wav2vec2-base-mirst500 / trainer_state.json
gary109's picture
End of training
1440fd4
raw
history blame contribute delete
No virus
80.9 kB
{
"best_metric": 0.7016984883693075,
"best_model_checkpoint": "wav2vec2-base-mirst500/checkpoint-6520",
"epoch": 4.999616711383672,
"global_step": 6520,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.6012269938650306e-07,
"loss": 2.0823,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 9.202453987730061e-07,
"loss": 2.0814,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 1.3803680981595093e-06,
"loss": 2.0803,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 1.8404907975460122e-06,
"loss": 2.0788,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 2.3006134969325154e-06,
"loss": 2.0776,
"step": 50
},
{
"epoch": 0.05,
"learning_rate": 2.7607361963190186e-06,
"loss": 2.0731,
"step": 60
},
{
"epoch": 0.05,
"learning_rate": 3.2208588957055217e-06,
"loss": 2.0728,
"step": 70
},
{
"epoch": 0.06,
"learning_rate": 3.6809815950920245e-06,
"loss": 2.0645,
"step": 80
},
{
"epoch": 0.07,
"learning_rate": 4.141104294478528e-06,
"loss": 2.0645,
"step": 90
},
{
"epoch": 0.08,
"learning_rate": 4.601226993865031e-06,
"loss": 2.0514,
"step": 100
},
{
"epoch": 0.08,
"learning_rate": 5.061349693251534e-06,
"loss": 2.0403,
"step": 110
},
{
"epoch": 0.09,
"learning_rate": 5.521472392638037e-06,
"loss": 2.0268,
"step": 120
},
{
"epoch": 0.1,
"learning_rate": 5.981595092024539e-06,
"loss": 2.0036,
"step": 130
},
{
"epoch": 0.11,
"learning_rate": 6.4417177914110434e-06,
"loss": 2.0021,
"step": 140
},
{
"epoch": 0.11,
"learning_rate": 6.901840490797547e-06,
"loss": 1.9849,
"step": 150
},
{
"epoch": 0.12,
"learning_rate": 7.361963190184049e-06,
"loss": 1.9574,
"step": 160
},
{
"epoch": 0.13,
"learning_rate": 7.822085889570552e-06,
"loss": 1.9671,
"step": 170
},
{
"epoch": 0.14,
"learning_rate": 8.282208588957055e-06,
"loss": 1.9527,
"step": 180
},
{
"epoch": 0.15,
"learning_rate": 8.742331288343558e-06,
"loss": 1.9551,
"step": 190
},
{
"epoch": 0.15,
"learning_rate": 9.202453987730062e-06,
"loss": 1.9561,
"step": 200
},
{
"epoch": 0.16,
"learning_rate": 9.662576687116563e-06,
"loss": 1.9289,
"step": 210
},
{
"epoch": 0.17,
"learning_rate": 1.0122699386503068e-05,
"loss": 1.9388,
"step": 220
},
{
"epoch": 0.18,
"learning_rate": 1.0582822085889571e-05,
"loss": 1.9122,
"step": 230
},
{
"epoch": 0.18,
"learning_rate": 1.1042944785276074e-05,
"loss": 1.8831,
"step": 240
},
{
"epoch": 0.19,
"learning_rate": 1.1503067484662577e-05,
"loss": 1.9166,
"step": 250
},
{
"epoch": 0.2,
"learning_rate": 1.1963190184049079e-05,
"loss": 1.8841,
"step": 260
},
{
"epoch": 0.21,
"learning_rate": 1.2423312883435584e-05,
"loss": 1.8977,
"step": 270
},
{
"epoch": 0.21,
"learning_rate": 1.2883435582822087e-05,
"loss": 1.9011,
"step": 280
},
{
"epoch": 0.22,
"learning_rate": 1.3343558282208588e-05,
"loss": 1.8778,
"step": 290
},
{
"epoch": 0.23,
"learning_rate": 1.3803680981595093e-05,
"loss": 1.8782,
"step": 300
},
{
"epoch": 0.24,
"learning_rate": 1.4263803680981595e-05,
"loss": 1.8568,
"step": 310
},
{
"epoch": 0.25,
"learning_rate": 1.4723926380368098e-05,
"loss": 1.8845,
"step": 320
},
{
"epoch": 0.25,
"learning_rate": 1.5184049079754601e-05,
"loss": 1.852,
"step": 330
},
{
"epoch": 0.26,
"learning_rate": 1.5598159509202456e-05,
"loss": 1.8479,
"step": 340
},
{
"epoch": 0.27,
"learning_rate": 1.6058282208588957e-05,
"loss": 1.8345,
"step": 350
},
{
"epoch": 0.28,
"learning_rate": 1.6518404907975462e-05,
"loss": 1.8518,
"step": 360
},
{
"epoch": 0.28,
"learning_rate": 1.6978527607361963e-05,
"loss": 1.8653,
"step": 370
},
{
"epoch": 0.29,
"learning_rate": 1.7438650306748465e-05,
"loss": 1.837,
"step": 380
},
{
"epoch": 0.3,
"learning_rate": 1.789877300613497e-05,
"loss": 1.8058,
"step": 390
},
{
"epoch": 0.31,
"learning_rate": 1.8358895705521475e-05,
"loss": 1.8301,
"step": 400
},
{
"epoch": 0.31,
"learning_rate": 1.8819018404907976e-05,
"loss": 1.8287,
"step": 410
},
{
"epoch": 0.32,
"learning_rate": 1.9279141104294478e-05,
"loss": 1.7848,
"step": 420
},
{
"epoch": 0.33,
"learning_rate": 1.9739263803680982e-05,
"loss": 1.7821,
"step": 430
},
{
"epoch": 0.34,
"learning_rate": 2.0199386503067484e-05,
"loss": 1.7985,
"step": 440
},
{
"epoch": 0.34,
"learning_rate": 2.065950920245399e-05,
"loss": 1.762,
"step": 450
},
{
"epoch": 0.35,
"learning_rate": 2.1119631901840494e-05,
"loss": 1.7812,
"step": 460
},
{
"epoch": 0.36,
"learning_rate": 2.1579754601226992e-05,
"loss": 1.7677,
"step": 470
},
{
"epoch": 0.37,
"learning_rate": 2.2039877300613497e-05,
"loss": 1.7733,
"step": 480
},
{
"epoch": 0.38,
"learning_rate": 2.25e-05,
"loss": 1.7699,
"step": 490
},
{
"epoch": 0.38,
"learning_rate": 2.2960122699386503e-05,
"loss": 1.7429,
"step": 500
},
{
"epoch": 0.39,
"learning_rate": 2.3420245398773008e-05,
"loss": 1.6911,
"step": 510
},
{
"epoch": 0.4,
"learning_rate": 2.388036809815951e-05,
"loss": 1.6975,
"step": 520
},
{
"epoch": 0.41,
"learning_rate": 2.434049079754601e-05,
"loss": 1.7233,
"step": 530
},
{
"epoch": 0.41,
"learning_rate": 2.4800613496932516e-05,
"loss": 1.6838,
"step": 540
},
{
"epoch": 0.42,
"learning_rate": 2.526073619631902e-05,
"loss": 1.6709,
"step": 550
},
{
"epoch": 0.43,
"learning_rate": 2.5720858895705522e-05,
"loss": 1.7078,
"step": 560
},
{
"epoch": 0.44,
"learning_rate": 2.6180981595092023e-05,
"loss": 1.6882,
"step": 570
},
{
"epoch": 0.44,
"learning_rate": 2.6641104294478528e-05,
"loss": 1.6386,
"step": 580
},
{
"epoch": 0.45,
"learning_rate": 2.7101226993865033e-05,
"loss": 1.6315,
"step": 590
},
{
"epoch": 0.46,
"learning_rate": 2.7561349693251535e-05,
"loss": 1.5773,
"step": 600
},
{
"epoch": 0.47,
"learning_rate": 2.802147239263804e-05,
"loss": 1.6123,
"step": 610
},
{
"epoch": 0.48,
"learning_rate": 2.848159509202454e-05,
"loss": 1.6244,
"step": 620
},
{
"epoch": 0.48,
"learning_rate": 2.8941717791411042e-05,
"loss": 1.5473,
"step": 630
},
{
"epoch": 0.49,
"learning_rate": 2.9401840490797547e-05,
"loss": 1.5417,
"step": 640
},
{
"epoch": 0.5,
"learning_rate": 2.9861963190184052e-05,
"loss": 1.5088,
"step": 650
},
{
"epoch": 0.51,
"learning_rate": 2.9964212678936606e-05,
"loss": 1.51,
"step": 660
},
{
"epoch": 0.51,
"learning_rate": 2.9913087934560325e-05,
"loss": 1.5141,
"step": 670
},
{
"epoch": 0.52,
"learning_rate": 2.9861963190184052e-05,
"loss": 1.4878,
"step": 680
},
{
"epoch": 0.53,
"learning_rate": 2.9810838445807772e-05,
"loss": 1.4722,
"step": 690
},
{
"epoch": 0.54,
"learning_rate": 2.9759713701431495e-05,
"loss": 1.4969,
"step": 700
},
{
"epoch": 0.54,
"learning_rate": 2.9708588957055215e-05,
"loss": 1.4691,
"step": 710
},
{
"epoch": 0.55,
"learning_rate": 2.9657464212678938e-05,
"loss": 1.4537,
"step": 720
},
{
"epoch": 0.56,
"learning_rate": 2.9606339468302658e-05,
"loss": 1.4395,
"step": 730
},
{
"epoch": 0.57,
"learning_rate": 2.955521472392638e-05,
"loss": 1.4219,
"step": 740
},
{
"epoch": 0.57,
"learning_rate": 2.9504089979550104e-05,
"loss": 1.421,
"step": 750
},
{
"epoch": 0.58,
"learning_rate": 2.9452965235173824e-05,
"loss": 1.4472,
"step": 760
},
{
"epoch": 0.59,
"learning_rate": 2.9401840490797547e-05,
"loss": 1.404,
"step": 770
},
{
"epoch": 0.6,
"learning_rate": 2.9350715746421267e-05,
"loss": 1.3762,
"step": 780
},
{
"epoch": 0.61,
"learning_rate": 2.929959100204499e-05,
"loss": 1.3499,
"step": 790
},
{
"epoch": 0.61,
"learning_rate": 2.924846625766871e-05,
"loss": 1.387,
"step": 800
},
{
"epoch": 0.62,
"learning_rate": 2.9197341513292437e-05,
"loss": 1.3872,
