Auto upload zain 2026-08-19T17:31:52.723720

zain/Activation/out/mlp-linear-9L_run/checkpoint-100/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3205cd2887410b1cdfe08cb74e4769a33196e2a13a43044fe0f59fc69036228d
+oid sha256:ee3150e1d93b5874623c63f0e2ea5b36fb2e65acf8d44077a0e287e12a034a46
 size 4010544

zain/Activation/out/mlp-linear-9L_run/checkpoint-100/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a882674dcbcbe9decabd0de3f09bb8588e04c2d7e98fe233ba5ad90cc7eb1b49
+oid sha256:e5025c23ee5dd3f3ad71dfcf508451b402edf9bf8bf3bd75060dc94f0d0b8991
 size 8068282

zain/Activation/out/mlp-linear-9L_run/checkpoint-100/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb46541d572e87fb0d4fda911efea60cde9a6c4b2c0ba1e6a6c081af0a9ab78c
+oid sha256:467abc10c7d90be39dedcb07aeb5ab431826fa1c3718145ad8ea209f579afd08
 size 1064

zain/Activation/out/mlp-linear-9L_run/checkpoint-100/trainer_state.json

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003370407819346141,
+  "epoch": 0.008426019548365353,
   "eval_steps": 100,
   "global_step": 100,
   "is_hyper_param_search": false,
@@ -10,51 +10,51 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0006740815638692282,
-      "grad_norm": 1.796875,
-      "learning_rate": 1.14e-05,
-      "loss": 8.322640228271485,
+      "epoch": 0.0016852039096730705,
+      "grad_norm": 1.2421875,
+      "learning_rate": 9.5e-05,
+      "loss": 8.200721740722656,
       "step": 20
     },
     {
-      "epoch": 0.0013481631277384564,
-      "grad_norm": 1.75,
-      "learning_rate": 2.34e-05,
-      "loss": 8.267462158203125,
+      "epoch": 0.003370407819346141,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.00019500000000000002,
+      "loss": 7.764720153808594,
       "step": 40
     },
     {
-      "epoch": 0.0020222446916076846,
-      "grad_norm": 1.3046875,
-      "learning_rate": 3.539999999999999e-05,
-      "loss": 8.106219482421874,
+      "epoch": 0.005055611729019211,
+      "grad_norm": 1.2265625,
+      "learning_rate": 0.000295,
+      "loss": 7.160160064697266,
       "step": 60
     },
     {
-      "epoch": 0.002696326255476913,
-      "grad_norm": 1.28125,
-      "learning_rate": 4.7399999999999993e-05,
-      "loss": 7.948130798339844,
+      "epoch": 0.006740815638692282,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.000395,
+      "loss": 6.480591583251953,
       "step": 80
     },
     {
-      "epoch": 0.003370407819346141,
-      "grad_norm": 1.25,
-      "learning_rate": 5.94e-05,
-      "loss": 7.777301788330078,
+      "epoch": 0.008426019548365353,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.000495,
+      "loss": 5.919136428833008,
       "step": 100
     },
     {
-      "epoch": 0.003370407819346141,
-      "eval_loss": 7.679966926574707,
-      "eval_runtime": 8.4901,
-      "eval_samples_per_second": 1122.134,
-      "eval_steps_per_second": 0.824,
+      "epoch": 0.008426019548365353,
+      "eval_loss": 5.634258270263672,
+      "eval_runtime": 7.97,
+      "eval_samples_per_second": 1195.356,
+      "eval_steps_per_second": 0.878,
       "step": 100
     }
   ],
   "logging_steps": 20,
-  "max_steps": 2500,
+  "max_steps": 1000,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,
@@ -70,8 +70,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 14519422156800.0,
-  "train_batch_size": 32,
+  "total_flos": 36298555392000.0,
+  "train_batch_size": 80,
   "trial_name": null,
   "trial_params": null
 }

zain/Activation/out/mlp-linear-9L_run/checkpoint-100/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2150980b46702de80cf5b9c95700c86dedab0889248b4672dd0d83fc71b3aa0
+oid sha256:1168ea4bbfb8182db6bef374718cd5e9bd631ffa3eb5aaea5cc2742de1e3c4e5
 size 4920

zain/Activation/out/mlp-linear-9L_run/checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25e6401ca6e833bf33559d76a3dcf9fa3a56c754a0d66fedcc3e509d540d7d6b
+oid sha256:9e9c917aa3b25bdbc40f473e1cf017022bafceb91187441f0ef9ae86b2f5e2e6
 size 4010544

zain/Activation/out/mlp-linear-9L_run/checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cff32e52980386695d98d3cfb8388189ece637a31d0a7b7a82292c82f55463d3
+oid sha256:07e2637072ec2fd39d857cefe3a2082774923a5818032efc7dd3a59dde3fa267
 size 8068282

zain/Activation/out/mlp-linear-9L_run/checkpoint-1000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43b0add3f094a83e4275a4cab099e7b30afdca210ad5d92ec236fce75cdb93b3
+oid sha256:caa55e3f57ed08f9a32b207aad2408ead6f5f9323ec1ed27900a7c11e3b8bc31
 size 1064

