.3634,
"step": 160
},
{
"epoch": 2.11,
"learning_rate": 0.00029593781344032093,
"loss": 0.3532,
"step": 165
},
{
"epoch": 2.17,
"learning_rate": 0.00029578736208625875,
"loss": 0.3591,
"step": 170
},
{
"epoch": 2.24,
"learning_rate": 0.0002956369107321965,
"loss": 0.3506,
"step": 175
},
{
"epoch": 2.3,
"learning_rate": 0.00029548645937813435,
"loss": 0.3494,
"step": 180
},
{
"epoch": 2.37,
"learning_rate": 0.0002953360080240722,
"loss": 0.3598,
"step": 185
},
{
"epoch": 2.43,
"learning_rate": 0.00029518555667001,
"loss": 0.3656,
"step": 190
},
{
"epoch": 2.49,
"learning_rate": 0.0002950351053159478,
"loss": 0.351,
"step": 195
},
{
"epoch": 2.56,
"learning_rate": 0.00029488465396188565,
"loss": 0.3589,
"step": 200
},
{
"epoch": 2.62,
"learning_rate": 0.0002947342026078234,
"loss": 0.3564,
"step": 205
},
{
"epoch": 2.69,
"learning_rate": 0.00029458375125376125,
"loss": 0.3665,
"step": 210
},
{
"epoch": 2.75,
"learning_rate": 0.0002944332998996991,
"loss": 0.3472,
"step": 215
},
{
"epoch": 2.81,
"learning_rate": 0.0002942828485456369,
"loss": 0.3876,
"step": 220
},
{
"epoch": 2.88,
"learning_rate": 0.0002941323971915747,
"loss": 0.3831,
"step": 225
},
{
"epoch": 2.94,
"learning_rate": 0.00029398194583751255,
"loss": 0.3597,
"step": 230
},
{
"epoch": 3.01,
"learning_rate": 0.0002938314944834503,
"loss": 0.3781,
"step": 235
},
{
"epoch": 3.07,
"learning_rate": 0.00029368104312938815,
"loss": 0.3078,
"step": 240
},
{
"epoch": 3.13,
"learning_rate": 0.00029353059177532597,
"loss": 0.2986,
"step": 245
},
{
"epoch": 3.2,
"learning_rate": 0.00029338014042126374,
"loss": 0.3031,
"step": 250
},
{
"epoch": 3.2,
"eval_loss": 0.9930399656295776,
"eval_runtime": 0.3176,
"eval_samples_per_second": 31.491,
"eval_steps_per_second": 3.149,
"step": 250
},
{
"epoch": 3.26,
"learning_rate": 0.00029322968906720157,
"loss": 0.3132,
"step": 255
},
{
"epoch": 3.33,
"learning_rate": 0.0002930792377131394,
"loss": 0.3044,
"step": 260
},
{
"epoch": 3.39,
"learning_rate": 0.0002929287863590772,
"loss": 0.3154,
"step": 265
},
{
"epoch": 3.45,
"learning_rate": 0.00029277833500501504,
"loss": 0.3143,
"step": 270
},
{
"epoch": 3.52,
"learning_rate": 0.00029262788365095287,
"loss": 0.3169,
"step": 275
},
{
"epoch": 3.58,
"learning_rate": 0.00029247743229689064,
"loss": 0.3181,
"step": 280
},
{
"epoch": 3.65,
"learning_rate": 0.00029232698094282846,
"loss": 0.3227,
"step": 285
},
{
"epoch": 3.71,
"learning_rate": 0.0002921765295887663,
"loss": 0.3181,
"step": 290
},
{
"epoch": 3.77,
"learning_rate": 0.00029202607823470406,
"loss": 0.3528,
"step": 295
},
{
"epoch": 3.84,
"learning_rate": 0.0002918756268806419,
"loss": 0.3341,
"step": 300
},
{
"epoch": 3.9,
"learning_rate": 0.0002917251755265797,
"loss": 0.3274,
"step": 305
},
{
"epoch": 3.96,
"learning_rate": 0.00029157472417251754,
"loss": 0.3227,
"step": 310
},
{
"epoch": 4.03,
"learning_rate": 0.00029142427281845536,
"loss": 0.3069,
"step": 315
},
{
"epoch": 4.09,
"learning_rate": 0.0002912738214643932,
"loss": 0.2687,
"step": 320
},
{
"epoch": 4.16,
"learning_rate": 0.00029112337011033096,
"loss": 0.2736,
"step": 325
},
{
"epoch": 4.22,
"learning_rate": 0.0002909729187562688,
"loss": 0.2736,
"step": 330
},
{
"epoch": 4.28,
"learning_rate": 0.0002908224674022066,
"loss": 0.2684,
"step": 335
},
{
"epoch": 4.35,
"learning_rate": 0.0002906720160481444,
"loss": 0.2608,
"step": 340
},
{
"epoch": 4.41,
"learning_rate": 0.0002905215646940822,
"loss": 0.2688,
"step": 345
},
{
"epoch": 4.48,
"learning_rate": 0.00029037111334002003,
"loss": 0.3065,
"step": 350
},
{
"epoch": 4.54,
"learning_rate": 0.00029022066198595785,
"loss": 0.2872,
"step": 355
},
{
"epoch": 4.6,
"learning_rate": 0.0002900702106318957,
"loss": 0.285,
"step": 360
},
{
"epoch": 4.67,
"learning_rate": 0.0002899197592778335,
"loss": 0.4004,
"step": 365
},
{
"epoch": 4.73,
"learning_rate": 0.0002897693079237713,
"loss": 0.2869,
"step": 370
},
{
"epoch": 4.8,
"learning_rate": 0.0002896188565697091,
"loss": 0.288,
"step": 375
},
{
"epoch": 4.86,
"learning_rate": 0.0002894684052156469,
"loss": 0.2779,
"step": 380
},
{
"epoch": 4.92,
"learning_rate": 0.0002893179538615847,
"loss": 0.2856,
"step": 385
},
{
"epoch": 4.99,
"learning_rate": 0.0002891675025075225,
"loss": 0.3069,
"step": 390
},
{
"epoch": 5.05,
"learning_rate": 0.00028901705115346035,