"step": 810
},
{
"epoch": 0.63,
"learning_rate": 2.9146216768916156e-05,
"loss": 1.3594,
"step": 820
},
{
"epoch": 0.64,
"learning_rate": 2.909509202453988e-05,
"loss": 1.3386,
"step": 830
},
{
"epoch": 0.64,
"learning_rate": 2.90439672801636e-05,
"loss": 1.362,
"step": 840
},
{
"epoch": 0.65,
"learning_rate": 2.8992842535787323e-05,
"loss": 1.4005,
"step": 850
},
{
"epoch": 0.66,
"learning_rate": 2.8941717791411042e-05,
"loss": 1.2967,
"step": 860
},
{
"epoch": 0.67,
"learning_rate": 2.8890593047034765e-05,
"loss": 1.3309,
"step": 870
},
{
"epoch": 0.67,
"learning_rate": 2.883946830265849e-05,
"loss": 1.3563,
"step": 880
},
{
"epoch": 0.68,
"learning_rate": 2.8788343558282212e-05,
"loss": 1.3469,
"step": 890
},
{
"epoch": 0.69,
"learning_rate": 2.873721881390593e-05,
"loss": 1.3561,
"step": 900
},
{
"epoch": 0.7,
"learning_rate": 2.8686094069529655e-05,
"loss": 1.3207,
"step": 910
},
{
"epoch": 0.71,
"learning_rate": 2.8634969325153375e-05,
"loss": 1.327,
"step": 920
},
{
"epoch": 0.71,
"learning_rate": 2.8583844580777094e-05,
"loss": 1.2817,
"step": 930
},
{
"epoch": 0.72,
"learning_rate": 2.8532719836400818e-05,
"loss": 1.2823,
"step": 940
},
{
"epoch": 0.73,
"learning_rate": 2.848159509202454e-05,
"loss": 1.2915,
"step": 950
},
{
"epoch": 0.74,
"learning_rate": 2.8430470347648264e-05,
"loss": 1.2361,
"step": 960
},
{
"epoch": 0.74,
"learning_rate": 2.8379345603271984e-05,
"loss": 1.2647,
"step": 970
},
{
"epoch": 0.75,
"learning_rate": 2.8328220858895707e-05,
"loss": 1.2677,
"step": 980
},
{
"epoch": 0.76,
"learning_rate": 2.8277096114519427e-05,
"loss": 1.2611,
"step": 990
},
{
"epoch": 0.77,
"learning_rate": 2.822597137014315e-05,
"loss": 1.293,
"step": 1000
},
{
"epoch": 0.77,
"learning_rate": 2.817484662576687e-05,
"loss": 1.2216,
"step": 1010
},
{
"epoch": 0.78,
"learning_rate": 2.8123721881390596e-05,
"loss": 1.3012,
"step": 1020
},
{
"epoch": 0.79,
"learning_rate": 2.8072597137014316e-05,
"loss": 1.2432,
"step": 1030
},
{
"epoch": 0.8,
"learning_rate": 2.802147239263804e-05,
"loss": 1.2935,
"step": 1040
},
{
"epoch": 0.8,
"learning_rate": 2.797034764826176e-05,
"loss": 1.2375,
"step": 1050
},
{
"epoch": 0.81,
"learning_rate": 2.7919222903885482e-05,
"loss": 1.2617,
"step": 1060
},
{
"epoch": 0.82,
"learning_rate": 2.7868098159509202e-05,
"loss": 1.2519,
"step": 1070
},
{
"epoch": 0.83,
"learning_rate": 2.7816973415132922e-05,
"loss": 1.1971,
"step": 1080
},
{
"epoch": 0.84,
"learning_rate": 2.776584867075665e-05,
"loss": 1.2598,
"step": 1090
},
{
"epoch": 0.84,
"learning_rate": 2.771472392638037e-05,
"loss": 1.2187,
"step": 1100
},
{
"epoch": 0.85,
"learning_rate": 2.766359918200409e-05,
"loss": 1.2202,
"step": 1110
},
{
"epoch": 0.86,
"learning_rate": 2.761247443762781e-05,
"loss": 1.2007,
"step": 1120
},
{
"epoch": 0.87,
"learning_rate": 2.7561349693251535e-05,
"loss": 1.2117,
"step": 1130
},
{
"epoch": 0.87,
"learning_rate": 2.7510224948875254e-05,
"loss": 1.2165,
"step": 1140
},
{
"epoch": 0.88,
"learning_rate": 2.7459100204498977e-05,
"loss": 1.2141,
"step": 1150
},
{
"epoch": 0.89,
"learning_rate": 2.74079754601227e-05,
"loss": 1.2257,
"step": 1160
},
{
"epoch": 0.9,
"learning_rate": 2.7356850715746424e-05,
"loss": 1.1844,
"step": 1170
},
{
"epoch": 0.9,
"learning_rate": 2.7305725971370144e-05,
"loss": 1.229,
"step": 1180
},
{
"epoch": 0.91,
"learning_rate": 2.7254601226993867e-05,
"loss": 1.2189,
"step": 1190
},
{
"epoch": 0.92,
"learning_rate": 2.7203476482617587e-05,
"loss": 1.2027,
"step": 1200
},
{
"epoch": 0.93,
"learning_rate": 2.715235173824131e-05,
"loss": 1.2362,
"step": 1210
},
{
"epoch": 0.94,
"learning_rate": 2.7101226993865033e-05,
"loss": 1.1787,
"step": 1220
},
{
"epoch": 0.94,
"learning_rate": 2.7050102249488753e-05,
"loss": 1.2087,
"step": 1230
},
{
"epoch": 0.95,
"learning_rate": 2.6998977505112476e-05,
"loss": 1.1646,
"step": 1240
},
{
"epoch": 0.96,
"learning_rate": 2.6947852760736196e-05,
"loss": 1.2548,
"step": 1250
},
{
"epoch": 0.97,
"learning_rate": 2.689672801635992e-05,
"loss": 1.2269,
"step": 1260
},
{
"epoch": 0.97,
"learning_rate": 2.684560327198364e-05,
"loss": 1.1421,
"step": 1270
},
{
"epoch": 0.98,
"learning_rate": 2.6794478527607362e-05,
"loss": 1.2349,
"step": 1280
},
{
"epoch": 0.99,
"learning_rate": 2.6743353783231085e-05,
"loss": 1.1553,
"step": 1290
},
{
"epoch": 1.0,
"learning_rate": 2.669222903885481e-05,
"loss": 1.1999,
"step": 1300
},
{
"epoch": 1.0,
"eval_accuracy": 0.5877392616726158,
"eval_loss": 1.102908730506897,
"eval_runtime": 301.1056,
"eval_samples_per_second": 138.632,
"eval_steps_per_second": 69.318,
"step": 1304
},
{
"epoch": 1.0,
"learning_rate": 2.6641104294478528e-05,
"loss": 1.2812,
"step": 1310
},
{
"epoch": 1.01,
"learning_rate": 2.658997955010225e-05,
"loss": 1.1977,
"step": 1320
},
{
"epoch": 1.02,
"learning_rate": 2.653885480572597e-05,
"loss": 1.1985,
"step": 1330
},
{
"epoch": 1.03,
"learning_rate": 2.6487730061349694e-05,
"loss": 1.1709,
"step": 1340
},
{
"epoch": 1.04,
"learning_rate": 2.6441717791411043e-05,
"loss": 1.2057,
"step": 1350
},
{
"epoch": 1.04,
"learning_rate": 2.6390593047034766e-05,
"loss": 1.1377,
"step": 1360
},
{
"epoch": 1.05,
"learning_rate": 2.6339468302658486e-05,
"loss": 1.1278,
"step": 1370
},
{
"epoch": 1.06,
"learning_rate": 2.628834355828221e-05,
"loss": 1.1997,
"step": 1380
},
{
"epoch": 1.07,
"learning_rate": 2.623721881390593e-05,
"loss": 1.121,
"step": 1390
},
{
"epoch": 1.07,
"learning_rate": 2.6186094069529655e-05,
"loss": 1.2115,
"step": 1400
},
{
"epoch": 1.08,
"learning_rate": 2.6134969325153375e-05,
"loss": 1.18,
"step": 1410
},
{
"epoch": 1.09,
"learning_rate": 2.6083844580777098e-05,
"loss": 1.1797,
"step": 1420
},
{
"epoch": 1.1,
"learning_rate": 2.6032719836400818e-05,
"loss": 1.1343,
"step": 1430
},
{
"epoch": 1.1,
"learning_rate": 2.598159509202454e-05,
"loss": 1.1437,
"step": 1440
},
{
"epoch": 1.11,
"learning_rate": 2.593047034764826e-05,
"loss": 1.1184,
"step": 1450
},
{
"epoch": 1.12,
"learning_rate": 2.5879345603271984e-05,
"loss": 1.1675,
"step": 1460
},
{
"epoch": 1.13,
"learning_rate": 2.5828220858895707e-05,
"loss": 1.171,
"step": 1470
},
{
"epoch": 1.13,
"learning_rate": 2.577709611451943e-05,
"loss": 1.1481,
"step": 1480
},
{
"epoch": 1.14,
"learning_rate": 2.572597137014315e-05,
"loss": 1.1237,
"step": 1490
},
{
"epoch": 1.15,
"learning_rate": 2.5674846625766873e-05,
"loss": 1.1696,
"step": 1500
},
{
"epoch": 1.16,
"learning_rate": 2.5623721881390593e-05,
"loss": 1.1376,
"step": 1510
},
{
"epoch": 1.17,
"learning_rate": 2.5572597137014313e-05,
"loss": 1.126,
"step": 1520
},
{
"epoch": 1.17,
"learning_rate": 2.5521472392638036e-05,
"loss": 1.1429,
"step": 1530
},
{
"epoch": 1.18,
"learning_rate": 2.547034764826176e-05,
"loss": 1.1271,
"step": 1540
},
{
"epoch": 1.19,
"learning_rate": 2.5419222903885483e-05,
"loss": 1.1538,
"step": 1550
},
{
"epoch": 1.2,
"learning_rate": 2.5368098159509202e-05,
"loss": 1.1844,
"step": 1560
},
{
"epoch": 1.2,
"learning_rate": 2.5316973415132926e-05,
"loss": 1.1682,
"step": 1570
},
{
"epoch": 1.21,
"learning_rate": 2.5265848670756645e-05,
"loss": 1.1432,
"step": 1580
},
{
"epoch": 1.22,
"learning_rate": 2.521472392638037e-05,
"loss": 1.1812,
"step": 1590
},
{
"epoch": 1.23,
"learning_rate": 2.516359918200409e-05,
"loss": 1.1812,
"step": 1600
},
{
"epoch": 1.23,
"learning_rate": 2.5112474437627815e-05,
"loss": 1.1207,
"step": 1610
},
{
"epoch": 1.24,
"learning_rate": 2.5061349693251535e-05,
"loss": 1.105,
"step": 1620
},
{
"epoch": 1.25,
"learning_rate": 2.5010224948875258e-05,