zain/Activation/out/mlp-linear-9L_run/checkpoint-1000/trainer_state.json

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03370407819346141,
+  "epoch": 0.08426019548365352,
   "eval_steps": 100,
   "global_step": 1000,
   "is_hyper_param_search": false,
@@ -10,438 +10,438 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0006740815638692282,
-      "grad_norm": 1.796875,
-      "learning_rate": 1.14e-05,
-      "loss": 8.322640228271485,
+      "epoch": 0.0016852039096730705,
+      "grad_norm": 1.2421875,
+      "learning_rate": 9.5e-05,
+      "loss": 8.200721740722656,
       "step": 20
     },
     {
-      "epoch": 0.0013481631277384564,
-      "grad_norm": 1.75,
-      "learning_rate": 2.34e-05,
-      "loss": 8.267462158203125,
+      "epoch": 0.003370407819346141,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.00019500000000000002,
+      "loss": 7.764720153808594,
       "step": 40
     },
     {
-      "epoch": 0.0020222446916076846,
-      "grad_norm": 1.3046875,
-      "learning_rate": 3.539999999999999e-05,
-      "loss": 8.106219482421874,
+      "epoch": 0.005055611729019211,
+      "grad_norm": 1.2265625,
+      "learning_rate": 0.000295,
+      "loss": 7.160160064697266,
       "step": 60
     },
     {
-      "epoch": 0.002696326255476913,
-      "grad_norm": 1.28125,
-      "learning_rate": 4.7399999999999993e-05,
-      "loss": 7.948130798339844,
+      "epoch": 0.006740815638692282,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.000395,
+      "loss": 6.480591583251953,
       "step": 80
     },
     {
-      "epoch": 0.003370407819346141,
-      "grad_norm": 1.25,
-      "learning_rate": 5.94e-05,
-      "loss": 7.777301788330078,
+      "epoch": 0.008426019548365353,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.000495,
+      "loss": 5.919136428833008,
       "step": 100
     },
     {
-      "epoch": 0.003370407819346141,
-      "eval_loss": 7.679966926574707,
-      "eval_runtime": 8.4901,
-      "eval_samples_per_second": 1122.134,
-      "eval_steps_per_second": 0.824,
+      "epoch": 0.008426019548365353,
+      "eval_loss": 5.634258270263672,
+      "eval_runtime": 7.97,
+      "eval_samples_per_second": 1195.356,
+      "eval_steps_per_second": 0.878,
       "step": 100
     },
     {
-      "epoch": 0.004044489383215369,
-      "grad_norm": 1.2578125,
-      "learning_rate": 7.139999999999999e-05,
-      "loss": 7.585383605957031,
+      "epoch": 0.010111223458038422,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0005949999999999999,
+      "loss": 5.412916946411133,
       "step": 120
     },
     {
-      "epoch": 0.0047185709470845974,
-      "grad_norm": 1.25,
-      "learning_rate": 8.34e-05,
-      "loss": 7.3637535095214846,
+      "epoch": 0.011796427367711493,
+      "grad_norm": 1.515625,
+      "learning_rate": 0.000695,
+      "loss": 5.0327880859375,
       "step": 140
     },
     {
-      "epoch": 0.005392652510953826,
-      "grad_norm": 1.25,
-      "learning_rate": 9.539999999999999e-05,
-      "loss": 7.1375579833984375,
+      "epoch": 0.013481631277384564,
+      "grad_norm": 0.9765625,
+      "learning_rate": 0.000795,
+      "loss": 4.69476089477539,
       "step": 160
     },
     {
-      "epoch": 0.006066734074823054,
-      "grad_norm": 1.34375,
-      "learning_rate": 0.00010739999999999998,
-      "loss": 6.910031127929687,
+      "epoch": 0.015166835187057633,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.0008950000000000001,
+      "loss": 4.4246673583984375,
       "step": 180
     },
     {
-      "epoch": 0.006740815638692282,
-      "grad_norm": 1.3359375,
-      "learning_rate": 0.0001194,
-      "loss": 6.671029663085937,
+      "epoch": 0.016852039096730706,
+      "grad_norm": 0.87890625,
+      "learning_rate": 0.000995,
+      "loss": 4.204695129394532,
       "step": 200
     },
     {
-      "epoch": 0.006740815638692282,
-      "eval_loss": 6.548758506774902,
-      "eval_runtime": 8.6601,
-      "eval_samples_per_second": 1100.105,
-      "eval_steps_per_second": 0.808,
+      "epoch": 0.016852039096730706,
+      "eval_loss": 4.133424282073975,
+      "eval_runtime": 7.9329,
+      "eval_samples_per_second": 1200.942,
+      "eval_steps_per_second": 0.882,
       "step": 200
     },
     {
-      "epoch": 0.00741489720256151,
-      "grad_norm": 1.578125,
-      "learning_rate": 0.0001314,
-      "loss": 6.457804107666016,
+      "epoch": 0.018537243006403775,
+      "grad_norm": 0.6875,
+      "learning_rate": 0.001,
+      "loss": 4.048733520507812,
       "step": 220
     },
     {
-      "epoch": 0.008088978766430738,
-      "grad_norm": 1.4921875,
-      "learning_rate": 0.0001434,
-      "loss": 6.254596328735351,
+      "epoch": 0.020222446916076844,
+      "grad_norm": 0.73828125,
+      "learning_rate": 0.001,
+      "loss": 3.9190834045410154,
       "step": 240
     },
     {
-      "epoch": 0.008763060330299966,
-      "grad_norm": 1.171875,
-      "learning_rate": 0.00015539999999999998,
-      "loss": 6.047513961791992,
