Auto upload zain 2026-08-18T15:42:29.977679

zain/Activation/out/mlp-gelu-9L_run/checkpoint-300/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be97744bd6d2a7fea11be213caf3b7bd082f2baadb987f45a080fa6e224fc4fd
+oid sha256:03705014f5e994ee6c7bb695dfa02b29999644eb23420736f48c816887af5cdf
 size 4010544

zain/Activation/out/mlp-gelu-9L_run/checkpoint-300/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:705c3ccbb221749e84d16da702d7513ad8ab2f195ce55b24c86ede8b0bf9c18d
+oid sha256:2b8ac6bbb72d940a73b24a8fdad518cd6df75c2a27072cda83dbea1bdfb2b9f4
 size 8068282

zain/Activation/out/mlp-gelu-9L_run/checkpoint-300/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:293635f74766f4fcae9882776529c6446698e9b875f847aa519f83843c9a249f
+oid sha256:58882af6bc66e44afb6aa7c1675e12212a966de0b9a2fc23de850f993cbc78d3
 size 1064

zain/Activation/out/mlp-gelu-9L_run/checkpoint-300/trainer_state.json

@@ -11,131 +11,131 @@
   "log_history": [
     {
       "epoch": 0.0006740815638692282,
-      "grad_norm": 1.8984375,
-      "learning_rate": 2.66e-05,
-      "loss": 8.290375518798829,
+      "grad_norm": 2.328125,
+      "learning_rate": 1.14e-05,
+      "loss": 8.309149932861327,
       "step": 20
     },
     {
       "epoch": 0.0013481631277384564,
-      "grad_norm": 1.3125,
-      "learning_rate": 5.46e-05,
-      "loss": 8.103549194335937,
+      "grad_norm": 1.734375,
+      "learning_rate": 2.34e-05,
+      "loss": 8.2459228515625,
       "step": 40
     },
     {
       "epoch": 0.0020222446916076846,
-      "grad_norm": 1.2734375,
-      "learning_rate": 8.259999999999999e-05,
-      "loss": 7.879036712646484,
+      "grad_norm": 1.296875,
+      "learning_rate": 3.539999999999999e-05,
+      "loss": 8.09324951171875,
       "step": 60
     },
     {
       "epoch": 0.002696326255476913,
-      "grad_norm": 1.2734375,
-      "learning_rate": 0.0001106,
-      "loss": 7.590550231933594,
+      "grad_norm": 1.28125,
+      "learning_rate": 4.7399999999999993e-05,
+      "loss": 7.956021881103515,
       "step": 80
     },
     {
       "epoch": 0.003370407819346141,
       "grad_norm": 1.25,
-      "learning_rate": 0.0001386,
-      "loss": 7.234850311279297,
+      "learning_rate": 5.94e-05,
+      "loss": 7.7899658203125,
       "step": 100
     },
     {
       "epoch": 0.003370407819346141,
-      "eval_loss": 7.028295993804932,
-      "eval_runtime": 7.9767,
-      "eval_samples_per_second": 1194.359,
-      "eval_steps_per_second": 1.254,
+      "eval_loss": 7.690263748168945,
+      "eval_runtime": 7.9534,
+      "eval_samples_per_second": 1197.859,
+      "eval_steps_per_second": 1.257,
       "step": 100
     },
     {
       "epoch": 0.004044489383215369,
-      "grad_norm": 1.7421875,
-      "learning_rate": 0.00016659999999999998,
-      "loss": 6.841970825195313,
+      "grad_norm": 1.25,
+      "learning_rate": 7.139999999999999e-05,
+      "loss": 7.591774749755859,
       "step": 120
     },
     {
       "epoch": 0.0047185709470845974,
-      "grad_norm": 1.1484375,
-      "learning_rate": 0.00019460000000000001,
-      "loss": 6.4576164245605465,
+      "grad_norm": 1.265625,
+      "learning_rate": 8.34e-05,
+      "loss": 7.362733459472656,
       "step": 140
     },
     {
       "epoch": 0.005392652510953826,
-      "grad_norm": 1.0859375,
-      "learning_rate": 0.0002226,
-      "loss": 6.111285781860351,
+      "grad_norm": 1.2734375,
+      "learning_rate": 9.539999999999999e-05,
+      "loss": 7.124365234375,
       "step": 160
     },
     {
       "epoch": 0.006066734074823054,
-      "grad_norm": 1.109375,
-      "learning_rate": 0.00025059999999999997,
-      "loss": 5.793069076538086,
+      "grad_norm": 1.2265625,
+      "learning_rate": 0.00010739999999999998,
+      "loss": 6.878346252441406,
       "step": 180
     },
     {
       "epoch": 0.006740815638692282,
-      "grad_norm": 0.85546875,
-      "learning_rate": 0.0002786,
-      "loss": 5.492683410644531,
+      "grad_norm": 1.8359375,
+      "learning_rate": 0.0001194,
+      "loss": 6.63219985961914,
       "step": 200
     },
     {
       "epoch": 0.006740815638692282,
-      "eval_loss": 5.342745304107666,
-      "eval_runtime": 7.9623,
-      "eval_samples_per_second": 1196.508,
-      "eval_steps_per_second": 1.256,
+      "eval_loss": 6.522833824157715,
+      "eval_runtime": 7.8828,
+      "eval_samples_per_second": 1208.576,
+      "eval_steps_per_second": 1.269,
       "step": 200
     },
     {
       "epoch": 0.00741489720256151,
-      "grad_norm": 0.87890625,
-      "learning_rate": 0.00030659999999999997,
-      "loss": 5.233791732788086,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.0001314,
+      "loss": 6.431203460693359,
       "step": 220
     },
     {
       "epoch": 0.008088978766430738,
-      "grad_norm": 0.78515625,
-      "learning_rate": 0.0003346,
-      "loss": 4.977091598510742,
+      "grad_norm": 1.1796875,
+      "learning_rate": 0.0001434,
+      "loss": 6.207939529418946,
       "step": 240
     },
     {
       "epoch": 0.008763060330299966,
-      "grad_norm": 0.87890625,
-      "learning_rate": 0.00036260000000000003,
-      "loss": 4.77899055480957,
+      "grad_norm": 1.125,
+      "learning_rate": 0.00015539999999999998,
+      "loss": 5.998645782470703,
       "step": 260
     },
     {
       "epoch": 0.009437141894169195,
-      "grad_norm": 0.91015625,
-      "learning_rate": 0.0003906,
-      "loss": 4.601796722412109,
+      "grad_norm": 1.0625,
+      "learning_rate": 0.0001674,
+      "loss": 5.795352172851563,
       "step": 280
     },
     {
       "epoch": 0.010111223458038422,
-      "grad_norm": 0.87109375,
-      "learning_rate": 0.0004186,
-      "loss": 4.450910949707032,
+      "grad_norm": 0.93359375,
+      "learning_rate": 0.00017939999999999997,
+      "loss": 5.597444915771485,
       "step": 300
     },
     {
       "epoch": 0.010111223458038422,
-      "eval_loss": 4.373648643493652,
-      "eval_runtime": 7.9961,
-      "eval_samples_per_second": 1191.458,
-      "eval_steps_per_second": 1.251,
+      "eval_loss": 5.480377674102783,
+      "eval_runtime": 7.8653,
+      "eval_samples_per_second": 1211.274,
+      "eval_steps_per_second": 1.271,
       "step": 300
     }
   ],

