Auto upload zain 2026-08-18T15:43:05.347262

zain/Activation/out/mlp-gelu-9L_run/checkpoint-600/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4500605646f57ecbaab3673eee29e548e0f21b262ac52c8de486c2731674412e
+oid sha256:2e975634df489a36f32879561ecc0bc3604a638ee0d3042123eb8170cbc3fb3f
 size 4010544

zain/Activation/out/mlp-gelu-9L_run/checkpoint-600/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ca8629aa0ae12792a389d2b05653c5d547427e3fb44e9d88a052e21869c803d
+oid sha256:a82464792de05e600d7649e002ffc0a88f8abb9a3c597b9a161bb66426a7092b
 size 8068282

zain/Activation/out/mlp-gelu-9L_run/checkpoint-600/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43a21235ddd7c8c0020d887652dce105923f094e2bc54766bffa71522037a007
+oid sha256:295d5fdc0e0bbae04d3db91b9c6051a7cccac49c004495947e95dcd6c59adda3
 size 1064

zain/Activation/out/mlp-gelu-9L_run/checkpoint-600/trainer_state.json

@@ -11,260 +11,260 @@
   "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
     },
     {
       "epoch": 0.01752612066059993,
-      "grad_norm": 0.8984375,
-      "learning_rate": 0.0007,
-      "loss": 3.620241165161133,
+      "grad_norm": 1.1484375,
+      "learning_rate": 0.0003,
+      "loss": 4.301048278808594,
       "step": 520
     },
     {
       "epoch": 0.01820020222446916,
-      "grad_norm": 1.140625,
-      "learning_rate": 0.0007,
-      "loss": 3.5605819702148436,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.0003,
+      "loss": 4.22619743347168,
       "step": 540
     },
     {
       "epoch": 0.01887428378833839,
-      "grad_norm": 0.84375,
-      "learning_rate": 0.0007,
-      "loss": 3.515232467651367,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.0003,
+      "loss": 4.173627090454102,
       "step": 560
     },
     {
       "epoch": 0.01954836535220762,
-      "grad_norm": 0.9609375,
-      "learning_rate": 0.0007,
-      "loss": 3.472977066040039,
+      "grad_norm": 0.97265625,
+      "learning_rate": 0.0003,
+      "loss": 4.122076797485351,
       "step": 580
     },
     {
       "epoch": 0.020222446916076844,
-      "grad_norm": 0.8828125,
-      "learning_rate": 0.0007,
-      "loss": 3.442094421386719,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.0003,
+      "loss": 4.078117370605469,
       "step": 600
     },
     {
       "epoch": 0.020222446916076844,
-      "eval_loss": 3.4318618774414062,
-      "eval_runtime": 7.8952,
-      "eval_samples_per_second": 1206.68,
-      "eval_steps_per_second": 1.267,
+      "eval_loss": 4.0582146644592285,
+      "eval_runtime": 7.9148,
+      "eval_samples_per_second": 1203.7,
+      "eval_steps_per_second": 1.263,
       "step": 600
     }
   ],

zain/Activation/out/mlp-gelu-9L_run/checkpoint-600/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-700/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daf72d92b87327e97db75c0c6c47e7b61fdeea058860c623997d66d12c7264c7
+oid sha256:13d7540500b76ad43155714e067c3a713d09b1ea639ba52982f613513c3be914
 size 4010544

zain/Activation/out/mlp-gelu-9L_run/checkpoint-700/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b83926bf5585093d371040082feb25ee0e434be1c9b62aa3ae0118705382a737
+oid sha256:fac036442baf982ac1611f727ee849a27fe6b26708473bf3f744affbfa5b74c3
 size 8068282

zain/Activation/out/mlp-gelu-9L_run/checkpoint-700/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aac662062525611dd137fd05108444d17dfbd69f137e40e8a3651bb69d2ba7e
+oid sha256:d6c38b4e6128ebabd81a22bafe942090015968e75f90e5e9ef25cd5ebdef8357
 size 1064

