rbelanec commited on
Commit
9f1843e
·
verified ·
1 Parent(s): 36f7466

Training in progress, step 17172

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +192 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ccc2e85797728666c27fb46b4afa9a755b87c6a1ac8662c124682deabf5bd5f
3
  size 1074144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:440461b7dfd5e4e61480a8631d430c7fa013f99dd5360e2683a0c496c00f3751
3
  size 1074144
trainer_log.jsonl CHANGED
@@ -3260,3 +3260,195 @@
3260
  {"current_steps": 16218, "total_steps": 19080, "eval_loss": 0.48336100578308105, "epoch": 8.5, "percentage": 85.0, "elapsed_time": "1:03:54", "remaining_time": "0:11:16", "throughput": 2765.24, "total_tokens": 10604656}
3261
  {"current_steps": 16220, "total_steps": 19080, "loss": 0.3983, "lr": 3.3470784107406976e-06, "epoch": 8.50104821802935, "percentage": 85.01, "elapsed_time": "1:03:56", "remaining_time": "0:11:16", "throughput": 2764.67, "total_tokens": 10605616}
3262
  {"current_steps": 16225, "total_steps": 19080, "loss": 0.6283, "lr": 3.3356568099349283e-06, "epoch": 8.503668763102725, "percentage": 85.04, "elapsed_time": "1:03:57", "remaining_time": "0:11:15", "throughput": 2764.76, "total_tokens": 10609040}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3260
  {"current_steps": 16218, "total_steps": 19080, "eval_loss": 0.48336100578308105, "epoch": 8.5, "percentage": 85.0, "elapsed_time": "1:03:54", "remaining_time": "0:11:16", "throughput": 2765.24, "total_tokens": 10604656}
3261
  {"current_steps": 16220, "total_steps": 19080, "loss": 0.3983, "lr": 3.3470784107406976e-06, "epoch": 8.50104821802935, "percentage": 85.01, "elapsed_time": "1:03:56", "remaining_time": "0:11:16", "throughput": 2764.67, "total_tokens": 10605616}
3262
  {"current_steps": 16225, "total_steps": 19080, "loss": 0.6283, "lr": 3.3356568099349283e-06, "epoch": 8.503668763102725, "percentage": 85.04, "elapsed_time": "1:03:57", "remaining_time": "0:11:15", "throughput": 2764.76, "total_tokens": 10609040}
3263
+ {"current_steps": 16230, "total_steps": 19080, "loss": 0.5626, "lr": 3.3242533368619435e-06, "epoch": 8.5062893081761, "percentage": 85.06, "elapsed_time": "1:03:58", "remaining_time": "0:11:14", "throughput": 2764.82, "total_tokens": 10612304}
3264
+ {"current_steps": 16235, "total_steps": 19080, "loss": 0.3899, "lr": 3.312868001063654e-06, "epoch": 8.508909853249476, "percentage": 85.09, "elapsed_time": "1:03:59", "remaining_time": "0:11:12", "throughput": 2764.83, "total_tokens": 10614928}
3265
+ {"current_steps": 16240, "total_steps": 19080, "loss": 0.5852, "lr": 3.3015008120668072e-06, "epoch": 8.51153039832285, "percentage": 85.12, "elapsed_time": "1:04:00", "remaining_time": "0:11:11", "throughput": 2764.91, "total_tokens": 10618320}
3266
+ {"current_steps": 16245, "total_steps": 19080, "loss": 0.4746, "lr": 3.290151779382922e-06, "epoch": 8.514150943396226, "percentage": 85.14, "elapsed_time": "1:04:01", "remaining_time": "0:11:10", "throughput": 2764.96, "total_tokens": 10621296}
3267
+ {"current_steps": 16250, "total_steps": 19080, "loss": 0.505, "lr": 3.2788209125083654e-06, "epoch": 8.516771488469601, "percentage": 85.17, "elapsed_time": "1:04:02", "remaining_time": "0:11:09", "throughput": 2765.0, "total_tokens": 10623984}
3268
+ {"current_steps": 16255, "total_steps": 19080, "loss": 0.4538, "lr": 3.267508220924287e-06, "epoch": 8.519392033542976, "percentage": 85.19, "elapsed_time": "1:04:03", "remaining_time": "0:11:08", "throughput": 2765.1, "total_tokens": 10628560}
3269
+ {"current_steps": 16260, "total_steps": 19080, "loss": 0.4187, "lr": 3.256213714096623e-06, "epoch": 8.522012578616351, "percentage": 85.22, "elapsed_time": "1:04:04", "remaining_time": "0:11:06", "throughput": 2765.18, "total_tokens": 10631856}
3270
+ {"current_steps": 16265, "total_steps": 19080, "loss": 0.432, "lr": 3.2449374014761114e-06, "epoch": 8.524633123689728, "percentage": 85.25, "elapsed_time": "1:04:06", "remaining_time": "0:11:05", "throughput": 2765.24, "total_tokens": 10635696}
3271
+ {"current_steps": 16270, "total_steps": 19080, "loss": 0.4774, "lr": 3.2336792924982514e-06, "epoch": 8.527253668763104, "percentage": 85.27, "elapsed_time": "1:04:07", "remaining_time": "0:11:04", "throughput": 2765.27, "total_tokens": 10638384}
3272
+ {"current_steps": 16275, "total_steps": 19080, "loss": 0.4925, "lr": 3.222439396583307e-06, "epoch": 8.529874213836479, "percentage": 85.3, "elapsed_time": "1:04:08", "remaining_time": "0:11:03", "throughput": 2765.3, "total_tokens": 10641456}
3273
+ {"current_steps": 16280, "total_steps": 19080, "loss": 0.3939, "lr": 3.2112177231363226e-06, "epoch": 8.532494758909854, "percentage": 85.32, "elapsed_time": "1:04:09", "remaining_time": "0:11:02", "throughput": 2765.34, "total_tokens": 10644336}
3274
+ {"current_steps": 16285, "total_steps": 19080, "loss": 0.4039, "lr": 3.2000142815470756e-06, "epoch": 8.535115303983229, "percentage": 85.35, "elapsed_time": "1:04:10", "remaining_time": "0:11:00", "throughput": 2765.4, "total_tokens": 10647440}
3275
+ {"current_steps": 16290, "total_steps": 19080, "loss": 0.4358, "lr": 3.188829081190095e-06, "epoch": 8.537735849056604, "percentage": 85.38, "elapsed_time": "1:04:11", "remaining_time": "0:10:59", "throughput": 2765.41, "total_tokens": 10649872}
3276
+ {"current_steps": 16295, "total_steps": 19080, "loss": 0.5181, "lr": 3.1776621314246384e-06, "epoch": 8.54035639412998, "percentage": 85.4, "elapsed_time": "1:04:12", "remaining_time": "0:10:58", "throughput": 2765.46, "total_tokens": 10652976}
3277
+ {"current_steps": 16300, "total_steps": 19080, "loss": 0.431, "lr": 3.1665134415947125e-06, "epoch": 8.542976939203355, "percentage": 85.43, "elapsed_time": "1:04:13", "remaining_time": "0:10:57", "throughput": 2765.5, "total_tokens": 10656016}
3278
+ {"current_steps": 16305, "total_steps": 19080, "loss": 0.5114, "lr": 3.1553830210290236e-06, "epoch": 8.54559748427673, "percentage": 85.46, "elapsed_time": "1:04:14", "remaining_time": "0:10:55", "throughput": 2765.58, "total_tokens": 10659536}
3279
+ {"current_steps": 16310, "total_steps": 19080, "loss": 0.3691, "lr": 3.1442708790410002e-06, "epoch": 8.548218029350105, "percentage": 85.48, "elapsed_time": "1:04:15", "remaining_time": "0:10:54", "throughput": 2765.63, "total_tokens": 10662416}
3280