+      "epoch": 0.021907650825749917,
+      "grad_norm": 0.68359375,
+      "learning_rate": 0.001,
+      "loss": 3.7833847045898437,
       "step": 260
     },
     {
-      "epoch": 0.009437141894169195,
-      "grad_norm": 1.8828125,
-      "learning_rate": 0.0001674,
-      "loss": 5.870236587524414,
+      "epoch": 0.023592854735422986,
+      "grad_norm": 0.82421875,
+      "learning_rate": 0.001,
+      "loss": 3.700960159301758,
       "step": 280
     },
     {
-      "epoch": 0.010111223458038422,
-      "grad_norm": 1.359375,
-      "learning_rate": 0.00017939999999999997,
-      "loss": 5.72708740234375,
+      "epoch": 0.025278058645096056,
+      "grad_norm": 0.984375,
+      "learning_rate": 0.001,
+      "loss": 3.6359439849853517,
       "step": 300
     },
     {
-      "epoch": 0.010111223458038422,
-      "eval_loss": 5.652859687805176,
-      "eval_runtime": 8.4927,
-      "eval_samples_per_second": 1121.794,
-      "eval_steps_per_second": 0.824,
+      "epoch": 0.025278058645096056,
+      "eval_loss": 3.5975606441497803,
+      "eval_runtime": 7.973,
+      "eval_samples_per_second": 1194.91,
+      "eval_steps_per_second": 0.878,
       "step": 300
     },
     {
-      "epoch": 0.010785305021907651,
-      "grad_norm": 1.609375,
-      "learning_rate": 0.0001914,
-      "loss": 5.585579681396484,
+      "epoch": 0.026963262554769128,
+      "grad_norm": 0.80859375,
+      "learning_rate": 0.001,
+      "loss": 3.5393722534179686,
       "step": 320
     },
     {
-      "epoch": 0.011459386585776879,
-      "grad_norm": 1.671875,
-      "learning_rate": 0.00020339999999999998,
-      "loss": 5.470914077758789,
+      "epoch": 0.028648466464442197,
+      "grad_norm": 0.72265625,
+      "learning_rate": 0.001,
+      "loss": 3.492219924926758,
       "step": 340
     },
     {
-      "epoch": 0.012133468149646108,
-      "grad_norm": 1.4140625,
-      "learning_rate": 0.00021539999999999998,
-      "loss": 5.318555068969727,
+      "epoch": 0.030333670374115267,
+      "grad_norm": 0.8203125,
+      "learning_rate": 0.001,
+      "loss": 3.4430694580078125,
       "step": 360
     },
     {
-      "epoch": 0.012807549713515335,
-      "grad_norm": 1.6015625,
-      "learning_rate": 0.00022739999999999997,
-      "loss": 5.185982894897461,
+      "epoch": 0.032018874283788336,
+      "grad_norm": 0.8203125,
+      "learning_rate": 0.001,
+      "loss": 3.3989883422851563,
       "step": 380
     },
     {
-      "epoch": 0.013481631277384564,
-      "grad_norm": 1.2578125,
-      "learning_rate": 0.0002394,
-      "loss": 5.065654754638672,
+      "epoch": 0.03370407819346141,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.001,
+      "loss": 3.341664123535156,
       "step": 400
     },
     {
-      "epoch": 0.013481631277384564,
-      "eval_loss": 5.008047103881836,
-      "eval_runtime": 8.5503,
-      "eval_samples_per_second": 1114.232,
-      "eval_steps_per_second": 0.819,
+      "epoch": 0.03370407819346141,
+      "eval_loss": 3.3295202255249023,
+      "eval_runtime": 8.1687,
+      "eval_samples_per_second": 1166.287,
+      "eval_steps_per_second": 0.857,
       "step": 400
     },
     {
-      "epoch": 0.014155712841253791,
-      "grad_norm": 2.140625,
-      "learning_rate": 0.0002514,
-      "loss": 4.935818481445312,
+      "epoch": 0.03538928210313448,
+      "grad_norm": 0.7109375,
+      "learning_rate": 0.001,
+      "loss": 3.3047794342041015,
       "step": 420
     },
     {
-      "epoch": 0.01482979440512302,
-      "grad_norm": 1.1875,
-      "learning_rate": 0.00026339999999999995,
-      "loss": 4.853317642211914,
+      "epoch": 0.03707448601280755,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.001,
+      "loss": 3.258700942993164,
       "step": 440
     },
     {
-      "epoch": 0.015503875968992248,
-      "grad_norm": 1.5390625,
-      "learning_rate": 0.00027539999999999997,
-      "loss": 4.7492321014404295,
+      "epoch": 0.03875968992248062,
+      "grad_norm": 0.73046875,
+      "learning_rate": 0.001,
+      "loss": 3.229313278198242,
       "step": 460
     },
     {
-      "epoch": 0.016177957532861477,
-      "grad_norm": 1.921875,
-      "learning_rate": 0.00028739999999999994,
-      "loss": 4.629489898681641,
+      "epoch": 0.04044489383215369,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.001,
+      "loss": 3.202067565917969,
       "step": 480
     },
     {
-      "epoch": 0.016852039096730706,
-      "grad_norm": 1.7890625,
-      "learning_rate": 0.00029939999999999996,
-      "loss": 4.565845108032226,
+      "epoch": 0.04213009774182676,
+      "grad_norm": 0.7265625,
+      "learning_rate": 0.001,
+      "loss": 3.163772201538086,
       "step": 500
     },
     {
-      "epoch": 0.016852039096730706,
-      "eval_loss": 4.530772686004639,
-      "eval_runtime": 8.4284,
-      "eval_samples_per_second": 1130.345,
-      "eval_steps_per_second": 0.831,
+      "epoch": 0.04213009774182676,
+      "eval_loss": 3.157355308532715,
