rbelanec commited on
Commit
2435a62
·
verified ·
1 Parent(s): 43d36db

Training in progress, step 38160

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +380 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff1d68a1826f35377223a6cd6cad40ef68d92fe5f7c5fad78e594621bfc467a5
3
  size 1638528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b13529cef821fd01e7696b55ffbcc6a7ca313bb6d1473e97ec144523e1188d77
3
  size 1638528
trainer_log.jsonl CHANGED
@@ -7271,3 +7271,383 @@
7271
  {"current_steps": 36260, "total_steps": 38160, "loss": 0.4126, "lr": 7.540629246103825e-06, "epoch": 19.0041928721174, "percentage": 95.02, "elapsed_time": "1:32:56", "remaining_time": "0:04:52", "throughput": 4240.82, "total_tokens": 23649760}
7272
  {"current_steps": 36265, "total_steps": 38160, "loss": 0.3458, "lr": 7.501114116613861e-06, "epoch": 19.006813417190777, "percentage": 95.03, "elapsed_time": "1:32:57", "remaining_time": "0:04:51", "throughput": 4240.82, "total_tokens": 23652672}
7273
  {"current_steps": 36270, "total_steps": 38160, "loss": 0.4088, "lr": 7.461702012272087e-06, "epoch": 19.00943396226415, "percentage": 95.05, "elapsed_time": "1:32:58", "remaining_time": "0:04:50", "throughput": 4240.83, "total_tokens": 23655584}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7271
  {"current_steps": 36260, "total_steps": 38160, "loss": 0.4126, "lr": 7.540629246103825e-06, "epoch": 19.0041928721174, "percentage": 95.02, "elapsed_time": "1:32:56", "remaining_time": "0:04:52", "throughput": 4240.82, "total_tokens": 23649760}
7272
  {"current_steps": 36265, "total_steps": 38160, "loss": 0.3458, "lr": 7.501114116613861e-06, "epoch": 19.006813417190777, "percentage": 95.03, "elapsed_time": "1:32:57", "remaining_time": "0:04:51", "throughput": 4240.82, "total_tokens": 23652672}
7273
  {"current_steps": 36270, "total_steps": 38160, "loss": 0.4088, "lr": 7.461702012272087e-06, "epoch": 19.00943396226415, "percentage": 95.05, "elapsed_time": "1:32:58", "remaining_time": "0:04:50", "throughput": 4240.83, "total_tokens": 23655584}
7274
+ {"current_steps": 36275, "total_steps": 38160, "loss": 0.4572, "lr": 7.422392941323075e-06, "epoch": 19.012054507337528, "percentage": 95.06, "elapsed_time": "1:32:58", "remaining_time": "0:04:49", "throughput": 4240.81, "total_tokens": 23658496}
7275
+ {"current_steps": 36280, "total_steps": 38160, "loss": 0.3665, "lr": 7.383186911989858e-06, "epoch": 19.0146750524109, "percentage": 95.07, "elapsed_time": "1:32:59", "remaining_time": "0:04:49", "throughput": 4240.77, "total_tokens": 23660928}
7276
+ {"current_steps": 36285, "total_steps": 38160, "loss": 0.6045, "lr": 7.344083932473822e-06, "epoch": 19.017295597484278, "percentage": 95.09, "elapsed_time": "1:33:00", "remaining_time": "0:04:48", "throughput": 4240.81, "total_tokens": 23664448}
7277
+ {"current_steps": 36290, "total_steps": 38160, "loss": 0.5478, "lr": 7.305084010954976e-06, "epoch": 19.01991614255765, "percentage": 95.1, "elapsed_time": "1:33:00", "remaining_time": "0:04:47", "throughput": 4240.88, "total_tokens": 23668128}
7278
+ {"current_steps": 36295, "total_steps": 38160, "loss": 0.4284, "lr": 7.26618715559152e-06, "epoch": 19.02253668763103, "percentage": 95.11, "elapsed_time": "1:33:01", "remaining_time": "0:04:46", "throughput": 4240.97, "total_tokens": 23672128}
7279
+ {"current_steps": 36300, "total_steps": 38160, "loss": 0.3928, "lr": 7.227393374520386e-06, "epoch": 19.0251572327044, "percentage": 95.13, "elapsed_time": "1:33:02", "remaining_time": "0:04:46", "throughput": 4241.01, "total_tokens": 23675392}
7280
+ {"current_steps": 36305, "total_steps": 38160, "loss": 0.471, "lr": 7.18870267585664e-06, "epoch": 19.02777777777778, "percentage": 95.14, "elapsed_time": "1:33:03", "remaining_time": "0:04:45", "throughput": 4241.08, "total_tokens": 23679136}
7281
+ {"current_steps": 36310, "total_steps": 38160, "loss": 0.4341, "lr": 7.150115067694085e-06, "epoch": 19.030398322851152, "percentage": 95.15, "elapsed_time": "1:33:03", "remaining_time": "0:04:44", "throughput": 4241.07, "total_tokens": 23681920}
7282
+ {"current_steps": 36315, "total_steps": 38160, "loss": 0.3693, "lr": 7.111630558104653e-06, "epoch": 19.03301886792453, "percentage": 95.17, "elapsed_time": "1:33:04", "remaining_time": "0:04:43", "throughput": 4241.16, "total_tokens": 23685824}
7283
+ {"current_steps": 36320, "total_steps": 38160, "loss": 0.4818, "lr": 7.073249155138961e-06, "epoch": 19.035639412997902, "percentage": 95.18, "elapsed_time": "1:33:05", "remaining_time": "0:04:42", "throughput": 4241.22, "total_tokens": 23689344}
7284
+ {"current_steps": 36325, "total_steps": 38160, "loss": 0.3727, "lr": 7.0349708668259736e-06, "epoch": 19.03825995807128, "percentage": 95.19, "elapsed_time": "1:33:06", "remaining_time": "0:04:42", "throughput": 4241.24, "total_tokens": 23692384}
7285
+ {"current_steps": 36330, "total_steps": 38160, "loss": 0.3992, "lr": 6.996795701173009e-06, "epoch": 19.040880503144653, "percentage": 95.2, "elapsed_time": "1:33:06", "remaining_time": "0:04:41", "throughput": 4241.3, "total_tokens": 23695936}
7286
+ {"current_steps": 36335, "total_steps": 38160, "loss": 0.4489, "lr": 6.958723666165901e-06, "epoch": 19.04350104821803, "percentage": 95.22, "elapsed_time": "1:33:07", "remaining_time": "0:04:40", "throughput": 4241.3, "total_tokens": 23698848}
7287
+ {"current_steps": 36340, "total_steps": 38160, "loss": 0.3901, "lr": 6.9207547697689446e-06, "epoch": 19.046121593291403, "percentage": 95.23, "elapsed_time": "1:33:08", "remaining_time": "0:04:39", "throughput": 4241.36, "total_tokens": 23702464}
7288
+ {"current_steps": 36345, "total_steps": 38160, "loss": 0.3496, "lr": 6.882889019924676e-06, "epoch": 19.04874213836478, "percentage": 95.24, "elapsed_time": "1:33:09", "remaining_time": "0:04:39", "throughput": 4241.36, "total_tokens": 23705344}
7289
+ {"current_steps": 36350, "total_steps": 38160, "loss": 0.4499, "lr": 6.84512642455426e-06, "epoch": 19.051362683438157, "percentage": 95.26, "elapsed_time": "1:33:09", "remaining_time": "0:04:38", "throughput": 4241.42, "total_tokens": 23708992}
7290
+ {"current_steps": 36355, "total_steps": 38160, "loss": 0.3377, "lr": 6.8074669915572095e-06, "epoch": 19.05398322851153, "percentage": 95.27, "elapsed_time": "1:33:10", "remaining_time": "0:04:37", "throughput": 4241.43, "total_tokens": 23711808}
7291
+ {"current_steps": 36360, "total_steps": 38160, "loss": 0.5293, "lr": 6.769910728811391e-06, "epoch": 19.056603773584907, "percentage": 95.28, "elapsed_time": "1:33:11", "remaining_time": "0:04:36", "throughput": 4241.44, "total_tokens": 23714720}
7292
+ {"current_steps": 36365, "total_steps": 38160, "loss": 0.5391, "lr": 6.73245764417324e-06, "epoch": 19.05922431865828, "percentage": 95.3, "elapsed_time": "1:33:11", "remaining_time": "0:04:36", "throughput": 4241.47, "total_tokens": 23717984}
7293
+ {"current_steps": 36370, "total_steps": 38160, "loss": 0.437, "lr": 6.695107745477435e-06, "epoch": 19.061844863731658, "percentage": 95.31, "elapsed_time": "1:33:12", "remaining_time": "0:04:35", "throughput": 4241.49, "total_tokens": 23721184}
7294
+ {"current_steps": 36375, "total_steps": 38160, "loss": 0.4458, "lr": 6.657861040537117e-06, "epoch": 19.06446540880503, "percentage": 95.32, "elapsed_time": "1:33:13", "remaining_time": "0:04:34", "throughput": 4241.51, "total_tokens": 23724384}
7295
+ {"current_steps": 36380, "total_steps": 38160, "loss": 0.4599, "lr": 6.620717537143994e-06, "epoch": 19.067085953878408, "percentage": 95.34, "elapsed_time": "1:33:14", "remaining_time": "0:04:33", "throughput": 4241.54, "total_tokens": 23727680}
7296
+ {"current_steps": 36385, "total_steps": 38160, "loss": 0.5164, "lr": 6.583677243067965e-06, "epoch": 19.06970649895178, "percentage": 95.35, "elapsed_time": "1:33:14", "remaining_time": "0:04:32", "throughput": 4241.54, "total_tokens": 23730464}
7297
+ {"current_steps": 36390, "total_steps": 38160, "loss": 0.3298, "lr": 6.546740166057441e-06, "epoch": 19.072327044025158, "percentage": 95.36, "elapsed_time": "1:33:15", "remaining_time": "0:04:32", "throughput": 4241.58, "total_tokens": 23733888}
7298
+ {"current_steps": 36395, "total_steps": 38160, "loss": 0.4311, "lr": 6.5099063138392975e-06, "epoch": 19.07494758909853, "percentage": 95.37, "elapsed_time": "1:33:16", "remaining_time": "0:04:31", "throughput": 4241.58, "total_tokens": 23736736}
7299
+ {"current_steps": 36400, "total_steps": 38160, "loss": 0.4452, "lr": 6.473175694118705e-06, "epoch": 19.07756813417191, "percentage": 95.39, "elapsed_time": "1:33:16", "remaining_time": "0:04:30", "throughput": 4241.6, "total_tokens": 23739872}
7300
+ {"current_steps": 36405, "total_steps": 38160, "loss": 0.3497, "lr": 6.436548314579349e-06, "epoch": 19.080188679245282, "percentage": 95.4, "elapsed_time": "1:33:17", "remaining_time": "0:04:29", "throughput": 4241.58, "total_tokens": 23742592}
7301
+ {"current_steps": 36410, "total_steps": 38160, "loss": 0.5368, "lr": 6.400024182883158e-06, "epoch": 19.08280922431866, "percentage": 95.41, "elapsed_time": "1:33:18", "remaining_time": "0:04:29", "throughput": 4241.73, "total_tokens": 23747296}
7302
+ {"current_steps": 36415, "total_steps": 38160, "loss": 0.4247, "lr": 6.363603306670629e-06, "epoch": 19.085429769392032, "percentage": 95.43, "elapsed_time": "1:33:19", "remaining_time": "0:04:28", "throughput": 4241.79, "total_tokens": 23751040}
7303
+ {"current_steps": 36420, "total_steps": 38160, "loss": 0.4725, "lr": 6.327285693560614e-06, "epoch": 19.08805031446541, "percentage": 95.44, "elapsed_time": "1:33:20", "remaining_time": "0:04:27", "throughput": 4241.87, "total_tokens": 23754976}
7304
+ {"current_steps": 36425, "total_steps": 38160, "loss": 0.5075, "lr": 6.2910713511503125e-06, "epoch": 19.090670859538783, "percentage": 95.45, "elapsed_time": "1:33:20", "remaining_time": "0:04:26", "throughput": 4241.92, "total_tokens": 23758464}
7305
+ {"current_steps": 36430, "total_steps": 38160, "loss": 0.4728, "lr": 6.254960287015332e-06, "epoch": 19.09329140461216, "percentage": 95.47, "elapsed_time": "1:33:21", "remaining_time": "0:04:26", "throughput": 4242.04, "total_tokens": 23762880}
7306
+ {"current_steps": 36435, "total_steps": 38160, "loss": 0.5596, "lr": 6.218952508709741e-06, "epoch": 19.095911949685533, "percentage": 95.48, "elapsed_time": "1:33:22", "remaining_time": "0:04:25", "throughput": 4242.03, "total_tokens": 23765664}
7307
+ {"current_steps": 36440, "total_steps": 38160, "loss": 0.573, "lr": 6.183048023765903e-06, "epoch": 19.09853249475891, "percentage": 95.49, "elapsed_time": "1:33:23", "remaining_time": "0:04:24", "throughput": 4242.15, "total_tokens": 23770016}
7308
+ {"current_steps": 36445, "total_steps": 38160, "loss": 0.4412, "lr": 6.147246839694698e-06, "epoch": 19.101153039832287, "percentage": 95.51, "elapsed_time": "1:33:24", "remaining_time": "0:04:23", "throughput": 4242.19, "total_tokens": 23773408}
7309
+ {"current_steps": 36450, "total_steps": 38160, "loss": 0.3591, "lr": 6.111548963985247e-06, "epoch": 19.10377358490566, "percentage": 95.52, "elapsed_time": "1:33:24", "remaining_time": "0:04:22", "throughput": 4242.21, "total_tokens": 23776672}
7310
+ {"current_steps": 36455, "total_steps": 38160, "loss": 0.3477, "lr": 6.075954404105188e-06, "epoch": 19.106394129979037, "percentage": 95.53, "elapsed_time": "1:33:25", "remaining_time": "0:04:22", "throughput": 4242.19, "total_tokens": 23779264}
7311
+ {"current_steps": 36460, "total_steps": 38160, "loss": 0.4582, "lr": 6.040463167500509e-06, "epoch": 19.10901467505241, "percentage": 95.55, "elapsed_time": "1:33:26", "remaining_time": "0:04:21", "throughput": 4242.27, "total_tokens": 23783104}
7312
+ {"current_steps": 36465, "total_steps": 38160, "loss": 0.3454, "lr": 6.005075261595494e-06, "epoch": 19.111635220125788, "percentage": 95.56, "elapsed_time": "1:33:26", "remaining_time": "0:04:20", "throughput": 4242.27, "total_tokens": 23785856}
7313
+ {"current_steps": 36470, "total_steps": 38160, "loss": 0.3494, "lr": 5.969790693792998e-06, "epoch": 19.11425576519916, "percentage": 95.57, "elapsed_time": "1:33:27", "remaining_time": "0:04:19", "throughput": 4242.32, "total_tokens": 23789344}
7314
