Auto upload zain 2026-08-12T20:53:45.402352

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+zain/Activation/wandb/run-20260812_204959-ha94g4f6/run-ha94g4f6.wandb filter=lfs diff=lfs merge=lfs -text

zain/Activation/out/glu-silu-150L_run/checkpoint-100/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "silu",
+  "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-silu-150L_run/checkpoint-100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:436e0f5fdc306f2612e5623c4bedab1a4f4a176e0336d27074637317efc2c601
+size 50427120

zain/Activation/out/glu-silu-150L_run/checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2017e0f4fc4d1c304ff89a73b5fec50ca4037cf7b8305cba9eaea451a92c672
+size 101708778

zain/Activation/out/glu-silu-150L_run/checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cf9097d4513154245c48236b6ec5137b7ee2a21c9f58f2cba798ea275c6026f
+size 14244

zain/Activation/out/glu-silu-150L_run/checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bdfac4f2e1738f5637e5bffe76e7b0fca096757dbd046b752f47ffea9583af4
+size 1064

zain/Activation/out/glu-silu-150L_run/checkpoint-100/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-silu-150L_run/checkpoint-100/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.003370407819346141,
+  "eval_steps": 50,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0006740815638692282,
+      "grad_norm": 1.4453125,
+      "learning_rate": 6.65e-05,
+      "loss": 8.234290313720702,
+      "step": 20
+    },
+    {
+      "epoch": 0.0013481631277384564,
+      "grad_norm": 1.375,
+      "learning_rate": 0.0001365,
+      "loss": 7.89990234375,
+      "step": 40
+    },
+    {
+      "epoch": 0.0016852039096730705,
+      "eval_loss": 7.460479736328125,
+      "eval_runtime": 19.2679,
+      "eval_samples_per_second": 494.451,
+      "eval_steps_per_second": 0.519,
+      "step": 50
+    },
+    {
+      "epoch": 0.0020222446916076846,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.00020649999999999998,
+      "loss": 7.466981506347656,
+      "step": 60
+    },
+    {
+      "epoch": 0.002696326255476913,
+      "grad_norm": 1.109375,
+      "learning_rate": 0.0002765,
+      "loss": 6.8938346862792965,
+      "step": 80
+    },
+    {
+      "epoch": 0.003370407819346141,
+      "grad_norm": 0.7578125,
+      "learning_rate": 0.0003465,
+      "loss": 6.388959884643555,
+      "step": 100
+    },
+    {
+      "epoch": 0.003370407819346141,
+      "eval_loss": 6.1897783279418945,
+      "eval_runtime": 19.5204,
+      "eval_samples_per_second": 488.055,
+      "eval_steps_per_second": 0.512,
+      "step": 100
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 241970656051200.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

zain/Activation/out/glu-silu-150L_run/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34970b4f4751a3a1bb227a3f64aec0449dc16fbc2c2a20a2076e0bb5edfa923d
+size 4920

zain/Activation/out/glu-silu-150L_run/checkpoint-200/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "silu",
+  "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-silu-150L_run/checkpoint-200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:598585638fb67244a1efce6bfc8cd39f25fef20131a6d843d4543614a2af08bc
+size 50427120

zain/Activation/out/glu-silu-150L_run/checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:338b68781bb7a92cb92b568cb517cdd2c0fee378cb54d8cfca6c2f948e886d1f
+size 101708778

zain/Activation/out/glu-silu-150L_run/checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecefbb3f17bb76b6655eb0157c98b5287c17fa4b4c72a6b9068b0823ce9fd18d
+size 14244

zain/Activation/out/glu-silu-150L_run/checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65adfad786ae2b224643009c3ac2998e8fc0229311e4b753becffd2fb9569fe9
+size 1064

zain/Activation/out/glu-silu-150L_run/checkpoint-200/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-silu-150L_run/checkpoint-200/trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.006740815638692282,
+  "eval_steps": 50,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0006740815638692282,
+      "grad_norm": 1.4453125,
+      "learning_rate": 6.65e-05,
+      "loss": 8.234290313720702,
+      "step": 20
+    },
+    {
+      "epoch": 0.0013481631277384564,
+      "grad_norm": 1.375,
+      "learning_rate": 0.0001365,
+      "loss": 7.89990234375,
+      "step": 40
+    },
+    {
+      "epoch": 0.0016852039096730705,
+      "eval_loss": 7.460479736328125,
+      "eval_runtime": 19.2679,
+      "eval_samples_per_second": 494.451,
+      "eval_steps_per_second": 0.519,
+      "step": 50
+    },
+    {
+      "epoch": 0.0020222446916076846,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.00020649999999999998,
+      "loss": 7.466981506347656,
+      "step": 60
+    },
+    {
+      "epoch": 0.002696326255476913,
+      "grad_norm": 1.109375,
+      "learning_rate": 0.0002765,
+      "loss": 6.8938346862792965,
+      "step": 80
+    },
+    {
+      "epoch": 0.003370407819346141,
+      "grad_norm": 0.7578125,
+      "learning_rate": 0.0003465,
+      "loss": 6.388959884643555,
+      "step": 100
+    },
+    {
+      "epoch": 0.003370407819346141,
+      "eval_loss": 6.1897783279418945,
+      "eval_runtime": 19.5204,
+      "eval_samples_per_second": 488.055,
+      "eval_steps_per_second": 0.512,
+      "step": 100
+    },
+    {
+      "epoch": 0.004044489383215369,
+      "grad_norm": 0.4140625,
+      "learning_rate": 0.0004165,
+      "loss": 6.100220108032227,
+      "step": 120
+    },
+    {
+      "epoch": 0.0047185709470845974,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00048649999999999995,
+      "loss": 5.89860954284668,
+      "step": 140
+    },
+    {
+      "epoch": 0.005055611729019211,
+      "eval_loss": 5.7081780433654785,
+      "eval_runtime": 19.2404,
+      "eval_samples_per_second": 495.155,
+      "eval_steps_per_second": 0.52,
+      "step": 150
+    },
+    {
+      "epoch": 0.005392652510953826,
+      "grad_norm": 2.515625,
+      "learning_rate": 0.0005565,
+      "loss": 5.742493438720703,
+      "step": 160
+    },
+    {
+      "epoch": 0.006066734074823054,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.0006265,
+      "loss": 5.54938850402832,
+      "step": 180
+    },
+    {
+      "epoch": 0.006740815638692282,
+      "grad_norm": 1.3671875,
+      "learning_rate": 0.0006965,
+      "loss": 5.339012145996094,
+      "step": 200
+    },
+    {
+      "epoch": 0.006740815638692282,
+      "eval_loss": 5.230809211730957,
+      "eval_runtime": 19.4737,
+      "eval_samples_per_second": 489.224,
+      "eval_steps_per_second": 0.514,
+      "step": 200
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 483941312102400.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

zain/Activation/out/glu-silu-150L_run/checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34970b4f4751a3a1bb227a3f64aec0449dc16fbc2c2a20a2076e0bb5edfa923d
+size 4920

zain/Activation/out/glu-silu-150L_run/checkpoint-300/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "silu",
+  "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-silu-150L_run/checkpoint-300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:330442f1dad101da8a1a2ce058521c445a73e89d837f5e1f92758870056e8ddf
+size 50427120

zain/Activation/out/glu-silu-150L_run/checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6084dedba551a04e104f8e8c053020bd37a0f622a430d82b2cb3765b166a3f5b
+size 101708778

zain/Activation/out/glu-silu-150L_run/checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:068fbd993087219c15b8c0baa13fc39644a4dcdfe92d8be3fa6434deece90371
+size 14244