+      "eval_runtime": 7.9503,
+      "eval_samples_per_second": 1198.315,
+      "eval_steps_per_second": 0.88,
       "step": 500
     },
     {
-      "epoch": 0.01752612066059993,
-      "grad_norm": 1.140625,
-      "learning_rate": 0.0003,
-      "loss": 4.50256233215332,
+      "epoch": 0.043815301651499834,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.001,
+      "loss": 3.1448848724365233,
       "step": 520
     },
     {
-      "epoch": 0.01820020222446916,
-      "grad_norm": 1.7265625,
-      "learning_rate": 0.0003,
-      "loss": 4.419484710693359,
+      "epoch": 0.0455005055611729,
+      "grad_norm": 0.828125,
+      "learning_rate": 0.001,
+      "loss": 3.103527069091797,
       "step": 540
     },
     {
-      "epoch": 0.01887428378833839,
-      "grad_norm": 1.3125,
-      "learning_rate": 0.0003,
-      "loss": 4.363323593139649,
+      "epoch": 0.04718570947084597,
+      "grad_norm": 0.7578125,
+      "learning_rate": 0.001,
+      "loss": 3.08404541015625,
       "step": 560
     },
     {
-      "epoch": 0.01954836535220762,
-      "grad_norm": 1.5,
-      "learning_rate": 0.0003,
-      "loss": 4.3072765350341795,
+      "epoch": 0.04887091338051904,
+      "grad_norm": 0.76953125,
+      "learning_rate": 0.001,
+      "loss": 3.0501741409301757,
       "step": 580
     },
     {
-      "epoch": 0.020222446916076844,
-      "grad_norm": 1.9765625,
-      "learning_rate": 0.0003,
-      "loss": 4.263522338867188,
+      "epoch": 0.05055611729019211,
+      "grad_norm": 0.96875,
+      "learning_rate": 0.001,
+      "loss": 3.0376760482788088,
       "step": 600
     },
     {
-      "epoch": 0.020222446916076844,
-      "eval_loss": 4.239859580993652,
-      "eval_runtime": 8.5836,
-      "eval_samples_per_second": 1109.908,
-      "eval_steps_per_second": 0.816,
+      "epoch": 0.05055611729019211,
+      "eval_loss": 3.0310890674591064,
+      "eval_runtime": 8.1195,
+      "eval_samples_per_second": 1173.346,
+      "eval_steps_per_second": 0.862,
       "step": 600
     },
     {
-      "epoch": 0.020896528479946073,
-      "grad_norm": 1.2265625,
-      "learning_rate": 0.0003,
-      "loss": 4.207575988769531,
+      "epoch": 0.05224132119986518,
+      "grad_norm": 0.82421875,
+      "learning_rate": 0.001,
+      "loss": 3.0314205169677733,
       "step": 620
     },
     {
-      "epoch": 0.021570610043815303,
-      "grad_norm": 1.3359375,
-      "learning_rate": 0.0003,
-      "loss": 4.179453659057617,
+      "epoch": 0.053926525109538256,
+      "grad_norm": 0.640625,
+      "learning_rate": 0.001,
+      "loss": 3.0014928817749023,
       "step": 640
     },
     {
-      "epoch": 0.022244691607684528,
-      "grad_norm": 1.09375,
-      "learning_rate": 0.0003,
-      "loss": 4.13963508605957,
+      "epoch": 0.055611729019211326,
+      "grad_norm": 0.70703125,
+      "learning_rate": 0.001,
+      "loss": 2.9963293075561523,
       "step": 660
     },
     {
-      "epoch": 0.022918773171553757,
-      "grad_norm": 1.328125,
-      "learning_rate": 0.0003,
-      "loss": 4.0913646697998045,
+      "epoch": 0.057296932928884395,
+      "grad_norm": 0.7109375,
+      "learning_rate": 0.001,
+      "loss": 2.9568761825561523,
       "step": 680
     },
     {
-      "epoch": 0.023592854735422986,
-      "grad_norm": 1.609375,
-      "learning_rate": 0.0003,
-      "loss": 4.082810974121093,
+      "epoch": 0.058982136838557464,
+      "grad_norm": 0.69921875,
+      "learning_rate": 0.001,
+      "loss": 2.9395275115966797,
       "step": 700
     },
     {
-      "epoch": 0.023592854735422986,
-      "eval_loss": 4.061285495758057,
-      "eval_runtime": 8.3862,
-      "eval_samples_per_second": 1136.028,
-      "eval_steps_per_second": 0.835,
+      "epoch": 0.058982136838557464,
+      "eval_loss": 2.939429759979248,
+      "eval_runtime": 7.975,
+      "eval_samples_per_second": 1194.602,
+      "eval_steps_per_second": 0.878,
       "step": 700
     },
     {
-      "epoch": 0.024266936299292215,
-      "grad_norm": 1.453125,
-      "learning_rate": 0.0003,
-      "loss": 4.052593612670899,
+      "epoch": 0.06066734074823053,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.001,
+      "loss": 2.922671890258789,
       "step": 720
     },
     {
-      "epoch": 0.02494101786316144,
-      "grad_norm": 1.46875,
-      "learning_rate": 0.0003,
-      "loss": 4.038698196411133,
+      "epoch": 0.06235254465790361,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.001,
+      "loss": 2.9145633697509767,
       "step": 740
     },
     {
-      "epoch": 0.02561509942703067,
-      "grad_norm": 1.671875,
-      "learning_rate": 0.0003,
-      "loss": 3.99466552734375,
+      "epoch": 0.06403774856757667,
+      "grad_norm": 0.7109375,
+      "learning_rate": 0.001,
+      "loss": 2.8876668930053713,
       "step": 760
     },
     {
-      "epoch": 0.0262891809908999,
-      "grad_norm": 1.3671875,
-      "learning_rate": 0.0003,
-      "loss": 3.9530941009521485,
+      "epoch": 0.06572295247724974,