zain/Activation/out/mlp-gelu-9L_run/checkpoint-300/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79e0def26beb7a751361df77096e4e9d429ab64974840e7eb3dcf84a49f4a583
+oid sha256:282bf64fd9cb5669a85393aac3b68bd51ade27ff8218886467eed07f2725602f
 size 4920

zain/Activation/out/mlp-gelu-9L_run/checkpoint-400/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be7171b0c196898e4fee570c5eb2344ed572df491aa3fea04bdbeb8fa0935dbc
+oid sha256:9f44b532d7e1c464e67774217a154dd668c3bc5e8d126b3cebebfcba51a545f8
 size 4010544

zain/Activation/out/mlp-gelu-9L_run/checkpoint-400/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a39dc2a5937e2ce39b9cbb469a0155109612ed52304a64fa8346d338313b93c
+oid sha256:82d623900be8e155dec0dab9ec2c08f2ed3d3c3ecf9115e14240a11a920e1f52
 size 8068282

zain/Activation/out/mlp-gelu-9L_run/checkpoint-400/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e47d7e6a52e25825fc169e8ad3b4276c59dc20b6f1c01729d3fa2f5a57f163a
+oid sha256:f768f3dc231ac5aded23c6f019b283714352126180577c2c811e2d205bc7704f
 size 1064