zain/Activation/out/glu-silu-150L_run/checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7275519db1cfbc1c3b3ff4cc789ae435d90674550d32700685019af96bdd8863
+size 1064

zain/Activation/out/glu-silu-150L_run/checkpoint-300/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-silu-150L_run/checkpoint-300/trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.010111223458038422,
+  "eval_steps": 50,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0006740815638692282,
+      "grad_norm": 1.4453125,
+      "learning_rate": 6.65e-05,
+      "loss": 8.234290313720702,
+      "step": 20
+    },
+    {
+      "epoch": 0.0013481631277384564,
+      "grad_norm": 1.375,
+      "learning_rate": 0.0001365,
+      "loss": 7.89990234375,
+      "step": 40
+    },
+    {
+      "epoch": 0.0016852039096730705,
+      "eval_loss": 7.460479736328125,
+      "eval_runtime": 19.2679,
+      "eval_samples_per_second": 494.451,
+      "eval_steps_per_second": 0.519,
+      "step": 50
+    },
+    {
+      "epoch": 0.0020222446916076846,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.00020649999999999998,
+      "loss": 7.466981506347656,
+      "step": 60
+    },
+    {
+      "epoch": 0.002696326255476913,
+      "grad_norm": 1.109375,
+      "learning_rate": 0.0002765,
+      "loss": 6.8938346862792965,
+      "step": 80
+    },
+    {
+      "epoch": 0.003370407819346141,
+      "grad_norm": 0.7578125,
+      "learning_rate": 0.0003465,
+      "loss": 6.388959884643555,
+      "step": 100
+    },
+    {
+      "epoch": 0.003370407819346141,
+      "eval_loss": 6.1897783279418945,
+      "eval_runtime": 19.5204,
+      "eval_samples_per_second": 488.055,
+      "eval_steps_per_second": 0.512,
+      "step": 100
+    },
+    {
+      "epoch": 0.004044489383215369,
+      "grad_norm": 0.4140625,
+      "learning_rate": 0.0004165,
+      "loss": 6.100220108032227,
+      "step": 120
+    },
+    {
+      "epoch": 0.0047185709470845974,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00048649999999999995,
+      "loss": 5.89860954284668,
+      "step": 140
+    },
+    {
+      "epoch": 0.005055611729019211,
+      "eval_loss": 5.7081780433654785,
+      "eval_runtime": 19.2404,
+      "eval_samples_per_second": 495.155,
+      "eval_steps_per_second": 0.52,
+      "step": 150
+    },
+    {
+      "epoch": 0.005392652510953826,
+      "grad_norm": 2.515625,
+      "learning_rate": 0.0005565,
+      "loss": 5.742493438720703,
+      "step": 160
+    },
+    {
+      "epoch": 0.006066734074823054,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.0006265,
+      "loss": 5.54938850402832,
+      "step": 180
+    },
+    {
+      "epoch": 0.006740815638692282,
+      "grad_norm": 1.3671875,
+      "learning_rate": 0.0006965,
+      "loss": 5.339012145996094,
+      "step": 200
+    },
+    {
+      "epoch": 0.006740815638692282,
+      "eval_loss": 5.230809211730957,
+      "eval_runtime": 19.4737,
+      "eval_samples_per_second": 489.224,
+      "eval_steps_per_second": 0.514,
+      "step": 200
+    },
+    {
+      "epoch": 0.00741489720256151,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.0007,
+      "loss": 5.185653305053711,
+      "step": 220
+    },
+    {
+      "epoch": 0.008088978766430738,
+      "grad_norm": 1.65625,
+      "learning_rate": 0.0007,
+      "loss": 4.989022064208984,
+      "step": 240
+    },
+    {
+      "epoch": 0.008426019548365353,
+      "eval_loss": 4.977165222167969,
+      "eval_runtime": 19.1939,
+      "eval_samples_per_second": 496.356,
+      "eval_steps_per_second": 0.521,
+      "step": 250
+    },
+    {
+      "epoch": 0.008763060330299966,
+      "grad_norm": 0.6328125,
+      "learning_rate": 0.0007,
+      "loss": 4.932804870605469,
+      "step": 260
+    },
+    {
+      "epoch": 0.009437141894169195,
+      "grad_norm": 1.578125,
+      "learning_rate": 0.0007,
+      "loss": 4.816947555541992,
+      "step": 280
+    },
+    {
+      "epoch": 0.010111223458038422,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.0007,
+      "loss": 4.680611419677734,
+      "step": 300
+    },
+    {
+      "epoch": 0.010111223458038422,
+      "eval_loss": 4.6526055335998535,
+      "eval_runtime": 19.5274,
+      "eval_samples_per_second": 487.879,
+      "eval_steps_per_second": 0.512,
+      "step": 300
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 725911968153600.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

zain/Activation/out/glu-silu-150L_run/checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34970b4f4751a3a1bb227a3f64aec0449dc16fbc2c2a20a2076e0bb5edfa923d
+size 4920

