Auto upload zain 2026-08-12T19:12:22.442943

zain/Activation/out/glu-linear-150L_run/checkpoint-1000/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "linear",
+  "architectures": [
+    "TinyLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "mlp_type": "glu",
+  "model_type": "tiny_llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 150,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "tokenizer_name": "w-ahmad/tiny-stories-tokenizer",
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": false,
+  "vocab_size": 4096,
+  "waleed_beta": 10.0
+}

zain/Activation/out/glu-linear-150L_run/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e76362c91e06038fea9af3a37c65bfaf32f86e70bc728754e698978b98cbf1
+size 50427120

zain/Activation/out/glu-linear-150L_run/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4fa94d550d1f477bf57f4c490f763e9c240d9c1a0d9c7de625d85494899b73b
+size 101708778

zain/Activation/out/glu-linear-150L_run/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:645b71843375baf4cc10bc75a2f0f04e91b8e3f8e8929f518a87022898b3bc20
+size 14244

zain/Activation/out/glu-linear-150L_run/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9db76f238494a413266398860b344c6c4c0f3a045ef78b23af1afac6775a12d1
+size 1064

zain/Activation/out/glu-linear-150L_run/checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

zain/Activation/out/glu-linear-150L_run/checkpoint-1000/trainer_state.json

@@ -0,0 +1,544 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.06740815638692282,
+  "eval_steps": 50,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0013481631277384564,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000475,
+      "loss": 7.956696319580078,
+      "step": 20
+    },
+    {
+      "epoch": 0.002696326255476913,
+      "grad_norm": 0.8671875,
+      "learning_rate": 0.0009750000000000001,
+      "loss": 6.816403198242187,
+      "step": 40
+    },
+    {
+      "epoch": 0.003370407819346141,
+      "eval_loss": 6.03591251373291,
+      "eval_runtime": 20.8366,
+      "eval_samples_per_second": 457.224,
+      "eval_steps_per_second": 3.599,
+      "step": 50
+    },
+    {
+      "epoch": 0.004044489383215369,
+      "grad_norm": 0.2421875,
+      "learning_rate": 0.001475,
+      "loss": 6.07518196105957,
+      "step": 60
+    },
+    {
+      "epoch": 0.005392652510953826,
+      "grad_norm": 0.255859375,
+      "learning_rate": 0.001975,
+      "loss": 5.979307556152344,
+      "step": 80
+    },
+    {
+      "epoch": 0.006740815638692282,
+      "grad_norm": 0.421875,
+      "learning_rate": 0.002475,
+      "loss": 6.011705780029297,
+      "step": 100
+    },
+    {
+      "epoch": 0.006740815638692282,
+      "eval_loss": 5.985101699829102,
+      "eval_runtime": 20.8812,
+      "eval_samples_per_second": 456.248,
+      "eval_steps_per_second": 3.592,
+      "step": 100
+    },
+    {
+      "epoch": 0.008088978766430738,
+      "grad_norm": 0.3203125,
+      "learning_rate": 0.0029749999999999998,
+      "loss": 5.911283111572265,
+      "step": 120
+    },
+    {
+      "epoch": 0.009437141894169195,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.003475,
+      "loss": 5.750088882446289,
+      "step": 140
+    },
+    {
+      "epoch": 0.010111223458038422,
+      "eval_loss": 5.503909111022949,
+      "eval_runtime": 21.0312,
+      "eval_samples_per_second": 452.993,
+      "eval_steps_per_second": 3.566,
+      "step": 150
+    },
+    {
+      "epoch": 0.010785305021907651,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.003975,
+      "loss": 5.520360946655273,
+      "step": 160
+    },
+    {
+      "epoch": 0.012133468149646108,
+      "grad_norm": 0.296875,
+      "learning_rate": 0.004475,
+      "loss": 5.556026840209961,
+      "step": 180
+    },
+    {
+      "epoch": 0.013481631277384564,
+      "grad_norm": 0.283203125,
+      "learning_rate": 0.004975,
+      "loss": 5.346047592163086,
+      "step": 200
+    },
+    {
+      "epoch": 0.013481631277384564,
+      "eval_loss": 5.2880539894104,
+      "eval_runtime": 21.1058,
+      "eval_samples_per_second": 451.393,
+      "eval_steps_per_second": 3.554,
+      "step": 200
+    },
+    {
+      "epoch": 0.01482979440512302,
+      "grad_norm": 0.58203125,
+      "learning_rate": 0.005,
+      "loss": 5.273908996582032,
+      "step": 220
+    },
+    {
+      "epoch": 0.016177957532861477,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 0.005,
+      "loss": 5.410552215576172,
+      "step": 240
+    },
+    {
+      "epoch": 0.016852039096730706,
+      "eval_loss": 5.188313007354736,
+      "eval_runtime": 20.8972,
+      "eval_samples_per_second": 455.898,
+      "eval_steps_per_second": 3.589,
+      "step": 250
+    },
+    {
+      "epoch": 0.01752612066059993,
+      "grad_norm": 1.7890625,
+      "learning_rate": 0.005,
+      "loss": 5.2268211364746096,
+      "step": 260
+    },
+    {
+      "epoch": 0.01887428378833839,
+      "grad_norm": 0.1796875,
+      "learning_rate": 0.005,
+      "loss": 5.473565292358399,
+      "step": 280
+    },
+    {
+      "epoch": 0.020222446916076844,
+      "grad_norm": 0.205078125,
+      "learning_rate": 0.005,
+      "loss": 5.219692993164062,
+      "step": 300
+    },
+    {
+      "epoch": 0.020222446916076844,
+      "eval_loss": 5.02672815322876,
+      "eval_runtime": 20.9666,
+      "eval_samples_per_second": 454.39,
+      "eval_steps_per_second": 3.577,
+      "step": 300
+    },
+    {
+      "epoch": 0.021570610043815303,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.005,
+      "loss": 4.967658615112304,
+      "step": 320
+    },
+    {
+      "epoch": 0.022918773171553757,
+      "grad_norm": 0.173828125,
+      "learning_rate": 0.005,
+      "loss": 4.778659820556641,
+      "step": 340
+    },
+    {
+      "epoch": 0.023592854735422986,
+      "eval_loss": 4.648769855499268,
+      "eval_runtime": 21.1707,
+      "eval_samples_per_second": 450.008,
+      "eval_steps_per_second": 3.543,
+      "step": 350
+    },
+    {
+      "epoch": 0.024266936299292215,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 0.005,
+      "loss": 4.660733032226562,
+      "step": 360
+    },
+    {
+      "epoch": 0.02561509942703067,
+      "grad_norm": 0.208984375,
+      "learning_rate": 0.005,
+      "loss": 4.559370040893555,
+      "step": 380
+    },
+    {
+      "epoch": 0.026963262554769128,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.005,
+      "loss": 4.45455322265625,
+      "step": 400
+    },
+    {
+      "epoch": 0.026963262554769128,
+      "eval_loss": 4.417364120483398,
+      "eval_runtime": 20.8283,
+      "eval_samples_per_second": 457.406,
+      "eval_steps_per_second": 3.601,
+      "step": 400
+    },
+    {
+      "epoch": 0.028311425682507583,
+      "grad_norm": 0.2177734375,
+      "learning_rate": 0.005,
+      "loss": 4.370449447631836,
+      "step": 420
+    },
+    {
+      "epoch": 0.02965958881024604,
+      "grad_norm": 0.310546875,
+      "learning_rate": 0.005,
+      "loss": 4.529141998291015,
+      "step": 440
+    },
+    {
+      "epoch": 0.030333670374115267,
+      "eval_loss": 4.386935234069824,
+      "eval_runtime": 21.0263,
+      "eval_samples_per_second": 453.099,
+      "eval_steps_per_second": 3.567,
+      "step": 450
+    },
+    {
+      "epoch": 0.031007751937984496,
+      "grad_norm": 0.251953125,
+      "learning_rate": 0.005,
+      "loss": 4.395891189575195,
+      "step": 460
+    },
+    {
+      "epoch": 0.032355915065722954,
+      "grad_norm": 0.2578125,
+      "learning_rate": 0.005,
+      "loss": 4.270762634277344,
+      "step": 480
+    },
+    {
+      "epoch": 0.03370407819346141,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.005,
+      "loss": 4.187443542480469,
+      "step": 500
+    },
+    {
+      "epoch": 0.03370407819346141,
+      "eval_loss": 4.152405261993408,
+      "eval_runtime": 20.9396,
+      "eval_samples_per_second": 454.976,
+      "eval_steps_per_second": 3.582,
+      "step": 500
+    },
+    {
+      "epoch": 0.03505224132119986,
+      "grad_norm": 0.302734375,
+      "learning_rate": 0.005,
+      "loss": 4.120236587524414,
+      "step": 520
+    },
+    {
+      "epoch": 0.03640040444893832,
+      "grad_norm": 0.3046875,
+      "learning_rate": 0.005,
+      "loss": 4.068311309814453,
+      "step": 540
+    },
+    {
+      "epoch": 0.03707448601280755,
+      "eval_loss": 4.019883632659912,
+      "eval_runtime": 21.08,
+      "eval_samples_per_second": 451.945,
+      "eval_steps_per_second": 3.558,
+      "step": 550
+    },
+    {
+      "epoch": 0.03774856757667678,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.005,
+      "loss": 4.021861267089844,
+      "step": 560
+    },
+    {
+      "epoch": 0.03909673070441524,
+      "grad_norm": 0.45703125,
+      "learning_rate": 0.005,
+      "loss": 4.028375625610352,
+      "step": 580
+    },
+    {
+      "epoch": 0.04044489383215369,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.005,
+      "loss": 4.143251419067383,
+      "step": 600
+    },
+    {
+      "epoch": 0.04044489383215369,
+      "eval_loss": 4.0677714347839355,
+      "eval_runtime": 20.7979,
+      "eval_samples_per_second": 458.074,
+      "eval_steps_per_second": 3.606,
+      "step": 600
+    },
+    {
+      "epoch": 0.04179305695989215,
+      "grad_norm": 0.408203125,
+      "learning_rate": 0.005,
+      "loss": 4.020790863037109,
+      "step": 620
+    },
+    {
+      "epoch": 0.043141220087630605,
+      "grad_norm": 0.62109375,
+      "learning_rate": 0.005,
+      "loss": 4.100545501708984,
+      "step": 640
+    },
+    {
+      "epoch": 0.043815301651499834,
+      "eval_loss": 4.084841251373291,
+      "eval_runtime": 21.002,
+      "eval_samples_per_second": 453.623,
+      "eval_steps_per_second": 3.571,
+      "step": 650
+    },
+    {
+      "epoch": 0.044489383215369056,
+      "grad_norm": 0.37109375,
+      "learning_rate": 0.005,
+      "loss": 4.0663604736328125,
+      "step": 660
+    },
+    {
+      "epoch": 0.045837546343107514,
+      "grad_norm": 0.625,
+      "learning_rate": 0.005,
+      "loss": 3.989541244506836,
+      "step": 680
+    },
+    {
+      "epoch": 0.04718570947084597,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.005,
+      "loss": 3.9411972045898436,
+      "step": 700
+    },
+    {
+      "epoch": 0.04718570947084597,
+      "eval_loss": 3.957554817199707,
+      "eval_runtime": 20.9069,
+      "eval_samples_per_second": 455.686,
+      "eval_steps_per_second": 3.587,
+      "step": 700
+    },
+    {
+      "epoch": 0.04853387259858443,
+      "grad_norm": 0.376953125,
+      "learning_rate": 0.005,
+      "loss": 3.9560787200927736,
+      "step": 720
+    },
+    {
+      "epoch": 0.04988203572632288,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.005,
+      "loss": 3.937845993041992,
+      "step": 740
+    },
+    {
+      "epoch": 0.05055611729019211,
+      "eval_loss": 3.883145332336426,
+      "eval_runtime": 20.8555,
+      "eval_samples_per_second": 456.811,
+      "eval_steps_per_second": 3.596,
+      "step": 750
+    },
+    {
+      "epoch": 0.05123019885406134,
+      "grad_norm": 0.28515625,
+      "learning_rate": 0.005,
+      "loss": 3.876919174194336,
+      "step": 760
+    },
+    {
+      "epoch": 0.0525783619817998,
+      "grad_norm": 0.23046875,
+      "learning_rate": 0.005,
+      "loss": 3.863613510131836,
+      "step": 780
+    },
+    {
+      "epoch": 0.053926525109538256,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.005,
+      "loss": 3.817916488647461,
+      "step": 800
+    },
+    {
+      "epoch": 0.053926525109538256,
+      "eval_loss": 3.805201768875122,
+      "eval_runtime": 20.868,
+      "eval_samples_per_second": 456.536,
+      "eval_steps_per_second": 3.594,
+      "step": 800
+    },
+    {
+      "epoch": 0.05527468823727671,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.005,
+      "loss": 3.8092723846435548,
+      "step": 820
+    },
+    {
+      "epoch": 0.056622851365015166,
+      "grad_norm": 0.4765625,
+      "learning_rate": 0.005,
+      "loss": 3.7842361450195314,
+      "step": 840
+    },
+    {
+      "epoch": 0.057296932928884395,
+      "eval_loss": 3.781162977218628,
+      "eval_runtime": 20.8153,
+      "eval_samples_per_second": 457.693,
+      "eval_steps_per_second": 3.603,
+      "step": 850
+    },
+    {
+      "epoch": 0.057971014492753624,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.005,
+      "loss": 3.772878646850586,
+      "step": 860
+    },
+    {
+      "epoch": 0.05931917762049208,
+      "grad_norm": 0.5703125,
+      "learning_rate": 0.005,
+      "loss": 3.7841278076171876,
+      "step": 880
+    },
+    {
+      "epoch": 0.06066734074823053,
+      "grad_norm": 0.466796875,
+      "learning_rate": 0.005,
+      "loss": 3.761078643798828,
+      "step": 900
+    },
+    {
+      "epoch": 0.06066734074823053,
+      "eval_loss": 3.7455968856811523,
+      "eval_runtime": 20.92,
+      "eval_samples_per_second": 455.402,
+      "eval_steps_per_second": 3.585,
+      "step": 900
+    },
+    {
+      "epoch": 0.06201550387596899,
+      "grad_norm": 0.39453125,
+      "learning_rate": 0.005,
+      "loss": 3.8091686248779295,
+      "step": 920
+    },
+    {
+      "epoch": 0.06336366700370745,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.005,
+      "loss": 3.816885757446289,
+      "step": 940
+    },
+    {
+      "epoch": 0.06403774856757667,
+      "eval_loss": 3.8163840770721436,
+      "eval_runtime": 20.8548,
+      "eval_samples_per_second": 456.826,
+      "eval_steps_per_second": 3.596,
+      "step": 950
+    },
+    {
+      "epoch": 0.06471183013144591,
+      "grad_norm": 0.4140625,
+      "learning_rate": 0.005,
+      "loss": 3.8143104553222655,
+      "step": 960
+    },
+    {
+      "epoch": 0.06605999325918437,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.005,
+      "loss": 3.8331851959228516,
+      "step": 980
+    },
+    {
+      "epoch": 0.06740815638692282,
+      "grad_norm": 0.546875,
+      "learning_rate": 0.005,
+      "loss": 3.895557403564453,
+      "step": 1000
+    },
+    {
+      "epoch": 0.06740815638692282,
+      "eval_loss": 3.8806943893432617,
+      "eval_runtime": 20.8642,
+      "eval_samples_per_second": 456.62,
+      "eval_steps_per_second": 3.595,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4839413121024000.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