"loss": 0.2484,
"step": 395
},
{
"epoch": 5.12,
"learning_rate": 0.0002888665997993982,
"loss": 0.2466,
"step": 400
},
{
"epoch": 5.18,
"learning_rate": 0.000288716148445336,
"loss": 0.2498,
"step": 405
},
{
"epoch": 5.24,
"learning_rate": 0.0002885656970912738,
"loss": 0.2475,
"step": 410
},
{
"epoch": 5.31,
"learning_rate": 0.0002884152457372116,
"loss": 0.2406,
"step": 415
},
{
"epoch": 5.37,
"learning_rate": 0.0002882647943831494,
"loss": 0.2436,
"step": 420
},
{
"epoch": 5.44,
"learning_rate": 0.00028811434302908724,
"loss": 0.2492,
"step": 425
},
{
"epoch": 5.5,
"learning_rate": 0.000287963891675025,
"loss": 0.2553,
"step": 430
},
{
"epoch": 5.56,
"learning_rate": 0.00028781344032096284,
"loss": 0.2551,
"step": 435
},
{
"epoch": 5.63,
"learning_rate": 0.00028766298896690067,
"loss": 0.2585,
"step": 440
},
{
"epoch": 5.69,
"learning_rate": 0.0002875125376128385,
"loss": 0.2648,
"step": 445
},
{
"epoch": 5.76,
"learning_rate": 0.0002873620862587763,
"loss": 0.2755,
"step": 450
},
{
"epoch": 5.82,
"learning_rate": 0.00028721163490471414,
"loss": 0.2614,
"step": 455
},
{
"epoch": 5.88,
"learning_rate": 0.0002870611835506519,
"loss": 0.2678,
"step": 460
},
{
"epoch": 5.95,
"learning_rate": 0.00028691073219658974,
"loss": 0.2726,
"step": 465
},
{
"epoch": 6.01,
"learning_rate": 0.00028676028084252756,
"loss": 0.2561,
"step": 470
},
{
"epoch": 6.08,
"learning_rate": 0.00028660982948846533,
"loss": 0.214,
"step": 475
},
{
"epoch": 6.14,
"learning_rate": 0.00028645937813440316,
"loss": 0.2213,
"step": 480
},
{
"epoch": 6.2,
"learning_rate": 0.000286308926780341,
"loss": 0.2217,
"step": 485
},
{
"epoch": 6.27,
"learning_rate": 0.0002861584754262788,
"loss": 0.2213,
"step": 490
},
{
"epoch": 6.33,
"learning_rate": 0.00028600802407221664,
"loss": 0.2344,
"step": 495
},
{
"epoch": 6.39,
"learning_rate": 0.00028585757271815446,
"loss": 0.4603,
"step": 500
},
{
"epoch": 6.39,
"eval_loss": 1.0373685359954834,
"eval_runtime": 0.3183,
"eval_samples_per_second": 31.418,
"eval_steps_per_second": 3.142,
"step": 500
},
{
"epoch": 6.46,
"learning_rate": 0.00028570712136409223,
"loss": 0.2353,
"step": 505
},
{
"epoch": 6.52,
"learning_rate": 0.00028555667001003006,
"loss": 0.2269,
"step": 510
},
{
"epoch": 6.59,
"learning_rate": 0.0002854062186559679,
"loss": 0.2318,
"step": 515
},
{
"epoch": 6.65,
"learning_rate": 0.00028525576730190565,
"loss": 0.2338,
"step": 520
},
{
"epoch": 6.71,
"learning_rate": 0.0002851053159478435,
"loss": 0.2336,
"step": 525
},
{
"epoch": 6.78,
"learning_rate": 0.0002849548645937813,
"loss": 0.2385,
"step": 530
},
{
"epoch": 6.84,
"learning_rate": 0.00028480441323971913,
"loss": 0.2356,
"step": 535
},
{
"epoch": 6.91,
"learning_rate": 0.00028465396188565695,
"loss": 0.2437,
"step": 540
},
{
"epoch": 6.97,
"learning_rate": 0.0002845035105315948,
"loss": 0.2417,
"step": 545
},
{
"epoch": 7.03,
"learning_rate": 0.00028435305917753255,
"loss": 0.2167,
"step": 550
},
{
"epoch": 7.1,
"learning_rate": 0.0002842026078234704,
"loss": 0.1974,
"step": 555
},
{
"epoch": 7.16,
"learning_rate": 0.0002840521564694082,
"loss": 0.2092,
"step": 560
},
{
"epoch": 7.23,
"learning_rate": 0.000283901705115346,
"loss": 0.2009,
"step": 565
},
{
"epoch": 7.29,
"learning_rate": 0.00028375125376128385,
"loss": 0.5423,
"step": 570
},
{
"epoch": 7.35,
"learning_rate": 0.0002836008024072217,
"loss": 0.7044,
"step": 575
},
{
"epoch": 7.42,
"learning_rate": 0.00028345035105315945,
"loss": 0.3172,
"step": 580
},
{
"epoch": 7.48,
"learning_rate": 0.00028329989969909727,
"loss": 0.2165,
"step": 585
},
{
"epoch": 7.55,
"learning_rate": 0.0002831494483450351,
"loss": 0.2017,
"step": 590
},
{
"epoch": 7.61,
"learning_rate": 0.00028299899699097287,
"loss": 0.1976,
"step": 595
},
{
"epoch": 7.67,
"learning_rate": 0.0002828485456369107,
"loss": 0.2036,
"step": 600
},
{
"epoch": 7.74,
"learning_rate": 0.0002826980942828485,
"loss": 0.2082,
"step": 605
},
{
"epoch": 7.8,
"learning_rate": 0.00028254764292878634,
"loss": 0.2104,
"step": 610
},
{
"epoch": 7.87,
"learning_rate": 0.00028239719157472417,
"loss": 0.2194,
"step": 615
},
{
"epoch": 7.93,
"learning_rate": 0.000282246740220662,
"loss": 0.2104,
"step": 620
},
{
"epoch": 7.99,
"learning_rate": 0.00028209628886659977,
"loss": 0.2183,
"step": 625
},
{
"epoch": 8.06,