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

@@ -0,0 +1,25 @@
+{"step": 20, "epoch": 0.0006740815638692282, "timestamp": 1786567746.8737483, "loss": 8.234290313720702, "grad_norm": 1.4453125, "learning_rate": 6.65e-05, "train/total_time_seconds": 6.460398405790329, "train/time_per_step_avg": 0.3230199202895164, "train/epoch_time_elapsed": 7.084352497011423, "train/estimated_remaining_minutes": 2.5841593623161314}
+{"step": 40, "epoch": 0.0013481631277384564, "timestamp": 1786567753.1599498, "loss": 7.89990234375, "grad_norm": 1.375, "learning_rate": 0.0001365, "train/total_time_seconds": 12.227118451148272, "train/time_per_step_avg": 0.3056779612787068, "train/epoch_time_elapsed": 13.370555110275745, "train/estimated_remaining_minutes": 2.343531036470085}
+{"step": 20, "epoch": 0.0006740815638692282, "timestamp": 1786567806.7755067, "loss": 8.234290313720702, "grad_norm": 1.4453125, "learning_rate": 6.65e-05, "train/total_time_seconds": 6.304238460958004, "train/time_per_step_avg": 0.3152119230479002, "train/epoch_time_elapsed": 6.934158425778151, "train/estimated_remaining_minutes": 2.5216953843832015}
+{"step": 40, "epoch": 0.0013481631277384564, "timestamp": 1786567812.9557588, "loss": 7.89990234375, "grad_norm": 1.375, "learning_rate": 0.0001365, "train/total_time_seconds": 11.966222673654556, "train/time_per_step_avg": 0.2991555668413639, "train/epoch_time_elapsed": 13.114412102848291, "train/estimated_remaining_minutes": 2.2935260124504566}
+{"step": 50, "epoch": 0.0016852039096730705, "timestamp": 1786567835.3119326, "eval_loss": 7.460479736328125, "eval_runtime": 19.2679, "eval_samples_per_second": 494.451, "eval_steps_per_second": 0.519, "train/total_time_seconds": 14.797902647405863, "train/time_per_step_avg": 0.2959580529481173, "train/epoch_time_elapsed": 35.47058588266373, "train/estimated_remaining_minutes": 2.2196853971108794}
+{"step": 60, "epoch": 0.0020222446916076846, "timestamp": 1786567838.5298808, "loss": 7.466981506347656, "grad_norm": 1.234375, "learning_rate": 0.00020649999999999998, "train/total_time_seconds": 17.75784918665886, "train/time_per_step_avg": 0.295964153110981, "train/epoch_time_elapsed": 38.68853436782956, "train/estimated_remaining_minutes": 2.170403789480527}
+{"step": 80, "epoch": 0.002696326255476913, "timestamp": 1786567845.2552493, "loss": 6.8938346862792965, "grad_norm": 1.109375, "learning_rate": 0.0002765, "train/total_time_seconds": 23.963823959231377, "train/time_per_step_avg": 0.29954779949039223, "train/epoch_time_elapsed": 45.41390248015523, "train/estimated_remaining_minutes": 2.0968345964327457}
+{"step": 100, "epoch": 0.003370407819346141, "timestamp": 1786567851.8974333, "loss": 6.388959884643555, "grad_norm": 0.7578125, "learning_rate": 0.0003465, "train/total_time_seconds": 30.095395665615797, "train/time_per_step_avg": 0.300953956656158, "train/epoch_time_elapsed": 52.05608719587326, "train/estimated_remaining_minutes": 2.006359711041053}
+{"step": 100, "epoch": 0.003370407819346141, "timestamp": 1786567871.4193368, "eval_loss": 6.1897783279418945, "eval_runtime": 19.5204, "eval_samples_per_second": 488.055, "eval_steps_per_second": 0.512, "train/total_time_seconds": 30.095395665615797, "train/time_per_step_avg": 0.300953956656158, "train/epoch_time_elapsed": 71.577990103513, "train/estimated_remaining_minutes": 2.006359711041053}
+{"step": 120, "epoch": 0.004044489383215369, "timestamp": 1786567878.3278444, "loss": 6.100220108032227, "grad_norm": 0.4140625, "learning_rate": 0.0004165, "train/total_time_seconds": 36.04865622520447, "train/time_per_step_avg": 0.2974441776424646, "train/epoch_time_elapsed": 78.48649704828858, "train/estimated_remaining_minutes": 1.902567967441347}
+{"step": 140, "epoch": 0.0047185709470845974, "timestamp": 1786567884.800851, "loss": 5.89860954284668, "grad_norm": 0.55859375, "learning_rate": 0.00048649999999999995, "train/total_time_seconds": 42.00394169613719, "train/time_per_step_avg": 0.30037719022482634, "train/epoch_time_elapsed": 84.95950577780604, "train/estimated_remaining_minutes": 1.800168929834451}
+{"step": 150, "epoch": 0.005055611729019211, "timestamp": 1786567907.3142965, "eval_loss": 5.7081780433654785, "eval_runtime": 19.2404, "eval_samples_per_second": 495.155, "eval_steps_per_second": 0.52, "train/total_time_seconds": 45.015298429876566, "train/time_per_step_avg": 0.302173957824707, "train/epoch_time_elapsed": 107.47294987365603, "train/estimated_remaining_minutes": 1.7505949389396442}
+{"step": 160, "epoch": 0.005392652510953826, "timestamp": 1786567910.5512593, "loss": 5.742493438720703, "grad_norm": 2.515625, "learning_rate": 0.0005565, "train/total_time_seconds": 47.99258862435818, "train/time_per_step_avg": 0.3023473943769932, "train/epoch_time_elapsed": 110.70991373807192, "train/estimated_remaining_minutes": 1.699737513779352}
+{"step": 180, "epoch": 0.006066734074823054, "timestamp": 1786567917.0364354, "loss": 5.54938850402832, "grad_norm": 1.234375, "learning_rate": 0.0006265, "train/total_time_seconds": 53.95190108567476, "train/time_per_step_avg": 0.29988077126443385, "train/epoch_time_elapsed": 117.19508977606893, "train/estimated_remaining_minutes": 1.598574846982956}
+{"step": 200, "epoch": 0.006740815638692282, "timestamp": 1786567923.5904472, "loss": 5.339012145996094, "grad_norm": 1.3671875, "learning_rate": 0.0006965, "train/total_time_seconds": 59.97218247875571, "train/time_per_step_avg": 0.29876786813139916, "train/epoch_time_elapsed": 123.7491016164422, "train/estimated_remaining_minutes": 1.4993045619688927}
+{"step": 200, "epoch": 0.006740815638692282, "timestamp": 1786567943.0655806, "eval_loss": 5.230809211730957, "eval_runtime": 19.4737, "eval_samples_per_second": 489.224, "eval_steps_per_second": 0.514, "train/total_time_seconds": 59.97218247875571, "train/time_per_step_avg": 0.29876786813139916, "train/epoch_time_elapsed": 143.22423388436437, "train/estimated_remaining_minutes": 1.4993045619688927}
+{"step": 220, "epoch": 0.00741489720256151, "timestamp": 1786567950.479565, "loss": 5.185653305053711, "grad_norm": 1.53125, "learning_rate": 0.0007, "train/total_time_seconds": 66.44817723333836, "train/time_per_step_avg": 0.3039952100813389, "train/epoch_time_elapsed": 150.6382187306881, "train/estimated_remaining_minutes": 1.4095067897980864}
+{"step": 240, "epoch": 0.008088978766430738, "timestamp": 1786567957.093375, "loss": 4.989022064208984, "grad_norm": 1.65625, "learning_rate": 0.0007, "train/total_time_seconds": 72.52528139576316, "train/time_per_step_avg": 0.3052133969962597, "train/epoch_time_elapsed": 157.25202928483486, "train/estimated_remaining_minutes": 1.3094842474235016}
+{"step": 250, "epoch": 0.008426019548365353, "timestamp": 1786567979.5580354, "eval_loss": 4.977165222167969, "eval_runtime": 19.1939, "eval_samples_per_second": 496.356, "eval_steps_per_second": 0.521, "train/total_time_seconds": 75.5365678369999, "train/time_per_step_avg": 0.30521269407123325, "train/epoch_time_elapsed": 179.71668792143464, "train/estimated_remaining_minutes": 1.2589427972833316}
+{"step": 260, "epoch": 0.008763060330299966, "timestamp": 1786567982.802241, "loss": 4.932804870605469, "grad_norm": 0.6328125, "learning_rate": 0.0007, "train/total_time_seconds": 78.5190594010055, "train/time_per_step_avg": 0.3052647077664733, "train/epoch_time_elapsed": 182.96089447289705, "train/estimated_remaining_minutes": 1.2079855292462385}
+{"step": 280, "epoch": 0.009437141894169195, "timestamp": 1786567989.3548305, "loss": 4.816947555541992, "grad_norm": 1.578125, "learning_rate": 0.0007, "train/total_time_seconds": 84.52964476123452, "train/time_per_step_avg": 0.3057774367555976, "train/epoch_time_elapsed": 189.5134849473834, "train/estimated_remaining_minutes": 1.1069358242542615}
+{"step": 300, "epoch": 0.010111223458038422, "timestamp": 1786567995.863883, "loss": 4.680611419677734, "grad_norm": 1.84375, "learning_rate": 0.0007, "train/total_time_seconds": 90.51709629967809, "train/time_per_step_avg": 0.30544913820922376, "train/epoch_time_elapsed": 196.02253611385822, "train/estimated_remaining_minutes": 1.0057455144408676}
+{"step": 300, "epoch": 0.010111223458038422, "timestamp": 1786568015.3927298, "eval_loss": 4.6526055335998535, "eval_runtime": 19.5274, "eval_samples_per_second": 487.879, "eval_steps_per_second": 0.512, "train/total_time_seconds": 90.51709629967809, "train/time_per_step_avg": 0.30544913820922376, "train/epoch_time_elapsed": 215.55138336867094, "train/estimated_remaining_minutes": 1.0057455144408676}
+{"step": 320, "epoch": 0.010785305021907651, "timestamp": 1786568022.3550558, "loss": 4.554249954223633, "grad_norm": 0.90625, "learning_rate": 0.0007, "train/total_time_seconds": 96.5381933413446, "train/time_per_step_avg": 0.3009001610800624, "train/epoch_time_elapsed": 222.5137095414102, "train/estimated_remaining_minutes": 0.9050455625751056}
+{"step": 340, "epoch": 0.011459386585776879, "timestamp": 1786568028.9446778, "loss": 4.416970825195312, "grad_norm": 0.69921875, "learning_rate": 0.0007, "train/total_time_seconds": 102.58192877471447, "train/time_per_step_avg": 0.3005664737895131, "train/epoch_time_elapsed": 229.10333258286119, "train/estimated_remaining_minutes": 0.8045641472526626}