+      "grad_norm": 0.69140625,
+      "learning_rate": 0.001,
+      "loss": 2.8692466735839846,
       "step": 780
     },
     {
-      "epoch": 0.026963262554769128,
-      "grad_norm": 1.4375,
-      "learning_rate": 0.0003,
-      "loss": 3.95872802734375,
+      "epoch": 0.06740815638692282,
+      "grad_norm": 0.68359375,
+      "learning_rate": 0.001,
+      "loss": 2.8788633346557617,
       "step": 800
     },
     {
-      "epoch": 0.026963262554769128,
-      "eval_loss": 3.9487836360931396,
-      "eval_runtime": 8.7643,
-      "eval_samples_per_second": 1087.026,
-      "eval_steps_per_second": 0.799,
+      "epoch": 0.06740815638692282,
+      "eval_loss": 2.8632190227508545,
+      "eval_runtime": 8.2773,
+      "eval_samples_per_second": 1150.973,
+      "eval_steps_per_second": 0.846,
       "step": 800
     },
     {
-      "epoch": 0.027637344118638354,
-      "grad_norm": 1.2734375,
-      "learning_rate": 0.0003,
-      "loss": 3.917556381225586,
+      "epoch": 0.0690933602965959,
+      "grad_norm": 0.6796875,
+      "learning_rate": 0.001,
+      "loss": 2.8496471405029298,
       "step": 820
     },
     {
-      "epoch": 0.028311425682507583,
-      "grad_norm": 1.390625,
-      "learning_rate": 0.0003,
-      "loss": 3.913285827636719,
+      "epoch": 0.07077856420626896,
+      "grad_norm": 0.62109375,
+      "learning_rate": 0.001,
+      "loss": 2.847636604309082,
       "step": 840
     },
     {
-      "epoch": 0.028985507246376812,
-      "grad_norm": 1.453125,
-      "learning_rate": 0.0003,
-      "loss": 3.9367324829101564,
+      "epoch": 0.07246376811594203,
+      "grad_norm": 0.73046875,
+      "learning_rate": 0.001,
+      "loss": 2.8339916229248048,
       "step": 860
     },
     {
-      "epoch": 0.02965958881024604,
-      "grad_norm": 1.328125,
-      "learning_rate": 0.0003,
-      "loss": 3.8899993896484375,
+      "epoch": 0.0741489720256151,
+      "grad_norm": 0.69921875,
+      "learning_rate": 0.001,
+      "loss": 2.8253028869628904,
       "step": 880
     },
     {
-      "epoch": 0.030333670374115267,
-      "grad_norm": 1.6875,
-      "learning_rate": 0.0003,
-      "loss": 3.8575370788574217,
+      "epoch": 0.07583417593528817,
+      "grad_norm": 0.6875,
+      "learning_rate": 0.001,
+      "loss": 2.7853120803833007,
       "step": 900
     },
     {
-      "epoch": 0.030333670374115267,
-      "eval_loss": 3.871619701385498,
-      "eval_runtime": 8.7624,
-      "eval_samples_per_second": 1087.263,
-      "eval_steps_per_second": 0.799,
+      "epoch": 0.07583417593528817,
+      "eval_loss": 2.8034849166870117,
+      "eval_runtime": 7.9593,
+      "eval_samples_per_second": 1196.967,
+      "eval_steps_per_second": 0.879,
       "step": 900
     },
     {
-      "epoch": 0.031007751937984496,
-      "grad_norm": 1.1875,
-      "learning_rate": 0.0003,
-      "loss": 3.870378112792969,
+      "epoch": 0.07751937984496124,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.001,
+      "loss": 2.794095993041992,
       "step": 920
     },
     {
-      "epoch": 0.031681833501853725,
-      "grad_norm": 1.234375,
-      "learning_rate": 0.0003,
-      "loss": 3.852782440185547,
+      "epoch": 0.07920458375463431,
+      "grad_norm": 0.671875,
+      "learning_rate": 0.001,
+      "loss": 2.7890634536743164,
       "step": 940
     },
     {
-      "epoch": 0.032355915065722954,
-      "grad_norm": 1.515625,
-      "learning_rate": 0.0003,
-      "loss": 3.821004867553711,
+      "epoch": 0.08088978766430738,
+      "grad_norm": 0.58203125,
+      "learning_rate": 0.001,
+      "loss": 2.784823989868164,
       "step": 960
     },
     {
-      "epoch": 0.03302999662959218,
-      "grad_norm": 1.4921875,
-      "learning_rate": 0.0003,
-      "loss": 3.8098331451416017,
+      "epoch": 0.08257499157398045,
+      "grad_norm": 0.60546875,
+      "learning_rate": 0.001,
+      "loss": 2.775278663635254,
       "step": 980
     },
     {
-      "epoch": 0.03370407819346141,
-      "grad_norm": 1.4453125,
-      "learning_rate": 0.0003,
-      "loss": 3.806192398071289,
+      "epoch": 0.08426019548365352,
+      "grad_norm": 0.78125,
+      "learning_rate": 0.001,
+      "loss": 2.753749656677246,
       "step": 1000
     },
     {
-      "epoch": 0.03370407819346141,
-      "eval_loss": 3.805492401123047,
-      "eval_runtime": 8.55,
-      "eval_samples_per_second": 1114.265,
-      "eval_steps_per_second": 0.819,
+      "epoch": 0.08426019548365352,
+      "eval_loss": 2.7597591876983643,
+      "eval_runtime": 7.9273,
+      "eval_samples_per_second": 1201.797,
+      "eval_steps_per_second": 0.883,
       "step": 1000
     }
   ],
   "logging_steps": 20,
-  "max_steps": 2500,
+  "max_steps": 1000,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,
@@ -452,13 +452,13 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 145194221568000.0,
-  "train_batch_size": 32,
+  "total_flos": 362985553920000.0,
+  "train_batch_size": 80,
   "trial_name": null,
   "trial_params": null
 }