zain/Activation/out/glu-linear-150L_run/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb806d4a439df151752019f391211c166395545923bb5e786d20bc3664157e3a
+size 4920

zain/Activation/out/glu-linear-150L_run/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "linear",
+  "architectures": [
+    "TinyLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "mlp_type": "glu",
+  "model_type": "tiny_llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 150,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "tokenizer_name": "w-ahmad/tiny-stories-tokenizer",
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": false,
+  "vocab_size": 4096,
+  "waleed_beta": 10.0
+}

zain/Activation/out/glu-linear-150L_run/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e76362c91e06038fea9af3a37c65bfaf32f86e70bc728754e698978b98cbf1
+size 50427120

zain/Activation/out/glu-linear-150L_run/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

zain/Activation/out/glu-linear-150L_run/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb806d4a439df151752019f391211c166395545923bb5e786d20bc3664157e3a
+size 4920

zain/Activation/out/glu-linear-150L_run/training_log.jsonl

@@ -46,3 +46,27 @@
 {"step": 660, "epoch": 0.044489383215369056, "timestamp": 1786561621.5550168, "loss": 4.0663604736328125, "grad_norm": 0.37109375, "learning_rate": 0.005, "train/total_time_seconds": 231.7532401382923, "train/time_per_step_avg": 0.34764930870383975, "train/epoch_time_elapsed": 537.3906552046537, "train/estimated_remaining_minutes": 1.9898005466419035}
 {"step": 680, "epoch": 0.045837546343107514, "timestamp": 1786561629.910806, "loss": 3.989541244506836, "grad_norm": 0.625, "learning_rate": 0.005, "train/total_time_seconds": 239.09254013746977, "train/time_per_step_avg": 0.35157852102071047, "train/epoch_time_elapsed": 545.7464439682662, "train/estimated_remaining_minutes": 1.8752356089213316}
 {"step": 700, "epoch": 0.04718570947084597, "timestamp": 1786561637.8702278, "loss": 3.9411972045898436, "grad_norm": 0.50390625, "learning_rate": 0.005, "train/total_time_seconds": 246.04394330829382, "train/time_per_step_avg": 0.35155317302793265, "train/epoch_time_elapsed": 553.7058657445014, "train/estimated_remaining_minutes": 1.7574567379163843}
+{"step": 700, "epoch": 0.04718570947084597, "timestamp": 1786561658.7787404, "eval_loss": 3.957554817199707, "eval_runtime": 20.9069, "eval_samples_per_second": 455.686, "eval_steps_per_second": 3.587, "train/total_time_seconds": 246.04394330829382, "train/time_per_step_avg": 0.35155317302793265, "train/epoch_time_elapsed": 574.6143769398332, "train/estimated_remaining_minutes": 1.7574567379163843}
+{"step": 720, "epoch": 0.04853387259858443, "timestamp": 1786561666.717939, "loss": 3.9560787200927736, "grad_norm": 0.376953125, "learning_rate": 0.005, "train/total_time_seconds": 252.98766312375665, "train/time_per_step_avg": 0.35152376390993595, "train/epoch_time_elapsed": 582.5535773076117, "train/estimated_remaining_minutes": 1.6397348535799041}
+{"step": 740, "epoch": 0.04988203572632288, "timestamp": 1786561674.6922324, "loss": 3.937845993041992, "grad_norm": 0.50390625, "learning_rate": 0.005, "train/total_time_seconds": 259.9603731483221, "train/time_per_step_avg": 0.3510817878320813, "train/epoch_time_elapsed": 590.5278697311878, "train/estimated_remaining_minutes": 1.5222904733910754}
+{"step": 750, "epoch": 0.05055611729019211, "timestamp": 1786561699.4916966, "eval_loss": 3.883145332336426, "eval_runtime": 20.8555, "eval_samples_per_second": 456.811, "eval_steps_per_second": 3.596, "train/total_time_seconds": 263.4158732369542, "train/time_per_step_avg": 0.35111497826874255, "train/epoch_time_elapsed": 615.3273340463638, "train/estimated_remaining_minutes": 1.463421517983079}
+{"step": 760, "epoch": 0.05123019885406134, "timestamp": 1786561703.5628746, "loss": 3.876919174194336, "grad_norm": 0.28515625, "learning_rate": 0.005, "train/total_time_seconds": 266.96413373202085, "train/time_per_step_avg": 0.3521089359372854, "train/epoch_time_elapsed": 619.3985130116343, "train/estimated_remaining_minutes": 1.4050743880632675}
+{"step": 780, "epoch": 0.0525783619817998, "timestamp": 1786561711.526361, "loss": 3.863613510131836, "grad_norm": 0.23046875, "learning_rate": 0.005, "train/total_time_seconds": 273.94282737746835, "train/time_per_step_avg": 0.3485028723999858, "train/epoch_time_elapsed": 627.3619999475777, "train/estimated_remaining_minutes": 1.2877654278428}
+{"step": 800, "epoch": 0.053926525109538256, "timestamp": 1786561719.4585655, "loss": 3.817916488647461, "grad_norm": 0.26171875, "learning_rate": 0.005, "train/total_time_seconds": 280.8883742876351, "train/time_per_step_avg": 0.3484443097934127, "train/epoch_time_elapsed": 635.2942031100392, "train/estimated_remaining_minutes": 1.1703682261984796}
+{"step": 800, "epoch": 0.053926525109538256, "timestamp": 1786561740.3282394, "eval_loss": 3.805201768875122, "eval_runtime": 20.868, "eval_samples_per_second": 456.536, "eval_steps_per_second": 3.594, "train/total_time_seconds": 280.8883742876351, "train/time_per_step_avg": 0.3484443097934127, "train/epoch_time_elapsed": 656.1638764068484, "train/estimated_remaining_minutes": 1.1703682261984796}
+{"step": 820, "epoch": 0.05527468823727671, "timestamp": 1786561748.6419787, "loss": 3.8092723846435548, "grad_norm": 0.275390625, "learning_rate": 0.005, "train/total_time_seconds": 288.1984957046807, "train/time_per_step_avg": 0.35210832580924034, "train/epoch_time_elapsed": 664.4776168353856, "train/estimated_remaining_minutes": 1.054384740382978}
+{"step": 840, "epoch": 0.056622851365015166, "timestamp": 1786561756.562155, "loss": 3.7842361450195314, "grad_norm": 0.4765625, "learning_rate": 0.005, "train/total_time_seconds": 295.12212934345007, "train/time_per_step_avg": 0.35161756195127963, "train/epoch_time_elapsed": 672.3977936692536, "train/estimated_remaining_minutes": 0.9368956487093653}
+{"step": 850, "epoch": 0.057296932928884395, "timestamp": 1786561781.390232, "eval_loss": 3.781162977218628, "eval_runtime": 20.8153, "eval_samples_per_second": 457.693, "eval_steps_per_second": 3.603, "train/total_time_seconds": 298.62293972074986, "train/time_per_step_avg": 0.3520706648379564, "train/epoch_time_elapsed": 697.2258685082197, "train/estimated_remaining_minutes": 0.8783027638845584}
+{"step": 860, "epoch": 0.057971014492753624, "timestamp": 1786561785.3252072, "loss": 3.772878646850586, "grad_norm": 0.349609375, "learning_rate": 0.005, "train/total_time_seconds": 302.0710848532617, "train/time_per_step_avg": 0.35106951121240854, "train/epoch_time_elapsed": 701.160845734179, "train/estimated_remaining_minutes": 0.8195727108421829}
+{"step": 880, "epoch": 0.05931917762049208, "timestamp": 1786561793.232581, "loss": 3.7841278076171876, "grad_norm": 0.5703125, "learning_rate": 0.005, "train/total_time_seconds": 308.99424478039145, "train/time_per_step_avg": 0.3505141740292311, "train/epoch_time_elapsed": 709.0682189725339, "train/estimated_remaining_minutes": 0.7022596472281624}
+{"step": 900, "epoch": 0.06066734074823053, "timestamp": 1786561801.1976156, "loss": 3.761078643798828, "grad_norm": 0.466796875, "learning_rate": 0.005, "train/total_time_seconds": 315.9700040668249, "train/time_per_step_avg": 0.35081629779189827, "train/epoch_time_elapsed": 717.0332538820803, "train/estimated_remaining_minutes": 0.5851296371607868}
+{"step": 900, "epoch": 0.06066734074823053, "timestamp": 1786561822.1191792, "eval_loss": 3.7455968856811523, "eval_runtime": 20.92, "eval_samples_per_second": 455.402, "eval_steps_per_second": 3.585, "train/total_time_seconds": 315.9700040668249, "train/time_per_step_avg": 0.35081629779189827, "train/epoch_time_elapsed": 737.9548166282475, "train/estimated_remaining_minutes": 0.5851296371607868}
+{"step": 920, "epoch": 0.06201550387596899, "timestamp": 1786561830.1104178, "loss": 3.8091686248779295, "grad_norm": 0.39453125, "learning_rate": 0.005, "train/total_time_seconds": 322.9559160992503, "train/time_per_step_avg": 0.3475742039456964, "train/epoch_time_elapsed": 745.9460563659668, "train/estimated_remaining_minutes": 0.4680520523177541}
+{"step": 940, "epoch": 0.06336366700370745, "timestamp": 1786561838.028804, "loss": 3.816885757446289, "grad_norm": 0.6015625, "learning_rate": 0.005, "train/total_time_seconds": 329.89182472229004, "train/time_per_step_avg": 0.3476969537883997, "train/epoch_time_elapsed": 753.8644422218204, "train/estimated_remaining_minutes": 0.35094874970456386}
+{"step": 950, "epoch": 0.06403774856757667, "timestamp": 1786561863.140793, "eval_loss": 3.8163840770721436, "eval_runtime": 20.8548, "eval_samples_per_second": 456.826, "eval_steps_per_second": 3.596, "train/total_time_seconds": 333.6575093641877, "train/time_per_step_avg": 0.35034569643437863, "train/epoch_time_elapsed": 778.9764298833907, "train/estimated_remaining_minutes": 0.29268202575805946}
+{"step": 960, "epoch": 0.06471183013144591, "timestamp": 1786561867.086198, "loss": 3.8143104553222655, "grad_norm": 0.4140625, "learning_rate": 0.005, "train/total_time_seconds": 337.11661945283413, "train/time_per_step_avg": 0.3504553459957242, "train/epoch_time_elapsed": 782.9218365363777, "train/estimated_remaining_minutes": 0.2341087635089126}
+{"step": 980, "epoch": 0.06605999325918437, "timestamp": 1786561874.9863226, "loss": 3.8331851959228516, "grad_norm": 0.56640625, "learning_rate": 0.005, "train/total_time_seconds": 344.0378700606525, "train/time_per_step_avg": 0.35043625280261037, "train/epoch_time_elapsed": 790.8219612874091, "train/estimated_remaining_minutes": 0.11701968369409949}
+{"step": 1000, "epoch": 0.06740815638692282, "timestamp": 1786561882.9242458, "loss": 3.895557403564453, "grad_norm": 0.546875, "learning_rate": 0.005, "train/total_time_seconds": 350.9824995547533, "train/time_per_step_avg": 0.3501249548792839, "train/epoch_time_elapsed": 798.7598841674626, "train/estimated_remaining_minutes": 0.0}
+{"step": 1000, "epoch": 0.06740815638692282, "timestamp": 1786561903.7903314, "eval_loss": 3.8806943893432617, "eval_runtime": 20.8642, "eval_samples_per_second": 456.62, "eval_steps_per_second": 3.595, "train/total_time_seconds": 350.9824995547533, "train/time_per_step_avg": 0.3501249548792839, "train/epoch_time_elapsed": 819.625968053937, "train/estimated_remaining_minutes": 0.0}
+{"step": 1000, "epoch": 0.06740815638692282, "timestamp": 1786561904.243015, "train_runtime": 821.1117, "train_samples_per_second": 77.943, "train_steps_per_second": 1.218, "total_flos": 4839413121024000.0, "train_loss": 4.614717056274414, "train/total_time_seconds": 350.9824995547533, "train/time_per_step_avg": 0.3501249548792839, "train/epoch_time_elapsed": 820.0786515437067, "train/estimated_remaining_minutes": 0.0}
+{"step": 1000, "epoch": 0.06740815638692282, "timestamp": 1786561925.2316225, "eval_loss": 3.8806943893432617, "eval_runtime": 20.9854, "eval_samples_per_second": 453.982, "eval_steps_per_second": 3.574, "train/total_time_seconds": 350.9824995547533, "train/time_per_step_avg": 0.3501249548792839, "train/epoch_time_elapsed": 841.0672598704696, "train/estimated_remaining_minutes": 0.0}