+ {"current_steps": 36475, "total_steps": 38160, "loss": 0.4377, "lr": 5.9346094714740615e-06, "epoch": 19.116876310272538, "percentage": 95.58, "elapsed_time": "1:33:28", "remaining_time": "0:04:19", "throughput": 4242.39, "total_tokens": 23793056}
7315
+ {"current_steps": 36480, "total_steps": 38160, "loss": 0.496, "lr": 5.8995316019982425e-06, "epoch": 19.11949685534591, "percentage": 95.6, "elapsed_time": "1:33:29", "remaining_time": "0:04:18", "throughput": 4242.36, "total_tokens": 23795552}
7316
+ {"current_steps": 36485, "total_steps": 38160, "loss": 0.3878, "lr": 5.8645570927034485e-06, "epoch": 19.122117400419288, "percentage": 95.61, "elapsed_time": "1:33:29", "remaining_time": "0:04:17", "throughput": 4242.32, "total_tokens": 23797920}
7317
+ {"current_steps": 36490, "total_steps": 38160, "loss": 0.4982, "lr": 5.8296859509058275e-06, "epoch": 19.12473794549266, "percentage": 95.62, "elapsed_time": "1:33:30", "remaining_time": "0:04:16", "throughput": 4242.33, "total_tokens": 23800864}
7318
+ {"current_steps": 36495, "total_steps": 38160, "loss": 0.4003, "lr": 5.794918183900155e-06, "epoch": 19.12735849056604, "percentage": 95.64, "elapsed_time": "1:33:31", "remaining_time": "0:04:15", "throughput": 4242.39, "total_tokens": 23804480}
7319
+ {"current_steps": 36500, "total_steps": 38160, "loss": 0.3456, "lr": 5.760253798959447e-06, "epoch": 19.129979035639412, "percentage": 95.65, "elapsed_time": "1:33:31", "remaining_time": "0:04:15", "throughput": 4242.38, "total_tokens": 23807296}
7320
+ {"current_steps": 36505, "total_steps": 38160, "loss": 0.3211, "lr": 5.725692803335015e-06, "epoch": 19.13259958071279, "percentage": 95.66, "elapsed_time": "1:33:32", "remaining_time": "0:04:14", "throughput": 4242.41, "total_tokens": 23810432}
7321
+ {"current_steps": 36510, "total_steps": 38160, "loss": 0.3634, "lr": 5.691235204256739e-06, "epoch": 19.135220125786162, "percentage": 95.68, "elapsed_time": "1:33:33", "remaining_time": "0:04:13", "throughput": 4242.39, "total_tokens": 23813088}
7322
+ {"current_steps": 36515, "total_steps": 38160, "loss": 0.6378, "lr": 5.65688100893258e-06, "epoch": 19.13784067085954, "percentage": 95.69, "elapsed_time": "1:33:33", "remaining_time": "0:04:12", "throughput": 4242.38, "total_tokens": 23815968}
7323
+ {"current_steps": 36520, "total_steps": 38160, "loss": 0.419, "lr": 5.622630224549174e-06, "epoch": 19.140461215932913, "percentage": 95.7, "elapsed_time": "1:33:34", "remaining_time": "0:04:12", "throughput": 4242.44, "total_tokens": 23819392}
7324
+ {"current_steps": 36525, "total_steps": 38160, "loss": 0.532, "lr": 5.588482858271404e-06, "epoch": 19.14308176100629, "percentage": 95.72, "elapsed_time": "1:33:35", "remaining_time": "0:04:11", "throughput": 4242.43, "total_tokens": 23822144}
7325
+ {"current_steps": 36530, "total_steps": 38160, "loss": 0.4649, "lr": 5.554438917242444e-06, "epoch": 19.145702306079663, "percentage": 95.73, "elapsed_time": "1:33:36", "remaining_time": "0:04:10", "throughput": 4242.53, "total_tokens": 23826144}
7326
+ {"current_steps": 36535, "total_steps": 38160, "loss": 0.4344, "lr": 5.520498408583985e-06, "epoch": 19.14832285115304, "percentage": 95.74, "elapsed_time": "1:33:36", "remaining_time": "0:04:09", "throughput": 4242.58, "total_tokens": 23829536}
7327
+ {"current_steps": 36540, "total_steps": 38160, "loss": 0.3224, "lr": 5.486661339395904e-06, "epoch": 19.150943396226417, "percentage": 95.75, "elapsed_time": "1:33:37", "remaining_time": "0:04:09", "throughput": 4242.66, "total_tokens": 23833408}
7328
+ {"current_steps": 36545, "total_steps": 38160, "loss": 0.335, "lr": 5.452927716756595e-06, "epoch": 19.15356394129979, "percentage": 95.77, "elapsed_time": "1:33:38", "remaining_time": "0:04:08", "throughput": 4242.62, "total_tokens": 23835808}
7329
+ {"current_steps": 36550, "total_steps": 38160, "loss": 0.5183, "lr": 5.419297547722635e-06, "epoch": 19.156184486373167, "percentage": 95.78, "elapsed_time": "1:33:38", "remaining_time": "0:04:07", "throughput": 4242.62, "total_tokens": 23838624}
7330
+ {"current_steps": 36555, "total_steps": 38160, "loss": 0.3105, "lr": 5.385770839329229e-06, "epoch": 19.15880503144654, "percentage": 95.79, "elapsed_time": "1:33:39", "remaining_time": "0:04:06", "throughput": 4242.6, "total_tokens": 23841312}
7331
+ {"current_steps": 36560, "total_steps": 38160, "loss": 0.3949, "lr": 5.352347598589713e-06, "epoch": 19.161425576519918, "percentage": 95.81, "elapsed_time": "1:33:40", "remaining_time": "0:04:05", "throughput": 4242.62, "total_tokens": 23844416}
7332
+ {"current_steps": 36565, "total_steps": 38160, "loss": 0.3408, "lr": 5.319027832495826e-06, "epoch": 19.16404612159329, "percentage": 95.82, "elapsed_time": "1:33:40", "remaining_time": "0:04:05", "throughput": 4242.65, "total_tokens": 23847744}
7333
+ {"current_steps": 36570, "total_steps": 38160, "loss": 0.5108, "lr": 5.285811548017661e-06, "epoch": 19.166666666666668, "percentage": 95.83, "elapsed_time": "1:33:41", "remaining_time": "0:04:04", "throughput": 4242.62, "total_tokens": 23850144}
7334
+ {"current_steps": 36575, "total_steps": 38160, "loss": 0.556, "lr": 5.252698752103713e-06, "epoch": 19.16928721174004, "percentage": 95.85, "elapsed_time": "1:33:42", "remaining_time": "0:04:03", "throughput": 4242.69, "total_tokens": 23853952}
7335
+ {"current_steps": 36580, "total_steps": 38160, "loss": 0.4346, "lr": 5.219689451680832e-06, "epoch": 19.171907756813418, "percentage": 95.86, "elapsed_time": "1:33:43", "remaining_time": "0:04:02", "throughput": 4242.73, "total_tokens": 23857376}
7336
+ {"current_steps": 36585, "total_steps": 38160, "loss": 0.4513, "lr": 5.186783653654214e-06, "epoch": 19.17452830188679, "percentage": 95.87, "elapsed_time": "1:33:43", "remaining_time": "0:04:02", "throughput": 4242.79, "total_tokens": 23861056}
7337
+ {"current_steps": 36590, "total_steps": 38160, "loss": 0.335, "lr": 5.153981364907245e-06, "epoch": 19.17714884696017, "percentage": 95.89, "elapsed_time": "1:33:44", "remaining_time": "0:04:01", "throughput": 4242.78, "total_tokens": 23863968}
7338
+ {"current_steps": 36595, "total_steps": 38160, "loss": 0.3893, "lr": 5.121282592301935e-06, "epoch": 19.179769392033542, "percentage": 95.9, "elapsed_time": "1:33:45", "remaining_time": "0:04:00", "throughput": 4242.78, "total_tokens": 23866912}
7339
+ {"current_steps": 36600, "total_steps": 38160, "loss": 0.3297, "lr": 5.088687342678422e-06, "epoch": 19.18238993710692, "percentage": 95.91, "elapsed_time": "1:33:45", "remaining_time": "0:03:59", "throughput": 4242.78, "total_tokens": 23869856}
7340
+ {"current_steps": 36605, "total_steps": 38160, "loss": 0.4246, "lr": 5.056195622855253e-06, "epoch": 19.185010482180292, "percentage": 95.93, "elapsed_time": "1:33:46", "remaining_time": "0:03:59", "throughput": 4242.81, "total_tokens": 23873088}
7341
+ {"current_steps": 36610, "total_steps": 38160, "loss": 0.3707, "lr": 5.023807439629324e-06, "epoch": 19.18763102725367, "percentage": 95.94, "elapsed_time": "1:33:47", "remaining_time": "0:03:58", "throughput": 4242.83, "total_tokens": 23876160}
7342
+ {"current_steps": 36615, "total_steps": 38160, "loss": 0.473, "lr": 4.991522799775938e-06, "epoch": 19.190251572327043, "percentage": 95.95, "elapsed_time": "1:33:48", "remaining_time": "0:03:57", "throughput": 4242.81, "total_tokens": 23878880}
7343
+ {"current_steps": 36620, "total_steps": 38160, "loss": 0.347, "lr": 4.9593417100485816e-06, "epoch": 19.19287211740042, "percentage": 95.96, "elapsed_time": "1:33:48", "remaining_time": "0:03:56", "throughput": 4242.9, "total_tokens": 23882912}
7344
+ {"current_steps": 36625, "total_steps": 38160, "loss": 0.3699, "lr": 4.927264177179258e-06, "epoch": 19.195492662473793, "percentage": 95.98, "elapsed_time": "1:33:49", "remaining_time": "0:03:55", "throughput": 4242.96, "total_tokens": 23886560}
7345
+ {"current_steps": 36630, "total_steps": 38160, "loss": 0.5331, "lr": 4.895290207878156e-06, "epoch": 19.19811320754717, "percentage": 95.99, "elapsed_time": "1:33:50", "remaining_time": "0:03:55", "throughput": 4242.98, "total_tokens": 23889728}
7346
+ {"current_steps": 36635, "total_steps": 38160, "loss": 0.4265, "lr": 4.863419808833924e-06, "epoch": 19.200733752620547, "percentage": 96.0, "elapsed_time": "1:33:51", "remaining_time": "0:03:54", "throughput": 4243.05, "total_tokens": 23893408}
7347
+ {"current_steps": 36640, "total_steps": 38160, "loss": 0.3684, "lr": 4.831652986713453e-06, "epoch": 19.20335429769392, "percentage": 96.02, "elapsed_time": "1:33:51", "remaining_time": "0:03:53", "throughput": 4243.1, "total_tokens": 23896960}
7348
+ {"current_steps": 36645, "total_steps": 38160, "loss": 0.3784, "lr": 4.799989748161926e-06, "epoch": 19.205974842767297, "percentage": 96.03, "elapsed_time": "1:33:52", "remaining_time": "0:03:52", "throughput": 4243.1, "total_tokens": 23899936}
7349
+ {"current_steps": 36650, "total_steps": 38160, "loss": 0.3593, "lr": 4.768430099803101e-06, "epoch": 19.20859538784067, "percentage": 96.04, "elapsed_time": "1:33:53", "remaining_time": "0:03:52", "throughput": 4243.14, "total_tokens": 23903360}
7350
+ {"current_steps": 36655, "total_steps": 38160, "loss": 0.3543, "lr": 4.736974048238696e-06, "epoch": 19.211215932914047, "percentage": 96.06, "elapsed_time": "1:33:54", "remaining_time": "0:03:51", "throughput": 4243.17, "total_tokens": 23906784}
7351
+ {"current_steps": 36660, "total_steps": 38160, "loss": 0.2881, "lr": 4.705621600049115e-06, "epoch": 19.21383647798742, "percentage": 96.07, "elapsed_time": "1:33:54", "remaining_time": "0:03:50", "throughput": 4243.22, "total_tokens": 23910240}
7352
+ {"current_steps": 36665, "total_steps": 38160, "loss": 0.4108, "lr": 4.674372761792889e-06, "epoch": 19.216457023060798, "percentage": 96.08, "elapsed_time": "1:33:55", "remaining_time": "0:03:49", "throughput": 4243.27, "total_tokens": 23913888}
7353
+ {"current_steps": 36670, "total_steps": 38160, "loss": 0.3626, "lr": 4.6432275400069e-06, "epoch": 19.21907756813417, "percentage": 96.1, "elapsed_time": "1:33:56", "remaining_time": "0:03:49", "throughput": 4243.31, "total_tokens": 23917312}
7354
+ {"current_steps": 36675, "total_steps": 38160, "loss": 0.3997, "lr": 4.6121859412063264e-06, "epoch": 19.221698113207548, "percentage": 96.11, "elapsed_time": "1:33:57", "remaining_time": "0:03:48", "throughput": 4243.29, "total_tokens": 23920032}
7355
+ {"current_steps": 36680, "total_steps": 38160, "loss": 0.4931, "lr": 4.581247971884861e-06, "epoch": 19.22431865828092, "percentage": 96.12, "elapsed_time": "1:33:57", "remaining_time": "0:03:47", "throughput": 4243.37, "total_tokens": 23924000}
7356
+ {"current_steps": 36685, "total_steps": 38160, "loss": 0.3236, "lr": 4.550413638514217e-06, "epoch": 19.2269392033543, "percentage": 96.13, "elapsed_time": "1:33:58", "remaining_time": "0:03:46", "throughput": 4243.47, "total_tokens": 23928128}
7357
+ {"current_steps": 36690, "total_steps": 38160, "loss": 0.427, "lr": 4.519682947544679e-06, "epoch": 19.229559748427672, "percentage": 96.15, "elapsed_time": "1:33:59", "remaining_time": "0:03:45", "throughput": 4243.52, "total_tokens": 23931712}
7358
+ {"current_steps": 36695, "total_steps": 38160, "loss": 0.4843, "lr": 4.489055905404715e-06, "epoch": 19.23218029350105, "percentage": 96.16, "elapsed_time": "1:34:00", "remaining_time": "0:03:45", "throughput": 4243.53, "total_tokens": 23934912}
7359
+ {"current_steps": 36700, "total_steps": 38160, "loss": 0.507, "lr": 4.4585325185012014e-06, "epoch": 19.234800838574422, "percentage": 96.17, "elapsed_time": "1:34:01", "remaining_time": "0:03:44", "throughput": 4243.58, "total_tokens": 23938560}
7360
+ {"current_steps": 36705, "total_steps": 38160, "loss": 0.4427, "lr": 4.428112793219197e-06, "epoch": 19.2374213836478, "percentage": 96.19, "elapsed_time": "1:34:01", "remaining_time": "0:03:43", "throughput": 4243.58, "total_tokens": 23941440}
7361
+ {"current_steps": 36710, "total_steps": 38160, "loss": 0.4182, "lr": 4.397796735922277e-06, "epoch": 19.240041928721173, "percentage": 96.2, "elapsed_time": "1:34:02", "remaining_time": "0:03:42", "throughput": 4243.6, "total_tokens": 23944736}
7362
+ {"current_steps": 36715, "total_steps": 38160, "loss": 0.6641, "lr": 4.367584352952092e-06, "epoch": 19.24266247379455, "percentage": 96.21, "elapsed_time": "1:34:03", "remaining_time": "0:03:42", "throughput": 4243.74, "total_tokens": 23949376}