zain/Activation/out/mlp-gelu-9L_run/checkpoint-700/trainer_state.json

@@ -11,303 +11,303 @@
   "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
     },
     {
       "epoch": 0.01752612066059993,
-      "grad_norm": 0.8984375,
-      "learning_rate": 0.0007,
-      "loss": 3.620241165161133,
+      "grad_norm": 1.1484375,
+      "learning_rate": 0.0003,
+      "loss": 4.301048278808594,
       "step": 520
     },
     {
       "epoch": 0.01820020222446916,
-      "grad_norm": 1.140625,
-      "learning_rate": 0.0007,
-      "loss": 3.5605819702148436,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.0003,
+      "loss": 4.22619743347168,
       "step": 540
     },
     {
       "epoch": 0.01887428378833839,
-      "grad_norm": 0.84375,
-      "learning_rate": 0.0007,
-      "loss": 3.515232467651367,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.0003,
+      "loss": 4.173627090454102,
       "step": 560
     },
     {
       "epoch": 0.01954836535220762,
-      "grad_norm": 0.9609375,
-      "learning_rate": 0.0007,
-      "loss": 3.472977066040039,
+      "grad_norm": 0.97265625,
+      "learning_rate": 0.0003,
+      "loss": 4.122076797485351,
       "step": 580
     },
     {
       "epoch": 0.020222446916076844,
-      "grad_norm": 0.8828125,
-      "learning_rate": 0.0007,
-      "loss": 3.442094421386719,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.0003,
+      "loss": 4.078117370605469,
       "step": 600
     },
     {
       "epoch": 0.020222446916076844,
-      "eval_loss": 3.4318618774414062,
-      "eval_runtime": 7.8952,
-      "eval_samples_per_second": 1206.68,
-      "eval_steps_per_second": 1.267,
+      "eval_loss": 4.0582146644592285,
+      "eval_runtime": 7.9148,
+      "eval_samples_per_second": 1203.7,
+      "eval_steps_per_second": 1.263,
       "step": 600
     },
     {
       "epoch": 0.020896528479946073,
-      "grad_norm": 0.91015625,
-      "learning_rate": 0.0007,
-      "loss": 3.3882373809814452,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.0003,
+      "loss": 4.019903182983398,
       "step": 620
     },
     {
       "epoch": 0.021570610043815303,
-      "grad_norm": 0.921875,
-      "learning_rate": 0.0007,
-      "loss": 3.363667297363281,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.0003,
+      "loss": 3.995362091064453,
       "step": 640
     },
     {
       "epoch": 0.022244691607684528,
-      "grad_norm": 0.77734375,
-      "learning_rate": 0.0007,
-      "loss": 3.3378562927246094,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0003,
+      "loss": 3.961619186401367,
       "step": 660
     },
     {
       "epoch": 0.022918773171553757,
-      "grad_norm": 0.859375,
-      "learning_rate": 0.0007,
-      "loss": 3.2941909790039063,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.0003,
+      "loss": 3.922329330444336,
       "step": 680
     },
     {
       "epoch": 0.023592854735422986,
-      "grad_norm": 0.7265625,
-      "learning_rate": 0.0007,
-      "loss": 3.2900840759277346,
+      "grad_norm": 1.34375,
+      "learning_rate": 0.0003,
+      "loss": 3.915304946899414,
       "step": 700
     },
     {
       "epoch": 0.023592854735422986,
-      "eval_loss": 3.277914047241211,
-      "eval_runtime": 7.9495,
-      "eval_samples_per_second": 1198.439,
-      "eval_steps_per_second": 1.258,
+      "eval_loss": 3.899839401245117,
+      "eval_runtime": 7.9432,
+      "eval_samples_per_second": 1199.387,
+      "eval_steps_per_second": 1.259,
       "step": 700
     }
   ],

zain/Activation/out/mlp-gelu-9L_run/checkpoint-700/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-800/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3d3613fc8d170ff8709329a4777d28e49a7f2ed4d7efd845881d72494af6c20
+oid sha256:5d3f04f78afdee67e816c503c9704cbb548b0c1e34d83274b2db79860fcb271c
 size 4010544

zain/Activation/out/mlp-gelu-9L_run/checkpoint-800/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cc15549707ce57325fd1535acadf307c7372cae5db1384d6e19ece30d7b7852
+oid sha256:84ec3365760c8c9d65abea8de19c2c704a7b06e6d5e4d868dd08f176d493ded6
 size 8068282

