{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 17.99960058580748,
"global_step": 33786,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.09,
"learning_rate": 1.8712499999999997e-05,
"loss": 6.2099,
"step": 500
},
{
"epoch": 0.09,
"eval_loss": 3.41253662109375,
"eval_runtime": 1358.074,
"eval_samples_per_second": 14.868,
"eval_steps_per_second": 0.465,
"eval_wer": 1.0,
"step": 500
},
{
"epoch": 0.18,
"learning_rate": 3.7462499999999996e-05,
"loss": 2.9961,
"step": 1000
},
{
"epoch": 0.18,
"eval_loss": 2.9223873615264893,
"eval_runtime": 1361.8836,
"eval_samples_per_second": 14.827,
"eval_steps_per_second": 0.463,
"eval_wer": 1.0,
"step": 1000
},
{
"epoch": 0.26,
"learning_rate": 5.62125e-05,
"loss": 2.2147,
"step": 1500
},
{
"epoch": 0.26,
"eval_loss": 0.6520791053771973,
"eval_runtime": 1355.9385,
"eval_samples_per_second": 14.892,
"eval_steps_per_second": 0.465,
"eval_wer": 0.5567824255052013,
"step": 1500
},
{
"epoch": 0.35,
"learning_rate": 7.49625e-05,
"loss": 1.3017,
"step": 2000
},
{
"epoch": 0.35,
"eval_loss": 0.31525641679763794,
"eval_runtime": 1371.0684,
"eval_samples_per_second": 14.727,
"eval_steps_per_second": 0.46,
"eval_wer": 0.27607269814249236,
"step": 2000
},
{
"epoch": 0.44,
"learning_rate": 7.431581352833637e-05,
"loss": 1.1196,
"step": 2500
},
{
"epoch": 0.44,
"eval_loss": 0.24444133043289185,
"eval_runtime": 1363.4869,
"eval_samples_per_second": 14.809,
"eval_steps_per_second": 0.463,
"eval_wer": 0.23673497683411066,
"step": 2500
},
{
"epoch": 0.53,
"learning_rate": 7.363162705667275e-05,
"loss": 1.0712,
"step": 3000
},
{
"epoch": 0.53,
"eval_loss": 0.23236490786075592,
"eval_runtime": 1368.4487,
"eval_samples_per_second": 14.755,
"eval_steps_per_second": 0.461,
"eval_wer": 0.21321861436015543,
"step": 3000
},
{
"epoch": 0.62,
"learning_rate": 7.294606946983546e-05,
"loss": 1.052,
"step": 3500
},
{
"epoch": 0.62,
"eval_loss": 0.21734564006328583,
"eval_runtime": 1358.6503,
"eval_samples_per_second": 14.862,
"eval_steps_per_second": 0.464,
"eval_wer": 0.20317428528513493,
"step": 3500
},
{
"epoch": 2.13,
"learning_rate": 3.375103277334068e-05,
"loss": 1.2813,
"step": 4000
},
{
"epoch": 2.13,
"eval_loss": 0.332599401473999,
"eval_runtime": 393.989,
"eval_samples_per_second": 10.906,
"eval_steps_per_second": 0.343,
"eval_wer": 0.20989847979467358,
"step": 4000
},
{
"epoch": 2.4,
"learning_rate": 2.3423299366565682e-05,
"loss": 1.2365,
"step": 4500
},
{
"epoch": 2.4,
"eval_loss": 0.3223731815814972,
"eval_runtime": 391.7507,
"eval_samples_per_second": 10.969,
"eval_steps_per_second": 0.345,
"eval_wer": 0.2003283560376986,
"step": 4500
},
{
"epoch": 2.66,
"learning_rate": 1.309556595979069e-05,
"loss": 1.2193,
"step": 5000
},
{
"epoch": 2.66,
"eval_loss": 0.31981074810028076,
"eval_runtime": 402.4439,
"eval_samples_per_second": 10.677,
"eval_steps_per_second": 0.335,
"eval_wer": 0.19565239980464894,
"step": 5000
},
{
"epoch": 2.93,
"learning_rate": 2.767832553015698e-06,
"loss": 1.2072,
"step": 5500
},
{
"epoch": 2.93,