zain/Activation/out/glu-waleed10-150L_run/training_log.jsonl

@@ -0,0 +1 @@
+{"step": 20, "epoch": 0.0013481631277384564, "timestamp": 1786561936.9982266, "loss": 7.956694793701172, "grad_norm": 1.2578125, "learning_rate": 0.000475, "train/total_time_seconds": 7.735054552555084, "train/time_per_step_avg": 0.3867527276277542, "train/epoch_time_elapsed": 8.816539153456688, "train/estimated_remaining_minutes": 6.316961217919985}

zain/Activation/wandb/debug-internal.log

@@ -1,83 +1,11 @@
-{"time":"2026-08-12T18:58:03.202093805Z","level":"INFO","msg":"wandb-core"}
-{"time":"2026-08-12T18:58:03.20225824Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
-{"time":"2026-08-12T18:58:03.567828199Z","level":"INFO","msg":"stream: created new stream","id":"0fh9o8ec"}
-{"time":"2026-08-12T18:58:03.567921692Z","level":"INFO","msg":"handler: started"}
-{"time":"2026-08-12T18:58:03.568002283Z","level":"INFO","msg":"stream: started"}
-{"time":"2026-08-12T18:58:03.568015447Z","level":"INFO","msg":"writer: started","stream_id":"0fh9o8ec"}
-{"time":"2026-08-12T18:58:03.568039922Z","level":"INFO","msg":"sender: started"}
-{"time":"2026-08-12T18:58:04.967067306Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T18:58:05.113925138Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T18:58:19.967889062Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":1,"events_offset":0,"events_lines":2,"console_offset":0,"console_lines":2,"uploaded_len":2}
-{"time":"2026-08-12T18:58:20.09283844Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T18:58:34.967571267Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":1,"history_lines":1,"events_offset":2,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T18:58:35.084944072Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T18:58:49.967746378Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":2,"history_lines":2,"events_offset":4,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T18:58:50.079249851Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T18:59:04.968093303Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":4,"history_lines":1,"events_offset":6,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T18:59:05.11887593Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T18:59:19.968009015Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":5,"history_lines":1,"events_offset":8,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T18:59:20.084880945Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T18:59:34.967693471Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":6,"history_lines":2,"events_offset":10,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T18:59:35.093283541Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T18:59:49.96781067Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":8,"history_lines":1,"events_offset":12,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T18:59:50.097289415Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:00:04.967153477Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":14,"events_lines":2,"console_offset":2,"console_lines":9}
-{"time":"2026-08-12T19:00:05.119455306Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:00:19.967405732Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":9,"history_lines":3,"events_offset":16,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T19:00:20.091552517Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:00:34.967556007Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":12,"history_lines":1,"events_offset":18,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T19:00:35.128589992Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:00:49.968126798Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":13,"history_lines":1,"events_offset":20,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T19:00:50.069858366Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:01:04.967363934Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":14,"history_lines":2,"events_offset":22,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T19:01:05.118996264Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:01:19.967736275Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":24,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T19:01:20.094495571Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:01:34.968203006Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":16,"history_lines":2,"events_offset":26,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T19:01:35.110131377Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:01:49.968184182Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":18,"history_lines":2,"events_offset":28,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T19:01:50.083478731Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:02:04.967694816Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":30,"events_lines":2,"console_offset":3,"console_lines":1}
-{"time":"2026-08-12T19:02:05.128134494Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:02:19.969351348Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":20,"history_lines":2,"events_offset":32,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T19:02:20.125378055Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:02:34.968122282Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":22,"history_lines":1,"events_offset":34,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T19:02:35.077553321Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:02:49.967650324Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":36,"events_lines":2,"console_offset":3,"console_lines":1}
-{"time":"2026-08-12T19:02:50.095156933Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:03:04.968092129Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":23,"history_lines":3,"events_offset":38,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T19:03:05.103316767Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:03:19.967549443Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":26,"history_lines":1,"events_offset":40,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T19:03:20.125965191Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:03:34.967712195Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":27,"history_lines":1,"events_offset":42,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T19:03:35.095371636Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:03:49.967868775Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":28,"history_lines":2,"events_offset":44,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T19:03:50.097705827Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:04:04.967648844Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":46,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T19:04:05.169450849Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:04:19.967877835Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":30,"history_lines":2,"events_offset":48,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T19:04:20.088652343Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:04:34.96819998Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":32,"history_lines":2,"events_offset":50,"events_lines":2,"console_offset":3,"console_lines":1}
-{"time":"2026-08-12T19:04:35.078642509Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:04:49.967543161Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":52,"events_lines":2,"console_offset":11,"console_lines":25}
-{"time":"2026-08-12T19:04:50.100233468Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:05:04.967482633Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":34,"history_lines":2,"events_offset":54,"events_lines":2,"console_offset":36,"console_lines":2}
-{"time":"2026-08-12T19:05:05.099637608Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:05:19.96802335Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":36,"history_lines":1,"events_offset":56,"events_lines":2,"console_offset":38,"console_lines":1}
-{"time":"2026-08-12T19:05:20.100207624Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:05:34.968134447Z","level":"INFO","msg":"filestream: sending request","total_files":1,"events_offset":58,"events_lines":2}
-{"time":"2026-08-12T19:05:35.13080051Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:05:49.967795369Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":37,"history_lines":3,"events_offset":60,"events_lines":2,"console_offset":39,"console_lines":3}
-{"time":"2026-08-12T19:05:50.102485294Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:06:04.96808016Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":40,"history_lines":1,"events_offset":62,"events_lines":2,"console_offset":42,"console_lines":1}
-{"time":"2026-08-12T19:06:05.152431619Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:06:19.968008286Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":41,"history_lines":1,"events_offset":64,"events_lines":2,"console_offset":43,"console_lines":1}
-{"time":"2026-08-12T19:06:20.078549067Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:06:34.967574849Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":42,"history_lines":2,"events_offset":66,"events_lines":2,"console_offset":44,"console_lines":2}
-{"time":"2026-08-12T19:06:35.09788236Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:06:49.967860521Z","level":"INFO","msg":"filestream: sending request","total_files":1,"events_offset":68,"events_lines":2}
-{"time":"2026-08-12T19:06:50.101857481Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:07:04.967824839Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":44,"history_lines":2,"events_offset":70,"events_lines":2,"console_offset":46,"console_lines":2}
-{"time":"2026-08-12T19:07:05.150996913Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T19:07:19.967569833Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":46,"history_lines":2,"events_offset":72,"events_lines":2,"console_offset":48,"console_lines":2}
-{"time":"2026-08-12T19:07:20.095159143Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:12:07.497196304Z","level":"INFO","msg":"wandb-core"}
+{"time":"2026-08-12T19:12:07.497332182Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
+{"time":"2026-08-12T19:12:07.759577369Z","level":"INFO","msg":"stream: created new stream","id":"w1cgnksl"}
+{"time":"2026-08-12T19:12:07.759657193Z","level":"INFO","msg":"handler: started"}
+{"time":"2026-08-12T19:12:07.759784998Z","level":"INFO","msg":"stream: started"}
+{"time":"2026-08-12T19:12:07.759790925Z","level":"INFO","msg":"writer: started","stream_id":"w1cgnksl"}
+{"time":"2026-08-12T19:12:07.759842787Z","level":"INFO","msg":"sender: started"}
+{"time":"2026-08-12T19:12:09.060585544Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
+{"time":"2026-08-12T19:12:09.183194227Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:12:24.061611124Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":1,"events_offset":0,"events_lines":2,"console_offset":0,"console_lines":2,"uploaded_len":2}
+{"time":"2026-08-12T19:12:24.181068505Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}