zain/Activation/out/mlp-gelu-9L_run/checkpoint-400/trainer_state.json

@@ -11,174 +11,174 @@
   "log_history": [
     {
       "epoch": 0.0006740815638692282,
-      "grad_norm": 1.8984375,
-      "learning_rate": 2.66e-05,
-      "loss": 8.290375518798829,
+      "grad_norm": 2.328125,
+      "learning_rate": 1.14e-05,
+      "loss": 8.309149932861327,
       "step": 20
     },
     {
       "epoch": 0.0013481631277384564,
-      "grad_norm": 1.3125,
-      "learning_rate": 5.46e-05,
-      "loss": 8.103549194335937,
+      "grad_norm": 1.734375,
+      "learning_rate": 2.34e-05,
+      "loss": 8.2459228515625,
       "step": 40
     },
     {
       "epoch": 0.0020222446916076846,
-      "grad_norm": 1.2734375,
-      "learning_rate": 8.259999999999999e-05,
-      "loss": 7.879036712646484,
+      "grad_norm": 1.296875,
+      "learning_rate": 3.539999999999999e-05,
+      "loss": 8.09324951171875,
       "step": 60
     },
     {
       "epoch": 0.002696326255476913,
-      "grad_norm": 1.2734375,
-      "learning_rate": 0.0001106,
-      "loss": 7.590550231933594,
+      "grad_norm": 1.28125,
+      "learning_rate": 4.7399999999999993e-05,
+      "loss": 7.956021881103515,
       "step": 80
     },
     {
       "epoch": 0.003370407819346141,
       "grad_norm": 1.25,
-      "learning_rate": 0.0001386,
-      "loss": 7.234850311279297,
+      "learning_rate": 5.94e-05,
+      "loss": 7.7899658203125,
       "step": 100
     },
     {
       "epoch": 0.003370407819346141,
-      "eval_loss": 7.028295993804932,
-      "eval_runtime": 7.9767,
-      "eval_samples_per_second": 1194.359,
-      "eval_steps_per_second": 1.254,
+      "eval_loss": 7.690263748168945,
+      "eval_runtime": 7.9534,
+      "eval_samples_per_second": 1197.859,
+      "eval_steps_per_second": 1.257,
       "step": 100
     },
     {
       "epoch": 0.004044489383215369,
-      "grad_norm": 1.7421875,
-      "learning_rate": 0.00016659999999999998,
-      "loss": 6.841970825195313,
+      "grad_norm": 1.25,
+      "learning_rate": 7.139999999999999e-05,
+      "loss": 7.591774749755859,
       "step": 120
     },
     {
       "epoch": 0.0047185709470845974,
-      "grad_norm": 1.1484375,
-      "learning_rate": 0.00019460000000000001,
-      "loss": 6.4576164245605465,
+      "grad_norm": 1.265625,
+      "learning_rate": 8.34e-05,
+      "loss": 7.362733459472656,
       "step": 140
     },
     {
       "epoch": 0.005392652510953826,
-      "grad_norm": 1.0859375,
-      "learning_rate": 0.0002226,
-      "loss": 6.111285781860351,
+      "grad_norm": 1.2734375,
+      "learning_rate": 9.539999999999999e-05,
+      "loss": 7.124365234375,
       "step": 160
     },
     {
       "epoch": 0.006066734074823054,
-      "grad_norm": 1.109375,
-      "learning_rate": 0.00025059999999999997,
-      "loss": 5.793069076538086,
+      "grad_norm": 1.2265625,
+      "learning_rate": 0.00010739999999999998,
+      "loss": 6.878346252441406,
       "step": 180
     },
     {
       "epoch": 0.006740815638692282,
-      "grad_norm": 0.85546875,
-      "learning_rate": 0.0002786,
-      "loss": 5.492683410644531,
+      "grad_norm": 1.8359375,
+      "learning_rate": 0.0001194,
+      "loss": 6.63219985961914,
       "step": 200
     },
     {
       "epoch": 0.006740815638692282,
-      "eval_loss": 5.342745304107666,
-      "eval_runtime": 7.9623,
-      "eval_samples_per_second": 1196.508,
-      "eval_steps_per_second": 1.256,
+      "eval_loss": 6.522833824157715,
+      "eval_runtime": 7.8828,
+      "eval_samples_per_second": 1208.576,
+      "eval_steps_per_second": 1.269,
       "step": 200
     },
     {
       "epoch": 0.00741489720256151,
-      "grad_norm": 0.87890625,
-      "learning_rate": 0.00030659999999999997,
-      "loss": 5.233791732788086,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.0001314,
+      "loss": 6.431203460693359,
       "step": 220
     },
     {
       "epoch": 0.008088978766430738,
-      "grad_norm": 0.78515625,
-      "learning_rate": 0.0003346,
-      "loss": 4.977091598510742,
+      "grad_norm": 1.1796875,
+      "learning_rate": 0.0001434,
+      "loss": 6.207939529418946,
       "step": 240
     },
     {
       "epoch": 0.008763060330299966,
-      "grad_norm": 0.87890625,
-      "learning_rate": 0.00036260000000000003,
-      "loss": 4.77899055480957,
+      "grad_norm": 1.125,
+      "learning_rate": 0.00015539999999999998,
+      "loss": 5.998645782470703,
       "step": 260
     },
     {
       "epoch": 0.009437141894169195,
-      "grad_norm": 0.91015625,
-      "learning_rate": 0.0003906,
-      "loss": 4.601796722412109,
+      "grad_norm": 1.0625,
+      "learning_rate": 0.0001674,
+      "loss": 5.795352172851563,
       "step": 280
     },
     {
       "epoch": 0.010111223458038422,
-      "grad_norm": 0.87109375,
-      "learning_rate": 0.0004186,
-      "loss": 4.450910949707032,
+      "grad_norm": 0.93359375,
+      "learning_rate": 0.00017939999999999997,
+      "loss": 5.597444915771485,
       "step": 300
     },
     {
       "epoch": 0.010111223458038422,
-      "eval_loss": 4.373648643493652,
-      "eval_runtime": 7.9961,
-      "eval_samples_per_second": 1191.458,
-      "eval_steps_per_second": 1.251,
+      "eval_loss": 5.480377674102783,
+      "eval_runtime": 7.8653,
+      "eval_samples_per_second": 1211.274,
+      "eval_steps_per_second": 1.271,
       "step": 300
     },
     {
       "epoch": 0.010785305021907651,
-      "grad_norm": 1.078125,
-      "learning_rate": 0.0004466,
-      "loss": 4.315410232543945,
+      "grad_norm": 0.94140625,
+      "learning_rate": 0.0001914,
+      "loss": 5.3849952697753904,
       "step": 320
     },
     {
       "epoch": 0.011459386585776879,
-      "grad_norm": 0.80078125,
-      "learning_rate": 0.00047460000000000004,
-      "loss": 4.23107795715332,
+      "grad_norm": 0.98828125,
+      "learning_rate": 0.00020339999999999998,
+      "loss": 5.2166282653808596,
       "step": 340
     },
     {
       "epoch": 0.012133468149646108,
-      "grad_norm": 0.91015625,
-      "learning_rate": 0.0005026,
-      "loss": 4.112172698974609,
+      "grad_norm": 1.078125,
+      "learning_rate": 0.00021539999999999998,
+      "loss": 5.036893081665039,
       "step": 360
     },
     {
       "epoch": 0.012807549713515335,
-      "grad_norm": 0.8828125,
-      "learning_rate": 0.0005306,
-      "loss": 4.030664443969727,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.00022739999999999997,
+      "loss": 4.901935195922851,
       "step": 380
     },
     {
       "epoch": 0.013481631277384564,
-      "grad_norm": 0.93359375,
-      "learning_rate": 0.0005586,
-      "loss": 3.95709228515625,
+      "grad_norm": 0.984375,
+      "learning_rate": 0.0002394,
+      "loss": 4.777506256103516,
       "step": 400
     },
     {
       "epoch": 0.013481631277384564,
-      "eval_loss": 3.9225285053253174,
-      "eval_runtime": 8.1083,
-      "eval_samples_per_second": 1174.974,
-      "eval_steps_per_second": 1.233,
+      "eval_loss": 4.718365669250488,
+      "eval_runtime": 7.988,
+      "eval_samples_per_second": 1192.66,
+      "eval_steps_per_second": 1.252,
       "step": 400
     }
   ],