+ {"current_steps": 16315, "total_steps": 19080, "loss": 0.3963, "lr": 3.133177024928771e-06, "epoch": 8.55083857442348, "percentage": 85.51, "elapsed_time": "1:04:16", "remaining_time": "0:10:53", "throughput": 2765.74, "total_tokens": 10666320}
3281
+ {"current_steps": 16320, "total_steps": 19080, "loss": 0.6304, "lr": 3.1221014679751777e-06, "epoch": 8.553459119496855, "percentage": 85.53, "elapsed_time": "1:04:17", "remaining_time": "0:10:52", "throughput": 2765.78, "total_tokens": 10669136}
3282
+ {"current_steps": 16325, "total_steps": 19080, "loss": 0.4408, "lr": 3.111044217447731e-06, "epoch": 8.55607966457023, "percentage": 85.56, "elapsed_time": "1:04:18", "remaining_time": "0:10:51", "throughput": 2765.82, "total_tokens": 10672240}
3283
+ {"current_steps": 16330, "total_steps": 19080, "loss": 0.4778, "lr": 3.1000052825986366e-06, "epoch": 8.558700209643606, "percentage": 85.59, "elapsed_time": "1:04:19", "remaining_time": "0:10:49", "throughput": 2765.86, "total_tokens": 10674992}
3284
+ {"current_steps": 16335, "total_steps": 19080, "loss": 0.508, "lr": 3.0889846726647657e-06, "epoch": 8.56132075471698, "percentage": 85.61, "elapsed_time": "1:04:20", "remaining_time": "0:10:48", "throughput": 2765.88, "total_tokens": 10677616}
3285
+ {"current_steps": 16340, "total_steps": 19080, "loss": 0.4715, "lr": 3.077982396867668e-06, "epoch": 8.563941299790356, "percentage": 85.64, "elapsed_time": "1:04:21", "remaining_time": "0:10:47", "throughput": 2765.97, "total_tokens": 10681136}
3286
+ {"current_steps": 16345, "total_steps": 19080, "loss": 0.6128, "lr": 3.066998464413545e-06, "epoch": 8.566561844863731, "percentage": 85.67, "elapsed_time": "1:04:22", "remaining_time": "0:10:46", "throughput": 2766.02, "total_tokens": 10684368}
3287
+ {"current_steps": 16350, "total_steps": 19080, "loss": 0.5237, "lr": 3.056032884493243e-06, "epoch": 8.569182389937106, "percentage": 85.69, "elapsed_time": "1:04:23", "remaining_time": "0:10:45", "throughput": 2766.06, "total_tokens": 10687632}
3288
+ {"current_steps": 16355, "total_steps": 19080, "loss": 0.4965, "lr": 3.045085666282266e-06, "epoch": 8.571802935010481, "percentage": 85.72, "elapsed_time": "1:04:25", "remaining_time": "0:10:44", "throughput": 2766.18, "total_tokens": 10692336}
3289
+ {"current_steps": 16360, "total_steps": 19080, "loss": 0.5053, "lr": 3.034156818940745e-06, "epoch": 8.574423480083858, "percentage": 85.74, "elapsed_time": "1:04:26", "remaining_time": "0:10:42", "throughput": 2766.28, "total_tokens": 10696048}
3290
+ {"current_steps": 16365, "total_steps": 19080, "loss": 0.4342, "lr": 3.0232463516134317e-06, "epoch": 8.577044025157234, "percentage": 85.77, "elapsed_time": "1:04:28", "remaining_time": "0:10:41", "throughput": 2766.36, "total_tokens": 10700304}
3291
+ {"current_steps": 16370, "total_steps": 19080, "loss": 0.4676, "lr": 3.0123542734297267e-06, "epoch": 8.579664570230609, "percentage": 85.8, "elapsed_time": "1:04:28", "remaining_time": "0:10:40", "throughput": 2766.39, "total_tokens": 10703120}
3292
+ {"current_steps": 16375, "total_steps": 19080, "loss": 0.47, "lr": 3.0014805935035973e-06, "epoch": 8.582285115303984, "percentage": 85.82, "elapsed_time": "1:04:30", "remaining_time": "0:10:39", "throughput": 2766.54, "total_tokens": 10707536}
3293
+ {"current_steps": 16380, "total_steps": 19080, "loss": 0.5378, "lr": 2.99062532093366e-06, "epoch": 8.584905660377359, "percentage": 85.85, "elapsed_time": "1:04:31", "remaining_time": "0:10:38", "throughput": 2766.59, "total_tokens": 10710384}
3294
+ {"current_steps": 16385, "total_steps": 19080, "loss": 0.4562, "lr": 2.979788464803107e-06, "epoch": 8.587526205450734, "percentage": 85.88, "elapsed_time": "1:04:32", "remaining_time": "0:10:36", "throughput": 2766.67, "total_tokens": 10713840}
3295
+ {"current_steps": 16390, "total_steps": 19080, "loss": 0.4114, "lr": 2.968970034179719e-06, "epoch": 8.59014675052411, "percentage": 85.9, "elapsed_time": "1:04:33", "remaining_time": "0:10:35", "throughput": 2766.7, "total_tokens": 10716720}
3296
+ {"current_steps": 16395, "total_steps": 19080, "loss": 0.512, "lr": 2.9581700381158735e-06, "epoch": 8.592767295597485, "percentage": 85.93, "elapsed_time": "1:04:34", "remaining_time": "0:10:34", "throughput": 2766.8, "total_tokens": 10720720}
3297
+ {"current_steps": 16400, "total_steps": 19080, "loss": 0.4469, "lr": 2.9473884856485113e-06, "epoch": 8.59538784067086, "percentage": 85.95, "elapsed_time": "1:04:35", "remaining_time": "0:10:33", "throughput": 2766.84, "total_tokens": 10723952}
3298
+ {"current_steps": 16405, "total_steps": 19080, "loss": 0.5638, "lr": 2.936625385799133e-06, "epoch": 8.598008385744235, "percentage": 85.98, "elapsed_time": "1:04:36", "remaining_time": "0:10:32", "throughput": 2766.8, "total_tokens": 10726096}
3299
+ {"current_steps": 16410, "total_steps": 19080, "loss": 0.3895, "lr": 2.925880747573831e-06, "epoch": 8.60062893081761, "percentage": 86.01, "elapsed_time": "1:04:37", "remaining_time": "0:10:30", "throughput": 2766.87, "total_tokens": 10729456}
3300
+ {"current_steps": 16415, "total_steps": 19080, "loss": 0.3606, "lr": 2.9151545799632003e-06, "epoch": 8.603249475890985, "percentage": 86.03, "elapsed_time": "1:04:38", "remaining_time": "0:10:29", "throughput": 2766.86, "total_tokens": 10731824}
3301
+ {"current_steps": 16420, "total_steps": 19080, "loss": 0.3585, "lr": 2.9044468919424305e-06, "epoch": 8.60587002096436, "percentage": 86.06, "elapsed_time": "1:04:39", "remaining_time": "0:10:28", "throughput": 2766.91, "total_tokens": 10734864}
3302
+ {"current_steps": 16425, "total_steps": 19080, "loss": 0.457, "lr": 2.8937576924712133e-06, "epoch": 8.608490566037736, "percentage": 86.08, "elapsed_time": "1:04:40", "remaining_time": "0:10:27", "throughput": 2766.95, "total_tokens": 10737744}
3303
+ {"current_steps": 16430, "total_steps": 19080, "loss": 0.3259, "lr": 2.883086990493783e-06, "epoch": 8.61111111111111, "percentage": 86.11, "elapsed_time": "1:04:41", "remaining_time": "0:10:26", "throughput": 2767.0, "total_tokens": 10740656}
3304
+ {"current_steps": 16435, "total_steps": 19080, "loss": 0.7093, "lr": 2.872434794938905e-06, "epoch": 8.613731656184486, "percentage": 86.14, "elapsed_time": "1:04:43", "remaining_time": "0:10:24", "throughput": 2767.1, "total_tokens": 10744688}
3305