"loss": 1.1223,
"step": 1630
},
{
"epoch": 1.26,
"learning_rate": 2.4959100204498978e-05,
"loss": 1.0973,
"step": 1640
},
{
"epoch": 1.27,
"learning_rate": 2.49079754601227e-05,
"loss": 1.131,
"step": 1650
},
{
"epoch": 1.27,
"learning_rate": 2.485685071574642e-05,
"loss": 1.1277,
"step": 1660
},
{
"epoch": 1.28,
"learning_rate": 2.4805725971370144e-05,
"loss": 1.0796,
"step": 1670
},
{
"epoch": 1.29,
"learning_rate": 2.4754601226993867e-05,
"loss": 1.1054,
"step": 1680
},
{
"epoch": 1.3,
"learning_rate": 2.4703476482617587e-05,
"loss": 1.1159,
"step": 1690
},
{
"epoch": 1.3,
"learning_rate": 2.465235173824131e-05,
"loss": 1.0675,
"step": 1700
},
{
"epoch": 1.31,
"learning_rate": 2.460122699386503e-05,
"loss": 1.1283,
"step": 1710
},
{
"epoch": 1.32,
"learning_rate": 2.4550102249488753e-05,
"loss": 1.1507,
"step": 1720
},
{
"epoch": 1.33,
"learning_rate": 2.4498977505112473e-05,
"loss": 1.1587,
"step": 1730
},
{
"epoch": 1.33,
"learning_rate": 2.44478527607362e-05,
"loss": 1.1495,
"step": 1740
},
{
"epoch": 1.34,
"learning_rate": 2.439672801635992e-05,
"loss": 1.1109,
"step": 1750
},
{
"epoch": 1.35,
"learning_rate": 2.4345603271983642e-05,
"loss": 1.124,
"step": 1760
},
{
"epoch": 1.36,
"learning_rate": 2.4294478527607362e-05,
"loss": 1.1369,
"step": 1770
},
{
"epoch": 1.36,
"learning_rate": 2.4243353783231085e-05,
"loss": 1.1066,
"step": 1780
},
{
"epoch": 1.37,
"learning_rate": 2.4192229038854805e-05,
"loss": 1.1119,
"step": 1790
},
{
"epoch": 1.38,
"learning_rate": 2.414110429447853e-05,
"loss": 1.0885,
"step": 1800
},
{
"epoch": 1.39,
"learning_rate": 2.408997955010225e-05,
"loss": 1.1023,
"step": 1810
},
{
"epoch": 1.4,
"learning_rate": 2.403885480572597e-05,
"loss": 1.1624,
"step": 1820
},
{
"epoch": 1.4,
"learning_rate": 2.3987730061349695e-05,
"loss": 1.089,
"step": 1830
},
{
"epoch": 1.41,
"learning_rate": 2.3936605316973414e-05,
"loss": 1.1186,
"step": 1840
},
{
"epoch": 1.42,
"learning_rate": 2.3885480572597138e-05,
"loss": 1.0953,
"step": 1850
},
{
"epoch": 1.43,
"learning_rate": 2.3834355828220857e-05,
"loss": 1.1036,
"step": 1860
},
{
"epoch": 1.43,
"learning_rate": 2.378323108384458e-05,
"loss": 1.0797,
"step": 1870
},
{
"epoch": 1.44,
"learning_rate": 2.3732106339468304e-05,
"loss": 1.1168,
"step": 1880
},
{
"epoch": 1.45,
"learning_rate": 2.3680981595092027e-05,
"loss": 1.1152,
"step": 1890
},
{
"epoch": 1.46,
"learning_rate": 2.3629856850715747e-05,
"loss": 1.0968,
"step": 1900
},
{
"epoch": 1.46,
"learning_rate": 2.357873210633947e-05,
"loss": 1.1493,
"step": 1910
},
{
"epoch": 1.47,
"learning_rate": 2.352760736196319e-05,
"loss": 1.0944,
"step": 1920
},
{
"epoch": 1.48,
"learning_rate": 2.3476482617586913e-05,
"loss": 1.0999,
"step": 1930
},
{
"epoch": 1.49,
"learning_rate": 2.3425357873210633e-05,
"loss": 1.072,
"step": 1940
},
{
"epoch": 1.5,
"learning_rate": 2.337423312883436e-05,
"loss": 1.1158,
"step": 1950
},
{
"epoch": 1.5,
"learning_rate": 2.332310838445808e-05,
"loss": 1.082,
"step": 1960
},
{
"epoch": 1.51,
"learning_rate": 2.32719836400818e-05,
"loss": 1.058,
"step": 1970
},
{
"epoch": 1.52,
"learning_rate": 2.3220858895705522e-05,
"loss": 1.1094,
"step": 1980
},
{
"epoch": 1.53,
"learning_rate": 2.3169734151329242e-05,
"loss": 1.0677,
"step": 1990
},
{
"epoch": 1.53,
"learning_rate": 2.3118609406952965e-05,
"loss": 1.0579,
"step": 2000
},
{
"epoch": 1.54,
"learning_rate": 2.3067484662576688e-05,
"loss": 1.0428,
"step": 2010
},
{
"epoch": 1.55,
"learning_rate": 2.301635991820041e-05,
"loss": 1.0322,
"step": 2020
},
{
"epoch": 1.56,
"learning_rate": 2.296523517382413e-05,
"loss": 1.083,
"step": 2030
},
{
"epoch": 1.56,
"learning_rate": 2.2914110429447854e-05,
"loss": 1.0952,
"step": 2040
},
{
"epoch": 1.57,
"learning_rate": 2.2862985685071574e-05,
"loss": 1.0667,
"step": 2050
},
{
"epoch": 1.58,
"learning_rate": 2.2811860940695297e-05,
"loss": 1.0549,
"step": 2060
},
{
"epoch": 1.59,
"learning_rate": 2.2760736196319017e-05,
"loss": 1.0916,
"step": 2070
},
{
"epoch": 1.59,
"learning_rate": 2.2709611451942744e-05,
"loss": 1.0978,
"step": 2080
},
{
"epoch": 1.6,
"learning_rate": 2.2658486707566464e-05,
"loss": 1.058,
"step": 2090
},
{
"epoch": 1.61,
"learning_rate": 2.2607361963190187e-05,
"loss": 1.1053,
"step": 2100
},
{
"epoch": 1.62,
"learning_rate": 2.2556237218813907e-05,
"loss": 1.1061,
"step": 2110
},
{
"epoch": 1.63,
"learning_rate": 2.2505112474437626e-05,
"loss": 1.0919,
"step": 2120
},
{
"epoch": 1.63,
"learning_rate": 2.245398773006135e-05,
"loss": 1.0499,
"step": 2130
},
{
"epoch": 1.64,
"learning_rate": 2.240286298568507e-05,
"loss": 1.0577,
"step": 2140
},
{
"epoch": 1.65,
"learning_rate": 2.2351738241308796e-05,
"loss": 1.0188,
"step": 2150
},
{
"epoch": 1.66,
"learning_rate": 2.2300613496932516e-05,
"loss": 1.0922,
"step": 2160
},
{
"epoch": 1.66,
"learning_rate": 2.224948875255624e-05,
"loss": 1.0659,
"step": 2170
},
{
"epoch": 1.67,
"learning_rate": 2.219836400817996e-05,
"loss": 1.0656,
"step": 2180
},
{
"epoch": 1.68,
"learning_rate": 2.2147239263803682e-05,
"loss": 1.0858,
"step": 2190
},
{
"epoch": 1.69,
"learning_rate": 2.2096114519427402e-05,
"loss": 1.0432,
"step": 2200
},
{
"epoch": 1.69,
"learning_rate": 2.2044989775051125e-05,
"loss": 1.0386,
"step": 2210
},
{
"epoch": 1.7,
"learning_rate": 2.1993865030674848e-05,
"loss": 1.0843,
"step": 2220
},
{
"epoch": 1.71,
"learning_rate": 2.194274028629857e-05,
"loss": 1.1272,
"step": 2230
},
{
"epoch": 1.72,
"learning_rate": 2.189161554192229e-05,
"loss": 1.0712,
"step": 2240
},
{
"epoch": 1.73,
"learning_rate": 2.1840490797546014e-05,
"loss": 0.9976,
"step": 2250
},
{
"epoch": 1.73,
"learning_rate": 2.1789366053169734e-05,
"loss": 1.0925,
"step": 2260
},
{
"epoch": 1.74,
"learning_rate": 2.1738241308793454e-05,
"loss": 1.0628,
"step": 2270
},
{
"epoch": 1.75,
"learning_rate": 2.1687116564417177e-05,
"loss": 1.0742,
"step": 2280
},
{
"epoch": 1.76,
"learning_rate": 2.16359918200409e-05,
"loss": 1.058,
"step": 2290
},
{
"epoch": 1.76,
"learning_rate": 2.1584867075664623e-05,
"loss": 1.033,
"step": 2300
},
{
"epoch": 1.77,
"learning_rate": 2.1533742331288343e-05,
"loss": 1.0682,
"step": 2310
},
{
"epoch": 1.78,
"learning_rate": 2.1482617586912066e-05,
"loss": 1.1028,
"step": 2320
},
{
"epoch": 1.79,
"learning_rate": 2.1431492842535786e-05,
"loss": 1.0428,
"step": 2330
},
{
"epoch": 1.79,
"learning_rate": 2.138036809815951e-05,
"loss": 1.0432,
"step": 2340
},
{
"epoch": 1.8,
"learning_rate": 2.1329243353783233e-05,
"loss": 1.0666,
"step": 2350
},
{
"epoch": 1.81,
"learning_rate": 2.1278118609406956e-05,
"loss": 1.0205,
"step": 2360
},
{
"epoch": 1.82,
"learning_rate": 2.1226993865030676e-05,
"loss": 1.0398,
"step": 2370
},
{
"epoch": 1.82,
"learning_rate": 2.11758691206544e-05,
"loss": 1.0386,
"step": 2380
},
{
"epoch": 1.83,
"learning_rate": 2.112474437627812e-05,
"loss": 1.0642,
"step": 2390
},
{
"epoch": 1.84,
"learning_rate": 2.1073619631901842e-05,
"loss": 1.0635,
"step": 2400
},
{
"epoch": 1.85,
"learning_rate": 2.102249488752556e-05,
"loss": 1.0366,
"step": 2410
},
{
"epoch": 1.86,
"learning_rate": 2.0971370143149285e-05,
"loss": 1.0517,
"step": 2420
},
{
"epoch": 1.86,
"learning_rate": 2.0920245398773008e-05,
"loss": 1.0518,
"step": 2430
},
{
"epoch": 1.87,
"learning_rate": 2.0869120654396728e-05,
"loss": 1.0715,
"step": 2440
},
{
"epoch": 1.88,
"learning_rate": 2.081799591002045e-05,
"loss": 1.0363,
"step": 2450
},
{
"epoch": 1.89,
"learning_rate": 2.076687116564417e-05,
"loss": 1.0384,
"step": 2460
},
{