zain/Activation/wandb/debug-internal.log

@@ -0,0 +1,39 @@
+{"time":"2026-08-12T20:49:59.231329238Z","level":"INFO","msg":"wandb-core"}
+{"time":"2026-08-12T20:49:59.231458005Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
+{"time":"2026-08-12T20:49:59.4901037Z","level":"INFO","msg":"stream: created new stream","id":"ha94g4f6"}
+{"time":"2026-08-12T20:49:59.490189081Z","level":"INFO","msg":"handler: started"}
+{"time":"2026-08-12T20:49:59.490265922Z","level":"INFO","msg":"stream: started"}
+{"time":"2026-08-12T20:49:59.490276077Z","level":"INFO","msg":"writer: started","stream_id":"ha94g4f6"}
+{"time":"2026-08-12T20:49:59.49030619Z","level":"INFO","msg":"sender: started"}
+{"time":"2026-08-12T20:49:59.978334344Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
+{"time":"2026-08-12T20:50:00.112397512Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:50:14.978575235Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":2,"events_offset":0,"events_lines":2,"console_offset":1,"console_lines":4,"uploaded_len":2}
+{"time":"2026-08-12T20:50:15.141418893Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:50:29.978639147Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":2,"events_lines":2,"console_offset":2,"console_lines":1}
+{"time":"2026-08-12T20:50:30.112487958Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:50:44.979520057Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":2,"history_lines":2,"events_offset":4,"events_lines":2,"console_offset":2,"console_lines":1}
+{"time":"2026-08-12T20:50:45.106709081Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:50:59.978634412Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":4,"history_lines":2,"events_offset":6,"events_lines":1,"console_offset":2,"console_lines":1}
+{"time":"2026-08-12T20:51:00.176400181Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:51:14.978675737Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":6,"history_lines":1,"events_offset":7,"events_lines":3,"console_offset":2,"console_lines":1}
+{"time":"2026-08-12T20:51:15.136480688Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:51:29.978816851Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":7,"history_lines":2,"events_offset":10,"events_lines":2,"console_offset":5,"console_lines":12}
+{"time":"2026-08-12T20:51:30.144315427Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:51:44.978880235Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":12,"events_lines":2,"console_offset":17,"console_lines":1}
+{"time":"2026-08-12T20:51:45.106187785Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:51:59.9795397Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":9,"history_lines":3,"events_offset":14,"events_lines":2,"console_offset":14,"console_lines":1}
+{"time":"2026-08-12T20:52:00.115108282Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:52:14.978616189Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":12,"history_lines":1,"events_offset":16,"events_lines":2,"console_offset":14,"console_lines":1}
+{"time":"2026-08-12T20:52:15.144083803Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:52:29.979233536Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":13,"history_lines":1,"events_offset":18,"events_lines":2,"console_offset":14,"console_lines":1}
+{"time":"2026-08-12T20:52:30.115302332Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:52:44.979378867Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":14,"history_lines":2,"events_offset":20,"events_lines":2,"console_offset":17,"console_lines":13}
+{"time":"2026-08-12T20:52:45.104669417Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:52:59.97898149Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":16,"history_lines":1,"events_offset":22,"events_lines":2,"console_offset":26,"console_lines":1}
+{"time":"2026-08-12T20:53:00.121062111Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:53:14.979322756Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":17,"history_lines":2,"events_offset":24,"events_lines":2,"console_offset":26,"console_lines":1}
+{"time":"2026-08-12T20:53:15.120861918Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:53:29.979219904Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":19,"history_lines":1,"events_offset":26,"events_lines":2,"console_offset":26,"console_lines":1}
+{"time":"2026-08-12T20:53:30.146291299Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:53:44.979549283Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":20,"history_lines":2,"events_offset":28,"events_lines":2,"console_offset":26,"console_lines":1}
+{"time":"2026-08-12T20:53:45.134028333Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}

zain/Activation/wandb/debug.log

@@ -0,0 +1,23 @@
+2026-08-12 20:49:59,229 INFO    MainThread:3035682 [wandb_setup.py:_flush():81] Current SDK version is 0.28.1
+2026-08-12 20:49:59,229 INFO    MainThread:3035682 [wandb_setup.py:_flush():81] Configure stats pid to 3035682
+2026-08-12 20:49:59,229 INFO    MainThread:3035682 [wandb_setup.py:_flush():81] Loading settings from environment variables
+2026-08-12 20:49:59,229 INFO    MainThread:3035682 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_204959-ha94g4f6/logs/debug.log
+2026-08-12 20:49:59,229 INFO    MainThread:3035682 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_204959-ha94g4f6/logs/debug-internal.log
+2026-08-12 20:49:59,229 INFO    MainThread:3035682 [wandb_init.py:init():772] calling init triggers
+2026-08-12 20:49:59,230 INFO    MainThread:3035682 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
+config: {'_wandb': {}}
+2026-08-12 20:49:59,230 INFO    MainThread:3035682 [wandb_init.py:init():820] starting backend
+2026-08-12 20:49:59,230 INFO    MainThread:3035682 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
+2026-08-12 20:49:59,230 INFO    MainThread:3035682 [wandb_init.py:init():835] sending inform_init request
+2026-08-12 20:49:59,490 INFO    MainThread:3035682 [wandb_init.py:init():840] backend started and connected
+2026-08-12 20:49:59,494 INFO    MainThread:3035682 [wandb_init.py:init():910] updated telemetry
+2026-08-12 20:49:59,501 INFO    MainThread:3035682 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
+2026-08-12 20:49:59,756 INFO    MainThread:3035682 [wandb_init.py:init():978] starting run threads in backend
+2026-08-12 20:49:59,831 INFO    MainThread:3035682 [wandb_run.py:_console_start():2621] atexit reg
+2026-08-12 20:49:59,832 INFO    MainThread:3035682 [wandb_run.py:_redirect():2471] redirect: wrap_raw
+2026-08-12 20:49:59,832 INFO    MainThread:3035682 [wandb_run.py:_redirect():2540] Wrapping output streams.
+2026-08-12 20:49:59,832 INFO    MainThread:3035682 [wandb_run.py:_redirect():2563] Redirects installed.
+2026-08-12 20:49:59,835 INFO    MainThread:3035682 [wandb_init.py:init():1016] run started, returning control to user process
+2026-08-12 20:49:59,835 INFO    MainThread:3035682 [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': 'silu', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-silu-150L_run', 'per_device_train_batch_size': 32, 'num_train_epochs': 1, 'max_steps': 500, 'learning_rate': 0.0007, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 200, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-silu-150L-25.1M-20260812-204958', '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': 1024, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 100, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/6L-glu-silu-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 20:49:59,841 INFO    MainThread:3035682 [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 0x152f60578810>>
+2026-08-12 20:49:59,841 INFO    MainThread:3035682 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 25138816 None