"learning_rate": 0.0002819458375125376,
"loss": 0.1773,
"step": 630
},
{
"epoch": 8.12,
"learning_rate": 0.0002817953861584754,
"loss": 0.1753,
"step": 635
},
{
"epoch": 8.19,
"learning_rate": 0.0002816449348044132,
"loss": 0.1737,
"step": 640
},
{
"epoch": 8.25,
"learning_rate": 0.000281494483450351,
"loss": 0.1807,
"step": 645
},
{
"epoch": 8.31,
"learning_rate": 0.00028134403209628884,
"loss": 0.1858,
"step": 650
},
{
"epoch": 8.38,
"learning_rate": 0.00028119358074222666,
"loss": 0.1836,
"step": 655
},
{
"epoch": 8.44,
"learning_rate": 0.0002810431293881645,
"loss": 0.1887,
"step": 660
},
{
"epoch": 8.51,
"learning_rate": 0.0002808926780341023,
"loss": 0.1908,
"step": 665
},
{
"epoch": 8.57,
"learning_rate": 0.0002807422266800401,
"loss": 0.1933,
"step": 670
},
{
"epoch": 8.63,
"learning_rate": 0.0002805917753259779,
"loss": 0.1969,
"step": 675
},
{
"epoch": 8.7,
"learning_rate": 0.00028044132397191574,
"loss": 0.194,
"step": 680
},
{
"epoch": 8.76,
"learning_rate": 0.0002802908726178535,
"loss": 0.1895,
"step": 685
},
{
"epoch": 8.82,
"learning_rate": 0.00028014042126379133,
"loss": 0.1957,
"step": 690
},
{
"epoch": 8.89,
"learning_rate": 0.00027998996990972916,
"loss": 0.1927,
"step": 695
},
{
"epoch": 8.95,
"learning_rate": 0.000279839518555667,
"loss": 0.1891,
"step": 700
},
{
"epoch": 9.02,
"learning_rate": 0.0002796890672016048,
"loss": 0.1809,
"step": 705
},
{
"epoch": 9.08,
"learning_rate": 0.00027953861584754263,
"loss": 0.1443,
"step": 710
},
{
"epoch": 9.14,
"learning_rate": 0.0002793881644934804,
"loss": 0.1487,
"step": 715
},
{
"epoch": 9.21,
"learning_rate": 0.00027923771313941823,
"loss": 0.1521,
"step": 720
},
{
"epoch": 9.27,
"learning_rate": 0.00027908726178535605,
"loss": 0.1544,
"step": 725
},
{
"epoch": 9.34,
"learning_rate": 0.0002789368104312938,
"loss": 0.1564,
"step": 730
},
{
"epoch": 9.4,
"learning_rate": 0.00027878635907723165,
"loss": 0.1634,
"step": 735
},
{
"epoch": 9.46,
"learning_rate": 0.0002786359077231695,
"loss": 0.1644,
"step": 740
},
{
"epoch": 9.53,
"learning_rate": 0.0002784854563691073,
"loss": 0.1643,
"step": 745
},
{
"epoch": 9.59,
"learning_rate": 0.0002783350050150451,
"loss": 0.1721,
"step": 750
},
{
"epoch": 9.59,
"eval_loss": 1.1369589567184448,
"eval_runtime": 0.3185,
"eval_samples_per_second": 31.399,
"eval_steps_per_second": 3.14,
"step": 750
},
{
"epoch": 9.66,
"learning_rate": 0.00027818455366098295,
"loss": 0.1755,
"step": 755
},
{
"epoch": 9.72,
"learning_rate": 0.0002780341023069207,
"loss": 0.1733,
"step": 760
},
{
"epoch": 9.78,
"learning_rate": 0.00027788365095285855,
"loss": 0.1689,
"step": 765
},
{
"epoch": 9.85,
"learning_rate": 0.00027773319959879637,
"loss": 0.1668,
"step": 770
},
{
"epoch": 9.91,
"learning_rate": 0.00027758274824473414,
"loss": 0.1774,
"step": 775
},
{
"epoch": 9.98,
"learning_rate": 0.00027743229689067197,
"loss": 0.1742,
"step": 780
},
{
"epoch": 10.04,
"learning_rate": 0.0002772818455366098,
"loss": 0.1513,
"step": 785
},
{
"epoch": 10.1,
"learning_rate": 0.0002771313941825476,
"loss": 0.1361,
"step": 790
},
{
"epoch": 10.17,
"learning_rate": 0.00027698094282848544,
"loss": 0.1387,
"step": 795
},
{
"epoch": 10.23,
"learning_rate": 0.00027683049147442327,
"loss": 0.1472,
"step": 800
},
{
"epoch": 10.3,
"learning_rate": 0.00027668004012036104,
"loss": 0.1439,
"step": 805
},
{
"epoch": 10.36,
"learning_rate": 0.00027652958876629887,
"loss": 0.1389,
"step": 810
},
{
"epoch": 10.42,
"learning_rate": 0.0002763791374122367,
"loss": 0.1454,
"step": 815
},
{
"epoch": 10.49,
"learning_rate": 0.00027622868605817446,
"loss": 0.1504,
"step": 820
},
{
"epoch": 10.55,
"learning_rate": 0.0002760782347041123,
"loss": 0.1475,
"step": 825
},
{
"epoch": 10.62,
"learning_rate": 0.0002759277833500501,
"loss": 0.1478,
"step": 830
},
{
"epoch": 10.68,
"learning_rate": 0.00027577733199598794,
"loss": 0.1496,
"step": 835
},
{
"epoch": 10.74,
"learning_rate": 0.00027562688064192576,
"loss": 0.1475,
"step": 840
},
{
"epoch": 10.81,
"learning_rate": 0.0002754764292878636,
"loss": 0.1499,
"step": 845
},
{
"epoch": 10.87,
"learning_rate": 0.00027532597793380136,
"loss": 0.152,
"step": 850
},
{
"epoch": 10.94,
"learning_rate": 0.0002751755265797392,
"loss": 0.1514,
"step": 855
},
{
"epoch": 11.0,
"learning_rate": 0.000275025075225677,
"loss": 0.153,
"step": 860
},
{