"eval_loss": 0.3063456118106842,
"eval_runtime": 396.6525,
"eval_samples_per_second": 10.833,
"eval_steps_per_second": 0.34,
"eval_wer": 0.19327285763271923,
"step": 5500
},
{
"epoch": 3.2,
"learning_rate": 4.263388037141005e-05,
"loss": 1.213,
"step": 6000
},
{
"epoch": 3.2,
"eval_loss": 0.3051116168498993,
"eval_runtime": 371.5477,
"eval_samples_per_second": 11.565,
"eval_steps_per_second": 0.363,
"eval_wer": 0.19797998690732255,
"step": 6000
},
{
"epoch": 3.46,
"learning_rate": 3.8585078816670256e-05,
"loss": 1.2074,
"step": 6500
},
{
"epoch": 3.46,
"eval_loss": 0.3011966645717621,
"eval_runtime": 372.0587,
"eval_samples_per_second": 11.549,
"eval_steps_per_second": 0.363,
"eval_wer": 0.18792148549934018,
"step": 6500
},
{
"epoch": 3.73,
"learning_rate": 3.4536277261930465e-05,
"loss": 1.1918,
"step": 7000
},
{
"epoch": 3.73,
"eval_loss": 0.29471954703330994,
"eval_runtime": 372.8767,
"eval_samples_per_second": 11.524,
"eval_steps_per_second": 0.362,
"eval_wer": 0.18287145276764655,
"step": 7000
},
{
"epoch": 4.0,
"learning_rate": 3.0487475707190668e-05,
"loss": 1.1893,
"step": 7500
},
{
"epoch": 4.0,
"eval_loss": 0.28953900933265686,
"eval_runtime": 372.4558,
"eval_samples_per_second": 11.537,
"eval_steps_per_second": 0.362,
"eval_wer": 0.1807205129004437,
"step": 7500
},
{
"epoch": 4.26,
"learning_rate": 2.643867415245087e-05,
"loss": 1.1751,
"step": 8000
},
{
"epoch": 4.26,
"eval_loss": 0.2877567410469055,
"eval_runtime": 371.9244,
"eval_samples_per_second": 11.553,
"eval_steps_per_second": 0.363,
"eval_wer": 0.17759281773122604,
"step": 8000
},
{
"epoch": 4.53,
"learning_rate": 2.2389872597711073e-05,
"loss": 1.1628,
"step": 8500
},
{
"epoch": 4.53,
"eval_loss": 0.28352275490760803,
"eval_runtime": 373.4388,
"eval_samples_per_second": 11.507,
"eval_steps_per_second": 0.362,
"eval_wer": 0.1730727267059447,
"step": 8500
},
{
"epoch": 4.79,
"learning_rate": 1.834107104297128e-05,
"loss": 1.1577,
"step": 9000
},
{
"epoch": 4.79,
"eval_loss": 0.28156954050064087,
"eval_runtime": 371.5997,
"eval_samples_per_second": 11.564,
"eval_steps_per_second": 0.363,
"eval_wer": 0.17605494768124527,
"step": 9000
},
{
"epoch": 5.06,
"learning_rate": 1.4300367091340963e-05,
"loss": 1.1448,
"step": 9500
},
{
"epoch": 5.06,
"eval_loss": 0.2757455110549927,
"eval_runtime": 373.7148,
"eval_samples_per_second": 11.498,
"eval_steps_per_second": 0.361,
"eval_wer": 0.17397674491100096,
"step": 9500
},
{
"epoch": 5.33,
"learning_rate": 1.0251565536601165e-05,
"loss": 1.1407,
"step": 10000
},
{
"epoch": 5.33,
"eval_loss": 0.2768358588218689,
"eval_runtime": 373.2273,
"eval_samples_per_second": 11.513,
"eval_steps_per_second": 0.362,
"eval_wer": 0.17976453962613131,
"step": 10000
},
{
"epoch": 5.59,
"learning_rate": 6.202763981861369e-06,
"loss": 1.1401,
"step": 10500
},
{
"epoch": 5.59,
"eval_loss": 0.2780420780181885,
"eval_runtime": 375.3753,
"eval_samples_per_second": 11.447,
"eval_steps_per_second": 0.36,
"eval_wer": 0.18160374907779753,
"step": 10500
},
{