zain/Activation/wandb/run-20260812_204859-c8cw38zl/files/config.yaml

@@ -0,0 +1,442 @@
+_name_or_path:
+    value: ""
+_wandb:
+    value:
+        cli_version: 0.28.1
+        e:
+            5l8bepqvwhf0bjm2vh0i5lowje16r2i4:
+                args:
+                    - --config
+                    - /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/configs/baseline150L.yaml
+                    - --variants
+                    - glu-silu
+                    - glu-waleed10
+                    - glu-silu-waleed10
+                    - glu-situglu
+                    - glu-waleed
+                    - glu-situglu_low
+                    - glu-waleedglu_low
+                    - glu-relu
+                    - glu-gelu
+                    - glu-sigmoid
+                    - glu-linear
+                codePath: sweep.py
+                codePathLocal: sweep.py
+                cpu_count: 112
+                cpu_count_logical: 224
+                cudaVersion: "12.4"
+                disk:
+                    /:
+                        total: "1560765693952"
+                        used: "716359323648"
+                email: deepnevro@gmail.com
+                executable: /mnt/data/zainulabideen/zain-exp/notebooks/my_env/bin/python
+                git:
+                    commit: 26a43c7dee7982e610a25ac78443de9ce18f5077
+                    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: "2026-08-12T20:48:59.130265Z"
+                writerId: 5l8bepqvwhf0bjm2vh0i5lowje16r2i4
+        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
+                - 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: silu
+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-silu-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: 0.0007
+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: 1
+max_position_embeddings:
+    value: 512
+max_steps:
+    value: 500
+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-silu-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: 32
+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-silu-150L-25.1M-20260812-204858
+save_on_each_node:
+    value: false
+save_only_model:
+    value: false
+save_steps:
+    value: 100
+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_204859-c8cw38zl/files/output.log

@@ -0,0 +1,6 @@
+[transformers] `use_return_dict` is deprecated! Use `return_dict` instead!
+[INFO] Causal mask (float with -inf) applied to all attention layers.
+ 10%|█         | 50/500 [00:17<02:19,  3.23it/s]
+{'loss': '8.234', 'grad_norm': '1.445', 'learning_rate': '6.65e-05', 'epoch': '0.0006741', 'train/total_time_seconds': '6.46', 'train/time_per_step_avg': '0.323', 'train/epoch_time_elapsed': '7.084', 'train/estimated_remaining_minutes': '2.584'}
+{'loss': '7.9', 'grad_norm': '1.375', 'learning_rate': '0.0001365', 'epoch': '0.001348', 'train/total_time_seconds': '12.23', 'train/time_per_step_avg': '0.3057', 'train/epoch_time_elapsed': '13.37', 'train/estimated_remaining_minutes': '2.344'}
+ 95%|█████████▍| 71/75 [00:19<00:01,  3.55it/s]

zain/Activation/wandb/run-20260812_204859-c8cw38zl/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_204859-c8cw38zl/files/wandb-metadata.json

@@ -0,0 +1,105 @@
+{
+  "os":  "Linux-5.15.0-126-generic-x86_64-with-glibc2.35",
+  "python":  "CPython 3.11.15",
+  "startedAt":  "2026-08-12T20:48:59.130265Z",
+  "args":  [
+    "--config",
+    "/mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/configs/baseline150L.yaml",
+    "--variants",
+    "glu-silu",
+    "glu-waleed10",
+    "glu-silu-waleed10",
+    "glu-situglu",
+    "glu-waleed",
+    "glu-situglu_low",
+    "glu-waleedglu_low",
+    "glu-relu",
+    "glu-gelu",
+    "glu-sigmoid",
+    "glu-linear"
+  ],
+  "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":  "26a43c7dee7982e610a25ac78443de9ce18f5077"
+  },
+  "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":  "716359323648"
+    }
+  },
+  "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":  "5l8bepqvwhf0bjm2vh0i5lowje16r2i4"
+}

zain/Activation/wandb/run-20260812_204859-c8cw38zl/files/wandb-summary.json

@@ -0,0 +1 @@
+{"_wandb":{"runtime":36},"_runtime":36,"train/epoch":0.0013481631277384564,"train/train/epoch_time_elapsed":13.370555110275745,"train/train/time_per_step_avg":0.3056779612787068,"train/train/total_time_seconds":12.227118451148272,"_step":1,"train/learning_rate":0.0001365,"train/grad_norm":1.375,"train/global_step":40,"train/loss":7.89990234375,"_timestamp":1.786567753160658e+09,"train/train/estimated_remaining_minutes":2.343531036470085}

zain/Activation/wandb/run-20260812_204859-c8cw38zl/logs/debug-core.log

@@ -0,0 +1,20 @@
+{"time":"2026-08-12T20:46:29.826542919Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpfq15lqwq/port-2980938.txt","pid":2980938,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2026-08-12T20:46:29.827630129Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":2980938}
+{"time":"2026-08-12T20:46:29.827605008Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-2980938-3003971-36328316/socket","Net":"unix"}}
+{"time":"2026-08-12T20:46:30.00400148Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2026-08-12T20:48:59.03423153Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"2(@)"}
+{"time":"2026-08-12T20:48:59.133025837Z","level":"INFO","msg":"handleInformInit: received","streamId":"c8cw38zl","id":"2(@)"}
+{"time":"2026-08-12T20:48:59.393728981Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"c8cw38zl","id":"2(@)"}
+{"time":"2026-08-12T20:49:04.781949197Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"t81j1d8lh5hv"}
+{"time":"2026-08-12T20:49:36.491139113Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"t81j1d8lh5hv"}
+{"time":"2026-08-12T20:49:37.029432845Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"t81j1d8lh5hv"}
+{"time":"2026-08-12T20:49:37.031098016Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"c8cw38zl","id":"2(@)"}
+{"time":"2026-08-12T20:49:37.032166543Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"c8cw38zl","id":"2(@)"}
+{"time":"2026-08-12T20:49:38.248051669Z","level":"INFO","msg":"connection: closing","id":"2(@)"}
+{"time":"2026-08-12T20:49:38.248082215Z","level":"INFO","msg":"processOutgoingData: finished","id":"2(@)"}
+{"time":"2026-08-12T20:49:38.248121683Z","level":"INFO","msg":"connection: closed successfully","id":"2(@)"}
+{"time":"2026-08-12T20:49:38.248148742Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"2(@)"}
+{"time":"2026-08-12T20:49:59.123664108Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"3(@)"}
+{"time":"2026-08-12T20:49:59.231166569Z","level":"INFO","msg":"handleInformInit: received","streamId":"ha94g4f6","id":"3(@)"}
+{"time":"2026-08-12T20:49:59.490273575Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"ha94g4f6","id":"3(@)"}
+{"time":"2026-08-12T20:50:04.834347925Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"k2vr6fkcyr5w"}

zain/Activation/wandb/run-20260812_204859-c8cw38zl/logs/debug-internal.log

@@ -0,0 +1,21 @@
+{"time":"2026-08-12T20:48:59.133193282Z","level":"INFO","msg":"wandb-core"}
+{"time":"2026-08-12T20:48:59.133492658Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
+{"time":"2026-08-12T20:48:59.393556846Z","level":"INFO","msg":"stream: created new stream","id":"c8cw38zl"}
+{"time":"2026-08-12T20:48:59.393638833Z","level":"INFO","msg":"handler: started"}
+{"time":"2026-08-12T20:48:59.393721422Z","level":"INFO","msg":"stream: started"}
+{"time":"2026-08-12T20:48:59.39374121Z","level":"INFO","msg":"writer: started","stream_id":"c8cw38zl"}
+{"time":"2026-08-12T20:48:59.393752619Z","level":"INFO","msg":"sender: started"}
+{"time":"2026-08-12T20:48:59.928325279Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
+{"time":"2026-08-12T20:49:00.037439797Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:49:14.928572316Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":2,"events_offset":0,"events_lines":2,"console_offset":1,"console_lines":4,"uploaded_len":2}
+{"time":"2026-08-12T20:49:15.084096643Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:49:29.928576017Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":2,"events_lines":2,"console_offset":2,"console_lines":1}
+{"time":"2026-08-12T20:49:30.057964315Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:49:36.899077971Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2026-08-12T20:49:36.899240331Z","level":"INFO","msg":"filestream: sending request","total_files":2,"console_offset":5,"console_lines":1,"uploaded_len":3,"complete":true,"exit_code":0}
+{"time":"2026-08-12T20:49:37.026514899Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:49:37.028023253Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2026-08-12T20:49:37.031130295Z","level":"INFO","msg":"stream: finishing up"}
+{"time":"2026-08-12T20:49:37.031171186Z","level":"INFO","msg":"handler: closed"}
+{"time":"2026-08-12T20:49:37.031234857Z","level":"INFO","msg":"sender: closed"}
+{"time":"2026-08-12T20:49:37.031238539Z","level":"INFO","msg":"stream: all finished"}