"epoch": 1.89,
"learning_rate": 2.0715746421267894e-05,
"loss": 1.0585,
"step": 2470
},
{
"epoch": 1.9,
"learning_rate": 2.0664621676891614e-05,
"loss": 1.0972,
"step": 2480
},
{
"epoch": 1.91,
"learning_rate": 2.061349693251534e-05,
"loss": 1.0248,
"step": 2490
},
{
"epoch": 1.92,
"learning_rate": 2.056237218813906e-05,
"loss": 1.0279,
"step": 2500
},
{
"epoch": 1.92,
"learning_rate": 2.0511247443762783e-05,
"loss": 1.0053,
"step": 2510
},
{
"epoch": 1.93,
"learning_rate": 2.0460122699386503e-05,
"loss": 1.0685,
"step": 2520
},
{
"epoch": 1.94,
"learning_rate": 2.0408997955010226e-05,
"loss": 1.0059,
"step": 2530
},
{
"epoch": 1.95,
"learning_rate": 2.0357873210633946e-05,
"loss": 1.029,
"step": 2540
},
{
"epoch": 1.96,
"learning_rate": 2.030674846625767e-05,
"loss": 1.0916,
"step": 2550
},
{
"epoch": 1.96,
"learning_rate": 2.0255623721881392e-05,
"loss": 1.0296,
"step": 2560
},
{
"epoch": 1.97,
"learning_rate": 2.0204498977505112e-05,
"loss": 1.0179,
"step": 2570
},
{
"epoch": 1.98,
"learning_rate": 2.0153374233128835e-05,
"loss": 1.0126,
"step": 2580
},
{
"epoch": 1.99,
"learning_rate": 2.0102249488752555e-05,
"loss": 1.0458,
"step": 2590
},
{
"epoch": 1.99,
"learning_rate": 2.005112474437628e-05,
"loss": 1.0779,
"step": 2600
},
{
"epoch": 2.0,
"eval_accuracy": 0.6555350597705004,
"eval_loss": 0.9455426335334778,
"eval_runtime": 303.4096,
"eval_samples_per_second": 137.58,
"eval_steps_per_second": 68.792,
"step": 2608
},
{
"epoch": 2.0,
"learning_rate": 1.9999999999999998e-05,
"loss": 1.1476,
"step": 2610
},
{
"epoch": 2.01,
"learning_rate": 1.994887525562372e-05,
"loss": 1.0322,
"step": 2620
},
{
"epoch": 2.02,
"learning_rate": 1.9897750511247445e-05,
"loss": 1.0394,
"step": 2630
},
{
"epoch": 2.02,
"learning_rate": 1.9846625766871168e-05,
"loss": 1.0319,
"step": 2640
},
{
"epoch": 2.03,
"learning_rate": 1.9795501022494888e-05,
"loss": 1.0061,
"step": 2650
},
{
"epoch": 2.04,
"learning_rate": 1.974437627811861e-05,
"loss": 1.0337,
"step": 2660
},
{
"epoch": 2.05,
"learning_rate": 1.969325153374233e-05,
"loss": 1.0778,
"step": 2670
},
{
"epoch": 2.06,
"learning_rate": 1.9642126789366054e-05,
"loss": 1.0107,
"step": 2680
},
{
"epoch": 2.06,
"learning_rate": 1.9591002044989777e-05,
"loss": 1.0841,
"step": 2690
},
{
"epoch": 2.07,
"learning_rate": 1.95398773006135e-05,
"loss": 1.0172,
"step": 2700
},
{
"epoch": 2.08,
"learning_rate": 1.948875255623722e-05,
"loss": 1.0077,
"step": 2710
},
{
"epoch": 2.09,
"learning_rate": 1.943762781186094e-05,
"loss": 1.0349,
"step": 2720
},
{
"epoch": 2.09,
"learning_rate": 1.9386503067484663e-05,
"loss": 0.9735,
"step": 2730
},
{
"epoch": 2.1,
"learning_rate": 1.9335378323108383e-05,
"loss": 1.0829,
"step": 2740
},
{
"epoch": 2.11,
"learning_rate": 1.9284253578732106e-05,
"loss": 1.0084,
"step": 2750
},
{
"epoch": 2.12,
"learning_rate": 1.923312883435583e-05,
"loss": 1.1453,
"step": 2760
},
{
"epoch": 2.12,
"learning_rate": 1.9182004089979552e-05,
"loss": 1.0449,
"step": 2770
},
{
"epoch": 2.13,
"learning_rate": 1.9130879345603272e-05,
"loss": 1.0324,
"step": 2780
},
{
"epoch": 2.14,
"learning_rate": 1.9079754601226995e-05,
"loss": 1.0473,
"step": 2790
},
{
"epoch": 2.15,
"learning_rate": 1.9028629856850715e-05,
"loss": 1.0417,
"step": 2800
},
{
"epoch": 2.15,
"learning_rate": 1.8977505112474438e-05,
"loss": 1.0275,
"step": 2810
},
{
"epoch": 2.16,
"learning_rate": 1.8926380368098158e-05,
"loss": 0.9963,
"step": 2820
},
{
"epoch": 2.17,
"learning_rate": 1.8875255623721885e-05,
"loss": 1.0089,
"step": 2830
},
{
"epoch": 2.18,
"learning_rate": 1.8824130879345604e-05,
"loss": 1.0995,
"step": 2840
},
{
"epoch": 2.19,
"learning_rate": 1.8773006134969328e-05,
"loss": 1.0087,
"step": 2850
},
{
"epoch": 2.19,
"learning_rate": 1.8721881390593047e-05,
"loss": 1.0147,
"step": 2860
},
{
"epoch": 2.2,
"learning_rate": 1.8670756646216767e-05,
"loss": 1.0342,
"step": 2870
},
{
"epoch": 2.21,
"learning_rate": 1.861963190184049e-05,
"loss": 1.0367,
"step": 2880
},
{
"epoch": 2.22,
"learning_rate": 1.856850715746421e-05,
"loss": 1.0202,
"step": 2890
},
{
"epoch": 2.22,
"learning_rate": 1.8517382413087937e-05,
"loss": 1.0607,
"step": 2900
},
{
"epoch": 2.23,
"learning_rate": 1.8466257668711657e-05,
"loss": 1.0357,
"step": 2910
},
{
"epoch": 2.24,
"learning_rate": 1.841513292433538e-05,
"loss": 1.0233,
"step": 2920
},
{
"epoch": 2.25,
"learning_rate": 1.83640081799591e-05,
"loss": 1.0346,
"step": 2930
},
{
"epoch": 2.25,
"learning_rate": 1.8312883435582823e-05,
"loss": 1.03,
"step": 2940
},
{
"epoch": 2.26,
"learning_rate": 1.8261758691206543e-05,
"loss": 0.9792,
"step": 2950
},
{
"epoch": 2.27,
"learning_rate": 1.8210633946830266e-05,
"loss": 1.0475,
"step": 2960
},
{
"epoch": 2.28,
"learning_rate": 1.815950920245399e-05,
"loss": 1.0535,
"step": 2970
},
{
"epoch": 2.29,
"learning_rate": 1.8108384458077712e-05,
"loss": 1.0164,
"step": 2980
},
{
"epoch": 2.29,
"learning_rate": 1.8057259713701432e-05,
"loss": 1.0234,
"step": 2990
},
{
"epoch": 2.3,
"learning_rate": 1.8006134969325155e-05,
"loss": 1.0178,
"step": 3000
},
{
"epoch": 2.31,
"learning_rate": 1.7955010224948875e-05,
"loss": 1.0093,
"step": 3010
},
{
"epoch": 2.32,
"learning_rate": 1.7903885480572595e-05,
"loss": 1.0081,
"step": 3020
},
{
"epoch": 2.32,
"learning_rate": 1.785276073619632e-05,
"loss": 0.9826,
"step": 3030
},
{
"epoch": 2.33,
"learning_rate": 1.780163599182004e-05,
"loss": 0.964,
"step": 3040
},
{
"epoch": 2.34,
"learning_rate": 1.7750511247443764e-05,
"loss": 0.9796,
"step": 3050
},
{
"epoch": 2.35,
"learning_rate": 1.7699386503067484e-05,
"loss": 1.0112,
"step": 3060
},
{
"epoch": 2.35,
"learning_rate": 1.7648261758691207e-05,
"loss": 0.9958,
"step": 3070
},
{
"epoch": 2.36,
"learning_rate": 1.7597137014314927e-05,
"loss": 1.0626,
"step": 3080
},
{
"epoch": 2.37,
"learning_rate": 1.754601226993865e-05,
"loss": 0.949,
"step": 3090
},
{
"epoch": 2.38,
"learning_rate": 1.7494887525562373e-05,
"loss": 0.9996,
"step": 3100
},
{
"epoch": 2.38,
"learning_rate": 1.7443762781186097e-05,
"loss": 0.923,
"step": 3110
},
{
"epoch": 2.39,
"learning_rate": 1.7392638036809816e-05,
"loss": 1.0195,
"step": 3120
},
{
"epoch": 2.4,
"learning_rate": 1.734151329243354e-05,
"loss": 1.0198,
"step": 3130
},
{
"epoch": 2.41,
"learning_rate": 1.729038854805726e-05,
"loss": 1.0267,
"step": 3140
},
{
"epoch": 2.42,
"learning_rate": 1.7239263803680983e-05,
"loss": 0.9649,
"step": 3150
},
{
"epoch": 2.42,
"learning_rate": 1.7188139059304702e-05,
"loss": 1.0171,
"step": 3160
},
{
"epoch": 2.43,
"learning_rate": 1.7137014314928426e-05,
"loss": 1.0343,
"step": 3170
},
{
"epoch": 2.44,
"learning_rate": 1.708588957055215e-05,
"loss": 1.0254,
"step": 3180
},
{
"epoch": 2.45,
"learning_rate": 1.703476482617587e-05,
"loss": 1.0452,
"step": 3190
},
{
"epoch": 2.45,
"learning_rate": 1.6983640081799592e-05,
"loss": 1.0527,
"step": 3200
},
{
"epoch": 2.46,
"learning_rate": 1.693251533742331e-05,
"loss": 0.9567,
"step": 3210
},
{
"epoch": 2.47,
"learning_rate": 1.6881390593047035e-05,
"loss": 0.9941,
"step": 3220
},
{
"epoch": 2.48,
"learning_rate": 1.6830265848670755e-05,
"loss": 1.0011,
"step": 3230
},
{
"epoch": 2.48,
"learning_rate": 1.677914110429448e-05,
"loss": 0.9983,
"step": 3240
},
{
"epoch": 2.49,
"learning_rate": 1.67280163599182e-05,
"loss": 1.0388,
"step": 3250
},
{
"epoch": 2.5,
"learning_rate": 1.6676891615541924e-05,
"loss": 0.9829,
"step": 3260
},
{
"epoch": 2.51,
"learning_rate": 1.6625766871165644e-05,
"loss": 1.047,
"step": 3270
},
{
"epoch": 2.52,