"epoch": 5.86,
"learning_rate": 2.153962427121572e-06,
"loss": 1.1333,
"step": 11000
},
{
"epoch": 5.86,
"eval_loss": 0.2748132646083832,
"eval_runtime": 371.6352,
"eval_samples_per_second": 11.562,
"eval_steps_per_second": 0.363,
"eval_wer": 0.17495350021301578,
"step": 11000
},
{
"epoch": 6.13,
"learning_rate": 4.029916195673358e-05,
"loss": 1.1571,
"step": 11500
},
{
"epoch": 6.13,
"eval_loss": 0.2807982861995697,
"eval_runtime": 393.9701,
"eval_samples_per_second": 10.907,
"eval_steps_per_second": 0.343,
"eval_wer": 0.17083865872793208,
"step": 11500
},
{
"epoch": 6.39,
"learning_rate": 3.8472032742155524e-05,
"loss": 1.1505,
"step": 12000
},
{
"epoch": 6.39,
"eval_loss": 0.27258625626564026,
"eval_runtime": 389.5937,
"eval_samples_per_second": 11.029,
"eval_steps_per_second": 0.347,
"eval_wer": 0.16920726955329032,
"step": 12000
},
{
"epoch": 6.66,
"learning_rate": 3.6648557786006625e-05,
"loss": 1.1519,
"step": 12500
},
{
"epoch": 6.66,
"eval_loss": 0.2748955190181732,
"eval_runtime": 387.583,
"eval_samples_per_second": 11.087,
"eval_steps_per_second": 0.348,
"eval_wer": 0.16539376746989204,
"step": 12500
},
{
"epoch": 6.93,
"learning_rate": 3.482142857142857e-05,
"loss": 1.136,
"step": 13000
},
{
"epoch": 6.93,
"eval_loss": 0.276467502117157,
"eval_runtime": 393.6733,
"eval_samples_per_second": 10.915,
"eval_steps_per_second": 0.343,
"eval_wer": 0.16425075594625768,
"step": 13000
},
{
"epoch": 7.19,
"learning_rate": 3.299429935685051e-05,
"loss": 1.1326,
"step": 13500
},
{
"epoch": 7.19,
"eval_loss": 0.27056241035461426,
"eval_runtime": 391.6082,
"eval_samples_per_second": 10.973,
"eval_steps_per_second": 0.345,
"eval_wer": 0.1668277273813606,
"step": 13500
},
{
"epoch": 7.46,
"learning_rate": 3.116717014227246e-05,
"loss": 1.1342,
"step": 14000
},
{
"epoch": 7.46,
"eval_loss": 0.26654428243637085,
"eval_runtime": 388.567,
"eval_samples_per_second": 11.059,
"eval_steps_per_second": 0.347,
"eval_wer": 0.1638247243783576,
"step": 14000
},
{
"epoch": 7.72,
"learning_rate": 2.9340040927694404e-05,
"loss": 1.1286,
"step": 14500
},
{
"epoch": 7.72,
"eval_loss": 0.2668865919113159,
"eval_runtime": 384.4478,
"eval_samples_per_second": 11.177,
"eval_steps_per_second": 0.351,
"eval_wer": 0.1635857310597795,
"step": 14500
},
{
"epoch": 7.99,
"learning_rate": 2.7516565971545504e-05,
"loss": 1.1243,
"step": 15000
},
{
"epoch": 7.99,
"eval_loss": 0.2619013488292694,
"eval_runtime": 392.1143,
"eval_samples_per_second": 10.959,
"eval_steps_per_second": 0.344,
"eval_wer": 0.16234920041148415,
"step": 15000
},
{
"epoch": 8.26,
"learning_rate": 2.5689436756967453e-05,
"loss": 1.1173,
"step": 15500
},
{
"epoch": 8.26,
"eval_loss": 0.2651631236076355,
"eval_runtime": 388.7223,
"eval_samples_per_second": 11.054,
"eval_steps_per_second": 0.347,
"eval_wer": 0.16037490777975208,
"step": 15500
},
{
"epoch": 8.52,
"learning_rate": 2.3862307542389395e-05,
"loss": 1.1129,
"step": 16000
},
{
"epoch": 8.52,
"eval_loss": 0.26095372438430786,
"eval_runtime": 387.1141,