+ {"current_steps": 16440, "total_steps": 19080, "loss": 0.5177, "lr": 2.861801114719842e-06, "epoch": 8.616352201257861, "percentage": 86.16, "elapsed_time": "1:04:43", "remaining_time": "0:10:23", "throughput": 2767.12, "total_tokens": 10747184}
3306
+ {"current_steps": 16445, "total_steps": 19080, "loss": 0.6002, "lr": 2.8511859587343704e-06, "epoch": 8.618972746331236, "percentage": 86.19, "elapsed_time": "1:04:44", "remaining_time": "0:10:22", "throughput": 2767.14, "total_tokens": 10750320}
3307
+ {"current_steps": 16450, "total_steps": 19080, "loss": 0.3905, "lr": 2.840589335864774e-06, "epoch": 8.621593291404611, "percentage": 86.22, "elapsed_time": "1:04:45", "remaining_time": "0:10:21", "throughput": 2767.2, "total_tokens": 10753328}
3308
+ {"current_steps": 16455, "total_steps": 19080, "loss": 0.4868, "lr": 2.830011254977821e-06, "epoch": 8.624213836477988, "percentage": 86.24, "elapsed_time": "1:04:46", "remaining_time": "0:10:20", "throughput": 2767.24, "total_tokens": 10756208}
3309
+ {"current_steps": 16460, "total_steps": 19080, "loss": 0.4328, "lr": 2.819451724924768e-06, "epoch": 8.626834381551364, "percentage": 86.27, "elapsed_time": "1:04:48", "remaining_time": "0:10:18", "throughput": 2767.32, "total_tokens": 10759888}
3310
+ {"current_steps": 16465, "total_steps": 19080, "loss": 0.4203, "lr": 2.8089107545413355e-06, "epoch": 8.629454926624739, "percentage": 86.29, "elapsed_time": "1:04:49", "remaining_time": "0:10:17", "throughput": 2767.39, "total_tokens": 10763152}
3311
+ {"current_steps": 16470, "total_steps": 19080, "loss": 0.4715, "lr": 2.7983883526477433e-06, "epoch": 8.632075471698114, "percentage": 86.32, "elapsed_time": "1:04:50", "remaining_time": "0:10:16", "throughput": 2767.51, "total_tokens": 10767024}
3312
+ {"current_steps": 16475, "total_steps": 19080, "loss": 0.3605, "lr": 2.7878845280486453e-06, "epoch": 8.634696016771489, "percentage": 86.35, "elapsed_time": "1:04:51", "remaining_time": "0:10:15", "throughput": 2767.55, "total_tokens": 10770096}
3313
+ {"current_steps": 16480, "total_steps": 19080, "loss": 0.534, "lr": 2.777399289533164e-06, "epoch": 8.637316561844864, "percentage": 86.37, "elapsed_time": "1:04:52", "remaining_time": "0:10:14", "throughput": 2767.7, "total_tokens": 10774576}
3314
+ {"current_steps": 16485, "total_steps": 19080, "loss": 0.3577, "lr": 2.766932645874873e-06, "epoch": 8.63993710691824, "percentage": 86.4, "elapsed_time": "1:04:53", "remaining_time": "0:10:12", "throughput": 2767.72, "total_tokens": 10777296}
3315
+ {"current_steps": 16490, "total_steps": 19080, "loss": 0.4095, "lr": 2.756484605831777e-06, "epoch": 8.642557651991615, "percentage": 86.43, "elapsed_time": "1:04:54", "remaining_time": "0:10:11", "throughput": 2767.71, "total_tokens": 10779696}
3316
+ {"current_steps": 16495, "total_steps": 19080, "loss": 0.3984, "lr": 2.74605517814632e-06, "epoch": 8.64517819706499, "percentage": 86.45, "elapsed_time": "1:04:55", "remaining_time": "0:10:10", "throughput": 2767.78, "total_tokens": 10783184}
3317
+ {"current_steps": 16500, "total_steps": 19080, "loss": 0.6156, "lr": 2.7356443715453705e-06, "epoch": 8.647798742138365, "percentage": 86.48, "elapsed_time": "1:04:57", "remaining_time": "0:10:09", "throughput": 2767.85, "total_tokens": 10786512}
3318
+ {"current_steps": 16505, "total_steps": 19080, "loss": 0.424, "lr": 2.725252194740213e-06, "epoch": 8.65041928721174, "percentage": 86.5, "elapsed_time": "1:04:58", "remaining_time": "0:10:08", "throughput": 2767.94, "total_tokens": 10789872}
3319
+ {"current_steps": 16510, "total_steps": 19080, "loss": 0.4045, "lr": 2.714878656426553e-06, "epoch": 8.653039832285115, "percentage": 86.53, "elapsed_time": "1:04:59", "remaining_time": "0:10:06", "throughput": 2767.98, "total_tokens": 10792944}
3320
+ {"current_steps": 16515, "total_steps": 19080, "loss": 0.4804, "lr": 2.704523765284489e-06, "epoch": 8.65566037735849, "percentage": 86.56, "elapsed_time": "1:05:00", "remaining_time": "0:10:05", "throughput": 2768.06, "total_tokens": 10796624}
3321
+ {"current_steps": 16520, "total_steps": 19080, "loss": 0.4536, "lr": 2.6941875299785174e-06, "epoch": 8.658280922431866, "percentage": 86.58, "elapsed_time": "1:05:01", "remaining_time": "0:10:04", "throughput": 2768.12, "total_tokens": 10800144}
3322
+ {"current_steps": 16525, "total_steps": 19080, "loss": 0.4143, "lr": 2.683869959157534e-06, "epoch": 8.66090146750524, "percentage": 86.61, "elapsed_time": "1:05:02", "remaining_time": "0:10:03", "throughput": 2768.15, "total_tokens": 10803152}
3323
+ {"current_steps": 16530, "total_steps": 19080, "loss": 0.51, "lr": 2.673571061454813e-06, "epoch": 8.663522012578616, "percentage": 86.64, "elapsed_time": "1:05:03", "remaining_time": "0:10:02", "throughput": 2768.13, "total_tokens": 10805552}
3324
+ {"current_steps": 16535, "total_steps": 19080, "loss": 0.4571, "lr": 2.6632908454879898e-06, "epoch": 8.666142557651991, "percentage": 86.66, "elapsed_time": "1:05:04", "remaining_time": "0:10:00", "throughput": 2768.19, "total_tokens": 10808880}
3325
+ {"current_steps": 16540, "total_steps": 19080, "loss": 0.4384, "lr": 2.653029319859096e-06, "epoch": 8.668763102725366, "percentage": 86.69, "elapsed_time": "1:05:05", "remaining_time": "0:09:59", "throughput": 2768.23, "total_tokens": 10812240}
3326
+ {"current_steps": 16545, "total_steps": 19080, "loss": 0.4276, "lr": 2.642786493154492e-06, "epoch": 8.671383647798741, "percentage": 86.71, "elapsed_time": "1:05:06", "remaining_time": "0:09:58", "throughput": 2768.3, "total_tokens": 10815600}
3327
+ {"current_steps": 16550, "total_steps": 19080, "loss": 0.448, "lr": 2.6325623739449108e-06, "epoch": 8.674004192872118, "percentage": 86.74, "elapsed_time": "1:05:08", "remaining_time": "0:09:57", "throughput": 2768.38, "total_tokens": 10819120}
3328
+ {"current_steps": 16555, "total_steps": 19080, "loss": 0.3961, "lr": 2.6223569707854444e-06, "epoch": 8.676624737945493, "percentage": 86.77, "elapsed_time": "1:05:09", "remaining_time": "0:09:56", "throughput": 2768.39, "total_tokens": 10821744}
3329
+ {"current_steps": 16560, "total_steps": 19080, "loss": 0.4291, "lr": 2.612170292215482e-06, "epoch": 8.679245283018869, "percentage": 86.79, "elapsed_time": "1:05:09", "remaining_time": "0:09:54", "throughput": 2768.41, "total_tokens": 10824336}
3330
