Auto upload zain 2026-08-19T17:15:02.582332 (part 2)

zain/Activation/out/mlp-linear-3L_run/checkpoint-900/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:177c32ccf97ffdbb828562681f87c484ed5050c885321afba4aa8a2d44d9c65c
+oid sha256:6210521539864a26a8dbb7e8e762ead750a9aebb991577b3ce8dbefe87900cef
 size 2036216

zain/Activation/out/mlp-linear-3L_run/checkpoint-900/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc5e0afd8d9ef1b88301ff5d80619f0e173469518f8ba83f1f3dc54a070bf28
+oid sha256:3bfd43e5934f5d24798fd85b66fe3d9a69b05a1e299d72f2187c5cb93c96eca8
 size 4089360

zain/Activation/out/mlp-linear-3L_run/checkpoint-900/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7af41faf99717dd67953037b442647180e36de84b90ea94fe9ee61f85ee5881
+oid sha256:819e7677327ec819a829273ee6bf375a38913eb519826c73009d0dd3825f5480
 size 1064

zain/Activation/out/mlp-linear-3L_run/checkpoint-900/trainer_state.json

@@ -11,389 +11,389 @@
   "log_history": [
     {
       "epoch": 0.0016852039096730705,
-      "grad_norm": 1.453125,
-      "learning_rate": 6.65e-05,
-      "loss": 8.268168640136718,
+      "grad_norm": 1.28125,
+      "learning_rate": 9.5e-05,
+      "loss": 8.230884552001953,
       "step": 20
     },
     {
       "epoch": 0.003370407819346141,
-      "grad_norm": 1.2421875,
-      "learning_rate": 0.0001365,
-      "loss": 7.894985961914062,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.00019500000000000002,
+      "loss": 7.774678802490234,
       "step": 40
     },
     {
       "epoch": 0.005055611729019211,
-      "grad_norm": 1.1953125,
-      "learning_rate": 0.00020649999999999998,
-      "loss": 7.41226806640625,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.000295,
+      "loss": 7.161412048339844,
       "step": 60
     },
     {
       "epoch": 0.006740815638692282,
-      "grad_norm": 1.125,
-      "learning_rate": 0.0002765,
-      "loss": 6.823537445068359,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.000395,
+      "loss": 6.473944091796875,
       "step": 80
     },
     {
       "epoch": 0.008426019548365353,
-      "grad_norm": 3.671875,
-      "learning_rate": 0.0003465,
-      "loss": 6.273388671875,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.000495,
+      "loss": 5.909336853027344,
       "step": 100
     },
     {
       "epoch": 0.008426019548365353,
-      "eval_loss": 6.012144565582275,
-      "eval_runtime": 7.5963,
-      "eval_samples_per_second": 1254.167,
-      "eval_steps_per_second": 0.922,
+      "eval_loss": 5.663336753845215,
+      "eval_runtime": 7.566,
+      "eval_samples_per_second": 1259.189,
+      "eval_steps_per_second": 0.925,
       "step": 100
     },
     {
       "epoch": 0.010111223458038422,
-      "grad_norm": 1.03125,
-      "learning_rate": 0.0004165,
-      "loss": 5.821277236938476,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.0005949999999999999,
+      "loss": 5.44867172241211,
       "step": 120
     },
     {
       "epoch": 0.011796427367711493,
-      "grad_norm": 1.3359375,
-      "learning_rate": 0.00048649999999999995,
-      "loss": 5.4205375671386715,
+      "grad_norm": 1.671875,
+      "learning_rate": 0.000695,
+      "loss": 5.003098678588867,
       "step": 140
     },
     {
       "epoch": 0.013481631277384564,
-      "grad_norm": 1.046875,
-      "learning_rate": 0.0005565,
-      "loss": 5.045843505859375,
+      "grad_norm": 0.98046875,
+      "learning_rate": 0.000795,
+      "loss": 4.667464065551758,
       "step": 160
     },
     {
       "epoch": 0.015166835187057633,
-      "grad_norm": 1.515625,
-      "learning_rate": 0.0006265,
-      "loss": 4.759759902954102,
+      "grad_norm": 0.72265625,
+      "learning_rate": 0.0008950000000000001,
+      "loss": 4.417913818359375,
       "step": 180
     },
     {
       "epoch": 0.016852039096730706,
-      "grad_norm": 1.0078125,
-      "learning_rate": 0.0006965,
-      "loss": 4.546141815185547,
+      "grad_norm": 1.4140625,
+      "learning_rate": 0.000995,
+      "loss": 4.196286392211914,
       "step": 200
     },