zain/Activation/out/mlp-gelu-9L_run/checkpoint-800/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4ae273f6e52d9470fdb0cf70fb543f74693bb1ddd058314f4d5c7d3c01c667e
+oid sha256:2224470b783e3f05273b6a4ac609fa6ba76b1099ae64a843a85fea2d2bf1e0dd
 size 1064

zain/Activation/out/mlp-gelu-9L_run/checkpoint-800/trainer_state.json

@@ -11,346 +11,346 @@
   "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
     },
     {
       "epoch": 0.01752612066059993,
-      "grad_norm": 0.8984375,
-      "learning_rate": 0.0007,
-      "loss": 3.620241165161133,
+      "grad_norm": 1.1484375,
+      "learning_rate": 0.0003,
+      "loss": 4.301048278808594,
       "step": 520
     },
     {
       "epoch": 0.01820020222446916,
-      "grad_norm": 1.140625,
-      "learning_rate": 0.0007,
-      "loss": 3.5605819702148436,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.0003,
+      "loss": 4.22619743347168,
       "step": 540
     },
     {
       "epoch": 0.01887428378833839,
-      "grad_norm": 0.84375,
-      "learning_rate": 0.0007,
-      "loss": 3.515232467651367,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.0003,
+      "loss": 4.173627090454102,
       "step": 560
     },
     {
       "epoch": 0.01954836535220762,
-      "grad_norm": 0.9609375,
-      "learning_rate": 0.0007,
-      "loss": 3.472977066040039,
+      "grad_norm": 0.97265625,
+      "learning_rate": 0.0003,
+      "loss": 4.122076797485351,
       "step": 580
     },
     {
       "epoch": 0.020222446916076844,
-      "grad_norm": 0.8828125,
-      "learning_rate": 0.0007,
-      "loss": 3.442094421386719,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.0003,
+      "loss": 4.078117370605469,
       "step": 600
     },
     {
       "epoch": 0.020222446916076844,
-      "eval_loss": 3.4318618774414062,
-      "eval_runtime": 7.8952,
-      "eval_samples_per_second": 1206.68,
-      "eval_steps_per_second": 1.267,
+      "eval_loss": 4.0582146644592285,
+      "eval_runtime": 7.9148,
+      "eval_samples_per_second": 1203.7,
+      "eval_steps_per_second": 1.263,
       "step": 600
     },
     {
       "epoch": 0.020896528479946073,
-      "grad_norm": 0.91015625,
-      "learning_rate": 0.0007,
-      "loss": 3.3882373809814452,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.0003,
+      "loss": 4.019903182983398,
       "step": 620
     },
     {
       "epoch": 0.021570610043815303,
-      "grad_norm": 0.921875,
-      "learning_rate": 0.0007,
-      "loss": 3.363667297363281,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.0003,
+      "loss": 3.995362091064453,
       "step": 640
     },
     {
       "epoch": 0.022244691607684528,
-      "grad_norm": 0.77734375,
-      "learning_rate": 0.0007,
-      "loss": 3.3378562927246094,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0003,
+      "loss": 3.961619186401367,
       "step": 660
     },
     {
       "epoch": 0.022918773171553757,
-      "grad_norm": 0.859375,
-      "learning_rate": 0.0007,
-      "loss": 3.2941909790039063,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.0003,
+      "loss": 3.922329330444336,
       "step": 680
     },
     {
       "epoch": 0.023592854735422986,
-      "grad_norm": 0.7265625,
-      "learning_rate": 0.0007,
-      "loss": 3.2900840759277346,
+      "grad_norm": 1.34375,
+      "learning_rate": 0.0003,
+      "loss": 3.915304946899414,
       "step": 700
     },
     {
       "epoch": 0.023592854735422986,
-      "eval_loss": 3.277914047241211,
-      "eval_runtime": 7.9495,
-      "eval_samples_per_second": 1198.439,
-      "eval_steps_per_second": 1.258,
+      "eval_loss": 3.899839401245117,
+      "eval_runtime": 7.9432,
+      "eval_samples_per_second": 1199.387,
+      "eval_steps_per_second": 1.259,
       "step": 700
     },
     {
       "epoch": 0.024266936299292215,
-      "grad_norm": 0.8203125,
-      "learning_rate": 0.0007,
-      "loss": 3.2640079498291015,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.0003,
+      "loss": 3.8832908630371095,
       "step": 720
     },
     {
       "epoch": 0.02494101786316144,
-      "grad_norm": 0.796875,
-      "learning_rate": 0.0007,
-      "loss": 3.2568283081054688,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.0003,
+      "loss": 3.873937225341797,
       "step": 740
     },
     {
       "epoch": 0.02561509942703067,
-      "grad_norm": 0.828125,
-      "learning_rate": 0.0007,
-      "loss": 3.206019973754883,
+      "grad_norm": 1.5,
+      "learning_rate": 0.0003,
+      "loss": 3.8289634704589846,
       "step": 760
     },
     {
       "epoch": 0.0262891809908999,
-      "grad_norm": 0.80078125,
-      "learning_rate": 0.0007,
-      "loss": 3.164164924621582,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.0003,
+      "loss": 3.78992919921875,
       "step": 780
     },
     {
       "epoch": 0.026963262554769128,
-      "grad_norm": 0.85546875,
-      "learning_rate": 0.0007,
-      "loss": 3.1771799087524415,
+      "grad_norm": 1.1015625,
+      "learning_rate": 0.0003,
+      "loss": 3.7991443634033204,
       "step": 800
     },
     {
       "epoch": 0.026963262554769128,
-      "eval_loss": 3.1695895195007324,
-      "eval_runtime": 7.9915,
-      "eval_samples_per_second": 1192.141,
-      "eval_steps_per_second": 1.251,
+      "eval_loss": 3.794043779373169,
+      "eval_runtime": 7.9171,
+      "eval_samples_per_second": 1203.347,
+      "eval_steps_per_second": 1.263,
       "step": 800
     }
   ],