zain/Activation/out/mlp-gelu-9L_run/checkpoint-400/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79e0def26beb7a751361df77096e4e9d429ab64974840e7eb3dcf84a49f4a583
+oid sha256:282bf64fd9cb5669a85393aac3b68bd51ade27ff8218886467eed07f2725602f
 size 4920

zain/Activation/out/mlp-gelu-9L_run/checkpoint-500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c7cc46bf400db7731d3fea6d8082e253fdc6a32858657bb1288eb4d6b450e8a
+oid sha256:0ea2ae49852ecadd9b510e4fe1a58c1d68080d625542a2263f3c90caad5c901d
 size 4010544

zain/Activation/out/mlp-gelu-9L_run/checkpoint-500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a420ac43c4ddb6df695385bd83edb57b4e5995b1046b939627312d466cac2d0d
+oid sha256:b8ef679aff3669160c28c972997086bc4010dc4cc0ca967aaff3b48ed5f510c2
 size 8068282

zain/Activation/out/mlp-gelu-9L_run/checkpoint-500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ad40e275c0c46c262ecd103385af8fb68cf3f382102b4f63937b0dbd1c69cfc
+oid sha256:7aade0a5cf98168c48557061a263a0ce94127833f42effbb1795ad03b5bd88a5
 size 1064