7363
+ {"current_steps": 36720, "total_steps": 38160, "loss": 0.4654, "lr": 4.337475650628808e-06, "epoch": 19.245283018867923, "percentage": 96.23, "elapsed_time": "1:34:04", "remaining_time": "0:03:41", "throughput": 4243.77, "total_tokens": 23952640}
7364
+ {"current_steps": 36725, "total_steps": 38160, "loss": 0.4095, "lr": 4.307470635250832e-06, "epoch": 19.2479035639413, "percentage": 96.24, "elapsed_time": "1:34:05", "remaining_time": "0:03:40", "throughput": 4243.88, "total_tokens": 23956992}
7365
+ {"current_steps": 36730, "total_steps": 38160, "loss": 0.3438, "lr": 4.277569313094809e-06, "epoch": 19.250524109014677, "percentage": 96.25, "elapsed_time": "1:34:05", "remaining_time": "0:03:39", "throughput": 4243.89, "total_tokens": 23960192}
7366
+ {"current_steps": 36735, "total_steps": 38160, "loss": 0.2995, "lr": 4.247771690415791e-06, "epoch": 19.25314465408805, "percentage": 96.27, "elapsed_time": "1:34:06", "remaining_time": "0:03:39", "throughput": 4243.89, "total_tokens": 23963040}
7367
+ {"current_steps": 36740, "total_steps": 38160, "loss": 0.4326, "lr": 4.218077773447071e-06, "epoch": 19.255765199161427, "percentage": 96.28, "elapsed_time": "1:34:07", "remaining_time": "0:03:38", "throughput": 4243.86, "total_tokens": 23965664}
7368
+ {"current_steps": 36745, "total_steps": 38160, "loss": 0.4281, "lr": 4.1884875684003455e-06, "epoch": 19.2583857442348, "percentage": 96.29, "elapsed_time": "1:34:07", "remaining_time": "0:03:37", "throughput": 4243.89, "total_tokens": 23968992}
7369
+ {"current_steps": 36750, "total_steps": 38160, "loss": 0.767, "lr": 4.159001081465497e-06, "epoch": 19.261006289308177, "percentage": 96.31, "elapsed_time": "1:34:08", "remaining_time": "0:03:36", "throughput": 4243.9, "total_tokens": 23972032}
7370
+ {"current_steps": 36755, "total_steps": 38160, "loss": 0.536, "lr": 4.129618318810702e-06, "epoch": 19.26362683438155, "percentage": 96.32, "elapsed_time": "1:34:09", "remaining_time": "0:03:35", "throughput": 4243.91, "total_tokens": 23975040}
7371
+ {"current_steps": 36760, "total_steps": 38160, "loss": 0.4195, "lr": 4.100339286582655e-06, "epoch": 19.266247379454928, "percentage": 96.33, "elapsed_time": "1:34:09", "remaining_time": "0:03:35", "throughput": 4243.87, "total_tokens": 23977408}
7372
+ {"current_steps": 36765, "total_steps": 38160, "loss": 0.4315, "lr": 4.071163990906068e-06, "epoch": 19.2688679245283, "percentage": 96.34, "elapsed_time": "1:34:10", "remaining_time": "0:03:34", "throughput": 4243.84, "total_tokens": 23980032}
7373
+ {"current_steps": 36770, "total_steps": 38160, "loss": 0.377, "lr": 4.042092437884115e-06, "epoch": 19.271488469601678, "percentage": 96.36, "elapsed_time": "1:34:11", "remaining_time": "0:03:33", "throughput": 4243.83, "total_tokens": 23982720}
7374
+ {"current_steps": 36775, "total_steps": 38160, "loss": 0.4636, "lr": 4.013124633598264e-06, "epoch": 19.27410901467505, "percentage": 96.37, "elapsed_time": "1:34:11", "remaining_time": "0:03:32", "throughput": 4243.86, "total_tokens": 23985984}
7375
+ {"current_steps": 36780, "total_steps": 38160, "loss": 0.5292, "lr": 3.984260584108168e-06, "epoch": 19.27672955974843, "percentage": 96.38, "elapsed_time": "1:34:12", "remaining_time": "0:03:32", "throughput": 4243.9, "total_tokens": 23989504}
7376
+ {"current_steps": 36785, "total_steps": 38160, "loss": 0.4322, "lr": 3.955500295451942e-06, "epoch": 19.279350104821802, "percentage": 96.4, "elapsed_time": "1:34:13", "remaining_time": "0:03:31", "throughput": 4243.89, "total_tokens": 23992160}
7377
+ {"current_steps": 36790, "total_steps": 38160, "loss": 0.5027, "lr": 3.926843773645883e-06, "epoch": 19.28197064989518, "percentage": 96.41, "elapsed_time": "1:34:14", "remaining_time": "0:03:30", "throughput": 4244.15, "total_tokens": 23998816}
7378
+ {"current_steps": 36795, "total_steps": 38160, "loss": 0.4209, "lr": 3.8982910246846415e-06, "epoch": 19.284591194968552, "percentage": 96.42, "elapsed_time": "1:34:15", "remaining_time": "0:03:29", "throughput": 4244.25, "total_tokens": 24003040}
7379
+ {"current_steps": 36800, "total_steps": 38160, "loss": 0.459, "lr": 3.869842054541051e-06, "epoch": 19.28721174004193, "percentage": 96.44, "elapsed_time": "1:34:16", "remaining_time": "0:03:29", "throughput": 4244.28, "total_tokens": 24006272}
7380
+ {"current_steps": 36805, "total_steps": 38160, "loss": 0.3771, "lr": 3.84149686916635e-06, "epoch": 19.289832285115303, "percentage": 96.45, "elapsed_time": "1:34:16", "remaining_time": "0:03:28", "throughput": 4244.33, "total_tokens": 24009792}
7381
+ {"current_steps": 36810, "total_steps": 38160, "loss": 0.3331, "lr": 3.8132554744900183e-06, "epoch": 19.29245283018868, "percentage": 96.46, "elapsed_time": "1:34:17", "remaining_time": "0:03:27", "throughput": 4244.35, "total_tokens": 24012960}
7382
+ {"current_steps": 36815, "total_steps": 38160, "loss": 0.5595, "lr": 3.7851178764198302e-06, "epoch": 19.295073375262053, "percentage": 96.48, "elapsed_time": "1:34:18", "remaining_time": "0:03:26", "throughput": 4244.4, "total_tokens": 24016416}
7383
+ {"current_steps": 36820, "total_steps": 38160, "loss": 0.3412, "lr": 3.7570840808419104e-06, "epoch": 19.29769392033543, "percentage": 96.49, "elapsed_time": "1:34:19", "remaining_time": "0:03:25", "throughput": 4244.42, "total_tokens": 24019520}
7384
+ {"current_steps": 36825, "total_steps": 38160, "loss": 0.4084, "lr": 3.729154093620568e-06, "epoch": 19.300314465408803, "percentage": 96.5, "elapsed_time": "1:34:19", "remaining_time": "0:03:25", "throughput": 4244.48, "total_tokens": 24023168}
7385
+ {"current_steps": 36830, "total_steps": 38160, "loss": 0.4144, "lr": 3.7013279205984073e-06, "epoch": 19.30293501048218, "percentage": 96.51, "elapsed_time": "1:34:20", "remaining_time": "0:03:24", "throughput": 4244.5, "total_tokens": 24026368}
7386
+ {"current_steps": 36835, "total_steps": 38160, "loss": 0.3441, "lr": 3.6736055675963275e-06, "epoch": 19.305555555555557, "percentage": 96.53, "elapsed_time": "1:34:21", "remaining_time": "0:03:23", "throughput": 4244.47, "total_tokens": 24028960}
7387
+ {"current_steps": 36840, "total_steps": 38160, "loss": 0.4784, "lr": 3.645987040413634e-06, "epoch": 19.30817610062893, "percentage": 96.54, "elapsed_time": "1:34:21", "remaining_time": "0:03:22", "throughput": 4244.43, "total_tokens": 24031392}
7388
+ {"current_steps": 36845, "total_steps": 38160, "loss": 0.4131, "lr": 3.6184723448277056e-06, "epoch": 19.310796645702307, "percentage": 96.55, "elapsed_time": "1:34:22", "remaining_time": "0:03:22", "throughput": 4244.43, "total_tokens": 24034368}
7389
+ {"current_steps": 36850, "total_steps": 38160, "loss": 0.4571, "lr": 3.5910614865943826e-06, "epoch": 19.31341719077568, "percentage": 96.57, "elapsed_time": "1:34:23", "remaining_time": "0:03:21", "throughput": 4244.45, "total_tokens": 24037472}
7390
+ {"current_steps": 36855, "total_steps": 38160, "loss": 0.4573, "lr": 3.563754471447689e-06, "epoch": 19.316037735849058, "percentage": 96.58, "elapsed_time": "1:34:23", "remaining_time": "0:03:20", "throughput": 4244.48, "total_tokens": 24040672}
7391
+ {"current_steps": 36860, "total_steps": 38160, "loss": 0.4154, "lr": 3.5365513050998334e-06, "epoch": 19.31865828092243, "percentage": 96.59, "elapsed_time": "1:34:24", "remaining_time": "0:03:19", "throughput": 4244.52, "total_tokens": 24044192}
7392
+ {"current_steps": 36865, "total_steps": 38160, "loss": 0.4202, "lr": 3.5094519932415414e-06, "epoch": 19.321278825995808, "percentage": 96.61, "elapsed_time": "1:34:25", "remaining_time": "0:03:19", "throughput": 4244.56, "total_tokens": 24047520}
7393
+ {"current_steps": 36870, "total_steps": 38160, "loss": 0.534, "lr": 3.4824565415416123e-06, "epoch": 19.32389937106918, "percentage": 96.62, "elapsed_time": "1:34:26", "remaining_time": "0:03:18", "throughput": 4244.59, "total_tokens": 24050944}
7394
+ {"current_steps": 36875, "total_steps": 38160, "loss": 0.3959, "lr": 3.4555649556471946e-06, "epoch": 19.32651991614256, "percentage": 96.63, "elapsed_time": "1:34:26", "remaining_time": "0:03:17", "throughput": 4244.56, "total_tokens": 24053440}
7395
+ {"current_steps": 36880, "total_steps": 38160, "loss": 0.4353, "lr": 3.4287772411837338e-06, "epoch": 19.329140461215932, "percentage": 96.65, "elapsed_time": "1:34:27", "remaining_time": "0:03:16", "throughput": 4244.57, "total_tokens": 24056480}
7396
+ {"current_steps": 36885, "total_steps": 38160, "loss": 0.3426, "lr": 3.402093403754858e-06, "epoch": 19.33176100628931, "percentage": 96.66, "elapsed_time": "1:34:28", "remaining_time": "0:03:15", "throughput": 4244.68, "total_tokens": 24060768}
7397
+ {"current_steps": 36890, "total_steps": 38160, "loss": 0.4913, "lr": 3.375513448942602e-06, "epoch": 19.334381551362682, "percentage": 96.67, "elapsed_time": "1:34:29", "remaining_time": "0:03:15", "throughput": 4244.64, "total_tokens": 24063200}
7398
+ {"current_steps": 36895, "total_steps": 38160, "loss": 0.5868, "lr": 3.349037382307074e-06, "epoch": 19.33700209643606, "percentage": 96.69, "elapsed_time": "1:34:29", "remaining_time": "0:03:14", "throughput": 4244.64, "total_tokens": 24066272}
7399
+ {"current_steps": 36900, "total_steps": 38160, "loss": 0.4101, "lr": 3.322665209386899e-06, "epoch": 19.339622641509433, "percentage": 96.7, "elapsed_time": "1:34:30", "remaining_time": "0:03:13", "throughput": 4244.62, "total_tokens": 24068960}
7400
+ {"current_steps": 36905, "total_steps": 38160, "loss": 0.5584, "lr": 3.29639693569872e-06, "epoch": 19.34224318658281, "percentage": 96.71, "elapsed_time": "1:34:31", "remaining_time": "0:03:12", "throughput": 4244.62, "total_tokens": 24071936}
7401
+ {"current_steps": 36910, "total_steps": 38160, "loss": 0.4329, "lr": 3.270232566737641e-06, "epoch": 19.344863731656183, "percentage": 96.72, "elapsed_time": "1:34:31", "remaining_time": "0:03:12", "throughput": 4244.61, "total_tokens": 24074752}
7402
+ {"current_steps": 36915, "total_steps": 38160, "loss": 0.4745, "lr": 3.244172107976895e-06, "epoch": 19.34748427672956, "percentage": 96.74, "elapsed_time": "1:34:32", "remaining_time": "0:03:11", "throughput": 4244.66, "total_tokens": 24078240}
7403
+ {"current_steps": 36920, "total_steps": 38160, "loss": 0.4198, "lr": 3.2182155648680657e-06, "epoch": 19.350104821802937, "percentage": 96.75, "elapsed_time": "1:34:33", "remaining_time": "0:03:10", "throughput": 4244.73, "total_tokens": 24081920}
7404
+ {"current_steps": 36925, "total_steps": 38160, "loss": 0.4922, "lr": 3.1923629428409205e-06, "epoch": 19.35272536687631, "percentage": 96.76, "elapsed_time": "1:34:34", "remaining_time": "0:03:09", "throughput": 4244.82, "total_tokens": 24085952}
7405
+ {"current_steps": 36930, "total_steps": 38160, "loss": 0.4111, "lr": 3.166614247303634e-06, "epoch": 19.355345911949687, "percentage": 96.78, "elapsed_time": "1:34:34", "remaining_time": "0:03:09", "throughput": 4244.81, "total_tokens": 24088672}
7406
+ {"current_steps": 36935, "total_steps": 38160, "loss": 0.4622, "lr": 3.140969483642453e-06, "epoch": 19.35796645702306, "percentage": 96.79, "elapsed_time": "1:34:35", "remaining_time": "0:03:08", "throughput": 4244.86, "total_tokens": 24092064}
7407
+ {"current_steps": 36940, "total_steps": 38160, "loss": 0.4965, "lr": 3.1154286572219747e-06, "epoch": 19.360587002096437, "percentage": 96.8, "elapsed_time": "1:34:36", "remaining_time": "0:03:07", "throughput": 4244.89, "total_tokens": 24095328}
7408
+ {"current_steps": 36945, "total_steps": 38160, "loss": 0.4752, "lr": 3.089991773385037e-06, "epoch": 19.36320754716981, "percentage": 96.82, "elapsed_time": "1:34:37", "remaining_time": "0:03:06", "throughput": 4244.91, "total_tokens": 24098560}
7409
+ {"current_steps": 36950, "total_steps": 38160, "loss": 0.4193, "lr": 3.064658837452772e-06, "epoch": 19.365828092243188, "percentage": 96.83, "elapsed_time": "1:34:37", "remaining_time": "0:03:05", "throughput": 4244.93, "total_tokens": 24101696}
7410
+ {"current_steps": 36955, "total_steps": 38160, "loss": 0.5001, "lr": 3.0394298547246068e-06, "epoch": 19.36844863731656, "percentage": 96.84, "elapsed_time": "1:34:38", "remaining_time": "0:03:05", "throughput": 4244.92, "total_tokens": 24104448}
7411