"epoch": 11.06,
"learning_rate": 0.0002748746238716148,
"loss": 0.1153,
"step": 865
},
{
"epoch": 11.13,
"learning_rate": 0.0002747241725175526,
"loss": 0.1181,
"step": 870
},
{
"epoch": 11.19,
"learning_rate": 0.00027457372116349043,
"loss": 0.1201,
"step": 875
},
{
"epoch": 11.25,
"learning_rate": 0.00027442326980942826,
"loss": 0.1164,
"step": 880
},
{
"epoch": 11.32,
"learning_rate": 0.0002742728184553661,
"loss": 0.1177,
"step": 885
},
{
"epoch": 11.38,
"learning_rate": 0.0002741223671013039,
"loss": 0.1205,
"step": 890
},
{
"epoch": 11.45,
"learning_rate": 0.0002739719157472417,
"loss": 0.1257,
"step": 895
},
{
"epoch": 11.51,
"learning_rate": 0.0002738214643931795,
"loss": 0.1291,
"step": 900
},
{
"epoch": 11.57,
"learning_rate": 0.00027367101303911733,
"loss": 0.1277,
"step": 905
},
{
"epoch": 11.64,
"learning_rate": 0.00027352056168505515,
"loss": 0.1343,
"step": 910
},
{
"epoch": 11.7,
"learning_rate": 0.000273370110330993,
"loss": 0.1312,
"step": 915
},
{
"epoch": 11.77,
"learning_rate": 0.0002732196589769308,
"loss": 0.1314,
"step": 920
},
{
"epoch": 11.83,
"learning_rate": 0.0002730692076228686,
"loss": 0.1367,
"step": 925
},
{
"epoch": 11.89,
"learning_rate": 0.0002729187562688064,
"loss": 0.1336,
"step": 930
},
{
"epoch": 11.96,
"learning_rate": 0.0002727683049147442,
"loss": 0.1367,
"step": 935
},
{
"epoch": 12.02,
"learning_rate": 0.000272617853560682,
"loss": 0.1266,
"step": 940
},
{
"epoch": 12.09,
"learning_rate": 0.0002724674022066198,
"loss": 0.1001,
"step": 945
},
{
"epoch": 12.15,
"learning_rate": 0.00027231695085255765,
"loss": 0.106,
"step": 950
},
{
"epoch": 12.21,
"learning_rate": 0.00027216649949849547,
"loss": 0.1078,
"step": 955
},
{
"epoch": 12.28,
"learning_rate": 0.0002720160481444333,
"loss": 0.1065,
"step": 960
},
{
"epoch": 12.34,
"learning_rate": 0.0002718655967903711,
"loss": 0.1077,
"step": 965
},
{
"epoch": 12.41,
"learning_rate": 0.0002717151454363089,
"loss": 0.1089,
"step": 970
},
{
"epoch": 12.47,
"learning_rate": 0.0002715646940822467,
"loss": 0.1094,
"step": 975
},
{
"epoch": 12.53,
"learning_rate": 0.00027141424272818454,
"loss": 0.1205,
"step": 980
},
{
"epoch": 12.6,
"learning_rate": 0.0002712637913741223,
"loss": 0.1231,
"step": 985
},
{
"epoch": 12.66,
"learning_rate": 0.00027111334002006014,
"loss": 0.1169,
"step": 990
},
{
"epoch": 12.73,
"learning_rate": 0.00027096288866599797,
"loss": 0.1154,
"step": 995
},
{
"epoch": 12.79,
"learning_rate": 0.0002708124373119358,
"loss": 0.113,
"step": 1000
},
{
"epoch": 12.79,
"eval_loss": 1.3787956237792969,
"eval_runtime": 0.319,
"eval_samples_per_second": 31.345,
"eval_steps_per_second": 3.135,
"step": 1000
},
{
"epoch": 12.85,
"learning_rate": 0.0002706619859578736,
"loss": 0.1123,
"step": 1005
},
{
"epoch": 12.92,
"learning_rate": 0.00027051153460381144,
"loss": 0.117,
"step": 1010
},
{
"epoch": 12.98,
"learning_rate": 0.0002703610832497492,
"loss": 0.1199,
"step": 1015
},
{
"epoch": 13.05,
"learning_rate": 0.00027021063189568704,
"loss": 0.0943,
"step": 1020
},
{
"epoch": 13.11,
"learning_rate": 0.00027006018054162486,
"loss": 0.0851,
"step": 1025
},
{
"epoch": 13.17,
"learning_rate": 0.00026990972918756263,
"loss": 0.0906,
"step": 1030
},
{
"epoch": 13.24,
"learning_rate": 0.00026975927783350046,
"loss": 0.0911,
"step": 1035
},
{
"epoch": 13.3,
"learning_rate": 0.0002696088264794383,
"loss": 0.0925,
"step": 1040
},
{
"epoch": 13.37,
"learning_rate": 0.0002694583751253761,
"loss": 0.095,
"step": 1045
},
{
"epoch": 13.43,
"learning_rate": 0.00026930792377131393,
"loss": 0.0921,
"step": 1050
},
{
"epoch": 13.49,
"learning_rate": 0.00026915747241725176,
"loss": 0.0958,
"step": 1055
},
{
"epoch": 13.56,
"learning_rate": 0.00026900702106318953,
"loss": 0.0969,
"step": 1060
},
{
"epoch": 13.62,
"learning_rate": 0.00026885656970912736,
"loss": 0.0973,
"step": 1065
},
{
"epoch": 13.69,
"learning_rate": 0.0002687061183550652,
"loss": 0.1008,
"step": 1070
},
{
"epoch": 13.75,
"learning_rate": 0.00026855566700100295,
"loss": 0.1021,
"step": 1075
},
{
"epoch": 13.81,
"learning_rate": 0.0002684052156469408,
"loss": 0.1018,
"step": 1080
},
{
"epoch": 13.88,
"learning_rate": 0.0002682547642928786,
"loss": 0.1019,
"step": 1085
},
{
"epoch": 13.94,
"learning_rate": 0.00026810431293881643,
"loss": 0.1035,
"step": 1090
},
{
"epoch": 14.0,