zain/Activation/wandb/debug.log

@@ -1,20 +1,20 @@
-2026-08-12 18:58:03,200 INFO    MainThread:1371664 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_185803-0fh9o8ec/logs/debug.log
-2026-08-12 18:58:03,200 INFO    MainThread:1371664 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_185803-0fh9o8ec/logs/debug-internal.log
-2026-08-12 18:58:03,200 INFO    MainThread:1371664 [wandb_init.py:init():772] calling init triggers
-2026-08-12 18:58:03,200 INFO    MainThread:1371664 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
+2026-08-12 19:12:07,495 INFO    MainThread:1371664 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_191207-w1cgnksl/logs/debug.log
+2026-08-12 19:12:07,496 INFO    MainThread:1371664 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_191207-w1cgnksl/logs/debug-internal.log
+2026-08-12 19:12:07,496 INFO    MainThread:1371664 [wandb_init.py:init():772] calling init triggers
+2026-08-12 19:12:07,496 INFO    MainThread:1371664 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
 config: {'_wandb': {}}
-2026-08-12 18:58:03,200 INFO    MainThread:1371664 [wandb_init.py:init():820] starting backend
-2026-08-12 18:58:03,200 INFO    MainThread:1371664 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
-2026-08-12 18:58:03,200 INFO    MainThread:1371664 [wandb_init.py:init():835] sending inform_init request
-2026-08-12 18:58:03,568 INFO    MainThread:1371664 [wandb_init.py:init():840] backend started and connected
-2026-08-12 18:58:03,569 INFO    MainThread:1371664 [wandb_init.py:init():910] updated telemetry
-2026-08-12 18:58:03,576 INFO    MainThread:1371664 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
-2026-08-12 18:58:04,074 INFO    MainThread:1371664 [wandb_init.py:init():978] starting run threads in backend
-2026-08-12 18:58:04,155 INFO    MainThread:1371664 [wandb_run.py:_console_start():2621] atexit reg
-2026-08-12 18:58:04,155 INFO    MainThread:1371664 [wandb_run.py:_redirect():2471] redirect: wrap_raw
-2026-08-12 18:58:04,155 INFO    MainThread:1371664 [wandb_run.py:_redirect():2540] Wrapping output streams.
-2026-08-12 18:58:04,155 INFO    MainThread:1371664 [wandb_run.py:_redirect():2563] Redirects installed.
-2026-08-12 18:58:04,156 INFO    MainThread:1371664 [wandb_init.py:init():1016] run started, returning control to user process
-2026-08-12 18:58:04,157 INFO    MainThread:1371664 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 150, 'num_attention_heads': 4, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'max_position_embeddings': 512, 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'pad_token_id': 0, 'bos_token_id': 1, 'eos_token_id': 2, 'pretraining_tp': 1, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 10000.0, 'rope_type': 'default'}, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 32, '_name_or_path': '', 'tokenizer_name': 'w-ahmad/tiny-stories-tokenizer', 'mlp_type': 'glu', 'activation': 'linear', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-linear-150L_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 1000, 'learning_rate': 0.005, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 200, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 0.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-linear-150L-25.1M-20260812-185802', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 50, 'eval_delay': 0, 'per_device_eval_batch_size': 128, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 1000, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/6L-glu-linear-150L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
-2026-08-12 18:58:04,164 INFO    MainThread:1371664 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 25138816 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14c70bba6950>>
-2026-08-12 18:58:04,164 INFO    MainThread:1371664 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 25138816 None
+2026-08-12 19:12:07,496 INFO    MainThread:1371664 [wandb_init.py:init():820] starting backend
+2026-08-12 19:12:07,496 INFO    MainThread:1371664 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
+2026-08-12 19:12:07,496 INFO    MainThread:1371664 [wandb_init.py:init():835] sending inform_init request
+2026-08-12 19:12:07,760 INFO    MainThread:1371664 [wandb_init.py:init():840] backend started and connected
+2026-08-12 19:12:07,761 INFO    MainThread:1371664 [wandb_init.py:init():910] updated telemetry
+2026-08-12 19:12:07,768 INFO    MainThread:1371664 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
+2026-08-12 19:12:08,094 INFO    MainThread:1371664 [wandb_init.py:init():978] starting run threads in backend
+2026-08-12 19:12:08,172 INFO    MainThread:1371664 [wandb_run.py:_console_start():2621] atexit reg
+2026-08-12 19:12:08,172 INFO    MainThread:1371664 [wandb_run.py:_redirect():2471] redirect: wrap_raw
+2026-08-12 19:12:08,172 INFO    MainThread:1371664 [wandb_run.py:_redirect():2540] Wrapping output streams.
+2026-08-12 19:12:08,172 INFO    MainThread:1371664 [wandb_run.py:_redirect():2563] Redirects installed.
+2026-08-12 19:12:08,173 INFO    MainThread:1371664 [wandb_init.py:init():1016] run started, returning control to user process
+2026-08-12 19:12:08,174 INFO    MainThread:1371664 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 150, 'num_attention_heads': 4, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'max_position_embeddings': 512, 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'pad_token_id': 0, 'bos_token_id': 1, 'eos_token_id': 2, 'pretraining_tp': 1, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 10000.0, 'rope_type': 'default'}, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 32, '_name_or_path': '', 'tokenizer_name': 'w-ahmad/tiny-stories-tokenizer', 'mlp_type': 'glu', 'activation': 'waleed10', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-waleed10-150L_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 1000, 'learning_rate': 0.005, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 200, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 0.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-waleed10-150L-25.1M-20260812-191206', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 50, 'eval_delay': 0, 'per_device_eval_batch_size': 128, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 1000, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/6L-glu-waleed10-150L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
+2026-08-12 19:12:08,181 INFO    MainThread:1371664 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 25138816 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14c5efb86510>>
+2026-08-12 19:12:08,181 INFO    MainThread:1371664 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 25138816 None

zain/Activation/wandb/run-20260812_175304-hrggki9k/logs/debug-core.log

@@ -46,3 +46,10 @@
 {"time":"2026-08-12T18:58:03.201898424Z","level":"INFO","msg":"handleInformInit: received","streamId":"0fh9o8ec","id":"3(@)"}
 {"time":"2026-08-12T18:58:03.568010316Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"0fh9o8ec","id":"3(@)"}
 {"time":"2026-08-12T18:58:09.158050393Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
+{"time":"2026-08-12T19:12:05.373774541Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
+{"time":"2026-08-12T19:12:05.978597092Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
+{"time":"2026-08-12T19:12:05.980085967Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"0fh9o8ec","id":"3(@)"}
+{"time":"2026-08-12T19:12:05.98075482Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"0fh9o8ec","id":"3(@)"}
+{"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
+{"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
+{"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}

zain/Activation/wandb/run-20260812_180713-utqzlg67/logs/debug-core.log

@@ -46,3 +46,10 @@
 {"time":"2026-08-12T18:58:03.201898424Z","level":"INFO","msg":"handleInformInit: received","streamId":"0fh9o8ec","id":"3(@)"}
 {"time":"2026-08-12T18:58:03.568010316Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"0fh9o8ec","id":"3(@)"}
 {"time":"2026-08-12T18:58:09.158050393Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
+{"time":"2026-08-12T19:12:05.373774541Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
+{"time":"2026-08-12T19:12:05.978597092Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
+{"time":"2026-08-12T19:12:05.980085967Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"0fh9o8ec","id":"3(@)"}
+{"time":"2026-08-12T19:12:05.98075482Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"0fh9o8ec","id":"3(@)"}
+{"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
+{"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
+{"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}

zain/Activation/wandb/run-20260812_182126-vyycsg6r/logs/debug-core.log

@@ -46,3 +46,10 @@
 {"time":"2026-08-12T18:58:03.201898424Z","level":"INFO","msg":"handleInformInit: received","streamId":"0fh9o8ec","id":"3(@)"}
 {"time":"2026-08-12T18:58:03.568010316Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"0fh9o8ec","id":"3(@)"}
 {"time":"2026-08-12T18:58:09.158050393Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
+{"time":"2026-08-12T19:12:05.373774541Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
+{"time":"2026-08-12T19:12:05.978597092Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
+{"time":"2026-08-12T19:12:05.980085967Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"0fh9o8ec","id":"3(@)"}
+{"time":"2026-08-12T19:12:05.98075482Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"0fh9o8ec","id":"3(@)"}
+{"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
+{"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
+{"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}

zain/Activation/wandb/run-20260812_183823-qtstmmvv/logs/debug-core.log

@@ -46,3 +46,10 @@
 {"time":"2026-08-12T18:58:03.201898424Z","level":"INFO","msg":"handleInformInit: received","streamId":"0fh9o8ec","id":"3(@)"}
 {"time":"2026-08-12T18:58:03.568010316Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"0fh9o8ec","id":"3(@)"}
 {"time":"2026-08-12T18:58:09.158050393Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
+{"time":"2026-08-12T19:12:05.373774541Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
+{"time":"2026-08-12T19:12:05.978597092Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
+{"time":"2026-08-12T19:12:05.980085967Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"0fh9o8ec","id":"3(@)"}
+{"time":"2026-08-12T19:12:05.98075482Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"0fh9o8ec","id":"3(@)"}
+{"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
+{"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
+{"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}