+ {"current_steps": 36960, "total_steps": 38160, "loss": 0.4235, "lr": 3.0143048304779875e-06, "epoch": 19.371069182389938, "percentage": 96.86, "elapsed_time": "1:34:39", "remaining_time": "0:03:04", "throughput": 4244.93, "total_tokens": 24107520}
7412
+ {"current_steps": 36965, "total_steps": 38160, "loss": 0.372, "lr": 2.989283769968987e-06, "epoch": 19.37368972746331, "percentage": 96.87, "elapsed_time": "1:34:39", "remaining_time": "0:03:03", "throughput": 4244.92, "total_tokens": 24110304}
7413
+ {"current_steps": 36970, "total_steps": 38160, "loss": 0.5129, "lr": 2.964366678431585e-06, "epoch": 19.37631027253669, "percentage": 96.88, "elapsed_time": "1:34:40", "remaining_time": "0:03:02", "throughput": 4244.97, "total_tokens": 24113792}
7414
+ {"current_steps": 36975, "total_steps": 38160, "loss": 0.4426, "lr": 2.9395535610781678e-06, "epoch": 19.378930817610062, "percentage": 96.89, "elapsed_time": "1:34:41", "remaining_time": "0:03:02", "throughput": 4244.94, "total_tokens": 24116224}
7415
+ {"current_steps": 36980, "total_steps": 38160, "loss": 0.3788, "lr": 2.9148444230994166e-06, "epoch": 19.38155136268344, "percentage": 96.91, "elapsed_time": "1:34:42", "remaining_time": "0:03:01", "throughput": 4245.04, "total_tokens": 24120480}
7416
+ {"current_steps": 36985, "total_steps": 38160, "loss": 0.5368, "lr": 2.890239269664141e-06, "epoch": 19.384171907756812, "percentage": 96.92, "elapsed_time": "1:34:42", "remaining_time": "0:03:00", "throughput": 4245.04, "total_tokens": 24123424}
7417
+ {"current_steps": 36990, "total_steps": 38160, "loss": 0.3593, "lr": 2.8657381059194466e-06, "epoch": 19.38679245283019, "percentage": 96.93, "elapsed_time": "1:34:43", "remaining_time": "0:02:59", "throughput": 4245.06, "total_tokens": 24126528}
7418
+ {"current_steps": 36995, "total_steps": 38160, "loss": 0.3643, "lr": 2.8413409369907885e-06, "epoch": 19.389412997903563, "percentage": 96.95, "elapsed_time": "1:34:44", "remaining_time": "0:02:59", "throughput": 4245.21, "total_tokens": 24131360}
7419
+ {"current_steps": 37000, "total_steps": 38160, "loss": 0.4317, "lr": 2.817047767981695e-06, "epoch": 19.39203354297694, "percentage": 96.96, "elapsed_time": "1:34:45", "remaining_time": "0:02:58", "throughput": 4245.19, "total_tokens": 24133920}
7420
+ {"current_steps": 37005, "total_steps": 38160, "loss": 0.3721, "lr": 2.7928586039740466e-06, "epoch": 19.394654088050313, "percentage": 96.97, "elapsed_time": "1:34:45", "remaining_time": "0:02:57", "throughput": 4245.25, "total_tokens": 24137536}
7421
+ {"current_steps": 37010, "total_steps": 38160, "loss": 0.3816, "lr": 2.7687734500279615e-06, "epoch": 19.39727463312369, "percentage": 96.99, "elapsed_time": "1:34:46", "remaining_time": "0:02:56", "throughput": 4245.24, "total_tokens": 24140448}
7422
+ {"current_steps": 37015, "total_steps": 38160, "loss": 0.4815, "lr": 2.744792311181743e-06, "epoch": 19.399895178197063, "percentage": 97.0, "elapsed_time": "1:34:47", "remaining_time": "0:02:55", "throughput": 4245.25, "total_tokens": 24143488}
7423
+ {"current_steps": 37020, "total_steps": 38160, "loss": 0.3899, "lr": 2.720915192451989e-06, "epoch": 19.40251572327044, "percentage": 97.01, "elapsed_time": "1:34:47", "remaining_time": "0:02:55", "throughput": 4245.3, "total_tokens": 24146944}
7424
+ {"current_steps": 37025, "total_steps": 38160, "loss": 0.4235, "lr": 2.697142098833538e-06, "epoch": 19.405136268343817, "percentage": 97.03, "elapsed_time": "1:34:48", "remaining_time": "0:02:54", "throughput": 4245.4, "total_tokens": 24150944}
7425
+ {"current_steps": 37030, "total_steps": 38160, "loss": 0.4184, "lr": 2.6734730352993563e-06, "epoch": 19.40775681341719, "percentage": 97.04, "elapsed_time": "1:34:49", "remaining_time": "0:02:53", "throughput": 4245.37, "total_tokens": 24153504}
7426
+ {"current_steps": 37035, "total_steps": 38160, "loss": 0.4093, "lr": 2.649908006800872e-06, "epoch": 19.410377358490567, "percentage": 97.05, "elapsed_time": "1:34:50", "remaining_time": "0:02:52", "throughput": 4245.37, "total_tokens": 24156480}
7427
+ {"current_steps": 37040, "total_steps": 38160, "loss": 0.5618, "lr": 2.626447018267586e-06, "epoch": 19.41299790356394, "percentage": 97.06, "elapsed_time": "1:34:50", "remaining_time": "0:02:52", "throughput": 4245.44, "total_tokens": 24160192}
7428
+ {"current_steps": 37045, "total_steps": 38160, "loss": 0.4577, "lr": 2.603090074607184e-06, "epoch": 19.415618448637318, "percentage": 97.08, "elapsed_time": "1:34:51", "remaining_time": "0:02:51", "throughput": 4245.4, "total_tokens": 24162560}
7429
+ {"current_steps": 37050, "total_steps": 38160, "loss": 0.4331, "lr": 2.579837180705813e-06, "epoch": 19.41823899371069, "percentage": 97.09, "elapsed_time": "1:34:52", "remaining_time": "0:02:50", "throughput": 4245.4, "total_tokens": 24165568}
7430
+ {"current_steps": 37055, "total_steps": 38160, "loss": 0.3426, "lr": 2.556688341427582e-06, "epoch": 19.420859538784068, "percentage": 97.1, "elapsed_time": "1:34:52", "remaining_time": "0:02:49", "throughput": 4245.42, "total_tokens": 24168608}
7431
+ {"current_steps": 37060, "total_steps": 38160, "loss": 0.5014, "lr": 2.5336435616150066e-06, "epoch": 19.42348008385744, "percentage": 97.12, "elapsed_time": "1:34:53", "remaining_time": "0:02:48", "throughput": 4245.43, "total_tokens": 24171552}
7432
+ {"current_steps": 37065, "total_steps": 38160, "loss": 0.3937, "lr": 2.510702846088786e-06, "epoch": 19.42610062893082, "percentage": 97.13, "elapsed_time": "1:34:54", "remaining_time": "0:02:48", "throughput": 4245.42, "total_tokens": 24174336}
7433
+ {"current_steps": 37070, "total_steps": 38160, "loss": 0.3085, "lr": 2.487866199647915e-06, "epoch": 19.428721174004192, "percentage": 97.14, "elapsed_time": "1:34:55", "remaining_time": "0:02:47", "throughput": 4245.52, "total_tokens": 24178400}
7434
+ {"current_steps": 37075, "total_steps": 38160, "loss": 0.3661, "lr": 2.4651336270695156e-06, "epoch": 19.43134171907757, "percentage": 97.16, "elapsed_time": "1:34:55", "remaining_time": "0:02:46", "throughput": 4245.52, "total_tokens": 24181312}
7435
+ {"current_steps": 37080, "total_steps": 38160, "loss": 0.4408, "lr": 2.442505133108952e-06, "epoch": 19.433962264150942, "percentage": 97.17, "elapsed_time": "1:34:56", "remaining_time": "0:02:45", "throughput": 4245.55, "total_tokens": 24184544}
7436
+ {"current_steps": 37085, "total_steps": 38160, "loss": 0.2861, "lr": 2.419980722499937e-06, "epoch": 19.43658280922432, "percentage": 97.18, "elapsed_time": "1:34:57", "remaining_time": "0:02:45", "throughput": 4245.49, "total_tokens": 24186720}
7437
+ {"current_steps": 37090, "total_steps": 38160, "loss": 0.4594, "lr": 2.397560399954202e-06, "epoch": 19.439203354297693, "percentage": 97.2, "elapsed_time": "1:34:57", "remaining_time": "0:02:44", "throughput": 4245.52, "total_tokens": 24189984}
7438
+ {"current_steps": 37095, "total_steps": 38160, "loss": 0.3654, "lr": 2.3752441701618833e-06, "epoch": 19.44182389937107, "percentage": 97.21, "elapsed_time": "1:34:58", "remaining_time": "0:02:43", "throughput": 4245.49, "total_tokens": 24192448}
7439
+ {"current_steps": 37100, "total_steps": 38160, "loss": 0.3748, "lr": 2.3530320377913027e-06, "epoch": 19.444444444444443, "percentage": 97.22, "elapsed_time": "1:34:59", "remaining_time": "0:02:42", "throughput": 4245.55, "total_tokens": 24196128}
7440
+ {"current_steps": 37105, "total_steps": 38160, "loss": 0.3611, "lr": 2.3309240074890213e-06, "epoch": 19.44706498951782, "percentage": 97.24, "elapsed_time": "1:34:59", "remaining_time": "0:02:42", "throughput": 4245.56, "total_tokens": 24199104}
7441
+ {"current_steps": 37110, "total_steps": 38160, "loss": 0.54, "lr": 2.3089200838796176e-06, "epoch": 19.449685534591197, "percentage": 97.25, "elapsed_time": "1:35:00", "remaining_time": "0:02:41", "throughput": 4245.57, "total_tokens": 24202176}
7442
+ {"current_steps": 37115, "total_steps": 38160, "loss": 0.4897, "lr": 2.2870202715662426e-06, "epoch": 19.45230607966457, "percentage": 97.26, "elapsed_time": "1:35:01", "remaining_time": "0:02:40", "throughput": 4245.62, "total_tokens": 24205824}
7443
+ {"current_steps": 37120, "total_steps": 38160, "loss": 0.5309, "lr": 2.265224575130009e-06, "epoch": 19.454926624737947, "percentage": 97.27, "elapsed_time": "1:35:02", "remaining_time": "0:02:39", "throughput": 4245.61, "total_tokens": 24208640}
7444
+ {"current_steps": 37125, "total_steps": 38160, "loss": 0.2571, "lr": 2.2435329991303268e-06, "epoch": 19.45754716981132, "percentage": 97.29, "elapsed_time": "1:35:03", "remaining_time": "0:02:39", "throughput": 4245.89, "total_tokens": 24215456}
7445
+ {"current_steps": 37130, "total_steps": 38160, "loss": 0.4262, "lr": 2.2219455481047868e-06, "epoch": 19.460167714884697, "percentage": 97.3, "elapsed_time": "1:35:03", "remaining_time": "0:02:38", "throughput": 4245.93, "total_tokens": 24218752}
7446
+ {"current_steps": 37135, "total_steps": 38160, "loss": 0.3992, "lr": 2.2004622265693886e-06, "epoch": 19.46278825995807, "percentage": 97.31, "elapsed_time": "1:35:04", "remaining_time": "0:02:37", "throughput": 4245.92, "total_tokens": 24221632}
7447
+ {"current_steps": 37140, "total_steps": 38160, "loss": 0.4954, "lr": 2.179083039018037e-06, "epoch": 19.465408805031448, "percentage": 97.33, "elapsed_time": "1:35:05", "remaining_time": "0:02:36", "throughput": 4246.03, "total_tokens": 24225824}
7448
+ {"current_steps": 37145, "total_steps": 38160, "loss": 0.4513, "lr": 2.157807989923044e-06, "epoch": 19.46802935010482, "percentage": 97.34, "elapsed_time": "1:35:06", "remaining_time": "0:02:35", "throughput": 4246.05, "total_tokens": 24228960}
7449
+ {"current_steps": 37150, "total_steps": 38160, "loss": 0.374, "lr": 2.1366370837349603e-06, "epoch": 19.470649895178198, "percentage": 97.35, "elapsed_time": "1:35:06", "remaining_time": "0:02:35", "throughput": 4246.1, "total_tokens": 24232352}
7450
+ {"current_steps": 37155, "total_steps": 38160, "loss": 0.3531, "lr": 2.1155703248825207e-06, "epoch": 19.47327044025157, "percentage": 97.37, "elapsed_time": "1:35:07", "remaining_time": "0:02:34", "throughput": 4246.12, "total_tokens": 24235456}
7451
+ {"current_steps": 37160, "total_steps": 38160, "loss": 0.4298, "lr": 2.094607717772534e-06, "epoch": 19.47589098532495, "percentage": 97.38, "elapsed_time": "1:35:08", "remaining_time": "0:02:33", "throughput": 4246.09, "total_tokens": 24238016}
7452
+ {"current_steps": 37165, "total_steps": 38160, "loss": 0.3859, "lr": 2.0737492667902702e-06, "epoch": 19.478511530398322, "percentage": 97.39, "elapsed_time": "1:35:08", "remaining_time": "0:02:32", "throughput": 4246.07, "total_tokens": 24240672}
7453
+ {"current_steps": 37170, "total_steps": 38160, "loss": 0.3173, "lr": 2.0529949762989608e-06, "epoch": 19.4811320754717, "percentage": 97.41, "elapsed_time": "1:35:09", "remaining_time": "0:02:32", "throughput": 4246.06, "total_tokens": 24243520}
7454
+ {"current_steps": 37175, "total_steps": 38160, "loss": 0.4524, "lr": 2.032344850640244e-06, "epoch": 19.483752620545072, "percentage": 97.42, "elapsed_time": "1:35:10", "remaining_time": "0:02:31", "throughput": 4246.08, "total_tokens": 24246784}
7455
+ {"current_steps": 37180, "total_steps": 38160, "loss": 0.6324, "lr": 2.011798894133887e-06, "epoch": 19.48637316561845, "percentage": 97.43, "elapsed_time": "1:35:11", "remaining_time": "0:02:30", "throughput": 4246.17, "total_tokens": 24250848}
7456
+ {"current_steps": 37185, "total_steps": 38160, "loss": 0.4488, "lr": 1.9913571110777852e-06, "epoch": 19.488993710691823, "percentage": 97.44, "elapsed_time": "1:35:11", "remaining_time": "0:02:29", "throughput": 4246.21, "total_tokens": 24254208}
7457
+ {"current_steps": 37190, "total_steps": 38160, "loss": 0.4439, "lr": 1.971019505748295e-06, "epoch": 19.4916142557652, "percentage": 97.46, "elapsed_time": "1:35:13", "remaining_time": "0:02:29", "throughput": 4246.47, "total_tokens": 24260896}
7458
+ {"current_steps": 37195, "total_steps": 38160, "loss": 0.4328, "lr": 1.9507860823996803e-06, "epoch": 19.494234800838573, "percentage": 97.47, "elapsed_time": "1:35:13", "remaining_time": "0:02:28", "throughput": 4246.43, "total_tokens": 24263232}
7459
+ {"current_steps": 37200, "total_steps": 38160, "loss": 0.4888, "lr": 1.9306568452645e-06, "epoch": 19.49685534591195, "percentage": 97.48, "elapsed_time": "1:35:14", "remaining_time": "0:02:27", "throughput": 4246.48, "total_tokens": 24266784}