"eval_samples_per_second": 11.1,
"eval_steps_per_second": 0.349,
"eval_wer": 0.1597514469486788,
"step": 16000
},
{
"epoch": 8.79,
"learning_rate": 2.203517832781134e-05,
"loss": 1.1091,
"step": 16500
},
{
"epoch": 8.79,
"eval_loss": 0.2608127295970917,
"eval_runtime": 386.5271,
"eval_samples_per_second": 11.117,
"eval_steps_per_second": 0.349,
"eval_wer": 0.15837983312031756,
"step": 16500
},
{
"epoch": 9.06,
"learning_rate": 2.0208049113233286e-05,
"loss": 1.1053,
"step": 17000
},
{
"epoch": 9.06,
"eval_loss": 0.2632738947868347,
"eval_runtime": 389.2784,
"eval_samples_per_second": 11.038,
"eval_steps_per_second": 0.347,
"eval_wer": 0.1664016958134605,
"step": 17000
},
{
"epoch": 9.32,
"learning_rate": 1.8384574157084387e-05,
"loss": 1.1004,
"step": 17500
},
{
"epoch": 9.32,
"eval_loss": 0.2594461441040039,
"eval_runtime": 388.9349,
"eval_samples_per_second": 11.048,
"eval_steps_per_second": 0.347,
"eval_wer": 0.16618348452258486,
"step": 17500
},
{
"epoch": 9.59,
"learning_rate": 1.6557444942506332e-05,
"loss": 1.0995,
"step": 18000
},
{
"epoch": 9.59,
"eval_loss": 0.26234543323516846,
"eval_runtime": 383.4387,
"eval_samples_per_second": 11.206,
"eval_steps_per_second": 0.352,
"eval_wer": 0.15694587320884898,
"step": 18000
},
{
"epoch": 9.86,
"learning_rate": 1.4730315727928276e-05,
"loss": 1.0964,
"step": 18500
},
{
"epoch": 9.86,
"eval_loss": 0.26244357228279114,
"eval_runtime": 384.9493,
"eval_samples_per_second": 11.163,
"eval_steps_per_second": 0.351,
"eval_wer": 0.15968910086557145,
"step": 18500
},
{
"epoch": 10.12,
"learning_rate": 1.2903186513350224e-05,
"loss": 1.09,
"step": 19000
},
{
"epoch": 10.12,
"eval_loss": 0.2576591968536377,
"eval_runtime": 391.5397,
"eval_samples_per_second": 10.975,
"eval_steps_per_second": 0.345,
"eval_wer": 0.15782910938620281,
"step": 19000
},
{
"epoch": 10.39,
"learning_rate": 1.108336581563048e-05,
"loss": 1.089,
"step": 19500
},
{
"epoch": 10.39,
"eval_loss": 0.25744903087615967,
"eval_runtime": 384.7348,
"eval_samples_per_second": 11.169,
"eval_steps_per_second": 0.351,
"eval_wer": 0.1531219801115995,
"step": 19500
},
{
"epoch": 10.66,
"learning_rate": 9.256236601052426e-06,
"loss": 1.0864,
"step": 20000
},
{
"epoch": 10.66,
"eval_loss": 0.2556162476539612,
"eval_runtime": 391.8515,
"eval_samples_per_second": 10.966,
"eval_steps_per_second": 0.345,
"eval_wer": 0.15464945914772904,
"step": 20000
},
{
"epoch": 10.92,
"learning_rate": 7.429107386474371e-06,
"loss": 1.0806,
"step": 20500
},
{
"epoch": 10.92,
"eval_loss": 0.2548317313194275,
"eval_runtime": 384.3272,
"eval_samples_per_second": 11.181,
"eval_steps_per_second": 0.351,
"eval_wer": 0.1583174870372102,
"step": 20500
},
{
"epoch": 11.19,
"learning_rate": 5.6019781718963155e-06,
"loss": 1.0842,
"step": 21000
},
{
"epoch": 11.19,
"eval_loss": 0.25501224398612976,
"eval_runtime": 383.8764,
"eval_samples_per_second": 11.194,
"eval_steps_per_second": 0.352,
"eval_wer": 0.1542026455521265,
"step": 21000
},
{
"epoch": 11.45,
"learning_rate": 3.774848957318261e-06,