     {
       "epoch": 0.016852039096730706,
-      "eval_loss": 4.442856311798096,
-      "eval_runtime": 7.4239,
-      "eval_samples_per_second": 1283.293,
-      "eval_steps_per_second": 0.943,
+      "eval_loss": 4.103216648101807,
+      "eval_runtime": 7.6083,
+      "eval_samples_per_second": 1252.178,
+      "eval_steps_per_second": 0.92,
       "step": 200
     },
     {
       "epoch": 0.018537243006403775,
-      "grad_norm": 0.89453125,
-      "learning_rate": 0.0007,
-      "loss": 4.347104263305664,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.001,
+      "loss": 4.029207611083985,
       "step": 220
     },
     {
       "epoch": 0.020222446916076844,
-      "grad_norm": 0.8125,
-      "learning_rate": 0.0007,
-      "loss": 4.1778076171875,
+      "grad_norm": 0.90625,
+      "learning_rate": 0.001,
+      "loss": 3.895578384399414,
       "step": 240
     },
     {
       "epoch": 0.021907650825749917,
-      "grad_norm": 0.8984375,
-      "learning_rate": 0.0007,
-      "loss": 4.0267986297607425,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.001,
+      "loss": 3.7797645568847655,
       "step": 260
     },
     {
       "epoch": 0.023592854735422986,
-      "grad_norm": 1.0234375,
-      "learning_rate": 0.0007,
-      "loss": 3.9356033325195314,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.001,
+      "loss": 3.693258285522461,
       "step": 280
     },
     {
       "epoch": 0.025278058645096056,
-      "grad_norm": 2.25,
-      "learning_rate": 0.0007,
-      "loss": 3.8599246978759765,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.001,
+      "loss": 3.6289249420166017,
       "step": 300
     },
     {
       "epoch": 0.025278058645096056,
-      "eval_loss": 3.8334245681762695,
-      "eval_runtime": 7.4769,
-      "eval_samples_per_second": 1274.187,
-      "eval_steps_per_second": 0.936,
+      "eval_loss": 3.5979104042053223,
+      "eval_runtime": 7.4719,
+      "eval_samples_per_second": 1275.037,
+      "eval_steps_per_second": 0.937,
       "step": 300
     },
     {
       "epoch": 0.026963262554769128,
-      "grad_norm": 0.87109375,
-      "learning_rate": 0.0007,
-      "loss": 3.7748882293701174,
+      "grad_norm": 0.9609375,
+      "learning_rate": 0.001,
+      "loss": 3.5430423736572267,
       "step": 320
     },
     {
       "epoch": 0.028648466464442197,
-      "grad_norm": 1.015625,
-      "learning_rate": 0.0007,
-      "loss": 3.724995422363281,
+      "grad_norm": 0.953125,
+      "learning_rate": 0.001,
+      "loss": 3.499795150756836,
       "step": 340
     },
     {
       "epoch": 0.030333670374115267,
-      "grad_norm": 0.9765625,
-      "learning_rate": 0.0007,
-      "loss": 3.6759109497070312,
+      "grad_norm": 1.0234375,
+      "learning_rate": 0.001,
+      "loss": 3.4527099609375,
       "step": 360
     },
     {
       "epoch": 0.032018874283788336,
-      "grad_norm": 1.09375,
-      "learning_rate": 0.0007,
-      "loss": 3.6255836486816406,
+      "grad_norm": 0.9453125,
+      "learning_rate": 0.001,
+      "loss": 3.409439468383789,
       "step": 380
     },
     {
       "epoch": 0.03370407819346141,
-      "grad_norm": 1.8203125,
-      "learning_rate": 0.0007,
-      "loss": 3.575853729248047,
+      "grad_norm": 1.296875,
+      "learning_rate": 0.001,
+      "loss": 3.360205078125,
       "step": 400
     },
     {
       "epoch": 0.03370407819346141,
-      "eval_loss": 3.558598279953003,
-      "eval_runtime": 7.3884,
-      "eval_samples_per_second": 1289.451,
-      "eval_steps_per_second": 0.947,
+      "eval_loss": 3.3530941009521484,
+      "eval_runtime": 7.5215,
+      "eval_samples_per_second": 1266.63,
+      "eval_steps_per_second": 0.931,
       "step": 400
     },
     {
       "epoch": 0.03538928210313448,
-      "grad_norm": 1.046875,
-      "learning_rate": 0.0007,
-      "loss": 3.5410614013671875,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.001,
+      "loss": 3.321756362915039,
       "step": 420
     },
     {
       "epoch": 0.03707448601280755,