zain/Activation/out/mlp-gelu-9L_run/checkpoint-500/trainer_state.json

@@ -11,216 +11,216 @@
   "log_history": [
     {
       "epoch": 0.0006740815638692282,
-      "grad_norm": 1.8984375,
-      "learning_rate": 2.66e-05,
-      "loss": 8.290375518798829,
+      "grad_norm": 2.328125,
+      "learning_rate": 1.14e-05,
+      "loss": 8.309149932861327,
       "step": 20
     },
     {
       "epoch": 0.0013481631277384564,
-      "grad_norm": 1.3125,
-      "learning_rate": 5.46e-05,
-      "loss": 8.103549194335937,
+      "grad_norm": 1.734375,
+      "learning_rate": 2.34e-05,
+      "loss": 8.2459228515625,
       "step": 40
     },
     {
       "epoch": 0.0020222446916076846,
-      "grad_norm": 1.2734375,
-      "learning_rate": 8.259999999999999e-05,
-      "loss": 7.879036712646484,
+      "grad_norm": 1.296875,
+      "learning_rate": 3.539999999999999e-05,
+      "loss": 8.09324951171875,
       "step": 60
     },
     {
       "epoch": 0.002696326255476913,
-      "grad_norm": 1.2734375,
-      "learning_rate": 0.0001106,
-      "loss": 7.590550231933594,
+      "grad_norm": 1.28125,
+      "learning_rate": 4.7399999999999993e-05,
+      "loss": 7.956021881103515,
       "step": 80
     },
     {
       "epoch": 0.003370407819346141,
       "grad_norm": 1.25,
-      "learning_rate": 0.0001386,
-      "loss": 7.234850311279297,
+      "learning_rate": 5.94e-05,
+      "loss": 7.7899658203125,
       "step": 100
     },
     {
       "epoch": 0.003370407819346141,
-      "eval_loss": 7.028295993804932,
-      "eval_runtime": 7.9767,
-      "eval_samples_per_second": 1194.359,
-      "eval_steps_per_second": 1.254,
+      "eval_loss": 7.690263748168945,
+      "eval_runtime": 7.9534,
+      "eval_samples_per_second": 1197.859,
+      "eval_steps_per_second": 1.257,
       "step": 100
     },
     {
       "epoch": 0.004044489383215369,
-      "grad_norm": 1.7421875,
-      "learning_rate": 0.00016659999999999998,
-      "loss": 6.841970825195313,
+      "grad_norm": 1.25,
+      "learning_rate": 7.139999999999999e-05,
+      "loss": 7.591774749755859,
       "step": 120
     },
     {
       "epoch": 0.0047185709470845974,
-      "grad_norm": 1.1484375,
-      "learning_rate": 0.00019460000000000001,
-      "loss": 6.4576164245605465,
+      "grad_norm": 1.265625,
+      "learning_rate": 8.34e-05,
+      "loss": 7.362733459472656,
       "step": 140
     },
     {
       "epoch": 0.005392652510953826,
-      "grad_norm": 1.0859375,
-      "learning_rate": 0.0002226,
-      "loss": 6.111285781860351,
+      "grad_norm": 1.2734375,
+      "learning_rate": 9.539999999999999e-05,
+      "loss": 7.124365234375,
       "step": 160
     },
     {
       "epoch": 0.006066734074823054,
-      "grad_norm": 1.109375,
-      "learning_rate": 0.00025059999999999997,
-      "loss": 5.793069076538086,
+      "grad_norm": 1.2265625,
+      "learning_rate": 0.00010739999999999998,
+      "loss": 6.878346252441406,
       "step": 180
     },
     {
       "epoch": 0.006740815638692282,
-      "grad_norm": 0.85546875,
-      "learning_rate": 0.0002786,
-      "loss": 5.492683410644531,
+      "grad_norm": 1.8359375,
+      "learning_rate": 0.0001194,
+      "loss": 6.63219985961914,
       "step": 200
     },
     {
       "epoch": 0.006740815638692282,
-      "eval_loss": 5.342745304107666,
-      "eval_runtime": 7.9623,
-      "eval_samples_per_second": 1196.508,
-      "eval_steps_per_second": 1.256,
+      "eval_loss": 6.522833824157715,
+      "eval_runtime": 7.8828,
+      "eval_samples_per_second": 1208.576,
+      "eval_steps_per_second": 1.269,
       "step": 200
     },
     {
       "epoch": 0.00741489720256151,
-      "grad_norm": 0.87890625,
-      "learning_rate": 0.00030659999999999997,
-      "loss": 5.233791732788086,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.0001314,
+      "loss": 6.431203460693359,
       "step": 220
     },
     {
       "epoch": 0.008088978766430738,
-      "grad_norm": 0.78515625,
-      "learning_rate": 0.0003346,
-      "loss": 4.977091598510742,
+      "grad_norm": 1.1796875,
+      "learning_rate": 0.0001434,
+      "loss": 6.207939529418946,
       "step": 240
     },
     {
       "epoch": 0.008763060330299966,
-      "grad_norm": 0.87890625,
-      "learning_rate": 0.00036260000000000003,
-      "loss": 4.77899055480957,
+      "grad_norm": 1.125,
+      "learning_rate": 0.00015539999999999998,
+      "loss": 5.998645782470703,
       "step": 260