"learning_rate": 1.6574642126789367e-05,
"loss": 0.9815,
"step": 3280
},
{
"epoch": 2.52,
"learning_rate": 1.6523517382413087e-05,
"loss": 0.9917,
"step": 3290
},
{
"epoch": 2.53,
"learning_rate": 1.647239263803681e-05,
"loss": 1.0505,
"step": 3300
},
{
"epoch": 2.54,
"learning_rate": 1.6421267893660533e-05,
"loss": 0.9786,
"step": 3310
},
{
"epoch": 2.55,
"learning_rate": 1.6370143149284253e-05,
"loss": 0.9499,
"step": 3320
},
{
"epoch": 2.55,
"learning_rate": 1.6319018404907976e-05,
"loss": 1.0274,
"step": 3330
},
{
"epoch": 2.56,
"learning_rate": 1.6267893660531696e-05,
"loss": 1.0012,
"step": 3340
},
{
"epoch": 2.57,
"learning_rate": 1.621676891615542e-05,
"loss": 1.0759,
"step": 3350
},
{
"epoch": 2.58,
"learning_rate": 1.616564417177914e-05,
"loss": 1.009,
"step": 3360
},
{
"epoch": 2.58,
"learning_rate": 1.6114519427402862e-05,
"loss": 0.9257,
"step": 3370
},
{
"epoch": 2.59,
"learning_rate": 1.6063394683026586e-05,
"loss": 1.0042,
"step": 3380
},
{
"epoch": 2.6,
"learning_rate": 1.601226993865031e-05,
"loss": 1.0145,
"step": 3390
},
{
"epoch": 2.61,
"learning_rate": 1.596114519427403e-05,
"loss": 0.9835,
"step": 3400
},
{
"epoch": 2.61,
"learning_rate": 1.591002044989775e-05,
"loss": 1.0112,
"step": 3410
},
{
"epoch": 2.62,
"learning_rate": 1.585889570552147e-05,
"loss": 1.0209,
"step": 3420
},
{
"epoch": 2.63,
"learning_rate": 1.5807770961145195e-05,
"loss": 1.1021,
"step": 3430
},
{
"epoch": 2.64,
"learning_rate": 1.5756646216768918e-05,
"loss": 0.9853,
"step": 3440
},
{
"epoch": 2.65,
"learning_rate": 1.570552147239264e-05,
"loss": 0.9676,
"step": 3450
},
{
"epoch": 2.65,
"learning_rate": 1.565439672801636e-05,
"loss": 1.0247,
"step": 3460
},
{
"epoch": 2.66,
"learning_rate": 1.560327198364008e-05,
"loss": 0.9681,
"step": 3470
},
{
"epoch": 2.67,
"learning_rate": 1.5552147239263804e-05,
"loss": 0.9989,
"step": 3480
},
{
"epoch": 2.68,
"learning_rate": 1.5501022494887524e-05,
"loss": 1.0103,
"step": 3490
},
{
"epoch": 2.68,
"learning_rate": 1.5449897750511247e-05,
"loss": 0.9726,
"step": 3500
},
{
"epoch": 2.69,
"learning_rate": 1.539877300613497e-05,
"loss": 0.9575,
"step": 3510
},
{
"epoch": 2.7,
"learning_rate": 1.5347648261758693e-05,
"loss": 1.0127,
"step": 3520
},
{
"epoch": 2.71,
"learning_rate": 1.5296523517382413e-05,
"loss": 0.9866,
"step": 3530
},
{
"epoch": 2.71,
"learning_rate": 1.5245398773006136e-05,
"loss": 0.9727,
"step": 3540
},
{
"epoch": 2.72,
"learning_rate": 1.5194274028629856e-05,
"loss": 1.0087,
"step": 3550
},
{
"epoch": 2.73,
"learning_rate": 1.5143149284253581e-05,
"loss": 1.0048,
"step": 3560
},
{
"epoch": 2.74,
"learning_rate": 1.50920245398773e-05,
"loss": 1.0397,
"step": 3570
},
{
"epoch": 2.75,
"learning_rate": 1.5040899795501024e-05,
"loss": 0.9903,
"step": 3580
},
{
"epoch": 2.75,
"learning_rate": 1.4989775051124744e-05,
"loss": 1.0429,
"step": 3590
},
{
"epoch": 2.76,
"learning_rate": 1.4938650306748467e-05,
"loss": 1.0008,
"step": 3600
},
{
"epoch": 2.77,
"learning_rate": 1.4887525562372188e-05,
"loss": 0.9799,
"step": 3610
},
{
"epoch": 2.78,
"learning_rate": 1.483640081799591e-05,
"loss": 0.9668,
"step": 3620
},
{
"epoch": 2.78,
"learning_rate": 1.4785276073619633e-05,
"loss": 1.0046,
"step": 3630
},
{
"epoch": 2.79,
"learning_rate": 1.4734151329243355e-05,
"loss": 1.0146,
"step": 3640
},
{
"epoch": 2.8,
"learning_rate": 1.4683026584867076e-05,
"loss": 0.9645,
"step": 3650
},
{
"epoch": 2.81,
"learning_rate": 1.46319018404908e-05,
"loss": 1.0449,
"step": 3660
},
{
"epoch": 2.81,
"learning_rate": 1.458077709611452e-05,
"loss": 1.0,
"step": 3670
},
{
"epoch": 2.82,
"learning_rate": 1.4529652351738242e-05,
"loss": 0.9965,
"step": 3680
},
{
"epoch": 2.83,
"learning_rate": 1.4478527607361964e-05,
"loss": 1.0086,
"step": 3690
},
{
"epoch": 2.84,
"learning_rate": 1.4427402862985685e-05,
"loss": 1.0889,
"step": 3700
},
{
"epoch": 2.84,
"learning_rate": 1.4376278118609407e-05,
"loss": 1.0154,
"step": 3710
},
{
"epoch": 2.85,
"learning_rate": 1.4325153374233128e-05,
"loss": 1.017,
"step": 3720
},
{
"epoch": 2.86,
"learning_rate": 1.4274028629856851e-05,
"loss": 0.9491,
"step": 3730
},
{
"epoch": 2.87,
"learning_rate": 1.4222903885480573e-05,
"loss": 0.9901,
"step": 3740
},
{
"epoch": 2.88,
"learning_rate": 1.4171779141104294e-05,
"loss": 1.0308,
"step": 3750
},
{
"epoch": 2.88,
"learning_rate": 1.4120654396728016e-05,
"loss": 0.9649,
"step": 3760
},
{
"epoch": 2.89,
"learning_rate": 1.4069529652351739e-05,
"loss": 0.9903,
"step": 3770
},
{
"epoch": 2.9,
"learning_rate": 1.401840490797546e-05,
"loss": 0.9283,
"step": 3780
},
{
"epoch": 2.91,
"learning_rate": 1.3967280163599182e-05,
"loss": 0.9714,
"step": 3790
},
{
"epoch": 2.91,
"learning_rate": 1.3916155419222905e-05,
"loss": 0.9989,
"step": 3800
},
{
"epoch": 2.92,
"learning_rate": 1.3865030674846627e-05,
"loss": 0.9711,
"step": 3810
},
{
"epoch": 2.93,
"learning_rate": 1.3813905930470348e-05,
"loss": 1.0136,
"step": 3820
},
{
"epoch": 2.94,
"learning_rate": 1.3762781186094071e-05,
"loss": 0.9706,
"step": 3830
},
{
"epoch": 2.94,
"learning_rate": 1.3711656441717793e-05,
"loss": 1.0298,
"step": 3840
},
{
"epoch": 2.95,
"learning_rate": 1.3660531697341513e-05,
"loss": 0.9527,
"step": 3850
},
{
"epoch": 2.96,
"learning_rate": 1.3609406952965234e-05,
"loss": 0.9867,
"step": 3860
},
{
"epoch": 2.97,
"learning_rate": 1.3558282208588957e-05,
"loss": 0.9672,
"step": 3870
},
{
"epoch": 2.98,
"learning_rate": 1.3507157464212679e-05,
"loss": 0.9654,
"step": 3880
},
{
"epoch": 2.98,
"learning_rate": 1.34560327198364e-05,
"loss": 0.9646,
"step": 3890
},
{
"epoch": 2.99,
"learning_rate": 1.3404907975460124e-05,
"loss": 0.9597,
"step": 3900
},
{
"epoch": 3.0,
"learning_rate": 1.3353783231083845e-05,
"loss": 0.9775,
"step": 3910
},
{
"epoch": 3.0,
"eval_accuracy": 0.6522530723714156,
"eval_loss": 0.9669816493988037,
"eval_runtime": 294.3351,
"eval_samples_per_second": 141.821,
"eval_steps_per_second": 70.912,
"step": 3912
},
{
"epoch": 3.01,
"learning_rate": 1.3302658486707567e-05,
"loss": 1.0613,
"step": 3920
},
{
"epoch": 3.01,
"learning_rate": 1.3251533742331288e-05,
"loss": 0.9874,
"step": 3930
},
{
"epoch": 3.02,
"learning_rate": 1.3200408997955011e-05,
"loss": 0.9708,
"step": 3940
},
{
"epoch": 3.03,
"learning_rate": 1.3149284253578733e-05,
"loss": 0.9617,
"step": 3950
},
{
"epoch": 3.04,
"learning_rate": 1.3098159509202454e-05,
"loss": 0.968,
"step": 3960
},
{
"epoch": 3.04,
"learning_rate": 1.3047034764826177e-05,
"loss": 0.9683,
"step": 3970
},
{
"epoch": 3.05,
"learning_rate": 1.2995910020449899e-05,
"loss": 0.9496,
"step": 3980
},
{
"epoch": 3.06,
"learning_rate": 1.294478527607362e-05,
"loss": 0.919,
"step": 3990
},
{
"epoch": 3.07,
"learning_rate": 1.2893660531697342e-05,
"loss": 0.9563,
"step": 4000
},
{
"epoch": 3.08,
"learning_rate": 1.2842535787321063e-05,
"loss": 0.9115,
"step": 4010
},
{
"epoch": 3.08,
"learning_rate": 1.2791411042944785e-05,
"loss": 0.9078,
"step": 4020
},
{
"epoch": 3.09,
"learning_rate": 1.2740286298568506e-05,
"loss": 0.9824,
"step": 4030
},
{
"epoch": 3.1,
"learning_rate": 1.268916155419223e-05,
"loss": 0.9953,
"step": 4040
},
{
"epoch": 3.11,
"learning_rate": 1.2638036809815951e-05,
"loss": 1.004,
"step": 4050
},
{
"epoch": 3.11,
"learning_rate": 1.2586912065439673e-05,
"loss": 0.9191,
"step": 4060
},
{
"epoch": 3.12,
"learning_rate": 1.2535787321063396e-05,
"loss": 0.9923,
"step": 4070
},
{
"epoch": 3.13,
"learning_rate": 1.2484662576687117e-05,
"loss": 0.9668,
"step": 4080
},
{
"epoch": 3.14,
"learning_rate": 1.2433537832310839e-05,