"loss": 1.0805,
"step": 21500
},
{
"epoch": 11.45,
"eval_loss": 0.25607678294181824,
"eval_runtime": 388.7678,
"eval_samples_per_second": 11.053,
"eval_steps_per_second": 0.347,
"eval_wer": 0.15236343610046033,
"step": 21500
},
{
"epoch": 11.72,
"learning_rate": 1.9477197427402063e-06,
"loss": 1.0722,
"step": 22000
},
{
"epoch": 11.72,
"eval_loss": 0.25402259826660156,
"eval_runtime": 385.5053,
"eval_samples_per_second": 11.146,
"eval_steps_per_second": 0.35,
"eval_wer": 0.1565614056963538,
"step": 22000
},
{
"epoch": 11.99,
"learning_rate": 1.2059052816215163e-07,
"loss": 1.0763,
"step": 22500
},
{
"epoch": 11.99,
"eval_loss": 0.2549177408218384,
"eval_runtime": 379.953,
"eval_samples_per_second": 11.309,
"eval_steps_per_second": 0.355,
"eval_wer": 0.15720564855512953,
"step": 22500
},
{
"epoch": 12.25,
"learning_rate": 2.5471119360724847e-05,
"loss": 1.0835,
"step": 23000
},
{
"epoch": 12.25,
"eval_loss": 0.25863561034202576,
"eval_runtime": 369.3533,
"eval_samples_per_second": 11.634,
"eval_steps_per_second": 0.366,
"eval_wer": 0.15212444278188222,
"step": 23000
},
{
"epoch": 12.52,
"learning_rate": 2.4293714213804817e-05,
"loss": 1.0883,
"step": 23500
},
{
"epoch": 12.52,
"eval_loss": 0.25827670097351074,
"eval_runtime": 370.2467,
"eval_samples_per_second": 11.606,
"eval_steps_per_second": 0.365,
"eval_wer": 0.15193740453256024,
"step": 23500
},
{
"epoch": 12.79,
"learning_rate": 2.3113949537532244e-05,
"loss": 1.0888,
"step": 24000
},
{
"epoch": 12.79,
"eval_loss": 0.2551300823688507,
"eval_runtime": 367.9843,
"eval_samples_per_second": 11.677,
"eval_steps_per_second": 0.367,
"eval_wer": 0.15819279487099555,
"step": 24000
},
{
"epoch": 13.05,
"learning_rate": 2.1934184861259672e-05,
"loss": 1.0933,
"step": 24500
},
{
"epoch": 13.05,
"eval_loss": 0.2628032863140106,
"eval_runtime": 369.9671,
"eval_samples_per_second": 11.615,
"eval_steps_per_second": 0.365,
"eval_wer": 0.1537142679011191,
"step": 24500
},
{
"epoch": 13.32,
"learning_rate": 2.07544201849871e-05,
"loss": 1.0799,
"step": 25000
},
{
"epoch": 13.32,
"eval_loss": 0.2600410580635071,
"eval_runtime": 374.9827,
"eval_samples_per_second": 11.459,
"eval_steps_per_second": 0.36,
"eval_wer": 0.150752828953521,
"step": 25000
},
{
"epoch": 13.59,
"learning_rate": 1.957701503806707e-05,
"loss": 1.0804,
"step": 25500
},
{
"epoch": 13.59,
"eval_loss": 0.26200664043426514,
"eval_runtime": 369.1646,
"eval_samples_per_second": 11.64,
"eval_steps_per_second": 0.366,
"eval_wer": 0.14753161465964235,
"step": 25500
},
{
"epoch": 13.85,
"learning_rate": 1.8397250361794498e-05,
"loss": 1.0814,
"step": 26000
},
{
"epoch": 13.85,
"eval_loss": 0.2537305951118469,
"eval_runtime": 368.6655,
"eval_samples_per_second": 11.656,
"eval_steps_per_second": 0.366,
"eval_wer": 0.15170880222783337,
"step": 26000
},
{
"epoch": 14.12,
"learning_rate": 1.7217485685521926e-05,
"loss": 1.0693,
"step": 26500
},
{
"epoch": 14.12,
"eval_loss": 0.25602129101753235,
"eval_runtime": 368.3159,