zain/Activation/out/mlp-linear-9L_run/checkpoint-1000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2150980b46702de80cf5b9c95700c86dedab0889248b4672dd0d83fc71b3aa0
+oid sha256:1168ea4bbfb8182db6bef374718cd5e9bd631ffa3eb5aaea5cc2742de1e3c4e5
 size 4920

zain/Activation/out/mlp-linear-9L_run/checkpoint-200/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dabdab62649a48b7e0719e987e21b5a8de4f75a2f5ce3a06bc1a965d554d2e35
+oid sha256:762656e814c7e30cb1d1201812e18f80bb82acb680371d50ce8a4d48aad63d22
 size 4010544

zain/Activation/out/mlp-linear-9L_run/checkpoint-200/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6deb9eaefae8a5323312dff49adc7d3484cf9c4e17c0a1e2428e7085ed21c689
+oid sha256:989b134329aeb289210a3d241dd378c16f615ba0122bd4c864664949d7649488
 size 8068282

zain/Activation/out/mlp-linear-9L_run/checkpoint-200/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8135ef28e3a46ab54526e011bfc69abed48145f3d54b2d14293e0383798411e
+oid sha256:7fcf92cd525e966db7d3124c96530397441749e7c16eb0c37e304bcf4507a234
 size 1064

zain/Activation/out/mlp-linear-9L_run/checkpoint-200/trainer_state.json

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006740815638692282,
+  "epoch": 0.016852039096730706,
   "eval_steps": 100,
   "global_step": 200,
   "is_hyper_param_search": false,
@@ -10,94 +10,94 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0006740815638692282,
-      "grad_norm": 1.796875,
-      "learning_rate": 1.14e-05,
-      "loss": 8.322640228271485,
+      "epoch": 0.0016852039096730705,
+      "grad_norm": 1.2421875,
+      "learning_rate": 9.5e-05,
+      "loss": 8.200721740722656,
       "step": 20
     },
     {
-      "epoch": 0.0013481631277384564,
-      "grad_norm": 1.75,
-      "learning_rate": 2.34e-05,
-      "loss": 8.267462158203125,
+      "epoch": 0.003370407819346141,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.00019500000000000002,
+      "loss": 7.764720153808594,
       "step": 40
     },
     {
-      "epoch": 0.0020222446916076846,
-      "grad_norm": 1.3046875,
-      "learning_rate": 3.539999999999999e-05,
-      "loss": 8.106219482421874,
+      "epoch": 0.005055611729019211,
+      "grad_norm": 1.2265625,
+      "learning_rate": 0.000295,
+      "loss": 7.160160064697266,
       "step": 60
     },
     {
-      "epoch": 0.002696326255476913,
-      "grad_norm": 1.28125,
-      "learning_rate": 4.7399999999999993e-05,
-      "loss": 7.948130798339844,
+      "epoch": 0.006740815638692282,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.000395,
+      "loss": 6.480591583251953,
       "step": 80
     },
     {
-      "epoch": 0.003370407819346141,
-      "grad_norm": 1.25,
-      "learning_rate": 5.94e-05,
-      "loss": 7.777301788330078,
+      "epoch": 0.008426019548365353,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.000495,
+      "loss": 5.919136428833008,
       "step": 100
     },
     {
-      "epoch": 0.003370407819346141,
-      "eval_loss": 7.679966926574707,
-      "eval_runtime": 8.4901,
-      "eval_samples_per_second": 1122.134,
-      "eval_steps_per_second": 0.824,
+      "epoch": 0.008426019548365353,
+      "eval_loss": 5.634258270263672,
+      "eval_runtime": 7.97,
+      "eval_samples_per_second": 1195.356,
+      "eval_steps_per_second": 0.878,
       "step": 100
     },
     {
-      "epoch": 0.004044489383215369,
-      "grad_norm": 1.2578125,
-      "learning_rate": 7.139999999999999e-05,
-      "loss": 7.585383605957031,
+      "epoch": 0.010111223458038422,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0005949999999999999,
+      "loss": 5.412916946411133,
       "step": 120
     },
     {
-      "epoch": 0.0047185709470845974,
-      "grad_norm": 1.25,
-      "learning_rate": 8.34e-05,
-      "loss": 7.3637535095214846,
+      "epoch": 0.011796427367711493,
+      "grad_norm": 1.515625,
+      "learning_rate": 0.000695,
+      "loss": 5.0327880859375,
       "step": 140
     },
     {
-      "epoch": 0.005392652510953826,
-      "grad_norm": 1.25,
-      "learning_rate": 9.539999999999999e-05,
-      "loss": 7.1375579833984375,
+      "epoch": 0.013481631277384564,
+      "grad_norm": 0.9765625,
+      "learning_rate": 0.000795,
+      "loss": 4.69476089477539,
       "step": 160
     },
     {
-      "epoch": 0.006066734074823054,
-      "grad_norm": 1.34375,
-      "learning_rate": 0.00010739999999999998,
-      "loss": 6.910031127929687,
+      "epoch": 0.015166835187057633,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.0008950000000000001,
+      "loss": 4.4246673583984375,
       "step": 180
     },
     {
-      "epoch": 0.006740815638692282,
-      "grad_norm": 1.3359375,
-      "learning_rate": 0.0001194,
-      "loss": 6.671029663085937,
+      "epoch": 0.016852039096730706,
+      "grad_norm": 0.87890625,
+      "learning_rate": 0.000995,
+      "loss": 4.204695129394532,
       "step": 200
     },
     {
-      "epoch": 0.006740815638692282,
-      "eval_loss": 6.548758506774902,
-      "eval_runtime": 8.6601,
-      "eval_samples_per_second": 1100.105,
-      "eval_steps_per_second": 0.808,
+      "epoch": 0.016852039096730706,
+      "eval_loss": 4.133424282073975,
+      "eval_runtime": 7.9329,
+      "eval_samples_per_second": 1200.942,
+      "eval_steps_per_second": 0.882,
       "step": 200
     }
   ],
   "logging_steps": 20,
-  "max_steps": 2500,
+  "max_steps": 1000,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,
@@ -113,8 +113,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 29038844313600.0,
-  "train_batch_size": 32,
+  "total_flos": 72597110784000.0,
+  "train_batch_size": 80,
   "trial_name": null,
   "trial_params": null
 }