"learning_rate": 0.00026795386158475425,
"loss": 0.1081,
"step": 1095
},
{
"epoch": 14.07,
"learning_rate": 0.0002678034102306921,
"loss": 0.0823,
"step": 1100
},
{
"epoch": 14.13,
"learning_rate": 0.00026765295887662985,
"loss": 0.0767,
"step": 1105
},
{
"epoch": 14.2,
"learning_rate": 0.0002675025075225677,
"loss": 0.0808,
"step": 1110
},
{
"epoch": 14.26,
"learning_rate": 0.0002673520561685055,
"loss": 0.0827,
"step": 1115
},
{
"epoch": 14.32,
"learning_rate": 0.00026720160481444327,
"loss": 0.0831,
"step": 1120
},
{
"epoch": 14.39,
"learning_rate": 0.0002670511534603811,
"loss": 0.0853,
"step": 1125
},
{
"epoch": 14.45,
"learning_rate": 0.0002669007021063189,
"loss": 0.084,
"step": 1130
},
{
"epoch": 14.52,
"learning_rate": 0.00026675025075225675,
"loss": 0.0867,
"step": 1135
},
{
"epoch": 14.58,
"learning_rate": 0.00026659979939819457,
"loss": 0.0856,
"step": 1140
},
{
"epoch": 14.64,
"learning_rate": 0.0002664493480441324,
"loss": 0.0864,
"step": 1145
},
{
"epoch": 14.71,
"learning_rate": 0.00026629889669007017,
"loss": 0.0867,
"step": 1150
},
{
"epoch": 14.77,
"learning_rate": 0.000266148445336008,
"loss": 0.0862,
"step": 1155
},
{
"epoch": 14.84,
"learning_rate": 0.0002659979939819458,
"loss": 0.0902,
"step": 1160
},
{
"epoch": 14.9,
"learning_rate": 0.0002658475426278836,
"loss": 0.0924,
"step": 1165
},
{
"epoch": 14.96,
"learning_rate": 0.0002656970912738214,
"loss": 0.0939,
"step": 1170
},
{
"epoch": 15.03,
"learning_rate": 0.00026554663991975924,
"loss": 0.082,
"step": 1175
},
{
"epoch": 15.09,
"learning_rate": 0.00026539618856569707,
"loss": 0.0703,
"step": 1180
},
{
"epoch": 15.16,
"learning_rate": 0.0002652457372116349,
"loss": 0.0695,
"step": 1185
},
{
"epoch": 15.22,
"learning_rate": 0.0002650952858575727,
"loss": 0.0703,
"step": 1190
},
{
"epoch": 15.28,
"learning_rate": 0.0002649448345035105,
"loss": 0.0707,
"step": 1195
},
{
"epoch": 15.35,
"learning_rate": 0.0002647943831494483,
"loss": 0.071,
"step": 1200
},
{
"epoch": 15.41,
"learning_rate": 0.00026464393179538614,
"loss": 0.0727,
"step": 1205
},
{
"epoch": 15.48,
"learning_rate": 0.0002644934804413239,
"loss": 0.0771,
"step": 1210
},
{
"epoch": 15.54,
"learning_rate": 0.00026434302908726173,
"loss": 0.0793,
"step": 1215
},
{
"epoch": 15.6,
"learning_rate": 0.00026419257773319956,
"loss": 0.076,
"step": 1220
},
{
"epoch": 15.67,
"learning_rate": 0.0002640421263791374,
"loss": 0.0744,
"step": 1225
},
{
"epoch": 15.73,
"learning_rate": 0.0002638916750250752,
"loss": 0.0779,
"step": 1230
},
{
"epoch": 15.8,
"learning_rate": 0.00026374122367101303,
"loss": 0.0785,
"step": 1235
},
{
"epoch": 15.86,
"learning_rate": 0.0002635907723169508,
"loss": 0.0782,
"step": 1240
},
{
"epoch": 15.92,
"learning_rate": 0.00026344032096288863,
"loss": 0.079,
"step": 1245
},
{
"epoch": 15.99,
"learning_rate": 0.00026328986960882646,
"loss": 0.0815,
"step": 1250
},
{
"epoch": 15.99,
"eval_loss": 1.4458354711532593,
"eval_runtime": 0.3198,
"eval_samples_per_second": 31.27,
"eval_steps_per_second": 3.127,
"step": 1250
},
{
"epoch": 16.05,
"learning_rate": 0.0002631394182547643,
"loss": 0.0598,
"step": 1255
},
{
"epoch": 16.12,
"learning_rate": 0.0002629889669007021,
"loss": 0.0578,
"step": 1260
},
{
"epoch": 16.18,
"learning_rate": 0.00026283851554663993,
"loss": 0.0596,
"step": 1265
},
{
"epoch": 16.24,
"learning_rate": 0.0002626880641925777,
"loss": 0.0588,
"step": 1270
},
{
"epoch": 16.31,
"learning_rate": 0.00026253761283851553,
"loss": 0.0592,
"step": 1275
},
{
"epoch": 16.37,
"learning_rate": 0.00026238716148445335,
"loss": 0.0614,
"step": 1280
},
{
"epoch": 16.43,
"learning_rate": 0.0002622367101303911,
"loss": 0.0641,
"step": 1285
},
{
"epoch": 16.5,
"learning_rate": 0.00026208625877632895,
"loss": 0.0661,
"step": 1290
},
{
"epoch": 16.56,
"learning_rate": 0.0002619358074222668,
"loss": 0.0685,
"step": 1295
},
{
"epoch": 16.63,
"learning_rate": 0.0002617853560682046,
"loss": 0.0646,
"step": 1300
},
{
"epoch": 16.69,
"learning_rate": 0.0002616349047141424,
"loss": 0.0662,
"step": 1305
},
{
"epoch": 16.75,
"learning_rate": 0.00026148445336008025,
"loss": 0.0699,
"step": 1310
},
{
"epoch": 16.82,
"learning_rate": 0.000261334002006018,
"loss": 0.069,
"step": 1315
},
{
"epoch": 16.88,
"learning_rate": 0.00026118355065195585,
"loss": 0.0683,
"step": 1320
},