zain/Activation/wandb/run-20260812_185803-0fh9o8ec/files/config.yaml

@@ -0,0 +1,445 @@
+_name_or_path:
+    value: ""
+_wandb:
+    value:
+        cli_version: 0.28.1
+        e:
+            5s5c961ipvtqlmgwyu6ebv7bl8rh3rsr:
+                args:
+                    - --config
+                    - /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/configs/baseline150L.yaml
+                    - --variants
+                    - glu-silu
+                    - glu-relu
+                    - glu-gelu
+                    - glu-sigmoid
+                    - glu-linear
+                    - glu-waleed10
+                    - mlp-waleed10
+                    - glu-silu-waleed10
+                    - mlp-silu-waleed10
+                    - glu-situglu
+                    - glu-waleed
+                    - glu-situglu_low
+                    - glu-waleedglu_low
+                codePath: sweep.py
+                codePathLocal: sweep.py
+                cpu_count: 112
+                cpu_count_logical: 224
+                cudaVersion: "12.4"
+                disk:
+                    /:
+                        total: "1560765693952"
+                        used: "716164648960"
+                email: deepnevro@gmail.com
+                executable: /mnt/data/zainulabideen/zain-exp/notebooks/my_env/bin/python
+                git:
+                    commit: c53713bcba08d1849136dad91288c4b82040634e
+                    remote: https://github.com/w-ahmad1a10/Activation.git
+                gpu: NVIDIA H100 80GB HBM3
+                gpu_count: 8
+                gpu_nvidia:
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-39c684a5-fde6-83d7-1663-0859795881ae
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-68012e5a-38b6-b643-0ca6-62fb66720bf3
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-132944c4-b689-2b5f-89a4-d730401677ab
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-2df386cc-6d26-d0e2-7a2d-a057b0d95864
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-bfa16575-1d94-1aa2-4537-2c93433f42ef
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-bc6c3e3c-9b90-09ca-c034-774961847c54
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-00a441e1-7c95-e7d6-4c35-43d6b291aea9
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-1c4d29a2-4647-6fce-d8fc-0c5ecfbbd6ea
+                host: deeplens-k3s-node1
+                memory:
+                    total: "2164089937920"
+                os: Linux-5.15.0-126-generic-x86_64-with-glibc2.35
+                program: /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/sweep.py
+                python: CPython 3.11.15
+                root: /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation
+                startedAt: "2026-08-12T18:58:03.199543Z"
+                writerId: 5s5c961ipvtqlmgwyu6ebv7bl8rh3rsr
+        m:
+            - "1": train/global_step
+              "6":
+                - 3
+              "7": []
+            - "2": '*'
+              "5": 1
+              "6":
+                - 1
+              "7": []
+        python_version: 3.11.15
+        t:
+            "1":
+                - 1
+                - 5
+                - 11
+                - 41
+                - 49
+                - 51
+                - 53
+                - 71
+            "2":
+                - 1
+                - 5
+                - 11
+                - 41
+                - 49
+                - 51
+                - 53
+                - 71
+            "3":
+                - 2
+                - 7
+                - 13
+                - 19
+                - 62
+                - 66
+            "4": 3.11.15
+            "5": 0.28.1
+            "6": 5.16.0.dev0
+            "9":
+                "1": transformers_trainer
+            "12": 0.28.1
+            "13": linux-x86_64
+accelerator_config:
+    value:
+        dispatch_batches: null
+        even_batches: true
+        gradient_accumulation_kwargs: null
+        non_blocking: false
+        split_batches: false
+        use_seedable_sampler: true
+activation:
+    value: linear
+adam_beta1:
+    value: 0.9
+adam_beta2:
+    value: 0.999
+adam_epsilon:
+    value: 1e-08
+architectures:
+    value: null
+attention_bias:
+    value: false
+attention_dropout:
+    value: 0
+auto_find_batch_size:
+    value: false
+average_tokens_across_devices:
+    value: true
+batch_eval_metrics:
+    value: false
+bf16:
+    value: true
+bf16_full_eval:
+    value: false
+bos_token_id:
+    value: 1
+chunk_size_feed_forward:
+    value: 0
+data_seed:
+    value: 42
+dataloader_drop_last:
+    value: false
+dataloader_in_order:
+    value: true
+dataloader_multiprocessing_context:
+    value: null
+dataloader_num_workers:
+    value: 0
+dataloader_persistent_workers:
+    value: false
+dataloader_pin_memory:
+    value: true
+dataloader_prefetch_factor:
+    value: null
+ddp_backend:
+    value: null
+ddp_broadcast_buffers:
+    value: null
+ddp_bucket_cap_mb:
+    value: null
+ddp_find_unused_parameters:
+    value: null
+ddp_static_graph:
+    value: null
+ddp_timeout:
+    value: 1800
+debug:
+    value: []
+deepspeed:
+    value: null
+disable_tqdm:
+    value: false
+do_eval:
+    value: true
+do_predict:
+    value: false
+do_train:
+    value: false
+dtype:
+    value: null
+enable_jit_checkpoint:
+    value: false
+eos_token_id:
+    value: 2
+eval_accumulation_steps:
+    value: null
+eval_delay:
+    value: 0
+eval_do_concat_batches:
+    value: true
+eval_on_start:
+    value: false
+eval_steps:
+    value: 50
+eval_strategy:
+    value: steps
+eval_use_gather_object:
+    value: false
+fp16:
+    value: false
+fp16_full_eval:
+    value: false
+fsdp:
+    value: null
+fsdp_config:
+    value: null
+full_determinism:
+    value: false
+gradient_accumulation_steps:
+    value: 1
+gradient_checkpointing:
+    value: false
+gradient_checkpointing_kwargs:
+    value: null
+greater_is_better:
+    value: null
+head_dim:
+    value: 32
+hidden_act:
+    value: silu
+hidden_size:
+    value: 128
+hub_always_push:
+    value: false
+hub_model_id:
+    value: w-ahmad/6L-glu-linear-150L
+hub_private_repo:
+    value: null
+hub_revision:
+    value: null
+hub_strategy:
+    value: every_save
+hub_token:
+    value: <HUB_TOKEN>
+id2label:
+    value:
+        "0": LABEL_0
+        "1": LABEL_1
+ignore_data_skip:
+    value: false
+include_for_metrics:
+    value: []
+include_num_input_tokens_seen:
+    value: "no"
+initializer_range:
+    value: 0.02
+intermediate_size:
+    value: 256
+is_encoder_decoder:
+    value: false
+label_names:
+    value: null
+label_smoothing_factor:
+    value: 0
+label2id:
+    value:
+        LABEL_0: 0
+        LABEL_1: 1
+learning_rate:
+    value: 0.005
+length_column_name:
+    value: length
+liger_kernel_config:
+    value: null
+load_best_model_at_end:
+    value: false
+local_rank:
+    value: -1
+log_level:
+    value: passive
+log_level_replica:
+    value: warning
+log_on_each_node:
+    value: true
+logging_first_step:
+    value: false
+logging_nan_inf_filter:
+    value: true
+logging_steps:
+    value: 20
+logging_strategy:
+    value: steps
+lr_scheduler_kwargs:
+    value: null
+lr_scheduler_type:
+    value: constant_with_warmup
+max_grad_norm:
+    value: 0
+max_position_embeddings:
+    value: 512
+max_steps:
+    value: 1000
+metric_for_best_model:
+    value: null
+mlp_bias:
+    value: false
+mlp_type:
+    value: glu
+model/num_parameters:
+    value: 25138816
+model_type:
+    value: tiny_llama
+neftune_noise_alpha:
+    value: null
+num_attention_heads:
+    value: 4
+num_hidden_layers:
+    value: 150
+num_key_value_heads:
+    value: 4
+num_train_epochs:
+    value: 1
+optim:
+    value: adamw_torch_fused
+optim_args:
+    value: null
+optim_target_modules:
+    value: null
+output_attentions:
+    value: false
+output_dir:
+    value: out/glu-linear-150L_run
+output_hidden_states:
+    value: false
+pad_token_id:
+    value: 0
+parallelism_config:
+    value: null
+per_device_eval_batch_size:
+    value: 128
+per_device_train_batch_size:
+    value: 64
+prediction_loss_only:
+    value: false
+pretraining_tp:
+    value: 1
+problem_type:
+    value: null
+project:
+    value: huggingface
+push_to_hub:
+    value: false
+remove_unused_columns:
+    value: false
+report_to:
+    value:
+        - wandb
+restore_callback_states_from_checkpoint:
+    value: false
+resume_from_checkpoint:
+    value: null
+return_dict:
+    value: true
+rms_norm_eps:
+    value: 1e-06
+rope_parameters:
+    value:
+        rope_theta: 10000
+        rope_type: default
+run_name:
+    value: LM-glu-linear-150L-25.1M-20260812-185802
+save_on_each_node:
+    value: false
+save_only_model:
+    value: false
+save_steps:
+    value: 1000
+save_strategy:
+    value: steps
+save_total_limit:
+    value: null
+seed:
+    value: 42
+skip_memory_metrics:
+    value: true
+tf32:
+    value: null
+tie_word_embeddings:
+    value: true
+tokenizer_name:
+    value: w-ahmad/tiny-stories-tokenizer
+torch_compile:
+    value: false
+torch_compile_backend:
+    value: null
+torch_compile_mode:
+    value: null
+torch_empty_cache_steps:
+    value: null
+trackio_bucket_id:
+    value: null
+trackio_space_id:
+    value: null
+trackio_static_space_id:
+    value: null
+train_sampling_strategy:
+    value: random
+transformers_version:
+    value: 5.16.0.dev0
+use_cache:
+    value: false
+use_cpu:
+    value: false
+use_liger_kernel:
+    value: false
+vocab_size:
+    value: 4096
+waleed_beta:
+    value: 10
+warmup_steps:
+    value: 200
+weight_decay:
+    value: 0