7460
+ {"current_steps": 37205, "total_steps": 38160, "loss": 0.357, "lr": 1.910631798553664e-06, "epoch": 19.499475890985323, "percentage": 97.5, "elapsed_time": "1:35:15", "remaining_time": "0:02:26", "throughput": 4246.52, "total_tokens": 24270112}
7461
+ {"current_steps": 37210, "total_steps": 38160, "loss": 0.4867, "lr": 1.8907109464562088e-06, "epoch": 19.5020964360587, "percentage": 97.51, "elapsed_time": "1:35:16", "remaining_time": "0:02:25", "throughput": 4246.53, "total_tokens": 24273184}
7462
+ {"current_steps": 37215, "total_steps": 38160, "loss": 0.4502, "lr": 1.870894293139247e-06, "epoch": 19.504716981132077, "percentage": 97.52, "elapsed_time": "1:35:16", "remaining_time": "0:02:25", "throughput": 4246.55, "total_tokens": 24276224}
7463
+ {"current_steps": 37220, "total_steps": 38160, "loss": 0.3666, "lr": 1.8511818427482396e-06, "epoch": 19.50733752620545, "percentage": 97.54, "elapsed_time": "1:35:17", "remaining_time": "0:02:24", "throughput": 4246.7, "total_tokens": 24281024}
7464
+ {"current_steps": 37225, "total_steps": 38160, "loss": 0.5454, "lr": 1.8315735994068327e-06, "epoch": 19.509958071278827, "percentage": 97.55, "elapsed_time": "1:35:18", "remaining_time": "0:02:23", "throughput": 4246.69, "total_tokens": 24283840}
7465
+ {"current_steps": 37230, "total_steps": 38160, "loss": 0.248, "lr": 1.8120695672168009e-06, "epoch": 19.5125786163522, "percentage": 97.56, "elapsed_time": "1:35:18", "remaining_time": "0:02:22", "throughput": 4246.65, "total_tokens": 24286240}
7466
+ {"current_steps": 37235, "total_steps": 38160, "loss": 0.3818, "lr": 1.792669750258158e-06, "epoch": 19.515199161425578, "percentage": 97.58, "elapsed_time": "1:35:19", "remaining_time": "0:02:22", "throughput": 4246.64, "total_tokens": 24288992}
7467
+ {"current_steps": 37240, "total_steps": 38160, "loss": 0.4034, "lr": 1.7733741525892134e-06, "epoch": 19.51781970649895, "percentage": 97.59, "elapsed_time": "1:35:20", "remaining_time": "0:02:21", "throughput": 4246.67, "total_tokens": 24292288}
7468
+ {"current_steps": 37245, "total_steps": 38160, "loss": 0.4658, "lr": 1.7541827782462937e-06, "epoch": 19.520440251572328, "percentage": 97.6, "elapsed_time": "1:35:21", "remaining_time": "0:02:20", "throughput": 4246.7, "total_tokens": 24295584}
7469
+ {"current_steps": 37250, "total_steps": 38160, "loss": 0.3764, "lr": 1.7350956312440768e-06, "epoch": 19.5230607966457, "percentage": 97.62, "elapsed_time": "1:35:21", "remaining_time": "0:02:19", "throughput": 4246.7, "total_tokens": 24298400}
7470
+ {"current_steps": 37255, "total_steps": 38160, "loss": 0.3428, "lr": 1.716112715575313e-06, "epoch": 19.52568134171908, "percentage": 97.63, "elapsed_time": "1:35:22", "remaining_time": "0:02:19", "throughput": 4246.69, "total_tokens": 24301280}
7471
+ {"current_steps": 37260, "total_steps": 38160, "loss": 0.4553, "lr": 1.6972340352110481e-06, "epoch": 19.528301886792452, "percentage": 97.64, "elapsed_time": "1:35:23", "remaining_time": "0:02:18", "throughput": 4246.68, "total_tokens": 24303968}
7472
+ {"current_steps": 37265, "total_steps": 38160, "loss": 0.4346, "lr": 1.6784595941004565e-06, "epoch": 19.53092243186583, "percentage": 97.65, "elapsed_time": "1:35:23", "remaining_time": "0:02:17", "throughput": 4246.72, "total_tokens": 24307456}
7473
+ {"current_steps": 37270, "total_steps": 38160, "loss": 0.3948, "lr": 1.659789396171063e-06, "epoch": 19.533542976939202, "percentage": 97.67, "elapsed_time": "1:35:24", "remaining_time": "0:02:16", "throughput": 4246.78, "total_tokens": 24310912}
7474
+ {"current_steps": 37275, "total_steps": 38160, "loss": 0.4151, "lr": 1.6412234453282993e-06, "epoch": 19.53616352201258, "percentage": 97.68, "elapsed_time": "1:35:25", "remaining_time": "0:02:15", "throughput": 4246.77, "total_tokens": 24313728}
7475
+ {"current_steps": 37280, "total_steps": 38160, "loss": 0.4073, "lr": 1.622761745456003e-06, "epoch": 19.538784067085953, "percentage": 97.69, "elapsed_time": "1:35:25", "remaining_time": "0:02:15", "throughput": 4246.8, "total_tokens": 24316928}
7476
+ {"current_steps": 37285, "total_steps": 38160, "loss": 0.366, "lr": 1.6044043004161958e-06, "epoch": 19.54140461215933, "percentage": 97.71, "elapsed_time": "1:35:26", "remaining_time": "0:02:14", "throughput": 4246.78, "total_tokens": 24319552}
7477
+ {"current_steps": 37290, "total_steps": 38160, "loss": 0.4135, "lr": 1.5861511140489725e-06, "epoch": 19.544025157232703, "percentage": 97.72, "elapsed_time": "1:35:27", "remaining_time": "0:02:13", "throughput": 4246.74, "total_tokens": 24321984}
7478
+ {"current_steps": 37295, "total_steps": 38160, "loss": 0.4859, "lr": 1.5680021901727237e-06, "epoch": 19.54664570230608, "percentage": 97.73, "elapsed_time": "1:35:27", "remaining_time": "0:02:12", "throughput": 4246.73, "total_tokens": 24324928}
7479
+ {"current_steps": 37300, "total_steps": 38160, "loss": 0.3087, "lr": 1.5499575325840232e-06, "epoch": 19.549266247379457, "percentage": 97.75, "elapsed_time": "1:35:28", "remaining_time": "0:02:12", "throughput": 4246.76, "total_tokens": 24328064}
7480
+ {"current_steps": 37305, "total_steps": 38160, "loss": 0.5207, "lr": 1.5320171450576293e-06, "epoch": 19.55188679245283, "percentage": 97.76, "elapsed_time": "1:35:29", "remaining_time": "0:02:11", "throughput": 4246.77, "total_tokens": 24331136}
7481
+ {"current_steps": 37310, "total_steps": 38160, "loss": 0.4399, "lr": 1.5141810313463733e-06, "epoch": 19.554507337526207, "percentage": 97.77, "elapsed_time": "1:35:30", "remaining_time": "0:02:10", "throughput": 4246.77, "total_tokens": 24334112}
7482
+ {"current_steps": 37315, "total_steps": 38160, "loss": 0.3635, "lr": 1.4964491951814374e-06, "epoch": 19.55712788259958, "percentage": 97.79, "elapsed_time": "1:35:30", "remaining_time": "0:02:09", "throughput": 4246.85, "total_tokens": 24338048}
7483
+ {"current_steps": 37320, "total_steps": 38160, "loss": 0.5321, "lr": 1.4788216402720766e-06, "epoch": 19.559748427672957, "percentage": 97.8, "elapsed_time": "1:35:31", "remaining_time": "0:02:09", "throughput": 4246.9, "total_tokens": 24341632}
7484
+ {"current_steps": 37325, "total_steps": 38160, "loss": 0.4173, "lr": 1.4612983703058413e-06, "epoch": 19.56236897274633, "percentage": 97.81, "elapsed_time": "1:35:32", "remaining_time": "0:02:08", "throughput": 4246.96, "total_tokens": 24345088}
7485
+ {"current_steps": 37330, "total_steps": 38160, "loss": 0.4175, "lr": 1.4438793889483549e-06, "epoch": 19.564989517819708, "percentage": 97.82, "elapsed_time": "1:35:33", "remaining_time": "0:02:07", "throughput": 4247.02, "total_tokens": 24348736}
7486
+ {"current_steps": 37335, "total_steps": 38160, "loss": 0.3316, "lr": 1.4265646998434246e-06, "epoch": 19.56761006289308, "percentage": 97.84, "elapsed_time": "1:35:33", "remaining_time": "0:02:06", "throughput": 4247.04, "total_tokens": 24351776}
7487
+ {"current_steps": 37340, "total_steps": 38160, "loss": 0.3668, "lr": 1.409354306613153e-06, "epoch": 19.570230607966458, "percentage": 97.85, "elapsed_time": "1:35:34", "remaining_time": "0:02:05", "throughput": 4247.09, "total_tokens": 24355296}
7488
+ {"current_steps": 37345, "total_steps": 38160, "loss": 0.4171, "lr": 1.3922482128577718e-06, "epoch": 19.57285115303983, "percentage": 97.86, "elapsed_time": "1:35:35", "remaining_time": "0:02:05", "throughput": 4247.17, "total_tokens": 24359168}
7489
+ {"current_steps": 37350, "total_steps": 38160, "loss": 0.4846, "lr": 1.3752464221556404e-06, "epoch": 19.57547169811321, "percentage": 97.88, "elapsed_time": "1:35:36", "remaining_time": "0:02:04", "throughput": 4247.23, "total_tokens": 24362720}
7490
+ {"current_steps": 37355, "total_steps": 38160, "loss": 0.382, "lr": 1.358348938063303e-06, "epoch": 19.578092243186582, "percentage": 97.89, "elapsed_time": "1:35:36", "remaining_time": "0:02:03", "throughput": 4247.24, "total_tokens": 24365824}
7491
+ {"current_steps": 37360, "total_steps": 38160, "loss": 0.35, "lr": 1.341555764115543e-06, "epoch": 19.58071278825996, "percentage": 97.9, "elapsed_time": "1:35:37", "remaining_time": "0:02:02", "throughput": 4247.26, "total_tokens": 24368928}
7492
+ {"current_steps": 37365, "total_steps": 38160, "loss": 0.3859, "lr": 1.3248669038253835e-06, "epoch": 19.583333333333332, "percentage": 97.92, "elapsed_time": "1:35:38", "remaining_time": "0:02:02", "throughput": 4247.3, "total_tokens": 24372192}
7493
+ {"current_steps": 37370, "total_steps": 38160, "loss": 0.4425, "lr": 1.3082823606838656e-06, "epoch": 19.58595387840671, "percentage": 97.93, "elapsed_time": "1:35:38", "remaining_time": "0:02:01", "throughput": 4247.28, "total_tokens": 24374912}
7494
+ {"current_steps": 37375, "total_steps": 38160, "loss": 0.3914, "lr": 1.2918021381603251e-06, "epoch": 19.588574423480082, "percentage": 97.94, "elapsed_time": "1:35:39", "remaining_time": "0:02:00", "throughput": 4247.31, "total_tokens": 24378176}
7495
+ {"current_steps": 37380, "total_steps": 38160, "loss": 0.3741, "lr": 1.275426239702171e-06, "epoch": 19.59119496855346, "percentage": 97.96, "elapsed_time": "1:35:40", "remaining_time": "0:01:59", "throughput": 4247.37, "total_tokens": 24381760}
7496
+ {"current_steps": 37385, "total_steps": 38160, "loss": 0.3935, "lr": 1.2591546687351073e-06, "epoch": 19.593815513626833, "percentage": 97.97, "elapsed_time": "1:35:41", "remaining_time": "0:01:59", "throughput": 4247.48, "total_tokens": 24386144}
7497
+ {"current_steps": 37390, "total_steps": 38160, "loss": 0.4078, "lr": 1.2429874286629673e-06, "epoch": 19.59643605870021, "percentage": 97.98, "elapsed_time": "1:35:42", "remaining_time": "0:01:58", "throughput": 4247.53, "total_tokens": 24389600}
7498
+ {"current_steps": 37395, "total_steps": 38160, "loss": 0.4075, "lr": 1.2269245228677116e-06, "epoch": 19.599056603773583, "percentage": 98.0, "elapsed_time": "1:35:42", "remaining_time": "0:01:57", "throughput": 4247.49, "total_tokens": 24392160}
7499
+ {"current_steps": 37400, "total_steps": 38160, "loss": 0.4063, "lr": 1.210965954709542e-06, "epoch": 19.60167714884696, "percentage": 98.01, "elapsed_time": "1:35:43", "remaining_time": "0:01:56", "throughput": 4247.54, "total_tokens": 24395584}
7500
+ {"current_steps": 37405, "total_steps": 38160, "loss": 0.3625, "lr": 1.1951117275268431e-06, "epoch": 19.604297693920337, "percentage": 98.02, "elapsed_time": "1:35:44", "remaining_time": "0:01:55", "throughput": 4247.47, "total_tokens": 24397696}
7501
+ {"current_steps": 37410, "total_steps": 38160, "loss": 0.4169, "lr": 1.1793618446360732e-06, "epoch": 19.60691823899371, "percentage": 98.03, "elapsed_time": "1:35:44", "remaining_time": "0:01:55", "throughput": 4247.55, "total_tokens": 24401696}
7502
+ {"current_steps": 37415, "total_steps": 38160, "loss": 0.4148, "lr": 1.1637163093319303e-06, "epoch": 19.609538784067087, "percentage": 98.05, "elapsed_time": "1:35:45", "remaining_time": "0:01:54", "throughput": 4247.53, "total_tokens": 24404416}
7503
+ {"current_steps": 37420, "total_steps": 38160, "loss": 0.37, "lr": 1.1481751248874072e-06, "epoch": 19.61215932914046, "percentage": 98.06, "elapsed_time": "1:35:46", "remaining_time": "0:01:53", "throughput": 4247.51, "total_tokens": 24407008}
7504
+ {"current_steps": 37425, "total_steps": 38160, "loss": 0.3025, "lr": 1.1327382945533482e-06, "epoch": 19.614779874213838, "percentage": 98.07, "elapsed_time": "1:35:46", "remaining_time": "0:01:52", "throughput": 4247.54, "total_tokens": 24410208}
7505
+ {"current_steps": 37430, "total_steps": 38160, "loss": 0.3042, "lr": 1.1174058215591143e-06, "epoch": 19.61740041928721, "percentage": 98.09, "elapsed_time": "1:35:47", "remaining_time": "0:01:52", "throughput": 4247.69, "total_tokens": 24415168}
7506
+ {"current_steps": 37435, "total_steps": 38160, "loss": 0.3679, "lr": 1.1021777091119732e-06, "epoch": 19.620020964360588, "percentage": 98.1, "elapsed_time": "1:35:48", "remaining_time": "0:01:51", "throughput": 4247.68, "total_tokens": 24417984}
7507
+ {"current_steps": 37440, "total_steps": 38160, "loss": 0.4822, "lr": 1.0870539603975994e-06, "epoch": 19.62264150943396, "percentage": 98.11, "elapsed_time": "1:35:49", "remaining_time": "0:01:50", "throughput": 4247.72, "total_tokens": 24421376}
7508