"loss": 1.0262,
"step": 4090
},
{
"epoch": 3.14,
"learning_rate": 1.238241308793456e-05,
"loss": 1.0177,
"step": 4100
},
{
"epoch": 3.15,
"learning_rate": 1.2331288343558283e-05,
"loss": 0.9461,
"step": 4110
},
{
"epoch": 3.16,
"learning_rate": 1.2280163599182005e-05,
"loss": 1.0468,
"step": 4120
},
{
"epoch": 3.17,
"learning_rate": 1.2229038854805726e-05,
"loss": 0.9567,
"step": 4130
},
{
"epoch": 3.17,
"learning_rate": 1.217791411042945e-05,
"loss": 0.936,
"step": 4140
},
{
"epoch": 3.18,
"learning_rate": 1.212678936605317e-05,
"loss": 0.9586,
"step": 4150
},
{
"epoch": 3.19,
"learning_rate": 1.2075664621676891e-05,
"loss": 0.964,
"step": 4160
},
{
"epoch": 3.2,
"learning_rate": 1.2024539877300614e-05,
"loss": 0.9221,
"step": 4170
},
{
"epoch": 3.21,
"learning_rate": 1.1973415132924336e-05,
"loss": 0.9604,
"step": 4180
},
{
"epoch": 3.21,
"learning_rate": 1.1922290388548057e-05,
"loss": 1.0227,
"step": 4190
},
{
"epoch": 3.22,
"learning_rate": 1.1871165644171779e-05,
"loss": 0.9817,
"step": 4200
},
{
"epoch": 3.23,
"learning_rate": 1.1820040899795502e-05,
"loss": 0.9773,
"step": 4210
},
{
"epoch": 3.24,
"learning_rate": 1.1768916155419223e-05,
"loss": 0.9468,
"step": 4220
},
{
"epoch": 3.24,
"learning_rate": 1.1717791411042945e-05,
"loss": 0.9356,
"step": 4230
},
{
"epoch": 3.25,
"learning_rate": 1.1666666666666668e-05,
"loss": 0.9818,
"step": 4240
},
{
"epoch": 3.26,
"learning_rate": 1.161554192229039e-05,
"loss": 0.9984,
"step": 4250
},
{
"epoch": 3.27,
"learning_rate": 1.1564417177914111e-05,
"loss": 1.0297,
"step": 4260
},
{
"epoch": 3.27,
"learning_rate": 1.1513292433537832e-05,
"loss": 0.9418,
"step": 4270
},
{
"epoch": 3.28,
"learning_rate": 1.1462167689161556e-05,
"loss": 0.9486,
"step": 4280
},
{
"epoch": 3.29,
"learning_rate": 1.1411042944785277e-05,
"loss": 0.9456,
"step": 4290
},
{
"epoch": 3.3,
"learning_rate": 1.1359918200408997e-05,
"loss": 0.9821,
"step": 4300
},
{
"epoch": 3.31,
"learning_rate": 1.130879345603272e-05,
"loss": 0.9672,
"step": 4310
},
{
"epoch": 3.31,
"learning_rate": 1.1257668711656442e-05,
"loss": 0.9769,
"step": 4320
},
{
"epoch": 3.32,
"learning_rate": 1.1206543967280163e-05,
"loss": 0.9806,
"step": 4330
},
{
"epoch": 3.33,
"learning_rate": 1.1155419222903885e-05,
"loss": 0.9755,
"step": 4340
},
{
"epoch": 3.34,
"learning_rate": 1.1104294478527608e-05,
"loss": 0.9019,
"step": 4350
},
{
"epoch": 3.34,
"learning_rate": 1.105316973415133e-05,
"loss": 0.9812,
"step": 4360
},
{
"epoch": 3.35,
"learning_rate": 1.100204498977505e-05,
"loss": 0.9808,
"step": 4370
},
{
"epoch": 3.36,
"learning_rate": 1.0950920245398774e-05,
"loss": 1.0226,
"step": 4380
},
{
"epoch": 3.37,
"learning_rate": 1.0899795501022495e-05,
"loss": 0.9444,
"step": 4390
},
{
"epoch": 3.37,
"learning_rate": 1.0848670756646217e-05,
"loss": 0.9383,
"step": 4400
},
{
"epoch": 3.38,
"learning_rate": 1.079754601226994e-05,
"loss": 0.8953,
"step": 4410
},
{
"epoch": 3.39,
"learning_rate": 1.0746421267893662e-05,
"loss": 0.9296,
"step": 4420
},
{
"epoch": 3.4,
"learning_rate": 1.0695296523517383e-05,
"loss": 0.967,
"step": 4430
},
{
"epoch": 3.4,
"learning_rate": 1.0644171779141105e-05,
"loss": 0.9711,
"step": 4440
},
{
"epoch": 3.41,
"learning_rate": 1.0593047034764828e-05,
"loss": 0.9028,
"step": 4450
},
{
"epoch": 3.42,
"learning_rate": 1.0541922290388548e-05,
"loss": 0.972,
"step": 4460
},
{
"epoch": 3.43,
"learning_rate": 1.0490797546012269e-05,
"loss": 0.9936,
"step": 4470
},
{
"epoch": 3.44,
"learning_rate": 1.0439672801635992e-05,
"loss": 1.0213,
"step": 4480
},
{
"epoch": 3.44,
"learning_rate": 1.0388548057259714e-05,
"loss": 0.9247,
"step": 4490
},
{
"epoch": 3.45,
"learning_rate": 1.0337423312883435e-05,
"loss": 0.9832,
"step": 4500
},
{
"epoch": 3.46,
"learning_rate": 1.0286298568507157e-05,
"loss": 0.9604,
"step": 4510
},
{
"epoch": 3.47,
"learning_rate": 1.023517382413088e-05,
"loss": 0.9799,
"step": 4520
},
{
"epoch": 3.47,
"learning_rate": 1.0184049079754601e-05,
"loss": 0.9318,
"step": 4530
},
{
"epoch": 3.48,
"learning_rate": 1.0132924335378323e-05,
"loss": 0.9727,
"step": 4540
},
{
"epoch": 3.49,
"learning_rate": 1.0081799591002046e-05,
"loss": 0.9929,
"step": 4550
},
{
"epoch": 3.5,
"learning_rate": 1.0030674846625768e-05,
"loss": 0.9488,
"step": 4560
},
{
"epoch": 3.5,
"learning_rate": 9.979550102249489e-06,
"loss": 0.97,
"step": 4570
},
{
"epoch": 3.51,
"learning_rate": 9.928425357873212e-06,
"loss": 0.953,
"step": 4580
},
{
"epoch": 3.52,
"learning_rate": 9.877300613496934e-06,
"loss": 0.9396,
"step": 4590
},
{
"epoch": 3.53,
"learning_rate": 9.826175869120655e-06,
"loss": 1.0,
"step": 4600
},
{
"epoch": 3.54,
"learning_rate": 9.775051124744375e-06,
"loss": 0.9872,
"step": 4610
},
{
"epoch": 3.54,
"learning_rate": 9.723926380368098e-06,
"loss": 0.9254,
"step": 4620
},
{
"epoch": 3.55,
"learning_rate": 9.67280163599182e-06,
"loss": 0.989,
"step": 4630
},
{
"epoch": 3.56,
"learning_rate": 9.621676891615541e-06,
"loss": 0.8786,
"step": 4640
},
{
"epoch": 3.57,
"learning_rate": 9.570552147239264e-06,
"loss": 0.9236,
"step": 4650
},
{
"epoch": 3.57,
"learning_rate": 9.519427402862986e-06,
"loss": 0.9162,
"step": 4660
},
{
"epoch": 3.58,
"learning_rate": 9.468302658486707e-06,
"loss": 0.9444,
"step": 4670
},
{
"epoch": 3.59,
"learning_rate": 9.417177914110429e-06,
"loss": 0.9698,
"step": 4680
},
{
"epoch": 3.6,
"learning_rate": 9.366053169734152e-06,
"loss": 1.0498,
"step": 4690
},
{
"epoch": 3.6,
"learning_rate": 9.314928425357874e-06,
"loss": 0.9529,
"step": 4700
},
{
"epoch": 3.61,
"learning_rate": 9.263803680981595e-06,
"loss": 0.9147,
"step": 4710
},
{
"epoch": 3.62,
"learning_rate": 9.212678936605318e-06,
"loss": 0.9755,
"step": 4720
},
{
"epoch": 3.63,
"learning_rate": 9.16155419222904e-06,
"loss": 1.007,
"step": 4730
},
{
"epoch": 3.63,
"learning_rate": 9.110429447852761e-06,
"loss": 0.9338,
"step": 4740
},
{
"epoch": 3.64,
"learning_rate": 9.059304703476484e-06,
"loss": 0.9356,
"step": 4750
},
{
"epoch": 3.65,
"learning_rate": 9.008179959100204e-06,
"loss": 0.9711,
"step": 4760
},
{
"epoch": 3.66,
"learning_rate": 8.957055214723926e-06,
"loss": 0.9662,
"step": 4770
},
{
"epoch": 3.67,
"learning_rate": 8.905930470347647e-06,
"loss": 0.9794,
"step": 4780
},
{
"epoch": 3.67,
"learning_rate": 8.85480572597137e-06,
"loss": 1.0016,
"step": 4790
},
{
"epoch": 3.68,
"learning_rate": 8.803680981595092e-06,
"loss": 0.9433,
"step": 4800
},
{
"epoch": 3.69,
"learning_rate": 8.752556237218813e-06,
"loss": 0.9584,
"step": 4810
},
{
"epoch": 3.7,
"learning_rate": 8.701431492842537e-06,
"loss": 0.9664,
"step": 4820
},
{
"epoch": 3.7,
"learning_rate": 8.650306748466258e-06,
"loss": 0.9164,
"step": 4830
},
{
"epoch": 3.71,
"learning_rate": 8.59918200408998e-06,
"loss": 0.9198,
"step": 4840
},
{
"epoch": 3.72,
"learning_rate": 8.548057259713701e-06,
"loss": 0.9766,
"step": 4850
},
{
"epoch": 3.73,
"learning_rate": 8.496932515337424e-06,
"loss": 0.9515,
"step": 4860
},
{
"epoch": 3.73,
"learning_rate": 8.445807770961146e-06,
"loss": 0.9538,
"step": 4870
},
{
"epoch": 3.74,
"learning_rate": 8.394683026584867e-06,
"loss": 0.9635,
"step": 4880
},
{
"epoch": 3.75,
"learning_rate": 8.34355828220859e-06,
"loss": 0.9385,
"step": 4890
},
{
"epoch": 3.76,
"learning_rate": 8.292433537832312e-06,
"loss": 0.9669,
"step": 4900
},
{
"epoch": 3.77,
"learning_rate": 8.241308793456032e-06,
"loss": 0.9672,
"step": 4910
},
{
"epoch": 3.77,
"learning_rate": 8.190184049079755e-06,
"loss": 0.9436,
"step": 4920
},
{
"epoch": 3.78,