zain/Activation/wandb/run-20260812_185803-0fh9o8ec/files/output.log

@@ -47,3 +47,37 @@
 {'eval_loss': '4.085', 'eval_runtime': '21', 'eval_samples_per_second': '453.6', 'eval_steps_per_second': '3.571', 'epoch': '0.04382', 'train/total_time_seconds': '228.3', 'train/time_per_step_avg': '0.3477', 'train/epoch_time_elapsed': '533.5', 'train/estimated_remaining_minutes': '2.049'}
 {'loss': '4.066', 'grad_norm': '0.3711', 'learning_rate': '0.005', 'epoch': '0.04449', 'train/total_time_seconds': '231.8', 'train/time_per_step_avg': '0.3476', 'train/epoch_time_elapsed': '537.4', 'train/estimated_remaining_minutes': '1.99'}
 {'loss': '3.99', 'grad_norm': '0.625', 'learning_rate': '0.005', 'epoch': '0.04584', 'train/total_time_seconds': '239.1', 'train/time_per_step_avg': '0.3516', 'train/epoch_time_elapsed': '545.7', 'train/estimated_remaining_minutes': '1.875'}
+{'loss': '3.941', 'grad_norm': '0.5039', 'learning_rate': '0.005', 'epoch': '0.04719', 'train/total_time_seconds': '246', 'train/time_per_step_avg': '0.3516', 'train/epoch_time_elapsed': '553.7', 'train/estimated_remaining_minutes': '1.757'}
+{'eval_loss': '3.958', 'eval_runtime': '20.91', 'eval_samples_per_second': '455.7', 'eval_steps_per_second': '3.587', 'epoch': '0.04719', 'train/total_time_seconds': '246', 'train/time_per_step_avg': '0.3516', 'train/epoch_time_elapsed': '574.6', 'train/estimated_remaining_minutes': '1.757'}
+{'loss': '3.956', 'grad_norm': '0.377', 'learning_rate': '0.005', 'epoch': '0.04853', 'train/total_time_seconds': '253', 'train/time_per_step_avg': '0.3515', 'train/epoch_time_elapsed': '582.6', 'train/estimated_remaining_minutes': '1.64'}
+{'loss': '3.938', 'grad_norm': '0.5039', 'learning_rate': '0.005', 'epoch': '0.04988', 'train/total_time_seconds': '260', 'train/time_per_step_avg': '0.3511', 'train/epoch_time_elapsed': '590.5', 'train/estimated_remaining_minutes': '1.522'}
+{'eval_loss': '3.883', 'eval_runtime': '20.86', 'eval_samples_per_second': '456.8', 'eval_steps_per_second': '3.596', 'epoch': '0.05056', 'train/total_time_seconds': '263.4', 'train/time_per_step_avg': '0.3511', 'train/epoch_time_elapsed': '615.3', 'train/estimated_remaining_minutes': '1.463'}
+{'loss': '3.877', 'grad_norm': '0.2852', 'learning_rate': '0.005', 'epoch': '0.05123', 'train/total_time_seconds': '267', 'train/time_per_step_avg': '0.3521', 'train/epoch_time_elapsed': '619.4', 'train/estimated_remaining_minutes': '1.405'}
+{'loss': '3.864', 'grad_norm': '0.2305', 'learning_rate': '0.005', 'epoch': '0.05258', 'train/total_time_seconds': '273.9', 'train/time_per_step_avg': '0.3485', 'train/epoch_time_elapsed': '627.4', 'train/estimated_remaining_minutes': '1.288'}
+{'loss': '3.818', 'grad_norm': '0.2617', 'learning_rate': '0.005', 'epoch': '0.05393', 'train/total_time_seconds': '280.9', 'train/time_per_step_avg': '0.3484', 'train/epoch_time_elapsed': '635.3', 'train/estimated_remaining_minutes': '1.17'}
+{'eval_loss': '3.805', 'eval_runtime': '20.87', 'eval_samples_per_second': '456.5', 'eval_steps_per_second': '3.594', 'epoch': '0.05393', 'train/total_time_seconds': '280.9', 'train/time_per_step_avg': '0.3484', 'train/epoch_time_elapsed': '656.2', 'train/estimated_remaining_minutes': '1.17'}
+{'loss': '3.809', 'grad_norm': '0.2754', 'learning_rate': '0.005', 'epoch': '0.05527', 'train/total_time_seconds': '288.2', 'train/time_per_step_avg': '0.3521', 'train/epoch_time_elapsed': '664.5', 'train/estimated_remaining_minutes': '1.054'}
+{'loss': '3.784', 'grad_norm': '0.4766', 'learning_rate': '0.005', 'epoch': '0.05662', 'train/total_time_seconds': '295.1', 'train/time_per_step_avg': '0.3516', 'train/epoch_time_elapsed': '672.4', 'train/estimated_remaining_minutes': '0.9369'}
+{'eval_loss': '3.781', 'eval_runtime': '20.82', 'eval_samples_per_second': '457.7', 'eval_steps_per_second': '3.603', 'epoch': '0.0573', 'train/total_time_seconds': '298.6', 'train/time_per_step_avg': '0.3521', 'train/epoch_time_elapsed': '697.2', 'train/estimated_remaining_minutes': '0.8783'}
+{'loss': '3.773', 'grad_norm': '0.3496', 'learning_rate': '0.005', 'epoch': '0.05797', 'train/total_time_seconds': '302.1', 'train/time_per_step_avg': '0.3511', 'train/epoch_time_elapsed': '701.2', 'train/estimated_remaining_minutes': '0.8196'}
+{'loss': '3.784', 'grad_norm': '0.5703', 'learning_rate': '0.005', 'epoch': '0.05932', 'train/total_time_seconds': '309', 'train/time_per_step_avg': '0.3505', 'train/epoch_time_elapsed': '709.1', 'train/estimated_remaining_minutes': '0.7023'}
+{'loss': '3.761', 'grad_norm': '0.4668', 'learning_rate': '0.005', 'epoch': '0.06067', 'train/total_time_seconds': '316', 'train/time_per_step_avg': '0.3508', 'train/epoch_time_elapsed': '717', 'train/estimated_remaining_minutes': '0.5851'}
+{'eval_loss': '3.746', 'eval_runtime': '20.92', 'eval_samples_per_second': '455.4', 'eval_steps_per_second': '3.585', 'epoch': '0.06067', 'train/total_time_seconds': '316', 'train/time_per_step_avg': '0.3508', 'train/epoch_time_elapsed': '738', 'train/estimated_remaining_minutes': '0.5851'}
+{'loss': '3.809', 'grad_norm': '0.3945', 'learning_rate': '0.005', 'epoch': '0.06202', 'train/total_time_seconds': '323', 'train/time_per_step_avg': '0.3476', 'train/epoch_time_elapsed': '745.9', 'train/estimated_remaining_minutes': '0.4681'}
+{'loss': '3.817', 'grad_norm': '0.6016', 'learning_rate': '0.005', 'epoch': '0.06336', 'train/total_time_seconds': '329.9', 'train/time_per_step_avg': '0.3477', 'train/epoch_time_elapsed': '753.9', 'train/estimated_remaining_minutes': '0.3509'}
+{'eval_loss': '3.816', 'eval_runtime': '20.85', 'eval_samples_per_second': '456.8', 'eval_steps_per_second': '3.596', 'epoch': '0.06404', 'train/total_time_seconds': '333.7', 'train/time_per_step_avg': '0.3503', 'train/epoch_time_elapsed': '779', 'train/estimated_remaining_minutes': '0.2927'}
+{'loss': '3.814', 'grad_norm': '0.4141', 'learning_rate': '0.005', 'epoch': '0.06471', 'train/total_time_seconds': '337.1', 'train/time_per_step_avg': '0.3505', 'train/epoch_time_elapsed': '782.9', 'train/estimated_remaining_minutes': '0.2341'}
+{'loss': '3.833', 'grad_norm': '0.5664', 'learning_rate': '0.005', 'epoch': '0.06606', 'train/total_time_seconds': '344', 'train/time_per_step_avg': '0.3504', 'train/epoch_time_elapsed': '790.8', 'train/estimated_remaining_minutes': '0.117'}
+{'loss': '3.896', 'grad_norm': '0.5469', 'learning_rate': '0.005', 'epoch': '0.06741', 'train/total_time_seconds': '351', 'train/time_per_step_avg': '0.3501', 'train/epoch_time_elapsed': '798.8', 'train/estimated_remaining_minutes': '0'}
+{'eval_loss': '3.881', 'eval_runtime': '20.86', 'eval_samples_per_second': '456.6', 'eval_steps_per_second': '3.595', 'epoch': '0.06741', 'train/total_time_seconds': '351', 'train/time_per_step_avg': '0.3501', 'train/epoch_time_elapsed': '819.6', 'train/estimated_remaining_minutes': '0'}
+  - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
+  - If you are not the owner of the model architecture class, please contact the model code owner to update it.
+Writing model shards: 100%|██████████| 1/1 [00:00<00:00,  8.45it/s]
+100%|██████████| 1000/1000 [13:41<00:00,  1.22it/s]0:00,  8.53it/s]
+{'train_runtime': '821.1', 'train_samples_per_second': '77.94', 'train_steps_per_second': '1.218', 'train_loss': '4.615', 'epoch': '0.06741', 'train/total_time_seconds': '351', 'train/time_per_step_avg': '0.3501', 'train/epoch_time_elapsed': '820.1', 'train/estimated_remaining_minutes': '0'}
+100%|██████████| 75/75 [00:20<00:00,  3.63it/s]
+[transformers] TinyLlamaForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly defined. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.
+  - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
+  - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
+  - If you are not the owner of the model architecture class, please contact the model code owner to update it.
+Writing model shards: 100%|██████████| 1/1 [00:00<00:00, 10.26it/s]

zain/Activation/wandb/run-20260812_185803-0fh9o8ec/files/wandb-summary.json

@@ -0,0 +1 @@
+{"_timestamp":1.7865619252318451e+09,"train/epoch":0.06740815638692282,"train/loss":3.895557403564453,"train/train/total_time_seconds":350.9824995547533,"train_loss":4.614717056274414,"train/learning_rate":0.005,"train_runtime":821.1117,"eval/loss":3.8806943893432617,"_runtime":841,"train/train/epoch_time_elapsed":841.0672598704696,"eval/steps_per_second":3.574,"eval/samples_per_second":453.982,"total_flos":4.839413121024e+15,"train/global_step":1000,"train_steps_per_second":1.218,"_wandb":{"runtime":841},"train/train/estimated_remaining_minutes":0,"_step":71,"train/grad_norm":0.546875,"train/train/time_per_step_avg":0.3501249548792839,"eval/runtime":20.9854,"train_samples_per_second":77.943}

zain/Activation/wandb/run-20260812_185803-0fh9o8ec/logs/debug-core.log

@@ -46,3 +46,10 @@
 {"time":"2026-08-12T18:58:03.201898424Z","level":"INFO","msg":"handleInformInit: received","streamId":"0fh9o8ec","id":"3(@)"}
 {"time":"2026-08-12T18:58:03.568010316Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"0fh9o8ec","id":"3(@)"}
 {"time":"2026-08-12T18:58:09.158050393Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
+{"time":"2026-08-12T19:12:05.373774541Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
+{"time":"2026-08-12T19:12:05.978597092Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
+{"time":"2026-08-12T19:12:05.980085967Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"0fh9o8ec","id":"3(@)"}
+{"time":"2026-08-12T19:12:05.98075482Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"0fh9o8ec","id":"3(@)"}
+{"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
+{"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
+{"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}

zain/Activation/wandb/run-20260812_185803-0fh9o8ec/logs/debug-internal.log

@@ -81,3 +81,49 @@
 {"time":"2026-08-12T19:07:05.150996913Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
 {"time":"2026-08-12T19:07:19.967569833Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":46,"history_lines":2,"events_offset":72,"events_lines":2,"console_offset":48,"console_lines":2}
 {"time":"2026-08-12T19:07:20.095159143Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:07:34.968087039Z","level":"INFO","msg":"filestream: sending request","total_files":1,"events_offset":74,"events_lines":2}
+{"time":"2026-08-12T19:07:35.076028881Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:07:49.967931616Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":48,"history_lines":2,"events_offset":76,"events_lines":2,"console_offset":50,"console_lines":2}
+{"time":"2026-08-12T19:07:50.087583527Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:08:04.967646345Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":50,"history_lines":1,"events_offset":78,"events_lines":2,"console_offset":52,"console_lines":1}
+{"time":"2026-08-12T19:08:05.093192616Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:08:19.968184797Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":51,"history_lines":1,"events_offset":80,"events_lines":2,"console_offset":53,"console_lines":1}
+{"time":"2026-08-12T19:08:20.077631081Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:08:34.967900118Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":52,"history_lines":2,"events_offset":82,"events_lines":2,"console_offset":54,"console_lines":2}
+{"time":"2026-08-12T19:08:35.095631517Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:08:49.96801683Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":54,"history_lines":1,"events_offset":84,"events_lines":2,"console_offset":56,"console_lines":1}
+{"time":"2026-08-12T19:08:50.084386151Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:09:04.967575337Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":55,"history_lines":1,"events_offset":86,"events_lines":2,"console_offset":57,"console_lines":1}
+{"time":"2026-08-12T19:09:05.110314263Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:09:19.968277391Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":56,"history_lines":2,"events_offset":88,"events_lines":2,"console_offset":58,"console_lines":2}
+{"time":"2026-08-12T19:09:20.091511305Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:09:34.967503914Z","level":"INFO","msg":"filestream: sending request","total_files":1,"events_offset":90,"events_lines":2}
+{"time":"2026-08-12T19:09:35.077394264Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:09:49.968127442Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":58,"history_lines":2,"events_offset":92,"events_lines":2,"console_offset":60,"console_lines":2}
+{"time":"2026-08-12T19:09:50.113660125Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:10:04.968241813Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":60,"history_lines":2,"events_offset":94,"events_lines":2,"console_offset":62,"console_lines":2}
+{"time":"2026-08-12T19:10:05.125944582Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:10:19.967352299Z","level":"INFO","msg":"filestream: sending request","total_files":1,"events_offset":96,"events_lines":2}
+{"time":"2026-08-12T19:10:20.092763964Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:10:34.967863162Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":62,"history_lines":2,"events_offset":98,"events_lines":2,"console_offset":64,"console_lines":2}
+{"time":"2026-08-12T19:10:35.130732444Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:10:49.967476903Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":64,"history_lines":1,"events_offset":100,"events_lines":2,"console_offset":66,"console_lines":1}
+{"time":"2026-08-12T19:10:50.074279719Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:11:04.967841914Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":65,"history_lines":1,"events_offset":102,"events_lines":2,"console_offset":67,"console_lines":1}
+{"time":"2026-08-12T19:11:05.09867196Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:11:19.967689076Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":66,"history_lines":2,"events_offset":104,"events_lines":2,"console_offset":68,"console_lines":2}
+{"time":"2026-08-12T19:11:20.127504086Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:11:34.967422496Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":68,"history_lines":1,"events_offset":106,"events_lines":2,"console_offset":70,"console_lines":1}
+{"time":"2026-08-12T19:11:35.091754172Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:11:49.968133577Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":69,"history_lines":2,"events_offset":108,"events_lines":2,"console_offset":71,"console_lines":7}
+{"time":"2026-08-12T19:11:50.098322431Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:12:04.967991024Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":110,"events_lines":2,"console_offset":77,"console_lines":1}
+{"time":"2026-08-12T19:12:05.102698098Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:12:05.782819675Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2026-08-12T19:12:05.78300509Z","level":"INFO","msg":"filestream: sending request","total_files":3,"history_offset":71,"history_lines":1,"console_offset":77,"console_lines":6,"uploaded_len":3,"complete":true,"exit_code":0}
+{"time":"2026-08-12T19:12:05.976418733Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:12:05.977555188Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2026-08-12T19:12:05.980107921Z","level":"INFO","msg":"stream: finishing up"}
+{"time":"2026-08-12T19:12:05.980122272Z","level":"INFO","msg":"handler: closed"}
+{"time":"2026-08-12T19:12:05.980240615Z","level":"INFO","msg":"sender: closed"}
+{"time":"2026-08-12T19:12:05.980245265Z","level":"INFO","msg":"stream: all finished"}