-      "grad_norm": 0.8125,
-      "learning_rate": 0.0007,
-      "loss": 3.4953586578369142,
+      "grad_norm": 0.73828125,
+      "learning_rate": 0.001,
+      "loss": 3.2804222106933594,
       "step": 440
     },
     {
       "epoch": 0.03875968992248062,
-      "grad_norm": 1.171875,
-      "learning_rate": 0.0007,
-      "loss": 3.4645240783691404,
+      "grad_norm": 0.796875,
+      "learning_rate": 0.001,
+      "loss": 3.2532787322998047,
       "step": 460
     },
     {
       "epoch": 0.04044489383215369,
-      "grad_norm": 0.984375,
-      "learning_rate": 0.0007,
-      "loss": 3.43664665222168,
+      "grad_norm": 0.953125,
+      "learning_rate": 0.001,
+      "loss": 3.22874755859375,
       "step": 480
     },
     {
       "epoch": 0.04213009774182676,
-      "grad_norm": 0.73828125,
-      "learning_rate": 0.0007,
-      "loss": 3.398360824584961,
+      "grad_norm": 0.890625,
+      "learning_rate": 0.001,
+      "loss": 3.197536659240723,
       "step": 500
     },
     {
       "epoch": 0.04213009774182676,
-      "eval_loss": 3.38920259475708,
-      "eval_runtime": 7.4934,
-      "eval_samples_per_second": 1271.379,
+      "eval_loss": 3.1904470920562744,
+      "eval_runtime": 7.4922,
+      "eval_samples_per_second": 1271.584,
       "eval_steps_per_second": 0.934,
       "step": 500
     },
     {
       "epoch": 0.043815301651499834,
-      "grad_norm": 0.9921875,
-      "learning_rate": 0.0007,
-      "loss": 3.3788318634033203,
+      "grad_norm": 0.96875,
+      "learning_rate": 0.001,
+      "loss": 3.184717559814453,
       "step": 520
     },
     {
       "epoch": 0.0455005055611729,
-      "grad_norm": 1.1015625,
-      "learning_rate": 0.0007,
-      "loss": 3.337381362915039,
+      "grad_norm": 0.828125,
+      "learning_rate": 0.001,
+      "loss": 3.144283103942871,
       "step": 540
     },
     {
       "epoch": 0.04718570947084597,
-      "grad_norm": 0.79296875,
-      "learning_rate": 0.0007,
-      "loss": 3.3178783416748048,
+      "grad_norm": 1.09375,
+      "learning_rate": 0.001,
+      "loss": 3.1321605682373046,
       "step": 560
     },
     {
       "epoch": 0.04887091338051904,
-      "grad_norm": 0.96484375,
-      "learning_rate": 0.0007,
-      "loss": 3.284391403198242,
+      "grad_norm": 0.94140625,
+      "learning_rate": 0.001,
+      "loss": 3.0999223709106447,
       "step": 580
     },
     {
       "epoch": 0.05055611729019211,
-      "grad_norm": 1.0625,
-      "learning_rate": 0.0007,
-      "loss": 3.272994613647461,
+      "grad_norm": 0.93359375,
+      "learning_rate": 0.001,
+      "loss": 3.0892059326171877,
       "step": 600
     },
     {
       "epoch": 0.05055611729019211,
-      "eval_loss": 3.265310287475586,
-      "eval_runtime": 7.4581,
-      "eval_samples_per_second": 1277.401,
-      "eval_steps_per_second": 0.939,
+      "eval_loss": 3.084484100341797,
+      "eval_runtime": 7.5354,
+      "eval_samples_per_second": 1264.304,
+      "eval_steps_per_second": 0.929,
       "step": 600
     },
     {
       "epoch": 0.05224132119986518,
-      "grad_norm": 1.09375,
-      "learning_rate": 0.0007,
-      "loss": 3.2680301666259766,
+      "grad_norm": 0.90625,
+      "learning_rate": 0.001,
+      "loss": 3.0873672485351564,
       "step": 620
     },
     {
       "epoch": 0.053926525109538256,
-      "grad_norm": 1.0625,
-      "learning_rate": 0.0007,
-      "loss": 3.2364547729492186,
+      "grad_norm": 1.0234375,
+      "learning_rate": 0.001,
+      "loss": 3.0600521087646486,
       "step": 640
     },
     {
       "epoch": 0.055611729019211326,
-      "grad_norm": 1.1640625,
-      "learning_rate": 0.0007,
-      "loss": 3.231397247314453,
+      "grad_norm": 0.81640625,
+      "learning_rate": 0.001,
+      "loss": 3.0599395751953127,
       "step": 660
     },
     {
       "epoch": 0.057296932928884395,
-      "grad_norm": 1.1171875,
-      "learning_rate": 0.0007,
-      "loss": 3.19937801361084,
+      "grad_norm": 0.98828125,
+      "learning_rate": 0.001,
+      "loss": 3.0222793579101563,