{
"epoch": 16.95,
"learning_rate": 0.00026103309929789367,
"loss": 0.0714,
"step": 1325
},
{
"epoch": 17.01,
"learning_rate": 0.00026088264794383144,
"loss": 0.0682,
"step": 1330
},
{
"epoch": 17.07,
"learning_rate": 0.00026073219658976927,
"loss": 0.0537,
"step": 1335
},
{
"epoch": 17.14,
"learning_rate": 0.0002605817452357071,
"loss": 0.055,
"step": 1340
},
{
"epoch": 17.2,
"learning_rate": 0.0002604312938816449,
"loss": 0.0557,
"step": 1345
},
{
"epoch": 17.27,
"learning_rate": 0.00026028084252758274,
"loss": 0.0544,
"step": 1350
},
{
"epoch": 17.33,
"learning_rate": 0.00026013039117352057,
"loss": 0.0545,
"step": 1355
},
{
"epoch": 17.39,
"learning_rate": 0.00025997993981945834,
"loss": 0.0589,
"step": 1360
},
{
"epoch": 17.46,
"learning_rate": 0.00025982948846539616,
"loss": 0.0598,
"step": 1365
},
{
"epoch": 17.52,
"learning_rate": 0.000259679037111334,
"loss": 0.0608,
"step": 1370
},
{
"epoch": 17.59,
"learning_rate": 0.00025952858575727176,
"loss": 0.0628,
"step": 1375
},
{
"epoch": 17.65,
"learning_rate": 0.0002593781344032096,
"loss": 0.0603,
"step": 1380
},
{
"epoch": 17.71,
"learning_rate": 0.0002592276830491474,
"loss": 0.065,
"step": 1385
},
{
"epoch": 17.78,
"learning_rate": 0.00025907723169508524,
"loss": 0.0648,
"step": 1390
},
{
"epoch": 17.84,
"learning_rate": 0.00025892678034102306,
"loss": 0.0649,
"step": 1395
},
{
"epoch": 17.91,
"learning_rate": 0.0002587763289869609,
"loss": 0.0647,
"step": 1400
},
{
"epoch": 17.97,
"learning_rate": 0.00025862587763289866,
"loss": 0.0687,
"step": 1405
},
{
"epoch": 18.03,
"learning_rate": 0.0002584754262788365,
"loss": 0.0592,
"step": 1410
},
{
"epoch": 18.1,
"learning_rate": 0.0002583249749247743,
"loss": 0.047,
"step": 1415
},
{
"epoch": 18.16,
"learning_rate": 0.0002581745235707121,
"loss": 0.0486,
"step": 1420
},
{
"epoch": 18.23,
"learning_rate": 0.0002580240722166499,
"loss": 0.0526,
"step": 1425
},
{
"epoch": 18.29,
"learning_rate": 0.00025787362086258773,
"loss": 0.05,
"step": 1430
},
{
"epoch": 18.35,
"learning_rate": 0.00025772316950852556,
"loss": 0.0646,
"step": 1435
},
{
"epoch": 18.42,
"learning_rate": 0.0002575727181544634,
"loss": 0.0557,
"step": 1440
},
{
"epoch": 18.48,
"learning_rate": 0.0002574222668004012,
"loss": 0.0534,
"step": 1445
},
{
"epoch": 18.55,
"learning_rate": 0.000257271815446339,
"loss": 0.056,
"step": 1450
},
{
"epoch": 18.61,
"learning_rate": 0.0002571213640922768,
"loss": 0.0553,
"step": 1455
},
{
"epoch": 18.67,
"learning_rate": 0.00025697091273821463,
"loss": 0.057,
"step": 1460
},
{
"epoch": 18.74,
"learning_rate": 0.0002568204613841524,
"loss": 0.0545,
"step": 1465
},
{
"epoch": 18.8,
"learning_rate": 0.0002566700100300902,
"loss": 0.0557,
"step": 1470
},
{
"epoch": 18.86,
"learning_rate": 0.00025651955867602805,
"loss": 0.0587,
"step": 1475
},
{
"epoch": 18.93,
"learning_rate": 0.0002563691073219659,
"loss": 0.0574,
"step": 1480
},
{
"epoch": 18.99,
"learning_rate": 0.0002562186559679037,
"loss": 0.0625,
"step": 1485
},
{
"epoch": 19.06,
"learning_rate": 0.0002560682046138415,
"loss": 0.1149,
"step": 1490
},
{
"epoch": 19.12,
"learning_rate": 0.0002559177532597793,
"loss": 0.059,
"step": 1495
},
{
"epoch": 19.18,
"learning_rate": 0.0002557673019057171,
"loss": 0.0472,
"step": 1500
},
{
"epoch": 19.18,
"eval_loss": 1.7803338766098022,
"eval_runtime": 0.3184,
"eval_samples_per_second": 31.405,
"eval_steps_per_second": 3.14,
"step": 1500
},
{
"epoch": 19.25,
"learning_rate": 0.00025561685055165495,
"loss": 0.0432,
"step": 1505
},
{
"epoch": 19.31,
"learning_rate": 0.0002554663991975927,
"loss": 0.0415,
"step": 1510
},
{
"epoch": 19.38,
"learning_rate": 0.00025531594784353054,
"loss": 0.047,
"step": 1515
},
{
"epoch": 19.44,
"learning_rate": 0.00025516549648946837,
"loss": 0.0473,
"step": 1520
},
{
"epoch": 19.5,
"learning_rate": 0.0002550150451354062,
"loss": 0.0482,
"step": 1525
},
{
"epoch": 19.57,
"learning_rate": 0.000254864593781344,
"loss": 0.0493,
"step": 1530
},
{
"epoch": 19.63,
"learning_rate": 0.00025471414242728184,
"loss": 0.0513,
"step": 1535
},
{
"epoch": 19.7,
"learning_rate": 0.0002545636910732196,
"loss": 0.0514,
"step": 1540
},
{
"epoch": 19.76,
"learning_rate": 0.00025441323971915744,
"loss": 0.0509,
"step": 1545
},
{
"epoch": 19.82,
"learning_rate": 0.00025426278836509526,
"loss": 0.0512,