+ {"current_steps": 16565, "total_steps": 19080, "loss": 0.5761, "lr": 2.6020023467587917e-06, "epoch": 8.681865828092244, "percentage": 86.82, "elapsed_time": "1:05:10", "remaining_time": "0:09:53", "throughput": 2768.42, "total_tokens": 10826672}
3331
+ {"current_steps": 16570, "total_steps": 19080, "loss": 0.3945, "lr": 2.5918531429234368e-06, "epoch": 8.684486373165619, "percentage": 86.84, "elapsed_time": "1:05:11", "remaining_time": "0:09:52", "throughput": 2768.49, "total_tokens": 10830192}
3332
+ {"current_steps": 16575, "total_steps": 19080, "loss": 0.64, "lr": 2.5817226892018016e-06, "epoch": 8.687106918238994, "percentage": 86.87, "elapsed_time": "1:05:13", "remaining_time": "0:09:51", "throughput": 2768.58, "total_tokens": 10834096}
3333
+ {"current_steps": 16580, "total_steps": 19080, "loss": 0.4613, "lr": 2.571610994070603e-06, "epoch": 8.68972746331237, "percentage": 86.9, "elapsed_time": "1:05:14", "remaining_time": "0:09:50", "throughput": 2768.63, "total_tokens": 10837360}
3334
+ {"current_steps": 16585, "total_steps": 19080, "loss": 0.5536, "lr": 2.561518065990834e-06, "epoch": 8.692348008385745, "percentage": 86.92, "elapsed_time": "1:05:15", "remaining_time": "0:09:49", "throughput": 2768.74, "total_tokens": 10841168}
3335
+ {"current_steps": 16590, "total_steps": 19080, "loss": 0.3425, "lr": 2.5514439134077945e-06, "epoch": 8.69496855345912, "percentage": 86.95, "elapsed_time": "1:05:16", "remaining_time": "0:09:47", "throughput": 2768.84, "total_tokens": 10844784}
3336
+ {"current_steps": 16595, "total_steps": 19080, "loss": 0.4656, "lr": 2.541388544751089e-06, "epoch": 8.697589098532495, "percentage": 86.98, "elapsed_time": "1:05:17", "remaining_time": "0:09:46", "throughput": 2768.84, "total_tokens": 10847376}
3337
+ {"current_steps": 16600, "total_steps": 19080, "loss": 0.3985, "lr": 2.53135196843457e-06, "epoch": 8.70020964360587, "percentage": 87.0, "elapsed_time": "1:05:18", "remaining_time": "0:09:45", "throughput": 2768.86, "total_tokens": 10850000}
3338
+ {"current_steps": 16605, "total_steps": 19080, "loss": 0.374, "lr": 2.521334192856403e-06, "epoch": 8.702830188679245, "percentage": 87.03, "elapsed_time": "1:05:19", "remaining_time": "0:09:44", "throughput": 2768.88, "total_tokens": 10852528}
3339
+ {"current_steps": 16610, "total_steps": 19080, "loss": 0.436, "lr": 2.5113352263990005e-06, "epoch": 8.70545073375262, "percentage": 87.05, "elapsed_time": "1:05:20", "remaining_time": "0:09:42", "throughput": 2768.92, "total_tokens": 10855312}
3340
+ {"current_steps": 16615, "total_steps": 19080, "loss": 0.6068, "lr": 2.5013550774290322e-06, "epoch": 8.708071278825996, "percentage": 87.08, "elapsed_time": "1:05:21", "remaining_time": "0:09:41", "throughput": 2769.03, "total_tokens": 10859376}
3341
+ {"current_steps": 16620, "total_steps": 19080, "loss": 0.4995, "lr": 2.491393754297444e-06, "epoch": 8.71069182389937, "percentage": 87.11, "elapsed_time": "1:05:22", "remaining_time": "0:09:40", "throughput": 2769.08, "total_tokens": 10862224}
3342
+ {"current_steps": 16625, "total_steps": 19080, "loss": 0.6035, "lr": 2.48145126533941e-06, "epoch": 8.713312368972746, "percentage": 87.13, "elapsed_time": "1:05:23", "remaining_time": "0:09:39", "throughput": 2769.1, "total_tokens": 10865104}
3343
+ {"current_steps": 16630, "total_steps": 19080, "loss": 0.3984, "lr": 2.4715276188743476e-06, "epoch": 8.715932914046121, "percentage": 87.16, "elapsed_time": "1:05:24", "remaining_time": "0:09:38", "throughput": 2769.15, "total_tokens": 10867792}
3344
+ {"current_steps": 16635, "total_steps": 19080, "loss": 0.4929, "lr": 2.461622823205917e-06, "epoch": 8.718553459119496, "percentage": 87.19, "elapsed_time": "1:05:25", "remaining_time": "0:09:36", "throughput": 2769.18, "total_tokens": 10870768}
3345
+ {"current_steps": 16640, "total_steps": 19080, "loss": 0.3308, "lr": 2.451736886621997e-06, "epoch": 8.721174004192871, "percentage": 87.21, "elapsed_time": "1:05:27", "remaining_time": "0:09:35", "throughput": 2769.28, "total_tokens": 10875056}
3346
+ {"current_steps": 16645, "total_steps": 19080, "loss": 0.5206, "lr": 2.4418698173946872e-06, "epoch": 8.723794549266248, "percentage": 87.24, "elapsed_time": "1:05:28", "remaining_time": "0:09:34", "throughput": 2769.35, "total_tokens": 10878288}
3347
+ {"current_steps": 16650, "total_steps": 19080, "loss": 0.4969, "lr": 2.432021623780295e-06, "epoch": 8.726415094339622, "percentage": 87.26, "elapsed_time": "1:05:28", "remaining_time": "0:09:33", "throughput": 2769.37, "total_tokens": 10880720}
3348
+ {"current_steps": 16655, "total_steps": 19080, "loss": 0.2893, "lr": 2.4221923140193477e-06, "epoch": 8.729035639412999, "percentage": 87.29, "elapsed_time": "1:05:30", "remaining_time": "0:09:32", "throughput": 2769.45, "total_tokens": 10884528}
3349
+ {"current_steps": 16660, "total_steps": 19080, "loss": 0.5694, "lr": 2.41238189633656e-06, "epoch": 8.731656184486374, "percentage": 87.32, "elapsed_time": "1:05:31", "remaining_time": "0:09:31", "throughput": 2769.43, "total_tokens": 10886960}
3350
+ {"current_steps": 16665, "total_steps": 19080, "loss": 0.4746, "lr": 2.402590378940836e-06, "epoch": 8.734276729559749, "percentage": 87.34, "elapsed_time": "1:05:32", "remaining_time": "0:09:29", "throughput": 2769.46, "total_tokens": 10889904}
3351
+ {"current_steps": 16670, "total_steps": 19080, "loss": 0.564, "lr": 2.3928177700252798e-06, "epoch": 8.736897274633124, "percentage": 87.37, "elapsed_time": "1:05:33", "remaining_time": "0:09:28", "throughput": 2769.52, "total_tokens": 10893072}
3352
+ {"current_steps": 16675, "total_steps": 19080, "loss": 0.5009, "lr": 2.3830640777671583e-06, "epoch": 8.7395178197065, "percentage": 87.4, "elapsed_time": "1:05:34", "remaining_time": "0:09:27", "throughput": 2769.66, "total_tokens": 10897392}
3353
+ {"current_steps": 16680, "total_steps": 19080, "loss": 0.5572, "lr": 2.3733293103279153e-06, "epoch": 8.742138364779874, "percentage": 87.42, "elapsed_time": "1:05:35", "remaining_time": "0:09:26", "throughput": 2769.74, "total_tokens": 10901008}
3354
+ {"current_steps": 16685, "total_steps": 19080, "loss": 0.5293, "lr": 2.3636134758531604e-06, "epoch": 8.74475890985325, "percentage": 87.45, "elapsed_time": "1:05:37", "remaining_time": "0:09:25", "throughput": 2769.83, "total_tokens": 10904848}
3355