       "step": 680
     },
     {
       "epoch": 0.058982136838557464,
-      "grad_norm": 1.171875,
-      "learning_rate": 0.0007,
-      "loss": 3.180939865112305,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.001,
+      "loss": 3.005843734741211,
       "step": 700
     },
     {
       "epoch": 0.058982136838557464,
-      "eval_loss": 3.1776986122131348,
-      "eval_runtime": 7.4344,
-      "eval_samples_per_second": 1281.48,
-      "eval_steps_per_second": 0.942,
+      "eval_loss": 3.0020792484283447,
+      "eval_runtime": 7.4884,
+      "eval_samples_per_second": 1272.237,
+      "eval_steps_per_second": 0.935,
       "step": 700
     },
     {
       "epoch": 0.06066734074823053,
-      "grad_norm": 0.9375,
-      "learning_rate": 0.0007,
-      "loss": 3.166289138793945,
+      "grad_norm": 0.90625,
+      "learning_rate": 0.001,
+      "loss": 2.989686965942383,
       "step": 720
     },
     {
       "epoch": 0.06235254465790361,
-      "grad_norm": 0.875,
-      "learning_rate": 0.0007,
-      "loss": 3.158111572265625,
+      "grad_norm": 1.1953125,
+      "learning_rate": 0.001,
+      "loss": 2.98439884185791,
       "step": 740
     },
     {
       "epoch": 0.06403774856757667,
-      "grad_norm": 0.91015625,
-      "learning_rate": 0.0007,
-      "loss": 3.1301828384399415,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.001,
+      "loss": 2.956541061401367,
       "step": 760
     },
     {
       "epoch": 0.06572295247724974,
-      "grad_norm": 1.4921875,
-      "learning_rate": 0.0007,
-      "loss": 3.1184850692749024,
+      "grad_norm": 0.75390625,
+      "learning_rate": 0.001,
+      "loss": 2.9446905136108397,
       "step": 780
     },
     {
       "epoch": 0.06740815638692282,
-      "grad_norm": 1.2265625,
-      "learning_rate": 0.0007,
-      "loss": 3.130735969543457,
+      "grad_norm": 0.88671875,
+      "learning_rate": 0.001,
+      "loss": 2.953716850280762,
       "step": 800
     },
     {
       "epoch": 0.06740815638692282,
-      "eval_loss": 3.1147701740264893,
-      "eval_runtime": 7.6636,
-      "eval_samples_per_second": 1243.145,
-      "eval_steps_per_second": 0.913,
+      "eval_loss": 2.9370172023773193,
+      "eval_runtime": 7.5152,
+      "eval_samples_per_second": 1267.706,
+      "eval_steps_per_second": 0.931,
       "step": 800
     },
     {
       "epoch": 0.0690933602965959,
-      "grad_norm": 1.0546875,
-      "learning_rate": 0.0007,
-      "loss": 3.1005388259887696,
+      "grad_norm": 0.7421875,
+      "learning_rate": 0.001,
+      "loss": 2.9271785736083986,
       "step": 820
     },
     {
       "epoch": 0.07077856420626896,
-      "grad_norm": 0.9453125,
-      "learning_rate": 0.0007,
-      "loss": 3.0969886779785156,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.001,
+      "loss": 2.9229846954345704,
       "step": 840
     },
     {
       "epoch": 0.07246376811594203,
-      "grad_norm": 0.8203125,
-      "learning_rate": 0.0007,
-      "loss": 3.080755615234375,
+      "grad_norm": 0.80078125,
+      "learning_rate": 0.001,
+      "loss": 2.909313774108887,
       "step": 860
     },
     {
       "epoch": 0.0741489720256151,
-      "grad_norm": 1.09375,
-      "learning_rate": 0.0007,
-      "loss": 3.0759674072265626,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.001,
+      "loss": 2.9065679550170898,
       "step": 880
     },
     {
       "epoch": 0.07583417593528817,
-      "grad_norm": 1.03125,
-      "learning_rate": 0.0007,
-      "loss": 3.036077308654785,
+      "grad_norm": 0.9921875,
+      "learning_rate": 0.001,
+      "loss": 2.868302917480469,
       "step": 900
     },
     {
       "epoch": 0.07583417593528817,
-      "eval_loss": 3.053579330444336,
-      "eval_runtime": 7.4246,
-      "eval_samples_per_second": 1283.162,
-      "eval_steps_per_second": 0.943,
+      "eval_loss": 2.8896827697753906,
+      "eval_runtime": 7.735,
+      "eval_samples_per_second": 1231.67,
+      "eval_steps_per_second": 0.905,
       "step": 900
     }
   ],