     },
     {
       "epoch": 0.009437141894169195,
-      "grad_norm": 0.91015625,
-      "learning_rate": 0.0003906,
-      "loss": 4.601796722412109,
+      "grad_norm": 1.0625,
+      "learning_rate": 0.0001674,
+      "loss": 5.795352172851563,
       "step": 280
     },
     {
       "epoch": 0.010111223458038422,
-      "grad_norm": 0.87109375,
-      "learning_rate": 0.0004186,
-      "loss": 4.450910949707032,
+      "grad_norm": 0.93359375,
+      "learning_rate": 0.00017939999999999997,
+      "loss": 5.597444915771485,
       "step": 300
     },
     {
       "epoch": 0.010111223458038422,
-      "eval_loss": 4.373648643493652,
-      "eval_runtime": 7.9961,
-      "eval_samples_per_second": 1191.458,
-      "eval_steps_per_second": 1.251,
+      "eval_loss": 5.480377674102783,
+      "eval_runtime": 7.8653,
+      "eval_samples_per_second": 1211.274,
+      "eval_steps_per_second": 1.271,
       "step": 300
     },
     {
       "epoch": 0.010785305021907651,
-      "grad_norm": 1.078125,
-      "learning_rate": 0.0004466,
-      "loss": 4.315410232543945,
+      "grad_norm": 0.94140625,
+      "learning_rate": 0.0001914,
+      "loss": 5.3849952697753904,
       "step": 320
     },
     {
       "epoch": 0.011459386585776879,
-      "grad_norm": 0.80078125,
-      "learning_rate": 0.00047460000000000004,
-      "loss": 4.23107795715332,
+      "grad_norm": 0.98828125,
+      "learning_rate": 0.00020339999999999998,
+      "loss": 5.2166282653808596,
       "step": 340
     },
     {
       "epoch": 0.012133468149646108,
-      "grad_norm": 0.91015625,
-      "learning_rate": 0.0005026,
-      "loss": 4.112172698974609,
+      "grad_norm": 1.078125,
+      "learning_rate": 0.00021539999999999998,
+      "loss": 5.036893081665039,
       "step": 360
     },
     {
       "epoch": 0.012807549713515335,
-      "grad_norm": 0.8828125,
-      "learning_rate": 0.0005306,
-      "loss": 4.030664443969727,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.00022739999999999997,
+      "loss": 4.901935195922851,
       "step": 380
     },
     {
       "epoch": 0.013481631277384564,
-      "grad_norm": 0.93359375,
-      "learning_rate": 0.0005586,
-      "loss": 3.95709228515625,
+      "grad_norm": 0.984375,
+      "learning_rate": 0.0002394,
+      "loss": 4.777506256103516,
       "step": 400
     },
     {
       "epoch": 0.013481631277384564,
-      "eval_loss": 3.9225285053253174,
-      "eval_runtime": 8.1083,
-      "eval_samples_per_second": 1174.974,
-      "eval_steps_per_second": 1.233,
+      "eval_loss": 4.718365669250488,
+      "eval_runtime": 7.988,
+      "eval_samples_per_second": 1192.66,
+      "eval_steps_per_second": 1.252,
       "step": 400
     },
     {
       "epoch": 0.014155712841253791,
-      "grad_norm": 1.0078125,
-      "learning_rate": 0.0005866,
-      "loss": 3.8780284881591798,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.0002514,
+      "loss": 4.656603622436523,
       "step": 420
     },
     {
       "epoch": 0.01482979440512302,
-      "grad_norm": 1.0078125,
-      "learning_rate": 0.0006146,
-      "loss": 3.837977981567383,
+      "grad_norm": 1.71875,
+      "learning_rate": 0.00026339999999999995,
+      "loss": 4.587258148193359,
       "step": 440
     },
     {
       "epoch": 0.015503875968992248,
-      "grad_norm": 1.171875,
-      "learning_rate": 0.0006426,
-      "loss": 3.777029800415039,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00027539999999999997,
+      "loss": 4.507755279541016,
       "step": 460
     },
     {
       "epoch": 0.016177957532861477,
-      "grad_norm": 0.79296875,
-      "learning_rate": 0.0006705999999999999,
-      "loss": 3.6980987548828126,
+      "grad_norm": 1.25,
+      "learning_rate": 0.00028739999999999994,
+      "loss": 4.410206985473633,
       "step": 480
     },
     {
       "epoch": 0.016852039096730706,
-      "grad_norm": 0.89453125,
-      "learning_rate": 0.0006986,
-      "loss": 3.6566497802734377,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.00029939999999999996,
+      "loss": 4.3579551696777346,
       "step": 500
     },
     {
       "epoch": 0.016852039096730706,
-      "eval_loss": 3.6329572200775146,
-      "eval_runtime": 7.8721,
-      "eval_samples_per_second": 1210.221,
+      "eval_loss": 4.317867755889893,
+      "eval_runtime": 7.8743,
+      "eval_samples_per_second": 1209.882,
       "eval_steps_per_second": 1.27,
       "step": 500
     }