+ {"current_steps": 16690, "total_steps": 19080, "loss": 0.4706, "lr": 2.3539165824726565e-06, "epoch": 8.747379454926625, "percentage": 87.47, "elapsed_time": "1:05:38", "remaining_time": "0:09:23", "throughput": 2769.91, "total_tokens": 10908528}
3356
+ {"current_steps": 16695, "total_steps": 19080, "loss": 0.5686, "lr": 2.344238638300328e-06, "epoch": 8.75, "percentage": 87.5, "elapsed_time": "1:05:39", "remaining_time": "0:09:22", "throughput": 2769.97, "total_tokens": 10912080}
3357
+ {"current_steps": 16700, "total_steps": 19080, "loss": 0.4755, "lr": 2.334579651434235e-06, "epoch": 8.752620545073375, "percentage": 87.53, "elapsed_time": "1:05:40", "remaining_time": "0:09:21", "throughput": 2770.07, "total_tokens": 10916528}
3358
+ {"current_steps": 16705, "total_steps": 19080, "loss": 0.4396, "lr": 2.3249396299565683e-06, "epoch": 8.75524109014675, "percentage": 87.55, "elapsed_time": "1:05:42", "remaining_time": "0:09:20", "throughput": 2770.19, "total_tokens": 10920688}
3359
+ {"current_steps": 16710, "total_steps": 19080, "loss": 0.4445, "lr": 2.3153185819336705e-06, "epoch": 8.757861635220126, "percentage": 87.58, "elapsed_time": "1:05:43", "remaining_time": "0:09:19", "throughput": 2770.2, "total_tokens": 10923600}
3360
+ {"current_steps": 16715, "total_steps": 19080, "loss": 0.388, "lr": 2.3057165154159873e-06, "epoch": 8.7604821802935, "percentage": 87.6, "elapsed_time": "1:05:44", "remaining_time": "0:09:18", "throughput": 2770.24, "total_tokens": 10926544}
3361
+ {"current_steps": 16720, "total_steps": 19080, "loss": 0.3898, "lr": 2.296133438438086e-06, "epoch": 8.763102725366876, "percentage": 87.63, "elapsed_time": "1:05:45", "remaining_time": "0:09:16", "throughput": 2770.27, "total_tokens": 10929392}
3362
+ {"current_steps": 16725, "total_steps": 19080, "loss": 0.4272, "lr": 2.2865693590186616e-06, "epoch": 8.765723270440251, "percentage": 87.66, "elapsed_time": "1:05:46", "remaining_time": "0:09:15", "throughput": 2770.37, "total_tokens": 10933456}
3363
+ {"current_steps": 16730, "total_steps": 19080, "loss": 0.6048, "lr": 2.2770242851604813e-06, "epoch": 8.768343815513626, "percentage": 87.68, "elapsed_time": "1:05:47", "remaining_time": "0:09:14", "throughput": 2770.41, "total_tokens": 10936336}
3364
+ {"current_steps": 16735, "total_steps": 19080, "loss": 0.4917, "lr": 2.2674982248504395e-06, "epoch": 8.770964360587001, "percentage": 87.71, "elapsed_time": "1:05:48", "remaining_time": "0:09:13", "throughput": 2770.46, "total_tokens": 10939696}
3365
+ {"current_steps": 16740, "total_steps": 19080, "loss": 0.3743, "lr": 2.257991186059502e-06, "epoch": 8.773584905660378, "percentage": 87.74, "elapsed_time": "1:05:49", "remaining_time": "0:09:12", "throughput": 2770.48, "total_tokens": 10942192}
3366
+ {"current_steps": 16745, "total_steps": 19080, "loss": 0.2947, "lr": 2.248503176742725e-06, "epoch": 8.776205450733752, "percentage": 87.76, "elapsed_time": "1:05:50", "remaining_time": "0:09:10", "throughput": 2770.5, "total_tokens": 10944624}
3367
+ {"current_steps": 16750, "total_steps": 19080, "loss": 0.3981, "lr": 2.2390342048392467e-06, "epoch": 8.778825995807129, "percentage": 87.79, "elapsed_time": "1:05:51", "remaining_time": "0:09:09", "throughput": 2770.55, "total_tokens": 10947952}
3368
+ {"current_steps": 16755, "total_steps": 19080, "loss": 0.4294, "lr": 2.229584278272265e-06, "epoch": 8.781446540880504, "percentage": 87.81, "elapsed_time": "1:05:52", "remaining_time": "0:09:08", "throughput": 2770.61, "total_tokens": 10951440}
3369
+ {"current_steps": 16760, "total_steps": 19080, "loss": 0.3924, "lr": 2.2201534049490436e-06, "epoch": 8.784067085953879, "percentage": 87.84, "elapsed_time": "1:05:53", "remaining_time": "0:09:07", "throughput": 2770.66, "total_tokens": 10954224}
3370
+ {"current_steps": 16765, "total_steps": 19080, "loss": 0.4796, "lr": 2.2107415927609176e-06, "epoch": 8.786687631027254, "percentage": 87.87, "elapsed_time": "1:05:54", "remaining_time": "0:09:06", "throughput": 2770.71, "total_tokens": 10957392}
3371
+ {"current_steps": 16770, "total_steps": 19080, "loss": 0.5098, "lr": 2.2013488495832542e-06, "epoch": 8.78930817610063, "percentage": 87.89, "elapsed_time": "1:05:55", "remaining_time": "0:09:04", "throughput": 2770.83, "total_tokens": 10961136}
3372
+ {"current_steps": 16775, "total_steps": 19080, "loss": 0.4934, "lr": 2.1919751832754714e-06, "epoch": 8.791928721174004, "percentage": 87.92, "elapsed_time": "1:05:56", "remaining_time": "0:09:03", "throughput": 2770.88, "total_tokens": 10964272}
3373
+ {"current_steps": 16780, "total_steps": 19080, "loss": 0.3662, "lr": 2.182620601681029e-06, "epoch": 8.79454926624738, "percentage": 87.95, "elapsed_time": "1:05:57", "remaining_time": "0:09:02", "throughput": 2770.94, "total_tokens": 10967344}
3374
+ {"current_steps": 16785, "total_steps": 19080, "loss": 0.4092, "lr": 2.1732851126274047e-06, "epoch": 8.797169811320755, "percentage": 87.97, "elapsed_time": "1:05:59", "remaining_time": "0:09:01", "throughput": 2771.0, "total_tokens": 10970800}
3375
+ {"current_steps": 16790, "total_steps": 19080, "loss": 0.4761, "lr": 2.1639687239261214e-06, "epoch": 8.79979035639413, "percentage": 88.0, "elapsed_time": "1:06:00", "remaining_time": "0:09:00", "throughput": 2771.09, "total_tokens": 10974544}
3376
+ {"current_steps": 16795, "total_steps": 19080, "loss": 0.5178, "lr": 2.1546714433726993e-06, "epoch": 8.802410901467505, "percentage": 88.02, "elapsed_time": "1:06:01", "remaining_time": "0:08:58", "throughput": 2771.08, "total_tokens": 10976784}
3377
+ {"current_steps": 16800, "total_steps": 19080, "loss": 0.5319, "lr": 2.1453932787466767e-06, "epoch": 8.80503144654088, "percentage": 88.05, "elapsed_time": "1:06:02", "remaining_time": "0:08:57", "throughput": 2771.15, "total_tokens": 10980400}
3378
+ {"current_steps": 16805, "total_steps": 19080, "loss": 0.3435, "lr": 2.1361342378116072e-06, "epoch": 8.807651991614255, "percentage": 88.08, "elapsed_time": "1:06:04", "remaining_time": "0:08:56", "throughput": 2771.34, "total_tokens": 10986160}
3379
+ {"current_steps": 16810, "total_steps": 19080, "loss": 0.4931, "lr": 2.1268943283150294e-06, "epoch": 8.81027253668763, "percentage": 88.1, "elapsed_time": "1:06:05", "remaining_time": "0:08:55", "throughput": 2771.42, "total_tokens": 10989584}
3380