+ {"current_steps": 37445, "total_steps": 38160, "loss": 0.2813, "lr": 1.0720345785795727e-06, "epoch": 19.62526205450734, "percentage": 98.13, "elapsed_time": "1:35:50", "remaining_time": "0:01:49", "throughput": 4247.74, "total_tokens": 24424544}
7509
+ {"current_steps": 37450, "total_steps": 38160, "loss": 0.3549, "lr": 1.0571195667998802e-06, "epoch": 19.627882599580712, "percentage": 98.14, "elapsed_time": "1:35:50", "remaining_time": "0:01:49", "throughput": 4247.73, "total_tokens": 24427488}
7510
+ {"current_steps": 37455, "total_steps": 38160, "loss": 0.4368, "lr": 1.042308928178526e-06, "epoch": 19.63050314465409, "percentage": 98.15, "elapsed_time": "1:35:51", "remaining_time": "0:01:48", "throughput": 4247.73, "total_tokens": 24430336}
7511
+ {"current_steps": 37460, "total_steps": 38160, "loss": 0.4106, "lr": 1.0276026658137538e-06, "epoch": 19.633123689727462, "percentage": 98.17, "elapsed_time": "1:35:52", "remaining_time": "0:01:47", "throughput": 4247.87, "total_tokens": 24435136}
7512
+ {"current_steps": 37465, "total_steps": 38160, "loss": 0.4952, "lr": 1.013000782781881e-06, "epoch": 19.63574423480084, "percentage": 98.18, "elapsed_time": "1:35:53", "remaining_time": "0:01:46", "throughput": 4247.93, "total_tokens": 24438848}
7513
+ {"current_steps": 37470, "total_steps": 38160, "loss": 0.4517, "lr": 9.985032821375195e-07, "epoch": 19.638364779874212, "percentage": 98.19, "elapsed_time": "1:35:53", "remaining_time": "0:01:45", "throughput": 4247.89, "total_tokens": 24441248}
7514
+ {"current_steps": 37475, "total_steps": 38160, "loss": 0.3931, "lr": 9.841101669134101e-07, "epoch": 19.64098532494759, "percentage": 98.2, "elapsed_time": "1:35:54", "remaining_time": "0:01:45", "throughput": 4247.86, "total_tokens": 24443840}
7515
+ {"current_steps": 37480, "total_steps": 38160, "loss": 0.4657, "lr": 9.69821440120311e-07, "epoch": 19.643605870020963, "percentage": 98.22, "elapsed_time": "1:35:55", "remaining_time": "0:01:44", "throughput": 4247.9, "total_tokens": 24447200}
7516
+ {"current_steps": 37485, "total_steps": 38160, "loss": 0.5455, "lr": 9.556371047473866e-07, "epoch": 19.64622641509434, "percentage": 98.23, "elapsed_time": "1:35:55", "remaining_time": "0:01:43", "throughput": 4247.91, "total_tokens": 24450368}
7517
+ {"current_steps": 37490, "total_steps": 38160, "loss": 0.3123, "lr": 9.415571637617082e-07, "epoch": 19.648846960167717, "percentage": 98.24, "elapsed_time": "1:35:56", "remaining_time": "0:01:42", "throughput": 4247.89, "total_tokens": 24452992}
7518
+ {"current_steps": 37495, "total_steps": 38160, "loss": 0.477, "lr": 9.275816201087528e-07, "epoch": 19.65146750524109, "percentage": 98.26, "elapsed_time": "1:35:57", "remaining_time": "0:01:42", "throughput": 4247.84, "total_tokens": 24455264}
7519
+ {"current_steps": 37500, "total_steps": 38160, "loss": 0.4983, "lr": 9.137104767120153e-07, "epoch": 19.654088050314467, "percentage": 98.27, "elapsed_time": "1:35:57", "remaining_time": "0:01:41", "throughput": 4247.84, "total_tokens": 24458304}
7520
+ {"current_steps": 37505, "total_steps": 38160, "loss": 0.486, "lr": 8.999437364731189e-07, "epoch": 19.65670859538784, "percentage": 98.28, "elapsed_time": "1:35:58", "remaining_time": "0:01:40", "throughput": 4247.89, "total_tokens": 24461824}
7521
+ {"current_steps": 37510, "total_steps": 38160, "loss": 0.3793, "lr": 8.862814022720378e-07, "epoch": 19.659329140461217, "percentage": 98.3, "elapsed_time": "1:35:59", "remaining_time": "0:01:39", "throughput": 4247.89, "total_tokens": 24464736}
7522
+ {"current_steps": 37515, "total_steps": 38160, "loss": 0.3724, "lr": 8.727234769666526e-07, "epoch": 19.66194968553459, "percentage": 98.31, "elapsed_time": "1:35:59", "remaining_time": "0:01:39", "throughput": 4247.86, "total_tokens": 24467264}
7523
+ {"current_steps": 37520, "total_steps": 38160, "loss": 0.4585, "lr": 8.592699633931389e-07, "epoch": 19.664570230607968, "percentage": 98.32, "elapsed_time": "1:36:00", "remaining_time": "0:01:38", "throughput": 4247.92, "total_tokens": 24470912}
7524
+ {"current_steps": 37525, "total_steps": 38160, "loss": 0.4497, "lr": 8.459208643659122e-07, "epoch": 19.66719077568134, "percentage": 98.34, "elapsed_time": "1:36:01", "remaining_time": "0:01:37", "throughput": 4247.97, "total_tokens": 24474304}
7525
+ {"current_steps": 37530, "total_steps": 38160, "loss": 0.3752, "lr": 8.326761826773499e-07, "epoch": 19.669811320754718, "percentage": 98.35, "elapsed_time": "1:36:02", "remaining_time": "0:01:36", "throughput": 4247.98, "total_tokens": 24477280}
7526
+ {"current_steps": 37535, "total_steps": 38160, "loss": 0.4012, "lr": 8.195359210981246e-07, "epoch": 19.67243186582809, "percentage": 98.36, "elapsed_time": "1:36:02", "remaining_time": "0:01:35", "throughput": 4247.91, "total_tokens": 24479456}
7527
+ {"current_steps": 37540, "total_steps": 38160, "loss": 0.4812, "lr": 8.065000823770929e-07, "epoch": 19.67505241090147, "percentage": 98.38, "elapsed_time": "1:36:03", "remaining_time": "0:01:35", "throughput": 4247.94, "total_tokens": 24482624}
7528
+ {"current_steps": 37545, "total_steps": 38160, "loss": 0.3898, "lr": 7.935686692410737e-07, "epoch": 19.677672955974842, "percentage": 98.39, "elapsed_time": "1:36:04", "remaining_time": "0:01:34", "throughput": 4247.96, "total_tokens": 24485792}
7529
+ {"current_steps": 37550, "total_steps": 38160, "loss": 0.3794, "lr": 7.807416843952364e-07, "epoch": 19.68029350104822, "percentage": 98.4, "elapsed_time": "1:36:04", "remaining_time": "0:01:33", "throughput": 4247.95, "total_tokens": 24488576}
7530
+ {"current_steps": 37555, "total_steps": 38160, "loss": 0.5857, "lr": 7.68019130522879e-07, "epoch": 19.682914046121592, "percentage": 98.41, "elapsed_time": "1:36:05", "remaining_time": "0:01:32", "throughput": 4247.92, "total_tokens": 24491136}
7531
+ {"current_steps": 37560, "total_steps": 38160, "loss": 0.6165, "lr": 7.554010102853726e-07, "epoch": 19.68553459119497, "percentage": 98.43, "elapsed_time": "1:36:06", "remaining_time": "0:01:32", "throughput": 4247.96, "total_tokens": 24494528}
7532
+ {"current_steps": 37565, "total_steps": 38160, "loss": 0.5233, "lr": 7.428873263223279e-07, "epoch": 19.688155136268342, "percentage": 98.44, "elapsed_time": "1:36:07", "remaining_time": "0:01:31", "throughput": 4248.06, "total_tokens": 24498816}
7533
+ {"current_steps": 37570, "total_steps": 38160, "loss": 0.3905, "lr": 7.304780812513734e-07, "epoch": 19.69077568134172, "percentage": 98.45, "elapsed_time": "1:36:07", "remaining_time": "0:01:30", "throughput": 4248.12, "total_tokens": 24502368}
7534
+ {"current_steps": 37575, "total_steps": 38160, "loss": 0.4011, "lr": 7.181732776684325e-07, "epoch": 19.693396226415093, "percentage": 98.47, "elapsed_time": "1:36:08", "remaining_time": "0:01:29", "throughput": 4248.14, "total_tokens": 24505440}
7535
+ {"current_steps": 37580, "total_steps": 38160, "loss": 0.4615, "lr": 7.059729181475572e-07, "epoch": 19.69601677148847, "percentage": 98.48, "elapsed_time": "1:36:09", "remaining_time": "0:01:29", "throughput": 4248.16, "total_tokens": 24508512}
7536
+ {"current_steps": 37585, "total_steps": 38160, "loss": 0.3764, "lr": 6.938770052409282e-07, "epoch": 19.698637316561843, "percentage": 98.49, "elapsed_time": "1:36:09", "remaining_time": "0:01:28", "throughput": 4248.16, "total_tokens": 24511360}
7537
+ {"current_steps": 37590, "total_steps": 38160, "loss": 0.4547, "lr": 6.81885541478855e-07, "epoch": 19.70125786163522, "percentage": 98.51, "elapsed_time": "1:36:10", "remaining_time": "0:01:27", "throughput": 4248.14, "total_tokens": 24514048}
7538
+ {"current_steps": 37595, "total_steps": 38160, "loss": 0.3693, "lr": 6.699985293697197e-07, "epoch": 19.703878406708597, "percentage": 98.52, "elapsed_time": "1:36:11", "remaining_time": "0:01:26", "throughput": 4248.14, "total_tokens": 24517088}
7539
+ {"current_steps": 37600, "total_steps": 38160, "loss": 0.4787, "lr": 6.582159714003111e-07, "epoch": 19.70649895178197, "percentage": 98.53, "elapsed_time": "1:36:11", "remaining_time": "0:01:25", "throughput": 4248.12, "total_tokens": 24519808}
7540
+ {"current_steps": 37605, "total_steps": 38160, "loss": 0.4893, "lr": 6.465378700352687e-07, "epoch": 19.709119496855347, "percentage": 98.55, "elapsed_time": "1:36:12", "remaining_time": "0:01:25", "throughput": 4248.26, "total_tokens": 24524320}
7541
+ {"current_steps": 37610, "total_steps": 38160, "loss": 0.4393, "lr": 6.349642277176382e-07, "epoch": 19.71174004192872, "percentage": 98.56, "elapsed_time": "1:36:13", "remaining_time": "0:01:24", "throughput": 4248.34, "total_tokens": 24528192}
7542
+ {"current_steps": 37615, "total_steps": 38160, "loss": 0.4694, "lr": 6.23495046868372e-07, "epoch": 19.714360587002098, "percentage": 98.57, "elapsed_time": "1:36:14", "remaining_time": "0:01:23", "throughput": 4248.32, "total_tokens": 24530880}
7543
+ {"current_steps": 37620, "total_steps": 38160, "loss": 0.4592, "lr": 6.121303298868286e-07, "epoch": 19.71698113207547, "percentage": 98.58, "elapsed_time": "1:36:14", "remaining_time": "0:01:22", "throughput": 4248.34, "total_tokens": 24533952}
7544
+ {"current_steps": 37625, "total_steps": 38160, "loss": 0.4091, "lr": 6.008700791502175e-07, "epoch": 19.719601677148848, "percentage": 98.6, "elapsed_time": "1:36:15", "remaining_time": "0:01:22", "throughput": 4248.37, "total_tokens": 24537152}
7545
+ {"current_steps": 37630, "total_steps": 38160, "loss": 0.2973, "lr": 5.8971429701421e-07, "epoch": 19.72222222222222, "percentage": 98.61, "elapsed_time": "1:36:16", "remaining_time": "0:01:21", "throughput": 4248.34, "total_tokens": 24539776}
7546
+ {"current_steps": 37635, "total_steps": 38160, "loss": 0.4464, "lr": 5.786629858123283e-07, "epoch": 19.7248427672956, "percentage": 98.62, "elapsed_time": "1:36:17", "remaining_time": "0:01:20", "throughput": 4248.36, "total_tokens": 24542944}
7547
+ {"current_steps": 37640, "total_steps": 38160, "loss": 0.3889, "lr": 5.677161478565008e-07, "epoch": 19.72746331236897, "percentage": 98.64, "elapsed_time": "1:36:17", "remaining_time": "0:01:19", "throughput": 4248.33, "total_tokens": 24545504}
7548
+ {"current_steps": 37645, "total_steps": 38160, "loss": 0.4629, "lr": 5.56873785436618e-07, "epoch": 19.73008385744235, "percentage": 98.65, "elapsed_time": "1:36:18", "remaining_time": "0:01:19", "throughput": 4248.35, "total_tokens": 24548736}
7549
+ {"current_steps": 37650, "total_steps": 38160, "loss": 0.6219, "lr": 5.4613590082081e-07, "epoch": 19.732704402515722, "percentage": 98.66, "elapsed_time": "1:36:19", "remaining_time": "0:01:18", "throughput": 4248.39, "total_tokens": 24552000}
7550
+ {"current_steps": 37655, "total_steps": 38160, "loss": 0.376, "lr": 5.355024962552801e-07, "epoch": 19.7353249475891, "percentage": 98.68, "elapsed_time": "1:36:19", "remaining_time": "0:01:17", "throughput": 4248.47, "total_tokens": 24555968}
7551
+ {"current_steps": 37660, "total_steps": 38160, "loss": 0.4779, "lr": 5.249735739644157e-07, "epoch": 19.737945492662472, "percentage": 98.69, "elapsed_time": "1:36:20", "remaining_time": "0:01:16", "throughput": 4248.5, "total_tokens": 24559104}
7552
+ {"current_steps": 37665, "total_steps": 38160, "loss": 0.4605, "lr": 5.145491361508436e-07, "epoch": 19.74056603773585, "percentage": 98.7, "elapsed_time": "1:36:21", "remaining_time": "0:01:15", "throughput": 4248.49, "total_tokens": 24561824}
7553
+ {"current_steps": 37670, "total_steps": 38160, "loss": 0.3957, "lr": 5.042291849950975e-07, "epoch": 19.743186582809223, "percentage": 98.72, "elapsed_time": "1:36:22", "remaining_time": "0:01:15", "throughput": 4248.5, "total_tokens": 24564864}
7554
+ {"current_steps": 37675, "total_steps": 38160, "loss": 0.3753, "lr": 4.940137226560615e-07, "epoch": 19.7458071278826, "percentage": 98.73, "elapsed_time": "1:36:22", "remaining_time": "0:01:14", "throughput": 4248.54, "total_tokens": 24568224}
7555
+ {"current_steps": 37680, "total_steps": 38160, "loss": 0.4078, "lr": 4.839027512706928e-07, "epoch": 19.748427672955973, "percentage": 98.74, "elapsed_time": "1:36:23", "remaining_time": "0:01:13", "throughput": 4248.72, "total_tokens": 24573312}
7556
+ {"current_steps": 37685, "total_steps": 38160, "loss": 0.3993, "lr": 4.7389627295407743e-07, "epoch": 19.75104821802935, "percentage": 98.76, "elapsed_time": "1:36:24", "remaining_time": "0:01:12", "throughput": 4248.8, "total_tokens": 24577248}