zain/Activation/out/mlp-gelu-9L_run/checkpoint-500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79e0def26beb7a751361df77096e4e9d429ab64974840e7eb3dcf84a49f4a583
+oid sha256:282bf64fd9cb5669a85393aac3b68bd51ade27ff8218886467eed07f2725602f
 size 4920

zain/Activation/out/mlp-gelu-9L_run/training_log.jsonl

@@ -98,3 +98,21 @@
 {"step": 260, "epoch": 0.008763060330299966, "timestamp": 1787067712.5354607, "loss": 5.998645782470703, "grad_norm": 1.125, "learning_rate": 0.00015539999999999998, "train/total_time_seconds": 6.03019142895937, "train/time_per_step_avg": 0.021212960965931414, "train/epoch_time_elapsed": 28.698206547647715, "train/estimated_remaining_minutes": 0.8658736410813453}
 {"step": 280, "epoch": 0.009437141894169195, "timestamp": 1787067713.4506016, "loss": 5.795352172851563, "grad_norm": 1.0625, "learning_rate": 0.0001674, "train/total_time_seconds": 6.449072878807783, "train/time_per_step_avg": 0.02115541972219944, "train/epoch_time_elapsed": 29.613347496837378, "train/estimated_remaining_minutes": 0.8521989161281714}
 {"step": 300, "epoch": 0.010111223458038422, "timestamp": 1787067714.3972738, "loss": 5.597444915771485, "grad_norm": 0.93359375, "learning_rate": 0.00017939999999999997, "train/total_time_seconds": 6.8785313330590725, "train/time_per_step_avg": 0.02100003503262997, "train/epoch_time_elapsed": 30.56001989543438, "train/estimated_remaining_minutes": 0.8407093851516644}
+{"step": 300, "epoch": 0.010111223458038422, "timestamp": 1787067722.2642279, "eval_loss": 5.480377674102783, "eval_runtime": 7.8653, "eval_samples_per_second": 1211.274, "eval_steps_per_second": 1.271, "train/total_time_seconds": 6.8785313330590725, "train/time_per_step_avg": 0.02100003503262997, "train/epoch_time_elapsed": 38.426972698420286, "train/estimated_remaining_minutes": 0.8407093851516644}
+{"step": 320, "epoch": 0.010785305021907651, "timestamp": 1787067723.2520854, "loss": 5.3849952697753904, "grad_norm": 0.94140625, "learning_rate": 0.0001914, "train/total_time_seconds": 7.3181765004992485, "train/time_per_step_avg": 0.02123529613018036, "train/epoch_time_elapsed": 39.4148313626647, "train/estimated_remaining_minutes": 0.8309179568275188}
+{"step": 340, "epoch": 0.011459386585776879, "timestamp": 1787067724.1838934, "loss": 5.2166282653808596, "grad_norm": 0.98828125, "learning_rate": 0.00020339999999999998, "train/total_time_seconds": 7.744759943336248, "train/time_per_step_avg": 0.02134319134056568, "train/epoch_time_elapsed": 40.34663977473974, "train/estimated_remaining_minutes": 0.8200334057650145}
+{"step": 360, "epoch": 0.012133468149646108, "timestamp": 1787067725.0994296, "loss": 5.036893081665039, "grad_norm": 1.078125, "learning_rate": 0.00021539999999999998, "train/total_time_seconds": 8.16234815865755, "train/time_per_step_avg": 0.02132156729698181, "train/epoch_time_elapsed": 41.2621755450964, "train/estimated_remaining_minutes": 0.8086770860892204}
+{"step": 380, "epoch": 0.012807549713515335, "timestamp": 1787067726.0075078, "loss": 4.901935195922851, "grad_norm": 1.2109375, "learning_rate": 0.00022739999999999997, "train/total_time_seconds": 8.576008681207895, "train/time_per_step_avg": 0.021269358024001123, "train/epoch_time_elapsed": 42.170253202319145, "train/estimated_remaining_minutes": 0.7974183510596815}
+{"step": 400, "epoch": 0.013481631277384564, "timestamp": 1787067726.9610987, "loss": 4.777506256103516, "grad_norm": 0.984375, "learning_rate": 0.0002394, "train/total_time_seconds": 9.008387830108404, "train/time_per_step_avg": 0.021298564970493317, "train/epoch_time_elapsed": 43.123844996094704, "train/estimated_remaining_minutes": 0.7882339351344854}
+{"step": 400, "epoch": 0.013481631277384564, "timestamp": 1787067734.95089, "eval_loss": 4.718365669250488, "eval_runtime": 7.988, "eval_samples_per_second": 1192.66, "eval_steps_per_second": 1.252, "train/total_time_seconds": 9.008387830108404, "train/time_per_step_avg": 0.021298564970493317, "train/epoch_time_elapsed": 51.113634552806616, "train/estimated_remaining_minutes": 0.7882339351344854}