+ {"current_steps": 16815, "total_steps": 19080, "loss": 0.5497, "lr": 2.1176735579884753e-06, "epoch": 8.812893081761006, "percentage": 88.13, "elapsed_time": "1:06:06", "remaining_time": "0:08:54", "throughput": 2771.47, "total_tokens": 10992464}
3381
+ {"current_steps": 16820, "total_steps": 19080, "loss": 0.5601, "lr": 2.1084719345474597e-06, "epoch": 8.815513626834381, "percentage": 88.16, "elapsed_time": "1:06:07", "remaining_time": "0:08:53", "throughput": 2771.51, "total_tokens": 10995472}
3382
+ {"current_steps": 16825, "total_steps": 19080, "loss": 0.4406, "lr": 2.0992894656914895e-06, "epoch": 8.818134171907756, "percentage": 88.18, "elapsed_time": "1:06:08", "remaining_time": "0:08:51", "throughput": 2771.59, "total_tokens": 10999088}
3383
+ {"current_steps": 16830, "total_steps": 19080, "loss": 0.4738, "lr": 2.0901261591040333e-06, "epoch": 8.820754716981131, "percentage": 88.21, "elapsed_time": "1:06:09", "remaining_time": "0:08:50", "throughput": 2771.64, "total_tokens": 11002000}
3384
+ {"current_steps": 16835, "total_steps": 19080, "loss": 0.6142, "lr": 2.0809820224525213e-06, "epoch": 8.823375262054507, "percentage": 88.23, "elapsed_time": "1:06:10", "remaining_time": "0:08:49", "throughput": 2771.68, "total_tokens": 11005360}
3385
+ {"current_steps": 16840, "total_steps": 19080, "loss": 0.3884, "lr": 2.0718570633883576e-06, "epoch": 8.825995807127882, "percentage": 88.26, "elapsed_time": "1:06:11", "remaining_time": "0:08:48", "throughput": 2771.72, "total_tokens": 11008272}
3386
+ {"current_steps": 16845, "total_steps": 19080, "loss": 0.4421, "lr": 2.0627512895468883e-06, "epoch": 8.828616352201259, "percentage": 88.29, "elapsed_time": "1:06:12", "remaining_time": "0:08:47", "throughput": 2771.8, "total_tokens": 11011760}
3387
+ {"current_steps": 16850, "total_steps": 19080, "loss": 0.5038, "lr": 2.0536647085474037e-06, "epoch": 8.831236897274634, "percentage": 88.31, "elapsed_time": "1:06:13", "remaining_time": "0:08:45", "throughput": 2771.83, "total_tokens": 11014736}
3388
+ {"current_steps": 16855, "total_steps": 19080, "loss": 0.4036, "lr": 2.044597327993153e-06, "epoch": 8.833857442348009, "percentage": 88.34, "elapsed_time": "1:06:14", "remaining_time": "0:08:44", "throughput": 2771.9, "total_tokens": 11018128}
3389
+ {"current_steps": 16860, "total_steps": 19080, "loss": 0.404, "lr": 2.035549155471289e-06, "epoch": 8.836477987421384, "percentage": 88.36, "elapsed_time": "1:06:16", "remaining_time": "0:08:43", "throughput": 2772.01, "total_tokens": 11022032}
3390
+ {"current_steps": 16865, "total_steps": 19080, "loss": 0.4399, "lr": 2.0265201985529226e-06, "epoch": 8.83909853249476, "percentage": 88.39, "elapsed_time": "1:06:17", "remaining_time": "0:08:42", "throughput": 2772.03, "total_tokens": 11024944}
3391
+ {"current_steps": 16870, "total_steps": 19080, "loss": 0.4264, "lr": 2.0175104647930655e-06, "epoch": 8.841719077568134, "percentage": 88.42, "elapsed_time": "1:06:18", "remaining_time": "0:08:41", "throughput": 2772.07, "total_tokens": 11028272}
3392
+ {"current_steps": 16875, "total_steps": 19080, "loss": 0.4812, "lr": 2.008519961730651e-06, "epoch": 8.84433962264151, "percentage": 88.44, "elapsed_time": "1:06:19", "remaining_time": "0:08:39", "throughput": 2772.11, "total_tokens": 11031088}
3393
+ {"current_steps": 16880, "total_steps": 19080, "loss": 0.5055, "lr": 1.9995486968885284e-06, "epoch": 8.846960167714885, "percentage": 88.47, "elapsed_time": "1:06:20", "remaining_time": "0:08:38", "throughput": 2772.1, "total_tokens": 11033456}
3394
+ {"current_steps": 16885, "total_steps": 19080, "loss": 0.4892, "lr": 1.990596677773435e-06, "epoch": 8.84958071278826, "percentage": 88.5, "elapsed_time": "1:06:21", "remaining_time": "0:08:37", "throughput": 2772.18, "total_tokens": 11036976}
3395
+ {"current_steps": 16890, "total_steps": 19080, "loss": 0.4678, "lr": 1.981663911876014e-06, "epoch": 8.852201257861635, "percentage": 88.52, "elapsed_time": "1:06:22", "remaining_time": "0:08:36", "throughput": 2772.2, "total_tokens": 11039472}
3396
+ {"current_steps": 16895, "total_steps": 19080, "loss": 0.4382, "lr": 1.972750406670801e-06, "epoch": 8.85482180293501, "percentage": 88.55, "elapsed_time": "1:06:23", "remaining_time": "0:08:35", "throughput": 2772.23, "total_tokens": 11042064}
3397
+ {"current_steps": 16900, "total_steps": 19080, "loss": 0.5058, "lr": 1.9638561696161962e-06, "epoch": 8.857442348008385, "percentage": 88.57, "elapsed_time": "1:06:24", "remaining_time": "0:08:33", "throughput": 2772.25, "total_tokens": 11045232}
3398
+ {"current_steps": 16905, "total_steps": 19080, "loss": 0.4216, "lr": 1.954981208154502e-06, "epoch": 8.86006289308176, "percentage": 88.6, "elapsed_time": "1:06:25", "remaining_time": "0:08:32", "throughput": 2772.33, "total_tokens": 11048784}
3399
+ {"current_steps": 16910, "total_steps": 19080, "loss": 0.5036, "lr": 1.9461255297118868e-06, "epoch": 8.862683438155136, "percentage": 88.63, "elapsed_time": "1:06:26", "remaining_time": "0:08:31", "throughput": 2772.41, "total_tokens": 11052528}
3400
+ {"current_steps": 16915, "total_steps": 19080, "loss": 0.7135, "lr": 1.937289141698359e-06, "epoch": 8.865303983228511, "percentage": 88.65, "elapsed_time": "1:06:27", "remaining_time": "0:08:30", "throughput": 2772.46, "total_tokens": 11055824}
3401
+ {"current_steps": 16920, "total_steps": 19080, "loss": 0.3224, "lr": 1.928472051507821e-06, "epoch": 8.867924528301886, "percentage": 88.68, "elapsed_time": "1:06:28", "remaining_time": "0:08:29", "throughput": 2772.54, "total_tokens": 11059504}
3402
+ {"current_steps": 16925, "total_steps": 19080, "loss": 0.4476, "lr": 1.919674266518004e-06, "epoch": 8.870545073375261, "percentage": 88.71, "elapsed_time": "1:06:29", "remaining_time": "0:08:28", "throughput": 2772.57, "total_tokens": 11062544}
3403
+ {"current_steps": 16930, "total_steps": 19080, "loss": 0.4293, "lr": 1.910895794090492e-06, "epoch": 8.873165618448636, "percentage": 88.73, "elapsed_time": "1:06:31", "remaining_time": "0:08:26", "throughput": 2772.59, "total_tokens": 11065584}
3404
+ {"current_steps": 16935, "total_steps": 19080, "loss": 0.383, "lr": 1.902136641570712e-06, "epoch": 8.875786163522012, "percentage": 88.76, "elapsed_time": "1:06:31", "remaining_time": "0:08:25", "throughput": 2772.63, "total_tokens": 11068336}
3405