zain/Activation/wandb/run-20260812_204859-c8cw38zl/logs/debug.log

@@ -0,0 +1,28 @@
+2026-08-12 20:48:59,131 INFO    MainThread:3026097 [wandb_setup.py:_flush():81] Current SDK version is 0.28.1
+2026-08-12 20:48:59,131 INFO    MainThread:3026097 [wandb_setup.py:_flush():81] Configure stats pid to 3026097
+2026-08-12 20:48:59,131 INFO    MainThread:3026097 [wandb_setup.py:_flush():81] Loading settings from environment variables
+2026-08-12 20:48:59,131 INFO    MainThread:3026097 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_204859-c8cw38zl/logs/debug.log
+2026-08-12 20:48:59,131 INFO    MainThread:3026097 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_204859-c8cw38zl/logs/debug-internal.log
+2026-08-12 20:48:59,131 INFO    MainThread:3026097 [wandb_init.py:init():772] calling init triggers
+2026-08-12 20:48:59,131 INFO    MainThread:3026097 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
+config: {'_wandb': {}}
+2026-08-12 20:48:59,131 INFO    MainThread:3026097 [wandb_init.py:init():820] starting backend
+2026-08-12 20:48:59,131 INFO    MainThread:3026097 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
+2026-08-12 20:48:59,131 INFO    MainThread:3026097 [wandb_init.py:init():835] sending inform_init request
+2026-08-12 20:48:59,394 INFO    MainThread:3026097 [wandb_init.py:init():840] backend started and connected
+2026-08-12 20:48:59,397 INFO    MainThread:3026097 [wandb_init.py:init():910] updated telemetry
+2026-08-12 20:48:59,404 INFO    MainThread:3026097 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
+2026-08-12 20:48:59,704 INFO    MainThread:3026097 [wandb_init.py:init():978] starting run threads in backend
+2026-08-12 20:48:59,779 INFO    MainThread:3026097 [wandb_run.py:_console_start():2621] atexit reg
+2026-08-12 20:48:59,779 INFO    MainThread:3026097 [wandb_run.py:_redirect():2471] redirect: wrap_raw
+2026-08-12 20:48:59,779 INFO    MainThread:3026097 [wandb_run.py:_redirect():2540] Wrapping output streams.
+2026-08-12 20:48:59,779 INFO    MainThread:3026097 [wandb_run.py:_redirect():2563] Redirects installed.
+2026-08-12 20:48:59,782 INFO    MainThread:3026097 [wandb_init.py:init():1016] run started, returning control to user process
+2026-08-12 20:48:59,783 INFO    MainThread:3026097 [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': 'silu', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-silu-150L_run', 'per_device_train_batch_size': 32, 'num_train_epochs': 1, 'max_steps': 500, 'learning_rate': 0.0007, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 200, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-silu-150L-25.1M-20260812-204858', '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': 100, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/6L-glu-silu-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 20:48:59,789 INFO    MainThread:3026097 [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 0x1501cc0fe0d0>>
+2026-08-12 20:48:59,789 INFO    MainThread:3026097 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 25138816 None
+2026-08-12 20:49:36,490 INFO    MainThread:3026097 [wandb_run.py:_finish():2383] finishing run deepnevro-deepnevro/research2/c8cw38zl
+2026-08-12 20:49:36,490 INFO    MainThread:3026097 [wandb_run.py:_atexit_cleanup():2588] got exitcode: 0
+2026-08-12 20:49:36,490 INFO    MainThread:3026097 [wandb_run.py:_restore():2570] restore
+2026-08-12 20:49:36,491 INFO    MainThread:3026097 [wandb_run.py:_restore():2576] restore done
+2026-08-12 20:49:37,030 INFO    MainThread:3026097 [wandb_run.py:_footer_sync_info():3993] logging synced files