zain/Activation/out/mlp-linear-3L_run/checkpoint-900/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cd05caa72046cca0058696052d04c76a35939ffa86c69a8876b919b059cbfdb
+oid sha256:69f6cee920e32c4b94b50a7a99ad53c35ddac080df64aa3ba5950fa167685ce5
 size 4920

zain/Activation/out/mlp-linear-3L_run/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a294ed6b00bcb89896578183adb7257d91383fe4db06da6ace2494379793964
+oid sha256:86881b88db1d7407158e4b85e34b7ba9e34a2e5052213243fc0962ba82adbe96
 size 2036216

zain/Activation/out/mlp-linear-3L_run/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cd05caa72046cca0058696052d04c76a35939ffa86c69a8876b919b059cbfdb
+oid sha256:69f6cee920e32c4b94b50a7a99ad53c35ddac080df64aa3ba5950fa167685ce5
 size 4920

zain/Activation/out/mlp-linear-3L_run/training_log.jsonl

@@ -548,3 +548,12 @@
 {"step": 860, "epoch": 0.07246376811594203, "timestamp": 1787159663.8000612, "loss": 2.909313774108887, "grad_norm": 0.80078125, "learning_rate": 0.001, "train/total_time_seconds": 15.076439164578915, "train/time_per_step_avg": 0.016551108807325365, "train/epoch_time_elapsed": 127.67662629112601, "train/estimated_remaining_minutes": 0.0409050675007955}
 {"step": 880, "epoch": 0.0741489720256151, "timestamp": 1787159665.3079937, "loss": 2.9065679550170898, "grad_norm": 1.1328125, "learning_rate": 0.001, "train/total_time_seconds": 15.406978622078896, "train/time_per_step_avg": 0.01655862484127283, "train/epoch_time_elapsed": 129.18455854058266, "train/estimated_remaining_minutes": 0.035015860504724765}
 {"step": 900, "epoch": 0.07583417593528817, "timestamp": 1787159666.8079824, "loss": 2.868302917480469, "grad_norm": 0.9921875, "learning_rate": 0.001, "train/total_time_seconds": 15.737355303019285, "train/time_per_step_avg": 0.01655557971447706, "train/epoch_time_elapsed": 130.68454774469137, "train/estimated_remaining_minutes": 0.029143250561146822}
+{"step": 900, "epoch": 0.07583417593528817, "timestamp": 1787159674.5448534, "eval_loss": 2.8896827697753906, "eval_runtime": 7.735, "eval_samples_per_second": 1231.67, "eval_steps_per_second": 0.905, "train/total_time_seconds": 15.737355303019285, "train/time_per_step_avg": 0.01655557971447706, "train/epoch_time_elapsed": 138.42141803354025, "train/estimated_remaining_minutes": 0.029143250561146822}
+{"step": 920, "epoch": 0.07751937984496124, "timestamp": 1787159676.0897264, "loss": 2.8754199981689452, "grad_norm": 0.8125, "learning_rate": 0.001, "train/total_time_seconds": 16.06913860887289, "train/time_per_step_avg": 0.01656209945678711, "train/epoch_time_elapsed": 139.96629093587399, "train/estimated_remaining_minutes": 0.02328860667952593}
+{"step": 940, "epoch": 0.07920458375463431, "timestamp": 1787159677.5917127, "loss": 2.8692115783691405, "grad_norm": 0.8046875, "learning_rate": 0.001, "train/total_time_seconds": 16.399292301386595, "train/time_per_step_avg": 0.01655644714832306, "train/epoch_time_elapsed": 141.46827787905931, "train/estimated_remaining_minutes": 0.017446055639772973}
+{"step": 960, "epoch": 0.08088978766430738, "timestamp": 1787159679.0892675, "loss": 2.8660629272460936, "grad_norm": 0.88671875, "learning_rate": 0.001, "train/total_time_seconds": 16.729277562350035, "train/time_per_step_avg": 0.0165283839777112, "train/epoch_time_elapsed": 142.96583257243037, "train/estimated_remaining_minutes": 0.01161755386274308}
+{"step": 980, "epoch": 0.08257499157398045, "timestamp": 1787159680.5901031, "loss": 2.8608421325683593, "grad_norm": 0.73828125, "learning_rate": 0.001, "train/total_time_seconds": 17.05958204343915, "train/time_per_step_avg": 0.016526034213602544, "train/epoch_time_elapsed": 144.46666844561696, "train/estimated_remaining_minutes": 0.005802578926339846}