"step": 1550
},
{
"epoch": 19.89,
"learning_rate": 0.0002541123370110331,
"loss": 0.0535,
"step": 1555
},
{
"epoch": 19.95,
"learning_rate": 0.00025396188565697086,
"loss": 0.0522,
"step": 1560
},
{
"epoch": 20.02,
"learning_rate": 0.0002538114343029087,
"loss": 0.0491,
"step": 1565
},
{
"epoch": 20.08,
"learning_rate": 0.0002536609829488465,
"loss": 0.0364,
"step": 1570
},
{
"epoch": 20.14,
"learning_rate": 0.00025351053159478434,
"loss": 0.0398,
"step": 1575
},
{
"epoch": 20.21,
"learning_rate": 0.00025336008024072216,
"loss": 0.0393,
"step": 1580
},
{
"epoch": 20.27,
"learning_rate": 0.00025320962888665993,
"loss": 0.0418,
"step": 1585
},
{
"epoch": 20.34,
"learning_rate": 0.00025305917753259776,
"loss": 0.0436,
"step": 1590
},
{
"epoch": 20.4,
"learning_rate": 0.0002529087261785356,
"loss": 0.0439,
"step": 1595
},
{
"epoch": 20.46,
"learning_rate": 0.0002527582748244734,
"loss": 0.0458,
"step": 1600
},
{
"epoch": 20.53,
"learning_rate": 0.00025260782347041123,
"loss": 0.0443,
"step": 1605
},
{
"epoch": 20.59,
"learning_rate": 0.00025245737211634906,
"loss": 0.0443,
"step": 1610
},
{
"epoch": 20.66,
"learning_rate": 0.00025230692076228683,
"loss": 0.0439,
"step": 1615
},
{
"epoch": 20.72,
"learning_rate": 0.00025215646940822465,
"loss": 0.0431,
"step": 1620
},
{
"epoch": 20.78,
"learning_rate": 0.0002520060180541625,
"loss": 0.0451,
"step": 1625
},
{
"epoch": 20.85,
"learning_rate": 0.00025185556670010025,
"loss": 0.0474,
"step": 1630
},
{
"epoch": 20.91,
"learning_rate": 0.0002517051153460381,
"loss": 0.0479,
"step": 1635
},
{
"epoch": 20.98,
"learning_rate": 0.0002515546639919759,
"loss": 0.0483,
"step": 1640
},
{
"epoch": 21.04,
"learning_rate": 0.0002514042126379137,
"loss": 0.0368,
"step": 1645
},
{
"epoch": 21.1,
"learning_rate": 0.00025125376128385155,
"loss": 0.032,
"step": 1650
},
{
"epoch": 21.17,
"learning_rate": 0.0002511033099297894,
"loss": 0.0343,
"step": 1655
},
{
"epoch": 21.23,
"learning_rate": 0.00025095285857572715,
"loss": 0.0366,
"step": 1660
},
{
"epoch": 21.29,
"learning_rate": 0.000250802407221665,
"loss": 0.0377,
"step": 1665
},
{
"epoch": 21.36,
"learning_rate": 0.0002506519558676028,
"loss": 0.0378,
"step": 1670
},
{
"epoch": 21.42,
"learning_rate": 0.00025050150451354057,
"loss": 0.0374,
"step": 1675
},
{
"epoch": 21.49,
"learning_rate": 0.0002503510531594784,
"loss": 0.0421,
"step": 1680
},
{
"epoch": 21.55,
"learning_rate": 0.0002502006018054162,
"loss": 0.037,
"step": 1685
},
{
"epoch": 21.61,
"learning_rate": 0.00025005015045135405,
"loss": 0.0392,
"step": 1690
},
{
"epoch": 21.68,
"learning_rate": 0.00024989969909729187,
"loss": 0.0421,
"step": 1695
},
{
"epoch": 21.74,
"learning_rate": 0.0002497492477432297,
"loss": 0.0425,
"step": 1700
},
{
"epoch": 21.81,
"learning_rate": 0.00024959879638916747,
"loss": 0.0442,
"step": 1705
},
{
"epoch": 21.87,
"learning_rate": 0.0002494483450351053,
"loss": 0.042,
"step": 1710
},
{
"epoch": 21.93,
"learning_rate": 0.0002492978936810431,
"loss": 0.0425,
"step": 1715
},
{
"epoch": 22.0,
"learning_rate": 0.0002491474423269809,
"loss": 0.0432,
"step": 1720
},
{
"epoch": 22.06,
"learning_rate": 0.0002489969909729187,
"loss": 0.029,
"step": 1725
},
{
"epoch": 22.13,
"learning_rate": 0.00024884653961885654,
"loss": 0.0303,
"step": 1730
},
{
"epoch": 22.19,
"learning_rate": 0.00024869608826479436,
"loss": 0.0324,
"step": 1735
},
{
"epoch": 22.25,
"learning_rate": 0.0002485456369107322,
"loss": 0.0319,
"step": 1740
},
{
"epoch": 22.32,
"learning_rate": 0.00024839518555667,
"loss": 0.0325,
"step": 1745
},
{
"epoch": 22.38,
"learning_rate": 0.0002482447342026078,
"loss": 0.033,
"step": 1750
},
{
"epoch": 22.38,
"eval_loss": 1.8502811193466187,
"eval_runtime": 0.319,
"eval_samples_per_second": 31.348,
"eval_steps_per_second": 3.135,
"step": 1750
},
{
"epoch": 22.45,
"learning_rate": 0.0002480942828485456,
"loss": 0.032,
"step": 1755
},
{
"epoch": 22.51,
"learning_rate": 0.00024794383149448344,
"loss": 0.0352,
"step": 1760
},
{
"epoch": 22.57,
"learning_rate": 0.0002477933801404212,
"loss": 0.0367,
"step": 1765
},
{
"epoch": 22.64,
"learning_rate": 0.00024764292878635903,
"loss": 0.0382,
"step": 1770
},
{
"epoch": 22.7,
"learning_rate": 0.00024749247743229686,
"loss": 0.039,
"step": 1775
},
{
"epoch": 22.77,
"learning_rate": 0.0002473420260782347,