zain/Activation/wandb/run-20260812_185803-0fh9o8ec/logs/debug.log

@@ -18,3 +18,8 @@ config: {'_wandb': {}}
 2026-08-12 18:58:04,157 INFO    MainThread:1371664 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 150, 'num_attention_heads': 4, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'max_position_embeddings': 512, 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'pad_token_id': 0, 'bos_token_id': 1, 'eos_token_id': 2, 'pretraining_tp': 1, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 10000.0, 'rope_type': 'default'}, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 32, '_name_or_path': '', 'tokenizer_name': 'w-ahmad/tiny-stories-tokenizer', 'mlp_type': 'glu', 'activation': 'linear', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-linear-150L_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 1000, 'learning_rate': 0.005, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 200, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 0.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-linear-150L-25.1M-20260812-185802', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 50, 'eval_delay': 0, 'per_device_eval_batch_size': 128, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 1000, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/6L-glu-linear-150L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
 2026-08-12 18:58:04,164 INFO    MainThread:1371664 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 25138816 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14c70bba6950>>
 2026-08-12 18:58:04,164 INFO    MainThread:1371664 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 25138816 None
+2026-08-12 19:12:05,373 INFO    MainThread:1371664 [wandb_run.py:_finish():2383] finishing run deepnevro-deepnevro/research2/0fh9o8ec
+2026-08-12 19:12:05,373 INFO    MainThread:1371664 [wandb_run.py:_atexit_cleanup():2588] got exitcode: 0
+2026-08-12 19:12:05,373 INFO    MainThread:1371664 [wandb_run.py:_restore():2570] restore
+2026-08-12 19:12:05,373 INFO    MainThread:1371664 [wandb_run.py:_restore():2576] restore done
+2026-08-12 19:12:05,979 INFO    MainThread:1371664 [wandb_run.py:_footer_sync_info():3993] logging synced files

zain/Activation/wandb/run-20260812_185803-0fh9o8ec/run-0fh9o8ec.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ee247da207b7e8c4d2e42220a12ea4355a250214358a66c69bd3e6dfc26b92d
-size 589824
+oid sha256:a2e36c69f50e69afcbbefac150ca832b6d96d840afbeed74742f5a1e4be4b90c
+size 939417

zain/Activation/wandb/run-20260812_191207-w1cgnksl/files/output.log

@@ -0,0 +1,2 @@
+  4%|▎         | 37/1000 [00:16<06:43,  2.39it/s]
+{'loss': '7.957', 'grad_norm': '1.258', 'learning_rate': '0.000475', 'epoch': '0.001348', 'train/total_time_seconds': '7.735', 'train/time_per_step_avg': '0.3868', 'train/epoch_time_elapsed': '8.817', 'train/estimated_remaining_minutes': '6.317'}

zain/Activation/wandb/run-20260812_191207-w1cgnksl/files/requirements.txt

@@ -0,0 +1,149 @@
+asttokens==3.0.1
+comm==0.2.3
+debugpy==1.8.21
+decorator==5.3.1
+executing==2.2.1
+nest-asyncio==1.6.0
+parso==0.8.7
+platformdirs==4.11.0
+psutil==7.2.2
+ptyprocess==0.7.0
+pure_eval==0.2.3
+Pygments==2.20.0
+pyzmq==27.1.0
+setuptools==83.0.0
+six==1.17.0
+tornado==6.5.7
+traitlets==5.15.0
+fsspec==2026.4.0
+wcwidth==0.8.2
+ipython_pygments_lexers==1.1.1
+jedi==0.20.0
+jupyter_core==5.9.1
+matplotlib-inline==0.2.2
+pexpect==4.9.0
+prompt_toolkit==3.0.53
+python-dateutil==2.9.0.post0
+stack_data==0.6.3
+wheel==0.47.0
+jupyter_client==8.9.1
+pip==26.1.2
+ipython==9.15.0
+ipykernel==7.2.0
+threadpoolctl==3.6.0
+pyparsing==3.3.2
+typing_extensions==4.15.0
+Jinja2==3.1.6
+narwhals==2.24.0
+kiwisolver==1.5.0
+joblib==1.5.3
+fonttools==4.63.0
+cycler==0.12.1
+scipy==1.17.1
+pandas==3.0.5
+contourpy==1.3.3
+scikit-learn==1.9.0
+matplotlib==3.11.1
+urllib3==2.7.0
+tqdm==4.70.0
+idna==3.18
+charset-normalizer==3.4.9
+certifi==2026.7.22
+requests==2.34.2
+seaborn==0.13.2
+uv==0.12.0
+shellingham==1.5.4
+mpmath==1.3.0
+attrs==26.1.0
+hf-xet==1.5.2
+nvidia-nccl-cu12==2.21.5
+MarkupSafe==3.0.3
+regex==2026.7.19
+importlib_metadata==9.0.0
+httpcore==1.0.9
+annotated-doc==0.0.5
+multidict==6.7.1
+aiohttp==3.14.3
+aiosignal==1.4.0
+xxhash==3.8.1
+aiohappyeyeballs==2.7.1
+mdurl==0.1.2
+cuda-toolkit==13.0.3.0
+networkx==3.6.1
+PyYAML==6.0.3
+nvidia-cufile==1.15.1.6
+typer==0.27.0
+torchaudio==2.6.0+cu124
+rich==15.0.0
+nvidia-cufft-cu12==11.2.1.3
+h11==0.16.0
+dill==0.4.1
+cuda-pathfinder==1.6.0
+filelock==3.29.0
+nvidia-nvtx-cu12==12.4.127
+httpx==0.28.1
+anyio==4.14.2
+numpy==2.4.4
+yarl==1.24.5
+click==8.4.2
+triton==3.2.0
+frozenlist==1.8.0
+zipp==4.1.0
+propcache==0.5.2
+tokenizers==0.22.2
+markdown-it-py==4.2.0
+nvidia-cuda-runtime==13.0.96
+cuda-bindings==13.3.1
+nvidia-cuda-cupti==13.0.85
+torch==2.6.0+cu124
+multiprocess==0.70.19
+pillow==12.2.0
+transformers==5.16.0.dev0
+wandb==0.28.1
+nvidia-curand==10.4.0.35
+sympy==1.13.1
+nvidia-cusparse==12.6.3.3
+nvidia-cuda-nvrtc==13.0.88
+typing-inspection==0.4.2
+nvidia-cusolver==12.0.4.66
+nvidia-cufft==12.0.0.61
+nvidia-cudnn-cu13==9.20.0.48
+nvidia-cublas==13.1.1.3
+pyarrow==25.0.0
+evaluate==0.4.6
+diffusers==0.39.0
+pydantic==2.13.4
+annotated-types==0.8.0
+protobuf==7.35.1
+sentry-sdk==2.66.1
+einops==0.8.2
+packaging==26.2
+nvidia-nvjitlink-cu12==12.4.127
+nvidia-curand-cu12==10.3.5.147
+nvidia-cusparselt-cu12==0.6.2
+nvidia-cusparse-cu12==12.3.1.170
+nvidia-cuda-runtime-cu12==12.4.127
+torchvision==0.21.0+cu124
+nvidia-cuda-nvrtc-cu12==12.4.127
+nvidia-cuda-cupti-cu12==12.4.127
+nvidia-cusolver-cu12==11.6.1.9
+nvidia-cublas-cu12==12.4.5.8
+nvidia-cudnn-cu12==9.1.0.70
+huggingface_hub==1.26.0
+datasets==5.0.1
+safetensors==0.8.0
+accelerate==1.14.0
+pydantic_core==2.46.4
+ninja==1.13.0
+autocommand==2.2.2
+backports.tarfile==1.2.0
+importlib_metadata==8.7.1
+jaraco.text==4.0.0
+jaraco.context==6.1.0
+jaraco.functools==4.4.0
+more-itertools==10.8.0
+packaging==26.0
+platformdirs==4.4.0
+tomli==2.4.0
+wheel==0.46.3
+zipp==3.23.0