+ {"current_steps": 16940, "total_steps": 19080, "loss": 0.4949, "lr": 1.8933968162879235e-06, "epoch": 8.878406708595389, "percentage": 88.78, "elapsed_time": "1:06:32", "remaining_time": "0:08:24", "throughput": 2772.67, "total_tokens": 11071184}
3406
+ {"current_steps": 16945, "total_steps": 19080, "loss": 0.2915, "lr": 1.8846763255552097e-06, "epoch": 8.881027253668764, "percentage": 88.81, "elapsed_time": "1:06:34", "remaining_time": "0:08:23", "throughput": 2772.73, "total_tokens": 11074320}
3407
+ {"current_steps": 16950, "total_steps": 19080, "loss": 0.4246, "lr": 1.8759751766694811e-06, "epoch": 8.883647798742139, "percentage": 88.84, "elapsed_time": "1:06:35", "remaining_time": "0:08:22", "throughput": 2772.76, "total_tokens": 11077168}
3408
+ {"current_steps": 16955, "total_steps": 19080, "loss": 0.4532, "lr": 1.8672933769114636e-06, "epoch": 8.886268343815514, "percentage": 88.86, "elapsed_time": "1:06:35", "remaining_time": "0:08:20", "throughput": 2772.79, "total_tokens": 11080080}
3409
+ {"current_steps": 16960, "total_steps": 19080, "loss": 0.3616, "lr": 1.8586309335456908e-06, "epoch": 8.88888888888889, "percentage": 88.89, "elapsed_time": "1:06:37", "remaining_time": "0:08:19", "throughput": 2772.86, "total_tokens": 11083408}
3410
+ {"current_steps": 16965, "total_steps": 19080, "loss": 0.5668, "lr": 1.8499878538204951e-06, "epoch": 8.891509433962264, "percentage": 88.92, "elapsed_time": "1:06:38", "remaining_time": "0:08:18", "throughput": 2772.94, "total_tokens": 11087184}
3411
+ {"current_steps": 16970, "total_steps": 19080, "loss": 0.3946, "lr": 1.8413641449680081e-06, "epoch": 8.89412997903564, "percentage": 88.94, "elapsed_time": "1:06:39", "remaining_time": "0:08:17", "throughput": 2773.03, "total_tokens": 11090864}
3412
+ {"current_steps": 16975, "total_steps": 19080, "loss": 0.4087, "lr": 1.8327598142041658e-06, "epoch": 8.896750524109015, "percentage": 88.97, "elapsed_time": "1:06:40", "remaining_time": "0:08:16", "throughput": 2773.09, "total_tokens": 11094288}
3413
+ {"current_steps": 16980, "total_steps": 19080, "loss": 0.3015, "lr": 1.824174868728673e-06, "epoch": 8.89937106918239, "percentage": 88.99, "elapsed_time": "1:06:41", "remaining_time": "0:08:14", "throughput": 2773.08, "total_tokens": 11096656}
3414
+ {"current_steps": 16985, "total_steps": 19080, "loss": 0.4374, "lr": 1.815609315725017e-06, "epoch": 8.901991614255765, "percentage": 89.02, "elapsed_time": "1:06:42", "remaining_time": "0:08:13", "throughput": 2773.15, "total_tokens": 11100144}
3415
+ {"current_steps": 16990, "total_steps": 19080, "loss": 0.404, "lr": 1.80706316236047e-06, "epoch": 8.90461215932914, "percentage": 89.05, "elapsed_time": "1:06:43", "remaining_time": "0:08:12", "throughput": 2773.21, "total_tokens": 11103440}
3416
+ {"current_steps": 16995, "total_steps": 19080, "loss": 0.4197, "lr": 1.7985364157860562e-06, "epoch": 8.907232704402515, "percentage": 89.07, "elapsed_time": "1:06:45", "remaining_time": "0:08:11", "throughput": 2773.27, "total_tokens": 11107056}
3417
+ {"current_steps": 17000, "total_steps": 19080, "loss": 0.4313, "lr": 1.7900290831365713e-06, "epoch": 8.90985324947589, "percentage": 89.1, "elapsed_time": "1:06:46", "remaining_time": "0:08:10", "throughput": 2773.34, "total_tokens": 11110640}
3418
+ {"current_steps": 17005, "total_steps": 19080, "loss": 0.3271, "lr": 1.781541171530554e-06, "epoch": 8.912473794549266, "percentage": 89.12, "elapsed_time": "1:06:48", "remaining_time": "0:08:09", "throughput": 2773.53, "total_tokens": 11117008}
3419
+ {"current_steps": 17010, "total_steps": 19080, "loss": 0.4094, "lr": 1.7730726880703125e-06, "epoch": 8.915094339622641, "percentage": 89.15, "elapsed_time": "1:06:49", "remaining_time": "0:08:07", "throughput": 2773.59, "total_tokens": 11120176}
3420
+ {"current_steps": 17015, "total_steps": 19080, "loss": 0.4822, "lr": 1.7646236398418835e-06, "epoch": 8.917714884696016, "percentage": 89.18, "elapsed_time": "1:06:50", "remaining_time": "0:08:06", "throughput": 2773.63, "total_tokens": 11123504}
3421
+ {"current_steps": 17020, "total_steps": 19080, "loss": 0.5016, "lr": 1.7561940339150373e-06, "epoch": 8.920335429769391, "percentage": 89.2, "elapsed_time": "1:06:51", "remaining_time": "0:08:05", "throughput": 2773.66, "total_tokens": 11126000}
3422
+ {"current_steps": 17025, "total_steps": 19080, "loss": 0.4286, "lr": 1.7477838773432926e-06, "epoch": 8.922955974842766, "percentage": 89.23, "elapsed_time": "1:06:52", "remaining_time": "0:08:04", "throughput": 2773.73, "total_tokens": 11129584}
3423
+ {"current_steps": 17030, "total_steps": 19080, "loss": 0.4846, "lr": 1.7393931771638839e-06, "epoch": 8.925576519916142, "percentage": 89.26, "elapsed_time": "1:06:53", "remaining_time": "0:08:03", "throughput": 2773.79, "total_tokens": 11132240}
3424
+ {"current_steps": 17035, "total_steps": 19080, "loss": 0.4928, "lr": 1.7310219403977563e-06, "epoch": 8.928197064989519, "percentage": 89.28, "elapsed_time": "1:06:54", "remaining_time": "0:08:01", "throughput": 2773.84, "total_tokens": 11135120}
3425
+ {"current_steps": 17040, "total_steps": 19080, "loss": 0.3383, "lr": 1.7226701740495926e-06, "epoch": 8.930817610062894, "percentage": 89.31, "elapsed_time": "1:06:55", "remaining_time": "0:08:00", "throughput": 2773.86, "total_tokens": 11137968}
3426
+ {"current_steps": 17045, "total_steps": 19080, "loss": 0.3672, "lr": 1.714337885107753e-06, "epoch": 8.933438155136269, "percentage": 89.33, "elapsed_time": "1:06:56", "remaining_time": "0:07:59", "throughput": 2773.85, "total_tokens": 11140368}
3427
+ {"current_steps": 17050, "total_steps": 19080, "loss": 0.5391, "lr": 1.7060250805443296e-06, "epoch": 8.936058700209644, "percentage": 89.36, "elapsed_time": "1:06:57", "remaining_time": "0:07:58", "throughput": 2774.04, "total_tokens": 11145168}
3428
+ {"current_steps": 17055, "total_steps": 19080, "loss": 0.4928, "lr": 1.6977317673150916e-06, "epoch": 8.93867924528302, "percentage": 89.39, "elapsed_time": "1:06:58", "remaining_time": "0:07:57", "throughput": 2774.14, "total_tokens": 11149008}
3429
+ {"current_steps": 17060, "total_steps": 19080, "loss": 0.4368, "lr": 1.6894579523595022e-06, "epoch": 8.941299790356394, "percentage": 89.41, "elapsed_time": "1:07:01", "remaining_time": "0:07:56", "throughput": 2774.37, "total_tokens": 11156336}