+{"step": 1000, "epoch": 0.08426019548365352, "timestamp": 1787159682.1642146, "loss": 2.8389766693115233, "grad_norm": 0.88671875, "learning_rate": 0.001, "train/total_time_seconds": 17.390934593975544, "train/time_per_step_avg": 0.01653579290956259, "train/epoch_time_elapsed": 146.0407790467143, "train/estimated_remaining_minutes": 0.0}
+{"step": 1000, "epoch": 0.08426019548365352, "timestamp": 1787159689.7607174, "eval_loss": 2.841240167617798, "eval_runtime": 7.5948, "eval_samples_per_second": 1254.405, "eval_steps_per_second": 0.922, "train/total_time_seconds": 17.390934593975544, "train/time_per_step_avg": 0.01653579290956259, "train/epoch_time_elapsed": 153.63728144019842, "train/estimated_remaining_minutes": 0.0}
+{"step": 1000, "epoch": 0.08426019548365352, "timestamp": 1787159689.8023045, "train_runtime": 154.6026, "train_samples_per_second": 517.456, "train_steps_per_second": 6.468, "total_flos": 121016156160000.0, "train_loss": 3.7283405075073244, "train/total_time_seconds": 17.390934593975544, "train/time_per_step_avg": 0.01653579290956259, "train/epoch_time_elapsed": 153.67886726930737, "train/estimated_remaining_minutes": 0.0}
+{"step": 1000, "epoch": 0.08426019548365352, "timestamp": 1787159697.355951, "eval_loss": 2.841240167617798, "eval_runtime": 7.5505, "eval_samples_per_second": 1261.772, "eval_steps_per_second": 0.927, "train/total_time_seconds": 17.390934593975544, "train/time_per_step_avg": 0.01653579290956259, "train/epoch_time_elapsed": 161.23251363635063, "train/estimated_remaining_minutes": 0.0}

zain/Activation/out/sweep_summary.json

@@ -1,9 +1,9 @@
 [
   {
     "variant": "mlp-linear-3L",
-    "eval_loss": 3.0161361694335938,
+    "eval_loss": 2.841240167617798,
     "out": "out/mlp-linear-3L_run",
-    "run_name": "LM-mlp-linear-3L-1.0M-20260819-170853",
+    "run_name": "LM-mlp-linear-3L-1.0M-20260819-171214",
     "status": "success"
   }
 ]

zain/Activation/wandb/debug-internal.log

@@ -23,3 +23,15 @@
 {"time":"2026-08-19T17:14:01.314421382Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
 {"time":"2026-08-19T17:14:16.125013671Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":41,"history_lines":6,"events_offset":13,"events_lines":2,"console_offset":68,"console_lines":1}
 {"time":"2026-08-19T17:14:16.73098493Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-19T17:14:31.124676234Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":47,"history_lines":6,"events_offset":15,"events_lines":2,"console_offset":74,"console_lines":23}
+{"time":"2026-08-19T17:14:31.25448083Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-19T17:14:46.124973259Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":53,"history_lines":6,"events_offset":17,"events_lines":2,"console_offset":90,"console_lines":1}
+{"time":"2026-08-19T17:14:46.269794228Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-19T17:14:58.136247949Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2026-08-19T17:14:58.136517121Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":59,"history_lines":3,"events_offset":19,"events_lines":1,"console_offset":96,"console_lines":25,"uploaded_len":3,"complete":true,"exit_code":0}
+{"time":"2026-08-19T17:14:58.277374581Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-19T17:14:58.278584446Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2026-08-19T17:14:58.281745009Z","level":"INFO","msg":"stream: finishing up"}
+{"time":"2026-08-19T17:14:58.281775882Z","level":"INFO","msg":"handler: closed"}
+{"time":"2026-08-19T17:14:58.281829879Z","level":"INFO","msg":"sender: closed"}
+{"time":"2026-08-19T17:14:58.281833448Z","level":"INFO","msg":"stream: all finished"}