"learning_rate": 8.139059304703476e-06,
"loss": 0.936,
"step": 4930
},
{
"epoch": 3.79,
"learning_rate": 8.087934560327198e-06,
"loss": 0.999,
"step": 4940
},
{
"epoch": 3.8,
"learning_rate": 8.03680981595092e-06,
"loss": 0.9724,
"step": 4950
},
{
"epoch": 3.8,
"learning_rate": 7.985685071574643e-06,
"loss": 0.9303,
"step": 4960
},
{
"epoch": 3.81,
"learning_rate": 7.934560327198364e-06,
"loss": 0.9705,
"step": 4970
},
{
"epoch": 3.82,
"learning_rate": 7.883435582822086e-06,
"loss": 0.9082,
"step": 4980
},
{
"epoch": 3.83,
"learning_rate": 7.832310838445809e-06,
"loss": 0.9417,
"step": 4990
},
{
"epoch": 3.83,
"learning_rate": 7.78118609406953e-06,
"loss": 0.9132,
"step": 5000
},
{
"epoch": 3.84,
"learning_rate": 7.730061349693252e-06,
"loss": 0.9844,
"step": 5010
},
{
"epoch": 3.85,
"learning_rate": 7.678936605316973e-06,
"loss": 0.9299,
"step": 5020
},
{
"epoch": 3.86,
"learning_rate": 7.6278118609406965e-06,
"loss": 0.9278,
"step": 5030
},
{
"epoch": 3.86,
"learning_rate": 7.576687116564418e-06,
"loss": 0.9335,
"step": 5040
},
{
"epoch": 3.87,
"learning_rate": 7.52556237218814e-06,
"loss": 0.9042,
"step": 5050
},
{
"epoch": 3.88,
"learning_rate": 7.474437627811861e-06,
"loss": 0.971,
"step": 5060
},
{
"epoch": 3.89,
"learning_rate": 7.423312883435583e-06,
"loss": 0.9237,
"step": 5070
},
{
"epoch": 3.9,
"learning_rate": 7.372188139059305e-06,
"loss": 0.9598,
"step": 5080
},
{
"epoch": 3.9,
"learning_rate": 7.321063394683027e-06,
"loss": 0.9941,
"step": 5090
},
{
"epoch": 3.91,
"learning_rate": 7.269938650306749e-06,
"loss": 0.9467,
"step": 5100
},
{
"epoch": 3.92,
"learning_rate": 7.21881390593047e-06,
"loss": 0.9411,
"step": 5110
},
{
"epoch": 3.93,
"learning_rate": 7.1676891615541924e-06,
"loss": 0.9672,
"step": 5120
},
{
"epoch": 3.93,
"learning_rate": 7.116564417177914e-06,
"loss": 0.8993,
"step": 5130
},
{
"epoch": 3.94,
"learning_rate": 7.065439672801636e-06,
"loss": 0.9833,
"step": 5140
},
{
"epoch": 3.95,
"learning_rate": 7.014314928425359e-06,
"loss": 0.9743,
"step": 5150
},
{
"epoch": 3.96,
"learning_rate": 6.96319018404908e-06,
"loss": 0.9413,
"step": 5160
},
{
"epoch": 3.96,
"learning_rate": 6.912065439672802e-06,
"loss": 0.9357,
"step": 5170
},
{
"epoch": 3.97,
"learning_rate": 6.860940695296523e-06,
"loss": 0.9368,
"step": 5180
},
{
"epoch": 3.98,
"learning_rate": 6.8098159509202454e-06,
"loss": 0.9175,
"step": 5190
},
{
"epoch": 3.99,
"learning_rate": 6.758691206543968e-06,
"loss": 0.9567,
"step": 5200
},
{
"epoch": 4.0,
"learning_rate": 6.707566462167689e-06,
"loss": 0.9542,
"step": 5210
},
{
"epoch": 4.0,
"eval_accuracy": 0.6945835229858899,
"eval_loss": 0.8809502124786377,
"eval_runtime": 297.753,
"eval_samples_per_second": 140.193,
"eval_steps_per_second": 70.098,
"step": 5216
},
{
"epoch": 4.0,
"learning_rate": 6.656441717791412e-06,
"loss": 0.9247,
"step": 5220
},
{
"epoch": 4.01,
"learning_rate": 6.605316973415133e-06,
"loss": 0.9581,
"step": 5230
},
{
"epoch": 4.02,
"learning_rate": 6.5541922290388555e-06,
"loss": 0.9375,
"step": 5240
},
{
"epoch": 4.03,
"learning_rate": 6.503067484662576e-06,
"loss": 0.9146,
"step": 5250
},
{
"epoch": 4.03,
"learning_rate": 6.4519427402862984e-06,
"loss": 0.9437,
"step": 5260
},
{
"epoch": 4.04,
"learning_rate": 6.400817995910021e-06,
"loss": 0.9554,
"step": 5270
},
{
"epoch": 4.05,
"learning_rate": 6.349693251533742e-06,
"loss": 0.9519,
"step": 5280
},
{
"epoch": 4.06,
"learning_rate": 6.298568507157465e-06,
"loss": 0.9291,
"step": 5290
},
{
"epoch": 4.06,
"learning_rate": 6.247443762781186e-06,
"loss": 0.8958,
"step": 5300
},
{
"epoch": 4.07,
"learning_rate": 6.1963190184049085e-06,
"loss": 0.9188,
"step": 5310
},
{
"epoch": 4.08,
"learning_rate": 6.14519427402863e-06,
"loss": 0.949,
"step": 5320
},
{
"epoch": 4.09,
"learning_rate": 6.0940695296523515e-06,
"loss": 0.9866,
"step": 5330
},
{
"epoch": 4.1,
"learning_rate": 6.042944785276074e-06,
"loss": 0.9078,
"step": 5340
},
{
"epoch": 4.1,
"learning_rate": 5.991820040899795e-06,
"loss": 0.9243,
"step": 5350
},
{
"epoch": 4.11,
"learning_rate": 5.940695296523518e-06,
"loss": 0.8902,
"step": 5360
},
{
"epoch": 4.12,
"learning_rate": 5.88957055214724e-06,
"loss": 0.9754,
"step": 5370
},
{
"epoch": 4.13,
"learning_rate": 5.8384458077709615e-06,
"loss": 0.8929,
"step": 5380
},
{
"epoch": 4.13,
"learning_rate": 5.787321063394684e-06,
"loss": 0.9311,
"step": 5390
},
{
"epoch": 4.14,
"learning_rate": 5.7361963190184045e-06,
"loss": 0.9267,
"step": 5400
},
{
"epoch": 4.15,
"learning_rate": 5.685071574642127e-06,
"loss": 0.9586,
"step": 5410
},
{
"epoch": 4.16,
"learning_rate": 5.633946830265848e-06,
"loss": 0.9446,
"step": 5420
},
{
"epoch": 4.16,
"learning_rate": 5.582822085889571e-06,
"loss": 0.9085,
"step": 5430
},
{
"epoch": 4.17,
"learning_rate": 5.531697341513293e-06,
"loss": 0.9376,
"step": 5440
},
{
"epoch": 4.18,
"learning_rate": 5.4805725971370145e-06,
"loss": 0.9498,
"step": 5450
},
{
"epoch": 4.19,
"learning_rate": 5.429447852760737e-06,
"loss": 0.8981,
"step": 5460
},
{
"epoch": 4.19,
"learning_rate": 5.378323108384458e-06,
"loss": 0.961,
"step": 5470
},
{
"epoch": 4.2,
"learning_rate": 5.32719836400818e-06,
"loss": 0.9169,
"step": 5480
},
{
"epoch": 4.21,
"learning_rate": 5.276073619631902e-06,
"loss": 0.9219,
"step": 5490
},
{
"epoch": 4.22,
"learning_rate": 5.224948875255624e-06,
"loss": 0.9491,
"step": 5500
},
{
"epoch": 4.23,
"learning_rate": 5.173824130879346e-06,
"loss": 0.9504,
"step": 5510
},
{
"epoch": 4.23,
"learning_rate": 5.1226993865030675e-06,
"loss": 0.9376,
"step": 5520
},
{
"epoch": 4.24,
"learning_rate": 5.07157464212679e-06,
"loss": 0.9051,
"step": 5530
},
{
"epoch": 4.25,
"learning_rate": 5.020449897750511e-06,
"loss": 0.9578,
"step": 5540
},
{
"epoch": 4.26,
"learning_rate": 4.969325153374233e-06,
"loss": 0.9037,
"step": 5550
},
{
"epoch": 4.26,
"learning_rate": 4.918200408997955e-06,
"loss": 0.8804,
"step": 5560
},
{
"epoch": 4.27,
"learning_rate": 4.867075664621677e-06,
"loss": 0.9226,
"step": 5570
},
{
"epoch": 4.28,
"learning_rate": 4.815950920245399e-06,
"loss": 0.8782,
"step": 5580
},
{
"epoch": 4.29,
"learning_rate": 4.7648261758691205e-06,
"loss": 0.8848,
"step": 5590
},
{
"epoch": 4.29,
"learning_rate": 4.713701431492843e-06,
"loss": 0.929,
"step": 5600
},
{
"epoch": 4.3,
"learning_rate": 4.662576687116565e-06,
"loss": 0.9304,
"step": 5610
},
{
"epoch": 4.31,
"learning_rate": 4.611451942740287e-06,
"loss": 0.8859,
"step": 5620
},
{
"epoch": 4.32,
"learning_rate": 4.560327198364008e-06,
"loss": 0.9106,
"step": 5630
},
{
"epoch": 4.33,
"learning_rate": 4.50920245398773e-06,
"loss": 0.9991,
"step": 5640
},
{
"epoch": 4.33,
"learning_rate": 4.458077709611452e-06,
"loss": 0.9229,
"step": 5650
},
{
"epoch": 4.34,
"learning_rate": 4.406952965235174e-06,
"loss": 0.9479,
"step": 5660
},
{
"epoch": 4.35,
"learning_rate": 4.355828220858896e-06,
"loss": 0.9028,
"step": 5670
},
{
"epoch": 4.36,
"learning_rate": 4.304703476482618e-06,
"loss": 0.9395,
"step": 5680
},
{
"epoch": 4.36,
"learning_rate": 4.25357873210634e-06,
"loss": 0.9212,
"step": 5690
},
{
"epoch": 4.37,
"learning_rate": 4.202453987730061e-06,
"loss": 0.9599,
"step": 5700
},
{
"epoch": 4.38,
"learning_rate": 4.151329243353783e-06,
"loss": 0.9109,
"step": 5710
},
{
"epoch": 4.39,
"learning_rate": 4.100204498977505e-06,
"loss": 0.9477,
"step": 5720
},
{
"epoch": 4.39,
"learning_rate": 4.049079754601227e-06,
"loss": 0.8823,
"step": 5730
},
{
"epoch": 4.4,
"learning_rate": 3.997955010224949e-06,
"loss": 0.9318,
"step": 5740
},
{
"epoch": 4.41,