3430
+ {"current_steps": 17065, "total_steps": 19080, "loss": 0.5557, "lr": 1.6812036426007176e-06, "epoch": 8.94392033542977, "percentage": 89.44, "elapsed_time": "1:07:02", "remaining_time": "0:07:54", "throughput": 2774.4, "total_tokens": 11159152}
3431
+ {"current_steps": 17070, "total_steps": 19080, "loss": 0.4033, "lr": 1.6729688449455689e-06, "epoch": 8.946540880503145, "percentage": 89.47, "elapsed_time": "1:07:03", "remaining_time": "0:07:53", "throughput": 2774.43, "total_tokens": 11162096}
3432
+ {"current_steps": 17075, "total_steps": 19080, "loss": 0.4524, "lr": 1.6647535662845466e-06, "epoch": 8.94916142557652, "percentage": 89.49, "elapsed_time": "1:07:04", "remaining_time": "0:07:52", "throughput": 2774.49, "total_tokens": 11165200}
3433
+ {"current_steps": 17080, "total_steps": 19080, "loss": 0.5809, "lr": 1.656557813491838e-06, "epoch": 8.951781970649895, "percentage": 89.52, "elapsed_time": "1:07:05", "remaining_time": "0:07:51", "throughput": 2774.53, "total_tokens": 11168368}
3434
+ {"current_steps": 17085, "total_steps": 19080, "loss": 0.5309, "lr": 1.6483815934252578e-06, "epoch": 8.95440251572327, "percentage": 89.54, "elapsed_time": "1:07:06", "remaining_time": "0:07:50", "throughput": 2774.62, "total_tokens": 11172048}
3435
+ {"current_steps": 17090, "total_steps": 19080, "loss": 0.4569, "lr": 1.6402249129263025e-06, "epoch": 8.957023060796645, "percentage": 89.57, "elapsed_time": "1:07:07", "remaining_time": "0:07:48", "throughput": 2774.7, "total_tokens": 11175600}
3436
+ {"current_steps": 17095, "total_steps": 19080, "loss": 0.4263, "lr": 1.6320877788201127e-06, "epoch": 8.95964360587002, "percentage": 89.6, "elapsed_time": "1:07:08", "remaining_time": "0:07:47", "throughput": 2774.73, "total_tokens": 11178576}
3437
+ {"current_steps": 17100, "total_steps": 19080, "loss": 0.5236, "lr": 1.6239701979154614e-06, "epoch": 8.962264150943396, "percentage": 89.62, "elapsed_time": "1:07:09", "remaining_time": "0:07:46", "throughput": 2774.72, "total_tokens": 11181168}
3438
+ {"current_steps": 17105, "total_steps": 19080, "loss": 0.4054, "lr": 1.6158721770047762e-06, "epoch": 8.964884696016771, "percentage": 89.65, "elapsed_time": "1:07:10", "remaining_time": "0:07:45", "throughput": 2774.77, "total_tokens": 11184400}
3439
+ {"current_steps": 17110, "total_steps": 19080, "loss": 0.5029, "lr": 1.6077937228641093e-06, "epoch": 8.967505241090146, "percentage": 89.68, "elapsed_time": "1:07:11", "remaining_time": "0:07:44", "throughput": 2774.81, "total_tokens": 11187536}
3440
+ {"current_steps": 17115, "total_steps": 19080, "loss": 0.4282, "lr": 1.5997348422531395e-06, "epoch": 8.970125786163521, "percentage": 89.7, "elapsed_time": "1:07:13", "remaining_time": "0:07:43", "throughput": 2774.88, "total_tokens": 11191568}
3441
+ {"current_steps": 17120, "total_steps": 19080, "loss": 0.3893, "lr": 1.5916955419151725e-06, "epoch": 8.972746331236896, "percentage": 89.73, "elapsed_time": "1:07:14", "remaining_time": "0:07:41", "throughput": 2774.93, "total_tokens": 11195024}
3442
+ {"current_steps": 17125, "total_steps": 19080, "loss": 0.5058, "lr": 1.5836758285771303e-06, "epoch": 8.975366876310272, "percentage": 89.75, "elapsed_time": "1:07:15", "remaining_time": "0:07:40", "throughput": 2774.97, "total_tokens": 11198480}
3443
+ {"current_steps": 17130, "total_steps": 19080, "loss": 0.4892, "lr": 1.5756757089495366e-06, "epoch": 8.977987421383649, "percentage": 89.78, "elapsed_time": "1:07:16", "remaining_time": "0:07:39", "throughput": 2775.04, "total_tokens": 11201712}
3444
+ {"current_steps": 17135, "total_steps": 19080, "loss": 0.4025, "lr": 1.5676951897265313e-06, "epoch": 8.980607966457024, "percentage": 89.81, "elapsed_time": "1:07:17", "remaining_time": "0:07:38", "throughput": 2775.1, "total_tokens": 11204720}
3445
+ {"current_steps": 17140, "total_steps": 19080, "loss": 0.4427, "lr": 1.5597342775858476e-06, "epoch": 8.983228511530399, "percentage": 89.83, "elapsed_time": "1:07:18", "remaining_time": "0:07:37", "throughput": 2775.13, "total_tokens": 11207440}
3446
+ {"current_steps": 17145, "total_steps": 19080, "loss": 0.443, "lr": 1.5517929791888125e-06, "epoch": 8.985849056603774, "percentage": 89.86, "elapsed_time": "1:07:19", "remaining_time": "0:07:35", "throughput": 2775.18, "total_tokens": 11210384}
3447
+ {"current_steps": 17150, "total_steps": 19080, "loss": 0.4532, "lr": 1.5438713011803385e-06, "epoch": 8.98846960167715, "percentage": 89.88, "elapsed_time": "1:07:20", "remaining_time": "0:07:34", "throughput": 2775.22, "total_tokens": 11213392}
3448
+ {"current_steps": 17155, "total_steps": 19080, "loss": 0.5348, "lr": 1.535969250188926e-06, "epoch": 8.991090146750524, "percentage": 89.91, "elapsed_time": "1:07:21", "remaining_time": "0:07:33", "throughput": 2775.27, "total_tokens": 11216016}
3449
+ {"current_steps": 17160, "total_steps": 19080, "loss": 0.5285, "lr": 1.5280868328266528e-06, "epoch": 8.9937106918239, "percentage": 89.94, "elapsed_time": "1:07:22", "remaining_time": "0:07:32", "throughput": 2775.24, "total_tokens": 11218160}
3450
+ {"current_steps": 17165, "total_steps": 19080, "loss": 0.7013, "lr": 1.520224055689165e-06, "epoch": 8.996331236897275, "percentage": 89.96, "elapsed_time": "1:07:23", "remaining_time": "0:07:31", "throughput": 2775.31, "total_tokens": 11222000}
3451
+ {"current_steps": 17170, "total_steps": 19080, "loss": 0.4824, "lr": 1.5123809253556692e-06, "epoch": 8.99895178197065, "percentage": 89.99, "elapsed_time": "1:07:24", "remaining_time": "0:07:29", "throughput": 2775.35, "total_tokens": 11224816}
3452
+ {"current_steps": 17172, "total_steps": 19080, "eval_loss": 0.4832555055618286, "epoch": 9.0, "percentage": 90.0, "elapsed_time": "1:07:39", "remaining_time": "0:07:31", "throughput": 2765.27, "total_tokens": 11225416}
3453
+ {"current_steps": 17175, "total_steps": 19080, "loss": 0.5808, "lr": 1.5045574483889463e-06, "epoch": 9.001572327044025, "percentage": 90.02, "elapsed_time": "1:07:40", "remaining_time": "0:07:30", "throughput": 2764.65, "total_tokens": 11227112}
3454
+ {"current_steps": 17180, "total_steps": 19080, "loss": 0.4166, "lr": 1.4967536313353237e-06, "epoch": 9.0041928721174, "percentage": 90.04, "elapsed_time": "1:07:41", "remaining_time": "0:07:29", "throughput": 2764.65, "total_tokens": 11229544}