zain/Activation/wandb/run-20260812_204959-ha94g4f6/files/output.log

@@ -0,0 +1,40 @@
+[transformers] `use_return_dict` is deprecated! Use `return_dict` instead!
+[INFO] Causal mask (float with -inf) applied to all attention layers.
+ 20%|██        | 100/500 [01:12<02:13,  2.99it/[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.
+{'loss': '8.234', 'grad_norm': '1.445', 'learning_rate': '6.65e-05', 'epoch': '0.0006741', 'train/total_time_seconds': '6.304', 'train/time_per_step_avg': '0.3152', 'train/epoch_time_elapsed': '6.934', 'train/estimated_remaining_minutes': '2.522'}
+{'loss': '7.9', 'grad_norm': '1.375', 'learning_rate': '0.0001365', 'epoch': '0.001348', 'train/total_time_seconds': '11.97', 'train/time_per_step_avg': '0.2992', 'train/epoch_time_elapsed': '13.11', 'train/estimated_remaining_minutes': '2.294'}
+  - 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
+{'eval_loss': '7.46', 'eval_runtime': '19.27', 'eval_samples_per_second': '494.5', 'eval_steps_per_second': '0.519', 'epoch': '0.001685', 'train/total_time_seconds': '14.8', 'train/time_per_step_avg': '0.296', 'train/epoch_time_elapsed': '35.47', 'train/estimated_remaining_minutes': '2.22'}
+{'loss': '7.467', 'grad_norm': '1.234', 'learning_rate': '0.0002065', 'epoch': '0.002022', 'train/total_time_seconds': '17.76', 'train/time_per_step_avg': '0.296', 'train/epoch_time_elapsed': '38.69', 'train/estimated_remaining_minutes': '2.17'}
+{'loss': '6.894', 'grad_norm': '1.109', 'learning_rate': '0.0002765', 'epoch': '0.002696', 'train/total_time_seconds': '23.96', 'train/time_per_step_avg': '0.2995', 'train/epoch_time_elapsed': '45.41', 'train/estimated_remaining_minutes': '2.097'}
+{'loss': '6.389', 'grad_norm': '0.7578', 'learning_rate': '0.0003465', 'epoch': '0.00337', 'train/total_time_seconds': '30.1', 'train/time_per_step_avg': '0.301', 'train/epoch_time_elapsed': '52.06', 'train/estimated_remaining_minutes': '2.006'}
+{'eval_loss': '6.19', 'eval_runtime': '19.52', 'eval_samples_per_second': '488.1', 'eval_steps_per_second': '0.512', 'epoch': '0.00337', 'train/total_time_seconds': '30.1', 'train/time_per_step_avg': '0.301', 'train/epoch_time_elapsed': '71.58', 'train/estimated_remaining_minutes': '2.006'}
+  - 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,  8.39it/s]
+ 40%|████      | 200/500 [02:23<01:38,  3.04it/[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.
+{'loss': '6.1', 'grad_norm': '0.4141', 'learning_rate': '0.0004165', 'epoch': '0.004044', 'train/total_time_seconds': '36.05', 'train/time_per_step_avg': '0.2974', 'train/epoch_time_elapsed': '78.49', 'train/estimated_remaining_minutes': '1.903'}
+{'loss': '5.899', 'grad_norm': '0.5586', 'learning_rate': '0.0004865', 'epoch': '0.004719', 'train/total_time_seconds': '42', 'train/time_per_step_avg': '0.3004', 'train/epoch_time_elapsed': '84.96', 'train/estimated_remaining_minutes': '1.8'}
+  - 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
+{'eval_loss': '5.708', 'eval_runtime': '19.24', 'eval_samples_per_second': '495.2', 'eval_steps_per_second': '0.52', 'epoch': '0.005056', 'train/total_time_seconds': '45.02', 'train/time_per_step_avg': '0.3022', 'train/epoch_time_elapsed': '107.5', 'train/estimated_remaining_minutes': '1.751'}
+{'loss': '5.742', 'grad_norm': '2.516', 'learning_rate': '0.0005565', 'epoch': '0.005393', 'train/total_time_seconds': '47.99', 'train/time_per_step_avg': '0.3023', 'train/epoch_time_elapsed': '110.7', 'train/estimated_remaining_minutes': '1.7'}
+{'loss': '5.549', 'grad_norm': '1.234', 'learning_rate': '0.0006265', 'epoch': '0.006067', 'train/total_time_seconds': '53.95', 'train/time_per_step_avg': '0.2999', 'train/epoch_time_elapsed': '117.2', 'train/estimated_remaining_minutes': '1.599'}
+{'loss': '5.339', 'grad_norm': '1.367', 'learning_rate': '0.0006965', 'epoch': '0.006741', 'train/total_time_seconds': '59.97', 'train/time_per_step_avg': '0.2988', 'train/epoch_time_elapsed': '123.7', 'train/estimated_remaining_minutes': '1.499'}
+{'eval_loss': '5.231', 'eval_runtime': '19.47', 'eval_samples_per_second': '489.2', 'eval_steps_per_second': '0.514', 'epoch': '0.006741', 'train/total_time_seconds': '59.97', 'train/time_per_step_avg': '0.2988', 'train/epoch_time_elapsed': '143.2', 'train/estimated_remaining_minutes': '1.499'}
+  - 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, 10.74it/s]
+ 60%|██████    | 300/500 [03:36<01:04,  3.09it/[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.
+{'loss': '5.186', 'grad_norm': '1.531', 'learning_rate': '0.0007', 'epoch': '0.007415', 'train/total_time_seconds': '66.45', 'train/time_per_step_avg': '0.304', 'train/epoch_time_elapsed': '150.6', 'train/estimated_remaining_minutes': '1.41'}
+{'loss': '4.989', 'grad_norm': '1.656', 'learning_rate': '0.0007', 'epoch': '0.008089', 'train/total_time_seconds': '72.53', 'train/time_per_step_avg': '0.3052', 'train/epoch_time_elapsed': '157.3', 'train/estimated_remaining_minutes': '1.309'}
+  - 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
+{'eval_loss': '4.977', 'eval_runtime': '19.19', 'eval_samples_per_second': '496.4', 'eval_steps_per_second': '0.521', 'epoch': '0.008426', 'train/total_time_seconds': '75.54', 'train/time_per_step_avg': '0.3052', 'train/epoch_time_elapsed': '179.7', 'train/estimated_remaining_minutes': '1.259'}
+{'loss': '4.933', 'grad_norm': '0.6328', 'learning_rate': '0.0007', 'epoch': '0.008763', 'train/total_time_seconds': '78.52', 'train/time_per_step_avg': '0.3053', 'train/epoch_time_elapsed': '183', 'train/estimated_remaining_minutes': '1.208'}
+{'loss': '4.817', 'grad_norm': '1.578', 'learning_rate': '0.0007', 'epoch': '0.009437', 'train/total_time_seconds': '84.53', 'train/time_per_step_avg': '0.3058', 'train/epoch_time_elapsed': '189.5', 'train/estimated_remaining_minutes': '1.107'}
+{'loss': '4.681', 'grad_norm': '1.844', 'learning_rate': '0.0007', 'epoch': '0.01011', 'train/total_time_seconds': '90.52', 'train/time_per_step_avg': '0.3054', 'train/epoch_time_elapsed': '196', 'train/estimated_remaining_minutes': '1.006'}
+{'eval_loss': '4.653', 'eval_runtime': '19.53', 'eval_samples_per_second': '487.9', 'eval_steps_per_second': '0.512', 'epoch': '0.01011', 'train/total_time_seconds': '90.52', 'train/time_per_step_avg': '0.3054', 'train/epoch_time_elapsed': '215.6', 'train/estimated_remaining_minutes': '1.006'}
+  - 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, 11.18it/s]
+ 65%|██████▌   | 327/500 [03:45<00:56,  3.06it/s]<?, ?it/s]
+{'loss': '4.554', 'grad_norm': '0.9062', 'learning_rate': '0.0007', 'epoch': '0.01079', 'train/total_time_seconds': '96.54', 'train/time_per_step_avg': '0.3009', 'train/epoch_time_elapsed': '222.5', 'train/estimated_remaining_minutes': '0.905'}

zain/Activation/wandb/run-20260812_204959-ha94g4f6/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_204959-ha94g4f6/files/wandb-metadata.json

@@ -0,0 +1,105 @@
+{
+  "os":  "Linux-5.15.0-126-generic-x86_64-with-glibc2.35",
+  "python":  "CPython 3.11.15",
+  "startedAt":  "2026-08-12T20:49:59.228474Z",
+  "args":  [
+    "--config",
+    "/mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/configs/baseline150L.yaml",
+    "--variants",
+    "glu-silu",
+    "glu-waleed10",
+    "glu-silu-waleed10",
+    "glu-situglu",
+    "glu-waleed",
+    "glu-situglu_low",
+    "glu-waleedglu_low",
+    "glu-relu",
+    "glu-gelu",
+    "glu-sigmoid",
+    "glu-linear"
+  ],
+  "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":  "26a43c7dee7982e610a25ac78443de9ce18f5077"
+  },
+  "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":  "716361342976"
+    }
+  },
+  "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":  "lhw9mxbb1se2iuh21qp40amrmz3558h6"
+}

zain/Activation/wandb/run-20260812_204959-ha94g4f6/logs/debug-core.log

@@ -0,0 +1,20 @@
+{"time":"2026-08-12T20:46:29.826542919Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpfq15lqwq/port-2980938.txt","pid":2980938,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2026-08-12T20:46:29.827630129Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":2980938}
+{"time":"2026-08-12T20:46:29.827605008Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-2980938-3003971-36328316/socket","Net":"unix"}}
+{"time":"2026-08-12T20:46:30.00400148Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2026-08-12T20:48:59.03423153Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"2(@)"}
+{"time":"2026-08-12T20:48:59.133025837Z","level":"INFO","msg":"handleInformInit: received","streamId":"c8cw38zl","id":"2(@)"}
+{"time":"2026-08-12T20:48:59.393728981Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"c8cw38zl","id":"2(@)"}
+{"time":"2026-08-12T20:49:04.781949197Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"t81j1d8lh5hv"}
+{"time":"2026-08-12T20:49:36.491139113Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"t81j1d8lh5hv"}
+{"time":"2026-08-12T20:49:37.029432845Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"t81j1d8lh5hv"}
+{"time":"2026-08-12T20:49:37.031098016Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"c8cw38zl","id":"2(@)"}
+{"time":"2026-08-12T20:49:37.032166543Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"c8cw38zl","id":"2(@)"}
+{"time":"2026-08-12T20:49:38.248051669Z","level":"INFO","msg":"connection: closing","id":"2(@)"}
+{"time":"2026-08-12T20:49:38.248082215Z","level":"INFO","msg":"processOutgoingData: finished","id":"2(@)"}
+{"time":"2026-08-12T20:49:38.248121683Z","level":"INFO","msg":"connection: closed successfully","id":"2(@)"}
+{"time":"2026-08-12T20:49:38.248148742Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"2(@)"}
+{"time":"2026-08-12T20:49:59.123664108Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"3(@)"}
+{"time":"2026-08-12T20:49:59.231166569Z","level":"INFO","msg":"handleInformInit: received","streamId":"ha94g4f6","id":"3(@)"}
+{"time":"2026-08-12T20:49:59.490273575Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"ha94g4f6","id":"3(@)"}
+{"time":"2026-08-12T20:50:04.834347925Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"k2vr6fkcyr5w"}