+{"step": 420, "epoch": 0.014155712841253791, "timestamp": 1787067735.8969417, "loss": 4.656603622436523, "grad_norm": 1.2109375, "learning_rate": 0.0002514, "train/total_time_seconds": 9.42536785453558, "train/time_per_step_avg": 0.02107191354036331, "train/epoch_time_elapsed": 52.059687077999115, "train/estimated_remaining_minutes": 0.7779668705330954}
+{"step": 440, "epoch": 0.01482979440512302, "timestamp": 1787067736.8117611, "loss": 4.587258148193359, "grad_norm": 1.71875, "learning_rate": 0.00026339999999999995, "train/total_time_seconds": 9.844896167516708, "train/time_per_step_avg": 0.0210013622418046, "train/epoch_time_elapsed": 52.974506851285696, "train/estimated_remaining_minutes": 0.7682002312531977}
+{"step": 460, "epoch": 0.015503875968992248, "timestamp": 1787067737.7257454, "loss": 4.507755279541016, "grad_norm": 1.21875, "learning_rate": 0.00027539999999999997, "train/total_time_seconds": 10.264130428433418, "train/time_per_step_avg": 0.021017822697758676, "train/epoch_time_elapsed": 53.88849103078246, "train/estimated_remaining_minutes": 0.7586531186233396}
+{"step": 480, "epoch": 0.016177957532861477, "timestamp": 1787067738.6469493, "loss": 4.410206985473633, "grad_norm": 1.25, "learning_rate": 0.00028739999999999994, "train/total_time_seconds": 10.695957120507956, "train/time_per_step_avg": 0.021199484393000602, "train/epoch_time_elapsed": 54.80969522893429, "train/estimated_remaining_minutes": 0.7502025480356275}
+{"step": 500, "epoch": 0.016852039096730706, "timestamp": 1787067739.5546324, "loss": 4.3579551696777346, "grad_norm": 1.3203125, "learning_rate": 0.00029939999999999996, "train/total_time_seconds": 11.110492404550314, "train/time_per_step_avg": 0.021021045744419098, "train/epoch_time_elapsed": 55.717378195375204, "train/estimated_remaining_minutes": 0.7406994936366876}
+{"step": 500, "epoch": 0.016852039096730706, "timestamp": 1787067747.4305458, "eval_loss": 4.317867755889893, "eval_runtime": 7.8743, "eval_samples_per_second": 1209.882, "eval_steps_per_second": 1.27, "train/total_time_seconds": 11.110492404550314, "train/time_per_step_avg": 0.021021045744419098, "train/epoch_time_elapsed": 63.593290999531746, "train/estimated_remaining_minutes": 0.7406994936366876}
+{"step": 520, "epoch": 0.01752612066059993, "timestamp": 1787067748.398958, "loss": 4.301048278808594, "grad_norm": 1.1484375, "learning_rate": 0.0003, "train/total_time_seconds": 11.544510286301374, "train/time_per_step_avg": 0.02119142431765795, "train/epoch_time_elapsed": 64.56170359626412, "train/estimated_remaining_minutes": 0.732632383553741}
+{"step": 540, "epoch": 0.01820020222446916, "timestamp": 1787067749.3196073, "loss": 4.22619743347168, "grad_norm": 1.3046875, "learning_rate": 0.0003, "train/total_time_seconds": 11.970127925276756, "train/time_per_step_avg": 0.021252317577600478, "train/epoch_time_elapsed": 65.48235335946083, "train/estimated_remaining_minutes": 0.7241188498006926}
+{"step": 560, "epoch": 0.01887428378833839, "timestamp": 1787067750.2357593, "loss": 4.173627090454102, "grad_norm": 1.1328125, "learning_rate": 0.0003, "train/total_time_seconds": 12.387610416859388, "train/time_per_step_avg": 0.021234799884259702, "train/epoch_time_elapsed": 66.3985048159957, "train/estimated_remaining_minutes": 0.7152370300210479}
+{"step": 580, "epoch": 0.01954836535220762, "timestamp": 1787067751.1435575, "loss": 4.122076797485351, "grad_norm": 0.97265625, "learning_rate": 0.0003, "train/total_time_seconds": 12.805801656097174, "train/time_per_step_avg": 0.02109844535589218, "train/epoch_time_elapsed": 67.30630354955792, "train/estimated_remaining_minutes": 0.7065269879226027}
+{"step": 600, "epoch": 0.020222446916076844, "timestamp": 1787067752.0671544, "loss": 4.078117370605469, "grad_norm": 1.2109375, "learning_rate": 0.0003, "train/total_time_seconds": 13.223767712712288, "train/time_per_step_avg": 0.02113275308161974, "train/epoch_time_elapsed": 68.22989998012781, "train/estimated_remaining_minutes": 0.6979210737264818}