"eval_samples_per_second": 11.667,
"eval_steps_per_second": 0.367,
"eval_wer": 0.15421303656597773,
"step": 26500
},
{
"epoch": 14.38,
"learning_rate": 1.6037721009249354e-05,
"loss": 1.0724,
"step": 27000
},
{
"epoch": 14.38,
"eval_loss": 0.2540068030357361,
"eval_runtime": 369.0094,
"eval_samples_per_second": 11.645,
"eval_steps_per_second": 0.366,
"eval_wer": 0.15736151376289784,
"step": 27000
},
{
"epoch": 14.65,
"learning_rate": 1.4857956332976782e-05,
"loss": 1.0704,
"step": 27500
},
{
"epoch": 14.65,
"eval_loss": 0.25483617186546326,
"eval_runtime": 365.0658,
"eval_samples_per_second": 11.77,
"eval_steps_per_second": 0.37,
"eval_wer": 0.16258819373006225,
"step": 27500
},
{
"epoch": 14.92,
"learning_rate": 1.3678191656704208e-05,
"loss": 1.0729,
"step": 28000
},
{
"epoch": 14.92,
"eval_loss": 0.254844069480896,
"eval_runtime": 367.5842,
"eval_samples_per_second": 11.69,
"eval_steps_per_second": 0.367,
"eval_wer": 0.16009435040576908,
"step": 28000
},
{
"epoch": 15.18,
"learning_rate": 1.2498426980431636e-05,
"loss": 1.0724,
"step": 28500
},
{
"epoch": 15.18,
"eval_loss": 0.25110504031181335,
"eval_runtime": 367.3861,
"eval_samples_per_second": 11.696,
"eval_steps_per_second": 0.367,
"eval_wer": 0.15124120660452842,
"step": 28500
},
{
"epoch": 15.45,
"learning_rate": 1.1318662304159062e-05,
"loss": 1.0655,
"step": 29000
},
{
"epoch": 15.45,
"eval_loss": 0.24978148937225342,
"eval_runtime": 375.4183,
"eval_samples_per_second": 11.446,
"eval_steps_per_second": 0.36,
"eval_wer": 0.14903831166806944,
"step": 29000
},
{
"epoch": 15.98,
"learning_rate": 8.963852010319007e-06,
"loss": 1.0608,
"step": 30000
},
{
"epoch": 15.98,
"eval_loss": 0.24873663485050201,
"eval_runtime": 370.6074,
"eval_samples_per_second": 11.594,
"eval_steps_per_second": 0.364,
"eval_wer": 0.14812390244916196,
"step": 30000
},
{
"epoch": 16.52,
"learning_rate": 6.604322657773862e-06,
"loss": 1.0541,
"step": 31000
},
{
"epoch": 16.52,
"eval_loss": 0.2467627078294754,
"eval_runtime": 371.5001,
"eval_samples_per_second": 11.567,
"eval_steps_per_second": 0.363,
"eval_wer": 0.15039953448257948,
"step": 31000
},
{
"epoch": 17.05,
"learning_rate": 4.244793305228717e-06,
"loss": 1.0584,
"step": 32000
},
{
"epoch": 17.05,
"eval_loss": 0.2466605007648468,
"eval_runtime": 370.8863,
"eval_samples_per_second": 11.586,
"eval_steps_per_second": 0.364,
"eval_wer": 0.1493084780282012,
"step": 32000
},
{
"epoch": 17.58,
"learning_rate": 1.8852639526835713e-06,
"loss": 1.0507,
"step": 33000
},
{
"epoch": 17.58,
"eval_loss": 0.2480592578649521,
"eval_runtime": 373.0281,
"eval_samples_per_second": 11.519,
"eval_steps_per_second": 0.362,
"eval_wer": 0.15173997526938704,
"step": 33000
},
{
"epoch": 18.0,
"step": 33786,
"total_flos": 9.499341430600616e+20,
"train_loss": 0.16521977071390054,
"train_runtime": 71350.5908,
"train_samples_per_second": 60.63,
"train_steps_per_second": 0.474
}
],
"max_steps": 33786,
"num_train_epochs": 18,
"total_flos": 9.499341430600616e+20,
"trial_name": null,
"trial_params": null
}