zain/Activation/wandb/debug.log

@@ -21,3 +21,8 @@ config: {'_wandb': {}}
 2026-08-19 17:12:16,120 INFO    MainThread:3920475 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 3, 'num_attention_heads': 4, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'max_position_embeddings': 512, 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'pad_token_id': 0, 'bos_token_id': 1, 'eos_token_id': 2, 'pretraining_tp': 1, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 10000.0, 'rope_type': 'default'}, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 32, '_name_or_path': '', 'tokenizer_name': 'w-ahmad/tiny-stories-tokenizer', 'mlp_type': 'mlp', 'activation': 'linear', 'waleed_beta': 10.0, 'powlu_m': 3.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/mlp-linear-3L_run', 'per_device_train_batch_size': 80, 'num_train_epochs': 1, 'max_steps': 1000, 'learning_rate': 0.001, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 200, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-mlp-linear-3L-1.0M-20260819-171214', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 100, 'eval_delay': 0, 'per_device_eval_batch_size': 1500, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 100, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/6L-mlp-linear-3L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
 2026-08-19 17:12:16,122 INFO    MainThread:3920475 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 1016704 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14f219615650>>
 2026-08-19 17:12:16,122 INFO    MainThread:3920475 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 1016704 None
+2026-08-19 17:14:57,366 INFO    MainThread:3920475 [wandb_run.py:_finish():2383] finishing run deepnevro-deepnevro/research-ultimate-checking/2nil4rqn
+2026-08-19 17:14:57,367 INFO    MainThread:3920475 [wandb_run.py:_atexit_cleanup():2588] got exitcode: 0
+2026-08-19 17:14:57,367 INFO    MainThread:3920475 [wandb_run.py:_restore():2570] restore
+2026-08-19 17:14:57,367 INFO    MainThread:3920475 [wandb_run.py:_restore():2576] restore done
+2026-08-19 17:14:58,281 INFO    MainThread:3920475 [wandb_run.py:_footer_sync_info():3993] logging synced files

zain/Activation/wandb/run-20260819_163845-74tq2syl/logs/debug-core.log

@@ -54,3 +54,11 @@
 {"time":"2026-08-19T17:12:15.319455303Z","level":"INFO","msg":"handleInformInit: received","streamId":"2nil4rqn","id":"6(@)"}
 {"time":"2026-08-19T17:12:15.582732337Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"2nil4rqn","id":"6(@)"}
 {"time":"2026-08-19T17:12:21.153010638Z","level":"INFO","msg":"connection: cancelling request","id":"6(@)","requestId":"g8ym1re70rep"}
+{"time":"2026-08-19T17:14:57.367689028Z","level":"INFO","msg":"connection: cancelling request","id":"6(@)","requestId":"g8ym1re70rep"}
+{"time":"2026-08-19T17:14:58.279859891Z","level":"INFO","msg":"connection: cancelling request","id":"6(@)","requestId":"g8ym1re70rep"}
+{"time":"2026-08-19T17:14:58.28171116Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"2nil4rqn","id":"6(@)"}
+{"time":"2026-08-19T17:14:58.282403203Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"2nil4rqn","id":"6(@)"}
+{"time":"2026-08-19T17:15:00.260323511Z","level":"INFO","msg":"connection: closing","id":"6(@)"}
+{"time":"2026-08-19T17:15:00.26039463Z","level":"INFO","msg":"connection: closed successfully","id":"6(@)"}
+{"time":"2026-08-19T17:15:00.260332968Z","level":"INFO","msg":"processOutgoingData: finished","id":"6(@)"}
+{"time":"2026-08-19T17:15:00.260403826Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"6(@)"}