7557
+ {"current_steps": 37690, "total_steps": 38160, "loss": 0.3869, "lr": 4.6399428979948534e-07, "epoch": 19.753668763102727, "percentage": 98.77, "elapsed_time": "1:36:25", "remaining_time": "0:01:12", "throughput": 4248.83, "total_tokens": 24580544}
7558
+ {"current_steps": 37695, "total_steps": 38160, "loss": 0.4324, "lr": 4.541968038782596e-07, "epoch": 19.7562893081761, "percentage": 98.78, "elapsed_time": "1:36:25", "remaining_time": "0:01:11", "throughput": 4248.79, "total_tokens": 24582944}
7559
+ {"current_steps": 37700, "total_steps": 38160, "loss": 0.5885, "lr": 4.445038172399829e-07, "epoch": 19.758909853249477, "percentage": 98.79, "elapsed_time": "1:36:26", "remaining_time": "0:01:10", "throughput": 4248.78, "total_tokens": 24585728}
7560
+ {"current_steps": 37705, "total_steps": 38160, "loss": 0.4863, "lr": 4.3491533191225563e-07, "epoch": 19.76153039832285, "percentage": 98.81, "elapsed_time": "1:36:27", "remaining_time": "0:01:09", "throughput": 4248.78, "total_tokens": 24588640}
7561
+ {"current_steps": 37710, "total_steps": 38160, "loss": 0.4548, "lr": 4.254313499009177e-07, "epoch": 19.764150943396228, "percentage": 98.82, "elapsed_time": "1:36:27", "remaining_time": "0:01:09", "throughput": 4248.82, "total_tokens": 24592064}
7562
+ {"current_steps": 37715, "total_steps": 38160, "loss": 0.3957, "lr": 4.1605187318982664e-07, "epoch": 19.7667714884696, "percentage": 98.83, "elapsed_time": "1:36:29", "remaining_time": "0:01:08", "throughput": 4249.08, "total_tokens": 24598944}
7563
+ {"current_steps": 37720, "total_steps": 38160, "loss": 0.3797, "lr": 4.067769037411906e-07, "epoch": 19.769392033542978, "percentage": 98.85, "elapsed_time": "1:36:29", "remaining_time": "0:01:07", "throughput": 4249.02, "total_tokens": 24601152}
7564
+ {"current_steps": 37725, "total_steps": 38160, "loss": 0.4028, "lr": 3.9760644349517984e-07, "epoch": 19.77201257861635, "percentage": 98.86, "elapsed_time": "1:36:30", "remaining_time": "0:01:06", "throughput": 4249.01, "total_tokens": 24603904}
7565
+ {"current_steps": 37730, "total_steps": 38160, "loss": 0.3788, "lr": 3.885404943700932e-07, "epoch": 19.77463312368973, "percentage": 98.87, "elapsed_time": "1:36:31", "remaining_time": "0:01:05", "throughput": 4248.97, "total_tokens": 24606240}
7566
+ {"current_steps": 37735, "total_steps": 38160, "loss": 0.445, "lr": 3.795790582624692e-07, "epoch": 19.7772536687631, "percentage": 98.89, "elapsed_time": "1:36:31", "remaining_time": "0:01:05", "throughput": 4248.97, "total_tokens": 24609088}
7567
+ {"current_steps": 37740, "total_steps": 38160, "loss": 0.3871, "lr": 3.707221370469749e-07, "epoch": 19.77987421383648, "percentage": 98.9, "elapsed_time": "1:36:32", "remaining_time": "0:01:04", "throughput": 4249.0, "total_tokens": 24612320}
7568
+ {"current_steps": 37745, "total_steps": 38160, "loss": 0.4046, "lr": 3.6196973257629494e-07, "epoch": 19.782494758909852, "percentage": 98.91, "elapsed_time": "1:36:33", "remaining_time": "0:01:03", "throughput": 4249.19, "total_tokens": 24617664}
7569
+ {"current_steps": 37750, "total_steps": 38160, "loss": 0.3933, "lr": 3.533218466813537e-07, "epoch": 19.78511530398323, "percentage": 98.93, "elapsed_time": "1:36:34", "remaining_time": "0:01:02", "throughput": 4249.34, "total_tokens": 24622304}
7570
+ {"current_steps": 37755, "total_steps": 38160, "loss": 0.3953, "lr": 3.447784811712595e-07, "epoch": 19.787735849056602, "percentage": 98.94, "elapsed_time": "1:36:35", "remaining_time": "0:01:02", "throughput": 4249.33, "total_tokens": 24625088}
7571
+ {"current_steps": 37760, "total_steps": 38160, "loss": 0.4197, "lr": 3.363396378331385e-07, "epoch": 19.79035639412998, "percentage": 98.95, "elapsed_time": "1:36:35", "remaining_time": "0:01:01", "throughput": 4249.36, "total_tokens": 24628544}
7572
+ {"current_steps": 37765, "total_steps": 38160, "loss": 0.5636, "lr": 3.280053184323006e-07, "epoch": 19.792976939203353, "percentage": 98.96, "elapsed_time": "1:36:36", "remaining_time": "0:01:00", "throughput": 4249.4, "total_tokens": 24631776}
7573
+ {"current_steps": 37770, "total_steps": 38160, "loss": 0.4295, "lr": 3.1977552471218476e-07, "epoch": 19.79559748427673, "percentage": 98.98, "elapsed_time": "1:36:37", "remaining_time": "0:00:59", "throughput": 4249.43, "total_tokens": 24634976}
7574
+ {"current_steps": 37775, "total_steps": 38160, "loss": 0.49, "lr": 3.116502583943581e-07, "epoch": 19.798218029350103, "percentage": 98.99, "elapsed_time": "1:36:37", "remaining_time": "0:00:59", "throughput": 4249.42, "total_tokens": 24637696}
7575
+ {"current_steps": 37780, "total_steps": 38160, "loss": 0.3671, "lr": 3.036295211785722e-07, "epoch": 19.80083857442348, "percentage": 99.0, "elapsed_time": "1:36:38", "remaining_time": "0:00:58", "throughput": 4249.44, "total_tokens": 24640864}
7576
+ {"current_steps": 37785, "total_steps": 38160, "loss": 0.2871, "lr": 2.957133147425961e-07, "epoch": 19.803459119496857, "percentage": 99.02, "elapsed_time": "1:36:39", "remaining_time": "0:00:57", "throughput": 4249.65, "total_tokens": 24646784}
7577
+ {"current_steps": 37790, "total_steps": 38160, "loss": 0.3882, "lr": 2.879016407425494e-07, "epoch": 19.80607966457023, "percentage": 99.03, "elapsed_time": "1:36:40", "remaining_time": "0:00:56", "throughput": 4249.68, "total_tokens": 24650048}
7578
+ {"current_steps": 37795, "total_steps": 38160, "loss": 0.3888, "lr": 2.8019450081240295e-07, "epoch": 19.808700209643607, "percentage": 99.04, "elapsed_time": "1:36:41", "remaining_time": "0:00:56", "throughput": 4249.74, "total_tokens": 24653728}
7579
+ {"current_steps": 37800, "total_steps": 38160, "loss": 0.3346, "lr": 2.7259189656447803e-07, "epoch": 19.81132075471698, "percentage": 99.06, "elapsed_time": "1:36:41", "remaining_time": "0:00:55", "throughput": 4249.71, "total_tokens": 24656288}
7580
+ {"current_steps": 37805, "total_steps": 38160, "loss": 0.3878, "lr": 2.650938295891692e-07, "epoch": 19.813941299790358, "percentage": 99.07, "elapsed_time": "1:36:42", "remaining_time": "0:00:54", "throughput": 4249.75, "total_tokens": 24659744}
7581
+ {"current_steps": 37810, "total_steps": 38160, "loss": 0.5245, "lr": 2.5770030145494395e-07, "epoch": 19.81656184486373, "percentage": 99.08, "elapsed_time": "1:36:43", "remaining_time": "0:00:53", "throughput": 4249.8, "total_tokens": 24663488}
7582
+ {"current_steps": 37815, "total_steps": 38160, "loss": 0.3635, "lr": 2.504113137083985e-07, "epoch": 19.819182389937108, "percentage": 99.1, "elapsed_time": "1:36:44", "remaining_time": "0:00:52", "throughput": 4249.8, "total_tokens": 24666272}
7583
+ {"current_steps": 37820, "total_steps": 38160, "loss": 0.2474, "lr": 2.4322686787442425e-07, "epoch": 19.82180293501048, "percentage": 99.11, "elapsed_time": "1:36:44", "remaining_time": "0:00:52", "throughput": 4249.89, "total_tokens": 24670400}
7584
+ {"current_steps": 37825, "total_steps": 38160, "loss": 0.3938, "lr": 2.3614696545581904e-07, "epoch": 19.82442348008386, "percentage": 99.12, "elapsed_time": "1:36:45", "remaining_time": "0:00:51", "throughput": 4249.88, "total_tokens": 24673280}
7585
+ {"current_steps": 37830, "total_steps": 38160, "loss": 0.4644, "lr": 2.2917160793367585e-07, "epoch": 19.82704402515723, "percentage": 99.14, "elapsed_time": "1:36:46", "remaining_time": "0:00:50", "throughput": 4249.9, "total_tokens": 24676320}
7586
+ {"current_steps": 37835, "total_steps": 38160, "loss": 0.3086, "lr": 2.2230079676716086e-07, "epoch": 19.82966457023061, "percentage": 99.15, "elapsed_time": "1:36:47", "remaining_time": "0:00:49", "throughput": 4250.02, "total_tokens": 24680960}
7587
+ {"current_steps": 37840, "total_steps": 38160, "loss": 0.4518, "lr": 2.1553453339356875e-07, "epoch": 19.832285115303982, "percentage": 99.16, "elapsed_time": "1:36:48", "remaining_time": "0:00:49", "throughput": 4250.17, "total_tokens": 24685792}
7588
+ {"current_steps": 37845, "total_steps": 38160, "loss": 0.3705, "lr": 2.0887281922826738e-07, "epoch": 19.83490566037736, "percentage": 99.17, "elapsed_time": "1:36:48", "remaining_time": "0:00:48", "throughput": 4250.15, "total_tokens": 24688448}
7589
+ {"current_steps": 37850, "total_steps": 38160, "loss": 0.3311, "lr": 2.023156556648642e-07, "epoch": 19.837526205450732, "percentage": 99.19, "elapsed_time": "1:36:49", "remaining_time": "0:00:47", "throughput": 4250.17, "total_tokens": 24691552}
7590
+ {"current_steps": 37855, "total_steps": 38160, "loss": 0.3933, "lr": 1.9586304407503975e-07, "epoch": 19.84014675052411, "percentage": 99.2, "elapsed_time": "1:36:50", "remaining_time": "0:00:46", "throughput": 4250.17, "total_tokens": 24694368}
7591
+ {"current_steps": 37860, "total_steps": 38160, "loss": 0.4543, "lr": 1.8951498580860315e-07, "epoch": 19.842767295597483, "percentage": 99.21, "elapsed_time": "1:36:50", "remaining_time": "0:00:46", "throughput": 4250.11, "total_tokens": 24696608}
7592
+ {"current_steps": 37865, "total_steps": 38160, "loss": 0.3981, "lr": 1.832714821934922e-07, "epoch": 19.84538784067086, "percentage": 99.23, "elapsed_time": "1:36:51", "remaining_time": "0:00:45", "throughput": 4250.14, "total_tokens": 24699872}
7593
+ {"current_steps": 37870, "total_steps": 38160, "loss": 0.3778, "lr": 1.7713253453577328e-07, "epoch": 19.848008385744233, "percentage": 99.24, "elapsed_time": "1:36:52", "remaining_time": "0:00:44", "throughput": 4250.3, "total_tokens": 24704608}
7594
+ {"current_steps": 37875, "total_steps": 38160, "loss": 0.4473, "lr": 1.7109814411964132e-07, "epoch": 19.85062893081761, "percentage": 99.25, "elapsed_time": "1:36:53", "remaining_time": "0:00:43", "throughput": 4250.38, "total_tokens": 24708544}
7595
+ {"current_steps": 37880, "total_steps": 38160, "loss": 0.4523, "lr": 1.651683122074754e-07, "epoch": 19.853249475890987, "percentage": 99.27, "elapsed_time": "1:36:53", "remaining_time": "0:00:42", "throughput": 4250.34, "total_tokens": 24710880}
7596
+ {"current_steps": 37885, "total_steps": 38160, "loss": 0.3786, "lr": 1.5934304003961675e-07, "epoch": 19.85587002096436, "percentage": 99.28, "elapsed_time": "1:36:54", "remaining_time": "0:00:42", "throughput": 4250.44, "total_tokens": 24715008}
7597
+ {"current_steps": 37890, "total_steps": 38160, "loss": 0.4264, "lr": 1.5362232883475713e-07, "epoch": 19.858490566037737, "percentage": 99.29, "elapsed_time": "1:36:55", "remaining_time": "0:00:41", "throughput": 4250.46, "total_tokens": 24718240}
7598
+ {"current_steps": 37895, "total_steps": 38160, "loss": 0.3491, "lr": 1.4800617978949492e-07, "epoch": 19.86111111111111, "percentage": 99.31, "elapsed_time": "1:36:56", "remaining_time": "0:00:40", "throughput": 4250.43, "total_tokens": 24720800}
7599
+ {"current_steps": 37900, "total_steps": 38160, "loss": 0.4266, "lr": 1.424945940787792e-07, "epoch": 19.863731656184488, "percentage": 99.32, "elapsed_time": "1:36:56", "remaining_time": "0:00:39", "throughput": 4250.4, "total_tokens": 24723392}
7600
+ {"current_steps": 37905, "total_steps": 38160, "loss": 0.4186, "lr": 1.3708757285552098e-07, "epoch": 19.86635220125786, "percentage": 99.33, "elapsed_time": "1:36:57", "remaining_time": "0:00:39", "throughput": 4250.37, "total_tokens": 24725792}
7601
+ {"current_steps": 37910, "total_steps": 38160, "loss": 0.3973, "lr": 1.3178511725076004e-07, "epoch": 19.868972746331238, "percentage": 99.34, "elapsed_time": "1:36:58", "remaining_time": "0:00:38", "throughput": 4250.37, "total_tokens": 24728672}
7602
+ {"current_steps": 37915, "total_steps": 38160, "loss": 0.4687, "lr": 1.265872283738312e-07, "epoch": 19.87159329140461, "percentage": 99.36, "elapsed_time": "1:36:58", "remaining_time": "0:00:37", "throughput": 4250.43, "total_tokens": 24732384}
7603
+ {"current_steps": 37920, "total_steps": 38160, "loss": 0.389, "lr": 1.2149390731192033e-07, "epoch": 19.87421383647799, "percentage": 99.37, "elapsed_time": "1:36:59", "remaining_time": "0:00:36", "throughput": 4250.47, "total_tokens": 24735744}
7604
+ {"current_steps": 37925, "total_steps": 38160, "loss": 0.4022, "lr": 1.1650515513061955e-07, "epoch": 19.87683438155136, "percentage": 99.38, "elapsed_time": "1:37:00", "remaining_time": "0:00:36", "throughput": 4250.45, "total_tokens": 24738496}
7605