zain/Activation/out/mlp-linear-9L_run/checkpoint-200/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2150980b46702de80cf5b9c95700c86dedab0889248b4672dd0d83fc71b3aa0
+oid sha256:1168ea4bbfb8182db6bef374718cd5e9bd631ffa3eb5aaea5cc2742de1e3c4e5
 size 4920

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb990e0914241d4792cac924c1bd1c5df31d8be53363d93f8974a9fb0dec2538
+oid sha256:b2e42aa29a0e4239b16970142301875769ce1b268e295391a75ea811c5a746ee
 size 4010544

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b94a0ae890ae65285e885b159c1fc16b34f98fedb60ba41ed1d76b33f9b25bd6
+oid sha256:966c63057f1db063d6121bec616b0b7e30bbd6e5ca64d4995afcd3ea5b56c684
 size 8068282

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58882af6bc66e44afb6aa7c1675e12212a966de0b9a2fc23de850f993cbc78d3
+oid sha256:41f2c5ea16f05cf86f93aaafaefd9dff965c2a78f38db3e537fd39e07a540ff4
 size 1064

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

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010111223458038422,
+  "epoch": 0.025278058645096056,
   "eval_steps": 100,
   "global_step": 300,
   "is_hyper_param_search": false,
@@ -10,137 +10,137 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0006740815638692282,
-      "grad_norm": 1.796875,
-      "learning_rate": 1.14e-05,
-      "loss": 8.322640228271485,
+      "epoch": 0.0016852039096730705,
+      "grad_norm": 1.2421875,
+      "learning_rate": 9.5e-05,
+      "loss": 8.200721740722656,
       "step": 20
     },
     {
-      "epoch": 0.0013481631277384564,
-      "grad_norm": 1.75,
-      "learning_rate": 2.34e-05,
-      "loss": 8.267462158203125,
+      "epoch": 0.003370407819346141,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.00019500000000000002,
+      "loss": 7.764720153808594,
       "step": 40
     },
     {
-      "epoch": 0.0020222446916076846,
-      "grad_norm": 1.3046875,
-      "learning_rate": 3.539999999999999e-05,
-      "loss": 8.106219482421874,
+      "epoch": 0.005055611729019211,
+      "grad_norm": 1.2265625,
+      "learning_rate": 0.000295,
+      "loss": 7.160160064697266,
       "step": 60
     },
     {
-      "epoch": 0.002696326255476913,
-      "grad_norm": 1.28125,
-      "learning_rate": 4.7399999999999993e-05,
-      "loss": 7.948130798339844,
+      "epoch": 0.006740815638692282,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.000395,
+      "loss": 6.480591583251953,
       "step": 80
     },
     {
-      "epoch": 0.003370407819346141,
-      "grad_norm": 1.25,
-      "learning_rate": 5.94e-05,
-      "loss": 7.777301788330078,
+      "epoch": 0.008426019548365353,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.000495,
+      "loss": 5.919136428833008,
       "step": 100
     },
     {
-      "epoch": 0.003370407819346141,
-      "eval_loss": 7.679966926574707,
-      "eval_runtime": 8.4901,
-      "eval_samples_per_second": 1122.134,
-      "eval_steps_per_second": 0.824,
+      "epoch": 0.008426019548365353,
+      "eval_loss": 5.634258270263672,
+      "eval_runtime": 7.97,
+      "eval_samples_per_second": 1195.356,
+      "eval_steps_per_second": 0.878,
       "step": 100
     },
     {
-      "epoch": 0.004044489383215369,
-      "grad_norm": 1.2578125,
-      "learning_rate": 7.139999999999999e-05,
-      "loss": 7.585383605957031,
+      "epoch": 0.010111223458038422,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0005949999999999999,
+      "loss": 5.412916946411133,
       "step": 120
     },
     {
-      "epoch": 0.0047185709470845974,
-      "grad_norm": 1.25,
-      "learning_rate": 8.34e-05,
-      "loss": 7.3637535095214846,
+      "epoch": 0.011796427367711493,
+      "grad_norm": 1.515625,
+      "learning_rate": 0.000695,
+      "loss": 5.0327880859375,
       "step": 140
     },
     {
-      "epoch": 0.005392652510953826,
-      "grad_norm": 1.25,
-      "learning_rate": 9.539999999999999e-05,
-      "loss": 7.1375579833984375,
+      "epoch": 0.013481631277384564,
+      "grad_norm": 0.9765625,
+      "learning_rate": 0.000795,
+      "loss": 4.69476089477539,