"learning_rate": 3.946830265848671e-06,
"loss": 0.8762,
"step": 5750
},
{
"epoch": 4.42,
"learning_rate": 3.895705521472393e-06,
"loss": 0.935,
"step": 5760
},
{
"epoch": 4.42,
"learning_rate": 3.844580777096115e-06,
"loss": 0.9151,
"step": 5770
},
{
"epoch": 4.43,
"learning_rate": 3.793456032719836e-06,
"loss": 0.9244,
"step": 5780
},
{
"epoch": 4.44,
"learning_rate": 3.7423312883435584e-06,
"loss": 0.9223,
"step": 5790
},
{
"epoch": 4.45,
"learning_rate": 3.6912065439672803e-06,
"loss": 0.8812,
"step": 5800
},
{
"epoch": 4.46,
"learning_rate": 3.6400817995910022e-06,
"loss": 0.9402,
"step": 5810
},
{
"epoch": 4.46,
"learning_rate": 3.588957055214724e-06,
"loss": 0.9159,
"step": 5820
},
{
"epoch": 4.47,
"learning_rate": 3.537832310838446e-06,
"loss": 0.9543,
"step": 5830
},
{
"epoch": 4.48,
"learning_rate": 3.4867075664621676e-06,
"loss": 0.9197,
"step": 5840
},
{
"epoch": 4.49,
"learning_rate": 3.4355828220858895e-06,
"loss": 0.945,
"step": 5850
},
{
"epoch": 4.49,
"learning_rate": 3.384458077709612e-06,
"loss": 0.9491,
"step": 5860
},
{
"epoch": 4.5,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.8835,
"step": 5870
},
{
"epoch": 4.51,
"learning_rate": 3.2822085889570552e-06,
"loss": 0.877,
"step": 5880
},
{
"epoch": 4.52,
"learning_rate": 3.231083844580777e-06,
"loss": 0.9487,
"step": 5890
},
{
"epoch": 4.52,
"learning_rate": 3.179959100204499e-06,
"loss": 0.9424,
"step": 5900
},
{
"epoch": 4.53,
"learning_rate": 3.1288343558282206e-06,
"loss": 0.9083,
"step": 5910
},
{
"epoch": 4.54,
"learning_rate": 3.077709611451943e-06,
"loss": 0.9283,
"step": 5920
},
{
"epoch": 4.55,
"learning_rate": 3.026584867075665e-06,
"loss": 0.9977,
"step": 5930
},
{
"epoch": 4.56,
"learning_rate": 2.9754601226993867e-06,
"loss": 0.9019,
"step": 5940
},
{
"epoch": 4.56,
"learning_rate": 2.9243353783231082e-06,
"loss": 0.9302,
"step": 5950
},
{
"epoch": 4.57,
"learning_rate": 2.87321063394683e-06,
"loss": 0.9267,
"step": 5960
},
{
"epoch": 4.58,
"learning_rate": 2.8220858895705525e-06,
"loss": 0.9545,
"step": 5970
},
{
"epoch": 4.59,
"learning_rate": 2.7709611451942744e-06,
"loss": 0.9349,
"step": 5980
},
{
"epoch": 4.59,
"learning_rate": 2.724948875255624e-06,
"loss": 0.8813,
"step": 5990
},
{
"epoch": 4.6,
"learning_rate": 2.6738241308793458e-06,
"loss": 0.9202,
"step": 6000
},
{
"epoch": 4.61,
"learning_rate": 2.6226993865030673e-06,
"loss": 0.9854,
"step": 6010
},
{
"epoch": 4.62,
"learning_rate": 2.571574642126789e-06,
"loss": 0.9226,
"step": 6020
},
{
"epoch": 4.62,
"learning_rate": 2.5204498977505115e-06,
"loss": 0.9729,
"step": 6030
},
{
"epoch": 4.63,
"learning_rate": 2.4693251533742334e-06,
"loss": 0.9218,
"step": 6040
},
{
"epoch": 4.64,
"learning_rate": 2.418200408997955e-06,
"loss": 0.917,
"step": 6050
},
{
"epoch": 4.65,
"learning_rate": 2.367075664621677e-06,
"loss": 0.9602,
"step": 6060
},
{
"epoch": 4.65,
"learning_rate": 2.3159509202453988e-06,
"loss": 0.8968,
"step": 6070
},
{
"epoch": 4.66,
"learning_rate": 2.264826175869121e-06,
"loss": 0.9104,
"step": 6080
},
{
"epoch": 4.67,
"learning_rate": 2.2137014314928426e-06,
"loss": 0.8855,
"step": 6090
},
{
"epoch": 4.68,
"learning_rate": 2.1625766871165645e-06,
"loss": 0.9322,
"step": 6100
},
{
"epoch": 4.69,
"learning_rate": 2.1114519427402864e-06,
"loss": 0.9361,
"step": 6110
},
{
"epoch": 4.69,
"learning_rate": 2.060327198364008e-06,
"loss": 0.917,
"step": 6120
},
{
"epoch": 4.7,
"learning_rate": 2.00920245398773e-06,
"loss": 0.9389,
"step": 6130
},
{
"epoch": 4.71,
"learning_rate": 1.958077709611452e-06,
"loss": 0.9851,
"step": 6140
},
{
"epoch": 4.72,
"learning_rate": 1.9069529652351741e-06,
"loss": 0.9481,
"step": 6150
},
{
"epoch": 4.72,
"learning_rate": 1.8558282208588958e-06,
"loss": 0.8991,
"step": 6160
},
{
"epoch": 4.73,
"learning_rate": 1.8047034764826175e-06,
"loss": 0.9207,
"step": 6170
},
{
"epoch": 4.74,
"learning_rate": 1.7535787321063397e-06,
"loss": 0.9402,
"step": 6180
},
{
"epoch": 4.75,
"learning_rate": 1.7024539877300614e-06,
"loss": 0.9713,
"step": 6190
},
{
"epoch": 4.75,
"learning_rate": 1.6513292433537833e-06,
"loss": 0.9374,
"step": 6200
},
{
"epoch": 4.76,
"learning_rate": 1.6002044989775052e-06,
"loss": 0.9352,
"step": 6210
},
{
"epoch": 4.77,
"learning_rate": 1.5490797546012271e-06,
"loss": 0.9246,
"step": 6220
},
{
"epoch": 4.78,
"learning_rate": 1.4979550102249488e-06,
"loss": 0.8953,
"step": 6230
},
{
"epoch": 4.78,
"learning_rate": 1.446830265848671e-06,
"loss": 0.9044,
"step": 6240
},
{
"epoch": 4.79,
"learning_rate": 1.3957055214723927e-06,
"loss": 0.927,
"step": 6250
},
{
"epoch": 4.8,
"learning_rate": 1.3445807770961146e-06,
"loss": 0.926,
"step": 6260
},
{
"epoch": 4.81,
"learning_rate": 1.2934560327198365e-06,
"loss": 0.9082,
"step": 6270
},
{
"epoch": 4.82,
"learning_rate": 1.2423312883435582e-06,
"loss": 0.9158,
"step": 6280
},
{
"epoch": 4.82,
"learning_rate": 1.1912065439672801e-06,
"loss": 0.9389,
"step": 6290
},
{
"epoch": 4.83,
"learning_rate": 1.140081799591002e-06,
"loss": 0.9288,
"step": 6300
},
{
"epoch": 4.84,
"learning_rate": 1.088957055214724e-06,
"loss": 0.93,
"step": 6310
},
{
"epoch": 4.85,
"learning_rate": 1.0378323108384457e-06,
"loss": 0.8904,
"step": 6320
},
{
"epoch": 4.85,
"learning_rate": 9.867075664621678e-07,
"loss": 0.9087,
"step": 6330
},
{
"epoch": 4.86,
"learning_rate": 9.355828220858896e-07,
"loss": 0.9703,
"step": 6340
},
{
"epoch": 4.87,
"learning_rate": 8.844580777096115e-07,
"loss": 0.8408,
"step": 6350
},
{
"epoch": 4.88,
"learning_rate": 8.333333333333333e-07,
"loss": 0.8819,
"step": 6360
},
{
"epoch": 4.88,
"learning_rate": 7.822085889570551e-07,
"loss": 0.8903,
"step": 6370
},
{
"epoch": 4.89,
"learning_rate": 7.310838445807771e-07,
"loss": 0.9052,
"step": 6380
},
{
"epoch": 4.9,
"learning_rate": 6.79959100204499e-07,
"loss": 0.9522,
"step": 6390
},
{
"epoch": 4.91,
"learning_rate": 6.288343558282209e-07,
"loss": 0.9269,
"step": 6400
},
{
"epoch": 4.92,
"learning_rate": 5.777096114519427e-07,
"loss": 0.9148,
"step": 6410
},
{
"epoch": 4.92,
"learning_rate": 5.265848670756646e-07,
"loss": 0.9424,
"step": 6420
},
{
"epoch": 4.93,
"learning_rate": 4.754601226993865e-07,
"loss": 0.9658,
"step": 6430
},
{
"epoch": 4.94,
"learning_rate": 4.243353783231084e-07,
"loss": 0.9388,
"step": 6440
},
{
"epoch": 4.95,
"learning_rate": 3.732106339468303e-07,
"loss": 0.9308,
"step": 6450
},
{
"epoch": 4.95,
"learning_rate": 3.220858895705522e-07,
"loss": 0.9122,
"step": 6460
},
{
"epoch": 4.96,
"learning_rate": 2.7096114519427406e-07,
"loss": 0.8978,
"step": 6470
},
{
"epoch": 4.97,
"learning_rate": 2.1983640081799592e-07,
"loss": 0.9449,
"step": 6480
},
{
"epoch": 4.98,
"learning_rate": 1.6871165644171781e-07,
"loss": 0.9018,
"step": 6490
},
{
"epoch": 4.98,
"learning_rate": 1.1758691206543969e-07,
"loss": 0.9552,
"step": 6500
},
{
"epoch": 4.99,
"learning_rate": 6.646216768916156e-08,
"loss": 0.9161,
"step": 6510
},
{
"epoch": 5.0,
"learning_rate": 1.533742331288344e-08,
"loss": 0.9403,
"step": 6520
},
{
"epoch": 5.0,
"eval_accuracy": 0.7016984883693075,
"eval_loss": 0.8677756190299988,
"eval_runtime": 303.2543,
"eval_samples_per_second": 137.65,
"eval_steps_per_second": 68.827,
"step": 6520
},
{
"epoch": 5.0,
"step": 6520,
"total_flos": 1.1511308168038711e+19,
"train_loss": 1.11384382686732,
"train_runtime": 4746.5723,
"train_samples_per_second": 175.884,
"train_steps_per_second": 1.374
}
],
"max_steps": 6520,
"num_train_epochs": 5,
"total_flos": 1.1511308168038711e+19,
"trial_name": null,
"trial_params": null
}