zain/Activation/out/mlp-gelu-9L_run/checkpoint-800/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

@@ -116,3 +116,18 @@
 {"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}
+{"step": 600, "epoch": 0.020222446916076844, "timestamp": 1787067759.983548, "eval_loss": 4.0582146644592285, "eval_runtime": 7.9148, "eval_samples_per_second": 1203.7, "eval_steps_per_second": 1.263, "train/total_time_seconds": 13.223767712712288, "train/time_per_step_avg": 0.02113275308161974, "train/epoch_time_elapsed": 76.14629316329956, "train/estimated_remaining_minutes": 0.6979210737264818}
+{"step": 620, "epoch": 0.020896528479946073, "timestamp": 1787067760.930155, "loss": 4.019903182983398, "grad_norm": 1.234375, "learning_rate": 0.0003, "train/total_time_seconds": 13.63673610985279, "train/time_per_step_avg": 0.020922258235514163, "train/epoch_time_elapsed": 77.09290066733956, "train/estimated_remaining_minutes": 0.6891683840463239}
+{"step": 640, "epoch": 0.021570610043815303, "timestamp": 1787067761.8332198, "loss": 3.995362091064453, "grad_norm": 1.421875, "learning_rate": 0.0003, "train/total_time_seconds": 14.049914173781872, "train/time_per_step_avg": 0.020797862485051156, "train/epoch_time_elapsed": 77.99596579000354, "train/estimated_remaining_minutes": 0.6805427177925594}
+{"step": 660, "epoch": 0.022244691607684528, "timestamp": 1787067762.7551243, "loss": 3.961619186401367, "grad_norm": 1.1875, "learning_rate": 0.0003, "train/total_time_seconds": 14.477505411952734, "train/time_per_step_avg": 0.020898949950933457, "train/epoch_time_elapsed": 78.91787022352219, "train/estimated_remaining_minutes": 0.6726921706563896}
+{"step": 680, "epoch": 0.022918773171553757, "timestamp": 1787067763.759098, "loss": 3.922329330444336, "grad_norm": 1.2578125, "learning_rate": 0.0003, "train/total_time_seconds": 14.928573966026306, "train/time_per_step_avg": 0.021227723099291326, "train/epoch_time_elapsed": 79.9218439757824, "train/estimated_remaining_minutes": 0.6659314857394087}
+{"step": 700, "epoch": 0.023592854735422986, "timestamp": 1787067764.7285035, "loss": 3.915304946899414, "grad_norm": 1.34375, "learning_rate": 0.0003, "train/total_time_seconds": 15.398288868367672, "train/time_per_step_avg": 0.02174521155655384, "train/epoch_time_elapsed": 80.89124953746796, "train/estimated_remaining_minutes": 0.659926665787186}
+{"step": 700, "epoch": 0.023592854735422986, "timestamp": 1787067772.6732872, "eval_loss": 3.899839401245117, "eval_runtime": 7.9432, "eval_samples_per_second": 1199.387, "eval_steps_per_second": 1.259, "train/total_time_seconds": 15.398288868367672, "train/time_per_step_avg": 0.02174521155655384, "train/epoch_time_elapsed": 88.83603245019913, "train/estimated_remaining_minutes": 0.659926665787186}