zain/Activation/wandb/run-20260812_204959-ha94g4f6/logs/debug-internal.log

@@ -0,0 +1,39 @@
+{"time":"2026-08-12T20:49:59.231329238Z","level":"INFO","msg":"wandb-core"}
+{"time":"2026-08-12T20:49:59.231458005Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
+{"time":"2026-08-12T20:49:59.4901037Z","level":"INFO","msg":"stream: created new stream","id":"ha94g4f6"}
+{"time":"2026-08-12T20:49:59.490189081Z","level":"INFO","msg":"handler: started"}
+{"time":"2026-08-12T20:49:59.490265922Z","level":"INFO","msg":"stream: started"}
+{"time":"2026-08-12T20:49:59.490276077Z","level":"INFO","msg":"writer: started","stream_id":"ha94g4f6"}
+{"time":"2026-08-12T20:49:59.49030619Z","level":"INFO","msg":"sender: started"}
+{"time":"2026-08-12T20:49:59.978334344Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
+{"time":"2026-08-12T20:50:00.112397512Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:50:14.978575235Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":2,"events_offset":0,"events_lines":2,"console_offset":1,"console_lines":4,"uploaded_len":2}
+{"time":"2026-08-12T20:50:15.141418893Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:50:29.978639147Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":2,"events_lines":2,"console_offset":2,"console_lines":1}
+{"time":"2026-08-12T20:50:30.112487958Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:50:44.979520057Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":2,"history_lines":2,"events_offset":4,"events_lines":2,"console_offset":2,"console_lines":1}
+{"time":"2026-08-12T20:50:45.106709081Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:50:59.978634412Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":4,"history_lines":2,"events_offset":6,"events_lines":1,"console_offset":2,"console_lines":1}
+{"time":"2026-08-12T20:51:00.176400181Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:51:14.978675737Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":6,"history_lines":1,"events_offset":7,"events_lines":3,"console_offset":2,"console_lines":1}
+{"time":"2026-08-12T20:51:15.136480688Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:51:29.978816851Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":7,"history_lines":2,"events_offset":10,"events_lines":2,"console_offset":5,"console_lines":12}
+{"time":"2026-08-12T20:51:30.144315427Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:51:44.978880235Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":12,"events_lines":2,"console_offset":17,"console_lines":1}
+{"time":"2026-08-12T20:51:45.106187785Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:51:59.9795397Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":9,"history_lines":3,"events_offset":14,"events_lines":2,"console_offset":14,"console_lines":1}
+{"time":"2026-08-12T20:52:00.115108282Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:52:14.978616189Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":12,"history_lines":1,"events_offset":16,"events_lines":2,"console_offset":14,"console_lines":1}
+{"time":"2026-08-12T20:52:15.144083803Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:52:29.979233536Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":13,"history_lines":1,"events_offset":18,"events_lines":2,"console_offset":14,"console_lines":1}
+{"time":"2026-08-12T20:52:30.115302332Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:52:44.979378867Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":14,"history_lines":2,"events_offset":20,"events_lines":2,"console_offset":17,"console_lines":13}
+{"time":"2026-08-12T20:52:45.104669417Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:52:59.97898149Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":16,"history_lines":1,"events_offset":22,"events_lines":2,"console_offset":26,"console_lines":1}
+{"time":"2026-08-12T20:53:00.121062111Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:53:14.979322756Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":17,"history_lines":2,"events_offset":24,"events_lines":2,"console_offset":26,"console_lines":1}
+{"time":"2026-08-12T20:53:15.120861918Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:53:29.979219904Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":19,"history_lines":1,"events_offset":26,"events_lines":2,"console_offset":26,"console_lines":1}
+{"time":"2026-08-12T20:53:30.146291299Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T20:53:44.979549283Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":20,"history_lines":2,"events_offset":28,"events_lines":2,"console_offset":26,"console_lines":1}
+{"time":"2026-08-12T20:53:45.134028333Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}

zain/Activation/wandb/run-20260812_204959-ha94g4f6/logs/debug.log

@@ -0,0 +1,23 @@
+2026-08-12 20:49:59,229 INFO    MainThread:3035682 [wandb_setup.py:_flush():81] Current SDK version is 0.28.1
+2026-08-12 20:49:59,229 INFO    MainThread:3035682 [wandb_setup.py:_flush():81] Configure stats pid to 3035682
+2026-08-12 20:49:59,229 INFO    MainThread:3035682 [wandb_setup.py:_flush():81] Loading settings from environment variables
+2026-08-12 20:49:59,229 INFO    MainThread:3035682 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_204959-ha94g4f6/logs/debug.log
+2026-08-12 20:49:59,229 INFO    MainThread:3035682 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_204959-ha94g4f6/logs/debug-internal.log
+2026-08-12 20:49:59,229 INFO    MainThread:3035682 [wandb_init.py:init():772] calling init triggers
+2026-08-12 20:49:59,230 INFO    MainThread:3035682 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
+config: {'_wandb': {}}
+2026-08-12 20:49:59,230 INFO    MainThread:3035682 [wandb_init.py:init():820] starting backend
+2026-08-12 20:49:59,230 INFO    MainThread:3035682 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
+2026-08-12 20:49:59,230 INFO    MainThread:3035682 [wandb_init.py:init():835] sending inform_init request
+2026-08-12 20:49:59,490 INFO    MainThread:3035682 [wandb_init.py:init():840] backend started and connected
+2026-08-12 20:49:59,494 INFO    MainThread:3035682 [wandb_init.py:init():910] updated telemetry
+2026-08-12 20:49:59,501 INFO    MainThread:3035682 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
+2026-08-12 20:49:59,756 INFO    MainThread:3035682 [wandb_init.py:init():978] starting run threads in backend
+2026-08-12 20:49:59,831 INFO    MainThread:3035682 [wandb_run.py:_console_start():2621] atexit reg
+2026-08-12 20:49:59,832 INFO    MainThread:3035682 [wandb_run.py:_redirect():2471] redirect: wrap_raw
+2026-08-12 20:49:59,832 INFO    MainThread:3035682 [wandb_run.py:_redirect():2540] Wrapping output streams.
+2026-08-12 20:49:59,832 INFO    MainThread:3035682 [wandb_run.py:_redirect():2563] Redirects installed.
+2026-08-12 20:49:59,835 INFO    MainThread:3035682 [wandb_init.py:init():1016] run started, returning control to user process
+2026-08-12 20:49:59,835 INFO    MainThread:3035682 [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': 'silu', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-silu-150L_run', 'per_device_train_batch_size': 32, 'num_train_epochs': 1, 'max_steps': 500, 'learning_rate': 0.0007, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 200, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-silu-150L-25.1M-20260812-204958', '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': 1024, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 100, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/6L-glu-silu-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 20:49:59,841 INFO    MainThread:3035682 [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 0x152f60578810>>
+2026-08-12 20:49:59,841 INFO    MainThread:3035682 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 25138816 None

zain/Activation/wandb/run-20260812_204959-ha94g4f6/run-ha94g4f6.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a583120c2a9016c4de971abd8734131c5499266894e348d5c3cbceb78d04219
+size 196608