+ {"current_steps": 37930, "total_steps": 38160, "loss": 0.3821, "lr": 1.1162097287342743e-07, "epoch": 19.87945492662474, "percentage": 99.4, "elapsed_time": "1:37:00", "remaining_time": "0:00:35", "throughput": 4250.51, "total_tokens": 24742080}
7606
+ {"current_steps": 37935, "total_steps": 38160, "loss": 0.3836, "lr": 1.0684136156213775e-07, "epoch": 19.882075471698112, "percentage": 99.41, "elapsed_time": "1:37:01", "remaining_time": "0:00:34", "throughput": 4250.48, "total_tokens": 24744512}
7607
+ {"current_steps": 37940, "total_steps": 38160, "loss": 0.3552, "lr": 1.0216632219650634e-07, "epoch": 19.88469601677149, "percentage": 99.42, "elapsed_time": "1:37:02", "remaining_time": "0:00:33", "throughput": 4250.55, "total_tokens": 24748224}
7608
+ {"current_steps": 37945, "total_steps": 38160, "loss": 0.5227, "lr": 9.759585575458418e-08, "epoch": 19.887316561844862, "percentage": 99.44, "elapsed_time": "1:37:03", "remaining_time": "0:00:32", "throughput": 4250.56, "total_tokens": 24751232}
7609
+ {"current_steps": 37950, "total_steps": 38160, "loss": 0.3906, "lr": 9.312996319238432e-08, "epoch": 19.88993710691824, "percentage": 99.45, "elapsed_time": "1:37:03", "remaining_time": "0:00:32", "throughput": 4250.57, "total_tokens": 24754208}
7610
+ {"current_steps": 37955, "total_steps": 38160, "loss": 0.414, "lr": 8.876864544421493e-08, "epoch": 19.892557651991613, "percentage": 99.46, "elapsed_time": "1:37:04", "remaining_time": "0:00:31", "throughput": 4250.6, "total_tokens": 24757440}
7611
+ {"current_steps": 37960, "total_steps": 38160, "loss": 0.4331, "lr": 8.451190342229077e-08, "epoch": 19.89517819706499, "percentage": 99.48, "elapsed_time": "1:37:05", "remaining_time": "0:00:30", "throughput": 4250.56, "total_tokens": 24759808}
7612
+ {"current_steps": 37965, "total_steps": 38160, "loss": 0.3844, "lr": 8.035973801717722e-08, "epoch": 19.897798742138363, "percentage": 99.49, "elapsed_time": "1:37:05", "remaining_time": "0:00:29", "throughput": 4250.5, "total_tokens": 24761952}
7613
+ {"current_steps": 37970, "total_steps": 38160, "loss": 0.5027, "lr": 7.631215009740178e-08, "epoch": 19.90041928721174, "percentage": 99.5, "elapsed_time": "1:37:06", "remaining_time": "0:00:29", "throughput": 4250.54, "total_tokens": 24765280}
7614
+ {"current_steps": 37975, "total_steps": 38160, "loss": 0.4227, "lr": 7.236914050973153e-08, "epoch": 19.903039832285117, "percentage": 99.52, "elapsed_time": "1:37:07", "remaining_time": "0:00:28", "throughput": 4250.55, "total_tokens": 24768320}
7615
+ {"current_steps": 37980, "total_steps": 38160, "loss": 0.4272, "lr": 6.853071007895117e-08, "epoch": 19.90566037735849, "percentage": 99.53, "elapsed_time": "1:37:07", "remaining_time": "0:00:27", "throughput": 4250.53, "total_tokens": 24770912}
7616
+ {"current_steps": 37985, "total_steps": 38160, "loss": 0.5197, "lr": 6.479685960797399e-08, "epoch": 19.908280922431867, "percentage": 99.54, "elapsed_time": "1:37:08", "remaining_time": "0:00:26", "throughput": 4250.56, "total_tokens": 24774176}
7617
+ {"current_steps": 37990, "total_steps": 38160, "loss": 0.4546, "lr": 6.116758987800841e-08, "epoch": 19.91090146750524, "percentage": 99.55, "elapsed_time": "1:37:09", "remaining_time": "0:00:26", "throughput": 4250.56, "total_tokens": 24777120}
7618
+ {"current_steps": 37995, "total_steps": 38160, "loss": 0.3814, "lr": 5.7642901648113924e-08, "epoch": 19.913522012578618, "percentage": 99.57, "elapsed_time": "1:37:09", "remaining_time": "0:00:25", "throughput": 4250.54, "total_tokens": 24779712}
7619
+ {"current_steps": 38000, "total_steps": 38160, "loss": 0.4565, "lr": 5.422279565570065e-08, "epoch": 19.91614255765199, "percentage": 99.58, "elapsed_time": "1:37:10", "remaining_time": "0:00:24", "throughput": 4250.59, "total_tokens": 24783200}
7620
+ {"current_steps": 38005, "total_steps": 38160, "loss": 0.533, "lr": 5.090727261619632e-08, "epoch": 19.918763102725368, "percentage": 99.59, "elapsed_time": "1:37:11", "remaining_time": "0:00:23", "throughput": 4250.63, "total_tokens": 24786592}
7621
+ {"current_steps": 38010, "total_steps": 38160, "loss": 0.3519, "lr": 4.7696333223212765e-08, "epoch": 19.92138364779874, "percentage": 99.61, "elapsed_time": "1:37:11", "remaining_time": "0:00:23", "throughput": 4250.64, "total_tokens": 24789664}
7622
+ {"current_steps": 38015, "total_steps": 38160, "loss": 0.4375, "lr": 4.4589978148323884e-08, "epoch": 19.92400419287212, "percentage": 99.62, "elapsed_time": "1:37:12", "remaining_time": "0:00:22", "throughput": 4250.62, "total_tokens": 24792288}
7623
+ {"current_steps": 38020, "total_steps": 38160, "loss": 0.3561, "lr": 4.1588208041454244e-08, "epoch": 19.92662473794549, "percentage": 99.63, "elapsed_time": "1:37:13", "remaining_time": "0:00:21", "throughput": 4250.68, "total_tokens": 24796000}
7624
+ {"current_steps": 38025, "total_steps": 38160, "loss": 0.3805, "lr": 3.8691023530545985e-08, "epoch": 19.92924528301887, "percentage": 99.65, "elapsed_time": "1:37:14", "remaining_time": "0:00:20", "throughput": 4250.69, "total_tokens": 24798976}
7625
+ {"current_steps": 38030, "total_steps": 38160, "loss": 0.3813, "lr": 3.589842522155884e-08, "epoch": 19.931865828092242, "percentage": 99.66, "elapsed_time": "1:37:14", "remaining_time": "0:00:19", "throughput": 4250.68, "total_tokens": 24801760}
7626
+ {"current_steps": 38035, "total_steps": 38160, "loss": 0.4208, "lr": 3.321041369874767e-08, "epoch": 19.93448637316562, "percentage": 99.67, "elapsed_time": "1:37:15", "remaining_time": "0:00:19", "throughput": 4250.74, "total_tokens": 24805376}
7627
+ {"current_steps": 38040, "total_steps": 38160, "loss": 0.4813, "lr": 3.0626989524384916e-08, "epoch": 19.937106918238992, "percentage": 99.69, "elapsed_time": "1:37:16", "remaining_time": "0:00:18", "throughput": 4250.82, "total_tokens": 24809440}
7628
+ {"current_steps": 38045, "total_steps": 38160, "loss": 0.4518, "lr": 2.8148153238927167e-08, "epoch": 19.93972746331237, "percentage": 99.7, "elapsed_time": "1:37:17", "remaining_time": "0:00:17", "throughput": 4250.91, "total_tokens": 24813472}
7629
+ {"current_steps": 38050, "total_steps": 38160, "loss": 0.4683, "lr": 2.5773905360904072e-08, "epoch": 19.942348008385743, "percentage": 99.71, "elapsed_time": "1:37:17", "remaining_time": "0:00:16", "throughput": 4250.93, "total_tokens": 24816608}
7630
+ {"current_steps": 38055, "total_steps": 38160, "loss": 0.4927, "lr": 2.3504246386918392e-08, "epoch": 19.94496855345912, "percentage": 99.72, "elapsed_time": "1:37:18", "remaining_time": "0:00:16", "throughput": 4250.95, "total_tokens": 24819776}
7631
+ {"current_steps": 38060, "total_steps": 38160, "loss": 0.3691, "lr": 2.133917679186803e-08, "epoch": 19.947589098532493, "percentage": 99.74, "elapsed_time": "1:37:19", "remaining_time": "0:00:15", "throughput": 4250.94, "total_tokens": 24822560}
7632
+ {"current_steps": 38065, "total_steps": 38160, "loss": 0.3015, "lr": 1.9278697028557447e-08, "epoch": 19.95020964360587, "percentage": 99.75, "elapsed_time": "1:37:20", "remaining_time": "0:00:14", "throughput": 4250.94, "total_tokens": 24825600}
7633
+ {"current_steps": 38070, "total_steps": 38160, "loss": 0.4665, "lr": 1.7322807528086238e-08, "epoch": 19.952830188679247, "percentage": 99.76, "elapsed_time": "1:37:20", "remaining_time": "0:00:13", "throughput": 4250.92, "total_tokens": 24828224}
7634
+ {"current_steps": 38075, "total_steps": 38160, "loss": 0.3996, "lr": 1.547150869957159e-08, "epoch": 19.95545073375262, "percentage": 99.78, "elapsed_time": "1:37:21", "remaining_time": "0:00:13", "throughput": 4250.9, "total_tokens": 24830848}
7635
+ {"current_steps": 38080, "total_steps": 38160, "loss": 0.4331, "lr": 1.3724800930314806e-08, "epoch": 19.958071278825997, "percentage": 99.79, "elapsed_time": "1:37:22", "remaining_time": "0:00:12", "throughput": 4250.94, "total_tokens": 24834304}
7636
+ {"current_steps": 38085, "total_steps": 38160, "loss": 0.3117, "lr": 1.2082684585634773e-08, "epoch": 19.96069182389937, "percentage": 99.8, "elapsed_time": "1:37:22", "remaining_time": "0:00:11", "throughput": 4251.02, "total_tokens": 24838112}
7637
+ {"current_steps": 38090, "total_steps": 38160, "loss": 0.3964, "lr": 1.0545160009145516e-08, "epoch": 19.963312368972748, "percentage": 99.82, "elapsed_time": "1:37:23", "remaining_time": "0:00:10", "throughput": 4251.12, "total_tokens": 24842240}
7638
+ {"current_steps": 38095, "total_steps": 38160, "loss": 0.3396, "lr": 9.112227522423133e-09, "epoch": 19.96593291404612, "percentage": 99.83, "elapsed_time": "1:37:24", "remaining_time": "0:00:09", "throughput": 4251.17, "total_tokens": 24845824}
7639
+ {"current_steps": 38100, "total_steps": 38160, "loss": 0.5092, "lr": 7.783887425172331e-09, "epoch": 19.968553459119498, "percentage": 99.84, "elapsed_time": "1:37:25", "remaining_time": "0:00:09", "throughput": 4251.18, "total_tokens": 24848704}
7640
+ {"current_steps": 38105, "total_steps": 38160, "loss": 0.2943, "lr": 6.560139995392955e-09, "epoch": 19.97117400419287, "percentage": 99.86, "elapsed_time": "1:37:26", "remaining_time": "0:00:08", "throughput": 4251.29, "total_tokens": 24853120}
7641
+ {"current_steps": 38110, "total_steps": 38160, "loss": 0.5035, "lr": 5.440985488935901e-09, "epoch": 19.97379454926625, "percentage": 99.87, "elapsed_time": "1:37:26", "remaining_time": "0:00:07", "throughput": 4251.34, "total_tokens": 24856800}
7642
+ {"current_steps": 38115, "total_steps": 38160, "loss": 0.4863, "lr": 4.426424140058227e-09, "epoch": 19.97641509433962, "percentage": 99.88, "elapsed_time": "1:37:27", "remaining_time": "0:00:06", "throughput": 4251.31, "total_tokens": 24859392}
7643
+ {"current_steps": 38120, "total_steps": 38160, "loss": 0.4299, "lr": 3.5164561608680424e-09, "epoch": 19.979035639413, "percentage": 99.9, "elapsed_time": "1:37:28", "remaining_time": "0:00:06", "throughput": 4251.4, "total_tokens": 24863328}
7644
+ {"current_steps": 38125, "total_steps": 38160, "loss": 0.3743, "lr": 2.7110817417685953e-09, "epoch": 19.981656184486372, "percentage": 99.91, "elapsed_time": "1:37:28", "remaining_time": "0:00:05", "throughput": 4251.42, "total_tokens": 24866496}
7645
+ {"current_steps": 38130, "total_steps": 38160, "loss": 0.3776, "lr": 2.010301051291741e-09, "epoch": 19.98427672955975, "percentage": 99.92, "elapsed_time": "1:37:29", "remaining_time": "0:00:04", "throughput": 4251.57, "total_tokens": 24871328}
7646
+ {"current_steps": 38135, "total_steps": 38160, "loss": 0.3589, "lr": 1.4141142359314074e-09, "epoch": 19.986897274633122, "percentage": 99.93, "elapsed_time": "1:37:30", "remaining_time": "0:00:03", "throughput": 4251.57, "total_tokens": 24874336}
7647
+ {"current_steps": 38140, "total_steps": 38160, "loss": 0.3865, "lr": 9.22521420476663e-10, "epoch": 19.9895178197065, "percentage": 99.95, "elapsed_time": "1:37:31", "remaining_time": "0:00:03", "throughput": 4251.55, "total_tokens": 24877024}
7648
+ {"current_steps": 38145, "total_steps": 38160, "loss": 0.4515, "lr": 5.355227077341596e-10, "epoch": 19.992138364779873, "percentage": 99.96, "elapsed_time": "1:37:31", "remaining_time": "0:00:02", "throughput": 4251.56, "total_tokens": 24880096}
7649
+ {"current_steps": 38150, "total_steps": 38160, "loss": 0.4372, "lr": 2.5311817863915566e-10, "epoch": 19.99475890985325, "percentage": 99.97, "elapsed_time": "1:37:32", "remaining_time": "0:00:01", "throughput": 4251.57, "total_tokens": 24883200}
7650
+ {"current_steps": 38155, "total_steps": 38160, "loss": 0.4077, "lr": 7.53078923110273e-11, "epoch": 19.997379454926623, "percentage": 99.99, "elapsed_time": "1:37:33", "remaining_time": "0:00:00", "throughput": 4251.54, "total_tokens": 24885664}
7651
+ {"current_steps": 38160, "total_steps": 38160, "loss": 0.301, "lr": 2.0918859422458526e-12, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "1:37:34", "remaining_time": "0:00:00", "throughput": 4251.37, "total_tokens": 24887720}
7652
+ {"current_steps": 38160, "total_steps": 38160, "eval_loss": 0.4668559730052948, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "1:37:47", "remaining_time": "0:00:00", "throughput": 4241.53, "total_tokens": 24887720}
7653
+ {"current_steps": 38160, "total_steps": 38160, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "1:37:49", "remaining_time": "0:00:00", "throughput": 4240.4, "total_tokens": 24887720}