"loss": 0.0387,
"step": 1780
},
{
"epoch": 22.83,
"learning_rate": 0.0002471915747241725,
"loss": 0.0411,
"step": 1785
},
{
"epoch": 22.89,
"learning_rate": 0.00024704112337011033,
"loss": 0.04,
"step": 1790
},
{
"epoch": 22.96,
"learning_rate": 0.0002468906720160481,
"loss": 0.0405,
"step": 1795
},
{
"epoch": 23.02,
"learning_rate": 0.00024674022066198593,
"loss": 0.0347,
"step": 1800
},
{
"epoch": 23.09,
"learning_rate": 0.00024658976930792375,
"loss": 0.0295,
"step": 1805
},
{
"epoch": 23.15,
"learning_rate": 0.0002464393179538615,
"loss": 0.0298,
"step": 1810
},
{
"epoch": 23.21,
"learning_rate": 0.00024628886659979935,
"loss": 0.0314,
"step": 1815
},
{
"epoch": 23.28,
"learning_rate": 0.0002461384152457372,
"loss": 0.0334,
"step": 1820
},
{
"epoch": 23.34,
"learning_rate": 0.000245987963891675,
"loss": 0.035,
"step": 1825
},
{
"epoch": 23.41,
"learning_rate": 0.0002458375125376128,
"loss": 0.033,
"step": 1830
},
{
"epoch": 23.47,
"learning_rate": 0.00024568706118355065,
"loss": 0.0336,
"step": 1835
},
{
"epoch": 23.53,
"learning_rate": 0.0002455366098294884,
"loss": 0.0338,
"step": 1840
},
{
"epoch": 23.6,
"learning_rate": 0.00024538615847542625,
"loss": 0.0371,
"step": 1845
},
{
"epoch": 23.66,
"learning_rate": 0.0002452357071213641,
"loss": 0.0372,
"step": 1850
},
{
"epoch": 23.73,
"learning_rate": 0.00024508525576730184,
"loss": 0.0365,
"step": 1855
},
{
"epoch": 23.79,
"learning_rate": 0.00024493480441323967,
"loss": 0.0368,
"step": 1860
},
{
"epoch": 23.85,
"learning_rate": 0.0002447843530591775,
"loss": 0.0347,
"step": 1865
},
{
"epoch": 23.92,
"learning_rate": 0.0002446339017051153,
"loss": 0.0362,
"step": 1870
},
{
"epoch": 23.98,
"learning_rate": 0.00024448345035105315,
"loss": 0.0379,
"step": 1875
},
{
"epoch": 24.04,
"learning_rate": 0.00024433299899699097,
"loss": 0.0398,
"step": 1880
},
{
"epoch": 24.11,
"learning_rate": 0.00024418254764292874,
"loss": 0.0288,
"step": 1885
},
{
"epoch": 24.17,
"learning_rate": 0.00024403209628886657,
"loss": 0.0305,
"step": 1890
},
{
"epoch": 24.24,
"learning_rate": 0.0002438816449348044,
"loss": 0.0304,
"step": 1895
},
{
"epoch": 24.3,
"learning_rate": 0.0002437311935807422,
"loss": 0.0282,
"step": 1900
},
{
"epoch": 24.36,
"learning_rate": 0.00024358074222668002,
"loss": 0.0289,
"step": 1905
},
{
"epoch": 24.43,
"learning_rate": 0.00024343029087261784,
"loss": 0.0302,
"step": 1910
},
{
"epoch": 24.49,
"learning_rate": 0.00024327983951855564,
"loss": 0.0258,
"step": 1915
},
{
"epoch": 24.56,
"learning_rate": 0.00024312938816449346,
"loss": 0.0266,
"step": 1920
},
{
"epoch": 24.62,
"learning_rate": 0.0002429789368104313,
"loss": 0.0278,
"step": 1925
},
{
"epoch": 24.68,
"learning_rate": 0.00024282848545636906,
"loss": 0.0316,
"step": 1930
},
{
"epoch": 24.75,
"learning_rate": 0.00024267803410230689,
"loss": 0.0328,
"step": 1935
},
{
"epoch": 24.81,
"learning_rate": 0.0002425275827482447,
"loss": 0.0336,
"step": 1940
},
{
"epoch": 24.88,
"learning_rate": 0.0002423771313941825,
"loss": 0.0311,
"step": 1945
},
{
"epoch": 24.94,
"learning_rate": 0.00024222668004012033,
"loss": 0.0324,
"step": 1950
},
{
"epoch": 25.0,
"learning_rate": 0.00024207622868605816,
"loss": 0.0339,
"step": 1955
},
{
"epoch": 25.07,
"learning_rate": 0.00024192577733199596,
"loss": 0.0235,
"step": 1960
},
{
"epoch": 25.13,
"learning_rate": 0.00024177532597793378,
"loss": 0.029,
"step": 1965
},
{
"epoch": 25.2,
"learning_rate": 0.0002416248746238716,
"loss": 0.0281,
"step": 1970
},
{
"epoch": 25.26,
"learning_rate": 0.00024147442326980938,
"loss": 0.0276,
"step": 1975
},
{
"epoch": 25.32,
"learning_rate": 0.0002413239719157472,
"loss": 0.0282,
"step": 1980
},
{
"epoch": 25.39,
"learning_rate": 0.00024117352056168503,
"loss": 0.0308,
"step": 1985
},
{
"epoch": 25.45,
"learning_rate": 0.00024102306920762283,
"loss": 0.0313,
"step": 1990
},
{
"epoch": 25.52,
"learning_rate": 0.00024087261785356065,
"loss": 0.0311,
"step": 1995
},
{
"epoch": 25.58,
"learning_rate": 0.00024072216649949848,
"loss": 0.0307,
"step": 2000
},
{
"epoch": 25.58,
"eval_loss": 1.802398920059204,
"eval_runtime": 0.3194,
"eval_samples_per_second": 31.309,
"eval_steps_per_second": 3.131,
"step": 2000
}
],
"max_steps": 10000,
"num_train_epochs": 129,
"total_flos": 4.2458758196763034e+17,
"trial_name": null,
"trial_params": null
}