zain/Activation/wandb/run-20260819_164534-glh82iyh/logs/debug-core.log

@@ -54,3 +54,11 @@
 {"time":"2026-08-19T17:12:15.319455303Z","level":"INFO","msg":"handleInformInit: received","streamId":"2nil4rqn","id":"6(@)"}
 {"time":"2026-08-19T17:12:15.582732337Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"2nil4rqn","id":"6(@)"}
 {"time":"2026-08-19T17:12:21.153010638Z","level":"INFO","msg":"connection: cancelling request","id":"6(@)","requestId":"g8ym1re70rep"}
+{"time":"2026-08-19T17:14:57.367689028Z","level":"INFO","msg":"connection: cancelling request","id":"6(@)","requestId":"g8ym1re70rep"}
+{"time":"2026-08-19T17:14:58.279859891Z","level":"INFO","msg":"connection: cancelling request","id":"6(@)","requestId":"g8ym1re70rep"}
+{"time":"2026-08-19T17:14:58.28171116Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"2nil4rqn","id":"6(@)"}
+{"time":"2026-08-19T17:14:58.282403203Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"2nil4rqn","id":"6(@)"}
+{"time":"2026-08-19T17:15:00.260323511Z","level":"INFO","msg":"connection: closing","id":"6(@)"}
+{"time":"2026-08-19T17:15:00.26039463Z","level":"INFO","msg":"connection: closed successfully","id":"6(@)"}
+{"time":"2026-08-19T17:15:00.260332968Z","level":"INFO","msg":"processOutgoingData: finished","id":"6(@)"}
+{"time":"2026-08-19T17:15:00.260403826Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"6(@)"}

zain/Activation/wandb/run-20260819_164553-44x03ghu/logs/debug-core.log

@@ -54,3 +54,11 @@
 {"time":"2026-08-19T17:12:15.319455303Z","level":"INFO","msg":"handleInformInit: received","streamId":"2nil4rqn","id":"6(@)"}
 {"time":"2026-08-19T17:12:15.582732337Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"2nil4rqn","id":"6(@)"}
 {"time":"2026-08-19T17:12:21.153010638Z","level":"INFO","msg":"connection: cancelling request","id":"6(@)","requestId":"g8ym1re70rep"}
+{"time":"2026-08-19T17:14:57.367689028Z","level":"INFO","msg":"connection: cancelling request","id":"6(@)","requestId":"g8ym1re70rep"}
+{"time":"2026-08-19T17:14:58.279859891Z","level":"INFO","msg":"connection: cancelling request","id":"6(@)","requestId":"g8ym1re70rep"}
+{"time":"2026-08-19T17:14:58.28171116Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"2nil4rqn","id":"6(@)"}
+{"time":"2026-08-19T17:14:58.282403203Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"2nil4rqn","id":"6(@)"}
+{"time":"2026-08-19T17:15:00.260323511Z","level":"INFO","msg":"connection: closing","id":"6(@)"}
+{"time":"2026-08-19T17:15:00.26039463Z","level":"INFO","msg":"connection: closed successfully","id":"6(@)"}
+{"time":"2026-08-19T17:15:00.260332968Z","level":"INFO","msg":"processOutgoingData: finished","id":"6(@)"}
+{"time":"2026-08-19T17:15:00.260403826Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"6(@)"}

zain/Activation/wandb/run-20260819_170854-zhg4u13t/logs/debug-core.log

@@ -54,3 +54,11 @@
 {"time":"2026-08-19T17:12:15.319455303Z","level":"INFO","msg":"handleInformInit: received","streamId":"2nil4rqn","id":"6(@)"}
 {"time":"2026-08-19T17:12:15.582732337Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"2nil4rqn","id":"6(@)"}
 {"time":"2026-08-19T17:12:21.153010638Z","level":"INFO","msg":"connection: cancelling request","id":"6(@)","requestId":"g8ym1re70rep"}
+{"time":"2026-08-19T17:14:57.367689028Z","level":"INFO","msg":"connection: cancelling request","id":"6(@)","requestId":"g8ym1re70rep"}
+{"time":"2026-08-19T17:14:58.279859891Z","level":"INFO","msg":"connection: cancelling request","id":"6(@)","requestId":"g8ym1re70rep"}
+{"time":"2026-08-19T17:14:58.28171116Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"2nil4rqn","id":"6(@)"}
+{"time":"2026-08-19T17:14:58.282403203Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"2nil4rqn","id":"6(@)"}
+{"time":"2026-08-19T17:15:00.260323511Z","level":"INFO","msg":"connection: closing","id":"6(@)"}
+{"time":"2026-08-19T17:15:00.26039463Z","level":"INFO","msg":"connection: closed successfully","id":"6(@)"}
+{"time":"2026-08-19T17:15:00.260332968Z","level":"INFO","msg":"processOutgoingData: finished","id":"6(@)"}
+{"time":"2026-08-19T17:15:00.260403826Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"6(@)"}