       "step": 160
     },
     {
-      "epoch": 0.006066734074823054,
-      "grad_norm": 1.34375,
-      "learning_rate": 0.00010739999999999998,
-      "loss": 6.910031127929687,
+      "epoch": 0.015166835187057633,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.0008950000000000001,
+      "loss": 4.4246673583984375,
       "step": 180
     },
     {
-      "epoch": 0.006740815638692282,
-      "grad_norm": 1.3359375,
-      "learning_rate": 0.0001194,
-      "loss": 6.671029663085937,
+      "epoch": 0.016852039096730706,
+      "grad_norm": 0.87890625,
+      "learning_rate": 0.000995,
+      "loss": 4.204695129394532,
       "step": 200
     },
     {
-      "epoch": 0.006740815638692282,
-      "eval_loss": 6.548758506774902,
-      "eval_runtime": 8.6601,
-      "eval_samples_per_second": 1100.105,
-      "eval_steps_per_second": 0.808,
+      "epoch": 0.016852039096730706,
+      "eval_loss": 4.133424282073975,
+      "eval_runtime": 7.9329,
+      "eval_samples_per_second": 1200.942,
+      "eval_steps_per_second": 0.882,
       "step": 200
     },
     {
-      "epoch": 0.00741489720256151,
-      "grad_norm": 1.578125,
-      "learning_rate": 0.0001314,
-      "loss": 6.457804107666016,
+      "epoch": 0.018537243006403775,
+      "grad_norm": 0.6875,
+      "learning_rate": 0.001,
+      "loss": 4.048733520507812,
       "step": 220
     },
     {
-      "epoch": 0.008088978766430738,
-      "grad_norm": 1.4921875,
-      "learning_rate": 0.0001434,
-      "loss": 6.254596328735351,
+      "epoch": 0.020222446916076844,
+      "grad_norm": 0.73828125,
+      "learning_rate": 0.001,
+      "loss": 3.9190834045410154,
       "step": 240
     },
     {
-      "epoch": 0.008763060330299966,
-      "grad_norm": 1.171875,
-      "learning_rate": 0.00015539999999999998,
-      "loss": 6.047513961791992,
+      "epoch": 0.021907650825749917,
+      "grad_norm": 0.68359375,
+      "learning_rate": 0.001,
+      "loss": 3.7833847045898437,
       "step": 260
     },
     {
-      "epoch": 0.009437141894169195,
-      "grad_norm": 1.8828125,
-      "learning_rate": 0.0001674,
-      "loss": 5.870236587524414,
+      "epoch": 0.023592854735422986,
+      "grad_norm": 0.82421875,
+      "learning_rate": 0.001,
+      "loss": 3.700960159301758,
       "step": 280
     },
     {
-      "epoch": 0.010111223458038422,
-      "grad_norm": 1.359375,
-      "learning_rate": 0.00017939999999999997,
-      "loss": 5.72708740234375,
+      "epoch": 0.025278058645096056,
+      "grad_norm": 0.984375,
+      "learning_rate": 0.001,
+      "loss": 3.6359439849853517,
       "step": 300
     },
     {
-      "epoch": 0.010111223458038422,
-      "eval_loss": 5.652859687805176,
-      "eval_runtime": 8.4927,
-      "eval_samples_per_second": 1121.794,
-      "eval_steps_per_second": 0.824,
+      "epoch": 0.025278058645096056,
+      "eval_loss": 3.5975606441497803,
+      "eval_runtime": 7.973,
+      "eval_samples_per_second": 1194.91,
+      "eval_steps_per_second": 0.878,
       "step": 300
     }
   ],
   "logging_steps": 20,
-  "max_steps": 2500,
+  "max_steps": 1000,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,
@@ -156,8 +156,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 43558266470400.0,
-  "train_batch_size": 32,
+  "total_flos": 108895666176000.0,
+  "train_batch_size": 80,
   "trial_name": null,
   "trial_params": null
 }

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2150980b46702de80cf5b9c95700c86dedab0889248b4672dd0d83fc71b3aa0
+oid sha256:1168ea4bbfb8182db6bef374718cd5e9bd631ffa3eb5aaea5cc2742de1e3c4e5
 size 4920

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:049537c1549b054350ff7c805931cdcbf686fe62e058a92106c3333654a38cf5
+oid sha256:2d0ff1e1088550403d6e0b8fef9452fd5b3227af8fe86abe61830ee7d0bf370c
 size 4010544

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2227c0e51f5fb74e817c276b3e8e52e1cbc463a8d31e8ce74c3f10d5f02f9bf3
+oid sha256:09d9c4167051eebf1c452b742773d843470782702987d8ad0f8f7e4b3f7e037c
 size 8068282