+{"step": 720, "epoch": 0.024266936299292215, "timestamp": 1787067773.6728122, "loss": 3.8832908630371095, "grad_norm": 1.265625, "learning_rate": 0.0003, "train/total_time_seconds": 15.860269576311111, "train/time_per_step_avg": 0.022235334664583207, "train/epoch_time_elapsed": 89.83555833995342, "train/estimated_remaining_minutes": 0.6535018482831894}
+{"step": 740, "epoch": 0.02494101786316144, "timestamp": 1787067774.6581304, "loss": 3.873937225341797, "grad_norm": 1.2734375, "learning_rate": 0.0003, "train/total_time_seconds": 16.31060327962041, "train/time_per_step_avg": 0.022606891058385373, "train/epoch_time_elapsed": 90.82087651267648, "train/estimated_remaining_minutes": 0.6465464363092774}
+{"step": 760, "epoch": 0.02561509942703067, "timestamp": 1787067775.5529265, "loss": 3.8289634704589846, "grad_norm": 1.5, "learning_rate": 0.0003, "train/total_time_seconds": 16.720402892678976, "train/time_per_step_avg": 0.02242897480726242, "train/epoch_time_elapsed": 91.71567215025425, "train/estimated_remaining_minutes": 0.6380153735364346}
+{"step": 780, "epoch": 0.0262891809908999, "timestamp": 1787067776.4514818, "loss": 3.78992919921875, "grad_norm": 1.265625, "learning_rate": 0.0003, "train/total_time_seconds": 17.129779014736414, "train/time_per_step_avg": 0.022012050487101077, "train/epoch_time_elapsed": 92.61422762274742, "train/estimated_remaining_minutes": 0.6295559808834751}
+{"step": 800, "epoch": 0.026963262554769128, "timestamp": 1787067777.3482258, "loss": 3.7991443634033204, "grad_norm": 1.1015625, "learning_rate": 0.0003, "train/total_time_seconds": 17.54112770035863, "train/time_per_step_avg": 0.021428388319909574, "train/epoch_time_elapsed": 93.51097171381116, "train/estimated_remaining_minutes": 0.6212482727210348}
+{"step": 800, "epoch": 0.026963262554769128, "timestamp": 1787067785.2667353, "eval_loss": 3.794043779373169, "eval_runtime": 7.9171, "eval_samples_per_second": 1203.347, "eval_steps_per_second": 1.263, "train/total_time_seconds": 17.54112770035863, "train/time_per_step_avg": 0.021428388319909574, "train/epoch_time_elapsed": 101.4294798001647, "train/estimated_remaining_minutes": 0.6212482727210348}
+{"step": 820, "epoch": 0.027637344118638354, "timestamp": 1787067786.2143607, "loss": 3.7606269836425783, "grad_norm": 1.140625, "learning_rate": 0.0003, "train/total_time_seconds": 17.96183804422617, "train/time_per_step_avg": 0.021015684679150583, "train/epoch_time_elapsed": 102.37710624560714, "train/estimated_remaining_minutes": 0.6133310551686986}
+{"step": 840, "epoch": 0.028311425682507583, "timestamp": 1787067787.139812, "loss": 3.7543869018554688, "grad_norm": 1.234375, "learning_rate": 0.0003, "train/total_time_seconds": 18.38495372235775, "train/time_per_step_avg": 0.02074350442737341, "train/epoch_time_elapsed": 103.30255784094334, "train/estimated_remaining_minutes": 0.6055361741887672}