zain/Activation/wandb/run-20260812_191207-w1cgnksl/files/wandb-metadata.json

@@ -0,0 +1,107 @@
+{
+  "os":  "Linux-5.15.0-126-generic-x86_64-with-glibc2.35",
+  "python":  "CPython 3.11.15",
+  "startedAt":  "2026-08-12T19:12:07.494929Z",
+  "args":  [
+    "--config",
+    "/mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/configs/baseline150L.yaml",
+    "--variants",
+    "glu-silu",
+    "glu-relu",
+    "glu-gelu",
+    "glu-sigmoid",
+    "glu-linear",
+    "glu-waleed10",
+    "mlp-waleed10",
+    "glu-silu-waleed10",
+    "mlp-silu-waleed10",
+    "glu-situglu",
+    "glu-waleed",
+    "glu-situglu_low",
+    "glu-waleedglu_low"
+  ],
+  "program":  "/mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/sweep.py",
+  "codePath":  "sweep.py",
+  "codePathLocal":  "sweep.py",
+  "git":  {
+    "remote":  "https://github.com/w-ahmad1a10/Activation.git",
+    "commit":  "c53713bcba08d1849136dad91288c4b82040634e"
+  },
+  "email":  "deepnevro@gmail.com",
+  "root":  "/mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation",
+  "host":  "deeplens-k3s-node1",
+  "executable":  "/mnt/data/zainulabideen/zain-exp/notebooks/my_env/bin/python",
+  "cpu_count":  112,
+  "cpu_count_logical":  224,
+  "gpu":  "NVIDIA H100 80GB HBM3",
+  "gpu_count":  8,
+  "disk":  {
+    "/":  {
+      "total":  "1560765693952",
+      "used":  "716198170624"
+    }
+  },
+  "memory":  {
+    "total":  "2164089937920"
+  },
+  "gpu_nvidia":  [
+    {
+      "name":  "NVIDIA H100 80GB HBM3",
+      "memoryTotal":  "85520809984",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-39c684a5-fde6-83d7-1663-0859795881ae"
+    },
+    {
+      "name":  "NVIDIA H100 80GB HBM3",
+      "memoryTotal":  "85520809984",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-68012e5a-38b6-b643-0ca6-62fb66720bf3"
+    },
+    {
+      "name":  "NVIDIA H100 80GB HBM3",
+      "memoryTotal":  "85520809984",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-132944c4-b689-2b5f-89a4-d730401677ab"
+    },
+    {
+      "name":  "NVIDIA H100 80GB HBM3",
+      "memoryTotal":  "85520809984",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-2df386cc-6d26-d0e2-7a2d-a057b0d95864"
+    },
+    {
+      "name":  "NVIDIA H100 80GB HBM3",
+      "memoryTotal":  "85520809984",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-bfa16575-1d94-1aa2-4537-2c93433f42ef"
+    },
+    {
+      "name":  "NVIDIA H100 80GB HBM3",
+      "memoryTotal":  "85520809984",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-bc6c3e3c-9b90-09ca-c034-774961847c54"
+    },
+    {
+      "name":  "NVIDIA H100 80GB HBM3",
+      "memoryTotal":  "85520809984",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-00a441e1-7c95-e7d6-4c35-43d6b291aea9"
+    },
+    {
+      "name":  "NVIDIA H100 80GB HBM3",
+      "memoryTotal":  "85520809984",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-1c4d29a2-4647-6fce-d8fc-0c5ecfbbd6ea"
+    }
+  ],
+  "cudaVersion":  "12.4",
+  "writerId":  "6lnbyc3acvy2bme0wurgw4k1v2n501g4"
+}

zain/Activation/wandb/run-20260812_191207-w1cgnksl/logs/debug-core.log

@@ -0,0 +1,55 @@
+{"time":"2026-08-12T17:51:29.496049185Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmp7lru5pey/port-1355517.txt","pid":1355517,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2026-08-12T17:51:29.496747364Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":1355517}
+{"time":"2026-08-12T17:51:29.49671311Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-1355517-1357782-3052194627/socket","Net":"unix"}}
+{"time":"2026-08-12T17:51:29.674347603Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2026-08-12T17:52:11.162138091Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"2(@)"}
+{"time":"2026-08-12T17:52:11.242645021Z","level":"INFO","msg":"handleInformInit: received","streamId":"ycyhhejh","id":"2(@)"}
+{"time":"2026-08-12T17:52:11.508233203Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"ycyhhejh","id":"2(@)"}
+{"time":"2026-08-12T17:52:17.001520061Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"6684d59dll8w"}
+{"time":"2026-08-12T17:52:32.412124918Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"6684d59dll8w"}
+{"time":"2026-08-12T17:52:32.887487538Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"6684d59dll8w"}
+{"time":"2026-08-12T17:52:32.888505Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"ycyhhejh","id":"2(@)"}
+{"time":"2026-08-12T17:52:32.889313366Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"ycyhhejh","id":"2(@)"}
+{"time":"2026-08-12T17:52:34.597228944Z","level":"INFO","msg":"connection: closing","id":"2(@)"}
+{"time":"2026-08-12T17:52:34.597314364Z","level":"INFO","msg":"connection: closed successfully","id":"2(@)"}
+{"time":"2026-08-12T17:52:34.597242804Z","level":"INFO","msg":"processOutgoingData: finished","id":"2(@)"}
+{"time":"2026-08-12T17:52:34.597322441Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"2(@)"}
+{"time":"2026-08-12T17:53:03.98517338Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"3(@)"}
+{"time":"2026-08-12T17:53:04.076747848Z","level":"INFO","msg":"handleInformInit: received","streamId":"hrggki9k","id":"3(@)"}
+{"time":"2026-08-12T17:53:04.339071164Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"hrggki9k","id":"3(@)"}
+{"time":"2026-08-12T17:53:09.739880255Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tj6i5mzy43l0"}
+{"time":"2026-08-12T18:07:11.667315857Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tj6i5mzy43l0"}
+{"time":"2026-08-12T18:07:12.178747012Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tj6i5mzy43l0"}
+{"time":"2026-08-12T18:07:12.180598654Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"hrggki9k","id":"3(@)"}
+{"time":"2026-08-12T18:07:12.181733156Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"hrggki9k","id":"3(@)"}
+{"time":"2026-08-12T18:07:13.412475061Z","level":"INFO","msg":"handleInformInit: received","streamId":"utqzlg67","id":"3(@)"}
+{"time":"2026-08-12T18:07:13.679314069Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"utqzlg67","id":"3(@)"}
+{"time":"2026-08-12T18:07:19.044675117Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"atkqmrzkldx8"}
+{"time":"2026-08-12T18:21:24.445193258Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"atkqmrzkldx8"}
+{"time":"2026-08-12T18:21:25.196343989Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"atkqmrzkldx8"}
+{"time":"2026-08-12T18:21:25.198067009Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"utqzlg67","id":"3(@)"}
+{"time":"2026-08-12T18:21:25.199000312Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"utqzlg67","id":"3(@)"}
+{"time":"2026-08-12T18:21:26.321522195Z","level":"INFO","msg":"handleInformInit: received","streamId":"vyycsg6r","id":"3(@)"}
+{"time":"2026-08-12T18:21:26.578729863Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"vyycsg6r","id":"3(@)"}
+{"time":"2026-08-12T18:21:31.999599169Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"h28g0ntapnl9"}
+{"time":"2026-08-12T18:38:21.284226521Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"h28g0ntapnl9"}
+{"time":"2026-08-12T18:38:21.818456712Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"h28g0ntapnl9"}
+{"time":"2026-08-12T18:38:21.81999609Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"vyycsg6r","id":"3(@)"}
+{"time":"2026-08-12T18:38:21.828229465Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"vyycsg6r","id":"3(@)"}
+{"time":"2026-08-12T18:38:23.104854149Z","level":"INFO","msg":"handleInformInit: received","streamId":"qtstmmvv","id":"3(@)"}
+{"time":"2026-08-12T18:38:23.372128976Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qtstmmvv","id":"3(@)"}
+{"time":"2026-08-12T18:38:28.777282159Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"b7qhqvo21369"}
+{"time":"2026-08-12T18:58:01.448371065Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"b7qhqvo21369"}
+{"time":"2026-08-12T18:58:02.001524628Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"b7qhqvo21369"}
+{"time":"2026-08-12T18:58:02.003105094Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"qtstmmvv","id":"3(@)"}
+{"time":"2026-08-12T18:58:02.003794074Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"qtstmmvv","id":"3(@)"}
+{"time":"2026-08-12T18:58:03.201898424Z","level":"INFO","msg":"handleInformInit: received","streamId":"0fh9o8ec","id":"3(@)"}
+{"time":"2026-08-12T18:58:03.568010316Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"0fh9o8ec","id":"3(@)"}
+{"time":"2026-08-12T18:58:09.158050393Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
+{"time":"2026-08-12T19:12:05.373774541Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
+{"time":"2026-08-12T19:12:05.978597092Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
+{"time":"2026-08-12T19:12:05.980085967Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"0fh9o8ec","id":"3(@)"}
+{"time":"2026-08-12T19:12:05.98075482Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"0fh9o8ec","id":"3(@)"}
+{"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
+{"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
+{"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}

zain/Activation/wandb/run-20260812_191207-w1cgnksl/logs/debug-internal.log

@@ -0,0 +1,11 @@
+{"time":"2026-08-12T19:12:07.497196304Z","level":"INFO","msg":"wandb-core"}
+{"time":"2026-08-12T19:12:07.497332182Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
+{"time":"2026-08-12T19:12:07.759577369Z","level":"INFO","msg":"stream: created new stream","id":"w1cgnksl"}
+{"time":"2026-08-12T19:12:07.759657193Z","level":"INFO","msg":"handler: started"}
+{"time":"2026-08-12T19:12:07.759784998Z","level":"INFO","msg":"stream: started"}
+{"time":"2026-08-12T19:12:07.759790925Z","level":"INFO","msg":"writer: started","stream_id":"w1cgnksl"}
+{"time":"2026-08-12T19:12:07.759842787Z","level":"INFO","msg":"sender: started"}
+{"time":"2026-08-12T19:12:09.060585544Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
+{"time":"2026-08-12T19:12:09.183194227Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T19:12:24.061611124Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":1,"events_offset":0,"events_lines":2,"console_offset":0,"console_lines":2,"uploaded_len":2}
+{"time":"2026-08-12T19:12:24.181068505Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}

zain/Activation/wandb/run-20260812_191207-w1cgnksl/logs/debug.log

@@ -0,0 +1,20 @@
+2026-08-12 19:12:07,495 INFO    MainThread:1371664 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_191207-w1cgnksl/logs/debug.log
+2026-08-12 19:12:07,496 INFO    MainThread:1371664 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_191207-w1cgnksl/logs/debug-internal.log
+2026-08-12 19:12:07,496 INFO    MainThread:1371664 [wandb_init.py:init():772] calling init triggers
+2026-08-12 19:12:07,496 INFO    MainThread:1371664 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
+config: {'_wandb': {}}
+2026-08-12 19:12:07,496 INFO    MainThread:1371664 [wandb_init.py:init():820] starting backend
+2026-08-12 19:12:07,496 INFO    MainThread:1371664 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
+2026-08-12 19:12:07,496 INFO    MainThread:1371664 [wandb_init.py:init():835] sending inform_init request
+2026-08-12 19:12:07,760 INFO    MainThread:1371664 [wandb_init.py:init():840] backend started and connected
+2026-08-12 19:12:07,761 INFO    MainThread:1371664 [wandb_init.py:init():910] updated telemetry
+2026-08-12 19:12:07,768 INFO    MainThread:1371664 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
+2026-08-12 19:12:08,094 INFO    MainThread:1371664 [wandb_init.py:init():978] starting run threads in backend
+2026-08-12 19:12:08,172 INFO    MainThread:1371664 [wandb_run.py:_console_start():2621] atexit reg
+2026-08-12 19:12:08,172 INFO    MainThread:1371664 [wandb_run.py:_redirect():2471] redirect: wrap_raw
+2026-08-12 19:12:08,172 INFO    MainThread:1371664 [wandb_run.py:_redirect():2540] Wrapping output streams.
+2026-08-12 19:12:08,172 INFO    MainThread:1371664 [wandb_run.py:_redirect():2563] Redirects installed.
+2026-08-12 19:12:08,173 INFO    MainThread:1371664 [wandb_init.py:init():1016] run started, returning control to user process
+2026-08-12 19:12:08,174 INFO    MainThread:1371664 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 150, 'num_attention_heads': 4, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'max_position_embeddings': 512, 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'pad_token_id': 0, 'bos_token_id': 1, 'eos_token_id': 2, 'pretraining_tp': 1, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 10000.0, 'rope_type': 'default'}, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 32, '_name_or_path': '', 'tokenizer_name': 'w-ahmad/tiny-stories-tokenizer', 'mlp_type': 'glu', 'activation': 'waleed10', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-waleed10-150L_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 1000, 'learning_rate': 0.005, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 200, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 0.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-waleed10-150L-25.1M-20260812-191206', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 50, 'eval_delay': 0, 'per_device_eval_batch_size': 128, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 1000, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/6L-glu-waleed10-150L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
+2026-08-12 19:12:08,181 INFO    MainThread:1371664 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 25138816 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14c5efb86510>>
+2026-08-12 19:12:08,181 INFO    MainThread:1371664 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 25138816 None