Auto upload zain 2026-08-14T21:35:16.328459 (part 3)

zain/Activation/out/glu-waleed10-21L_run/checkpoint-100/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "waleed10",
+  "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": 21,
+  "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-waleed10-21L_run/checkpoint-100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23ab1b31bcb11397bd80ec3e4e5c6abdb0fc687c21b77afea19332b3f8f7da8d
+size 7961528

zain/Activation/out/glu-waleed10-21L_run/checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a620acef2e0005500c7c1363f29d54ff2e5807a4052b91201178ea0703ab5199
+size 16041274

zain/Activation/out/glu-waleed10-21L_run/checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

zain/Activation/out/glu-waleed10-21L_run/checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:906745ab5f61e73e8c1ba850ef3b839e2766eba889b49c843836266988895165
+size 1064

zain/Activation/out/glu-waleed10-21L_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-waleed10-21L_run/checkpoint-100/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.05392289026691831,
+  "eval_steps": 60000,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010784578053383662,
+      "grad_norm": 4.0,
+      "learning_rate": 0.001,
+      "loss": 28.876385498046876,
+      "step": 20
+    },
+    {
+      "epoch": 0.021569156106767323,
+      "grad_norm": 1.3984375,
+      "learning_rate": 0.001,
+      "loss": 24.010443115234374,
+      "step": 40
+    },
+    {
+      "epoch": 0.032353734160150985,
+      "grad_norm": 1.453125,
+      "learning_rate": 0.001,
+      "loss": 22.35637664794922,
+      "step": 60
+    },
+    {
+      "epoch": 0.043138312213534646,
+      "grad_norm": 3.34375,
+      "learning_rate": 0.001,
+      "loss": 20.596783447265626,
+      "step": 80
+    },
+    {
+      "epoch": 0.05392289026691831,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.001,
+      "loss": 18.65278015136719,
+      "step": 100
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 1000,
+  "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": 542031583641600.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

zain/Activation/out/glu-waleed10-21L_run/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a5fb74d92c2a824150af3ee3051d6e747acb606e30ff7dc799c234f6c87bd3
+size 4920

zain/Activation/out/glu-waleed10-21L_run/training_log.jsonl

@@ -0,0 +1,10 @@
+{"step": 20, "epoch": 0.010784578053383662, "timestamp": 1786743136.1027415, "loss": 28.876385498046876, "grad_norm": 4.0, "learning_rate": 0.001, "train/total_time_seconds": 13.991009909659624, "train/time_per_step_avg": 0.6995504954829812, "train/epoch_time_elapsed": 21.68653191253543, "train/estimated_remaining_minutes": 11.425991426222026}
+{"step": 40, "epoch": 0.021569156106767323, "timestamp": 1786743157.294506, "loss": 24.010443115234374, "grad_norm": 1.3984375, "learning_rate": 0.001, "train/total_time_seconds": 27.58999863639474, "train/time_per_step_avg": 0.6897499659098685, "train/epoch_time_elapsed": 42.87829800695181, "train/estimated_remaining_minutes": 11.035999454557896}
+{"step": 60, "epoch": 0.032353734160150985, "timestamp": 1786743178.5719721, "loss": 22.35637664794922, "grad_norm": 1.453125, "learning_rate": 0.001, "train/total_time_seconds": 41.22402549535036, "train/time_per_step_avg": 0.6870670915891727, "train/epoch_time_elapsed": 64.1557636745274, "train/estimated_remaining_minutes": 10.764051101563705}
+{"step": 80, "epoch": 0.043138312213534646, "timestamp": 1786743199.783026, "loss": 20.596783447265626, "grad_norm": 3.34375, "learning_rate": 0.001, "train/total_time_seconds": 54.91238158941269, "train/time_per_step_avg": 0.6864047698676586, "train/epoch_time_elapsed": 85.36681762337685, "train/estimated_remaining_minutes": 10.524873137970765}
+{"step": 100, "epoch": 0.05392289026691831, "timestamp": 1786743220.9183896, "loss": 18.65278015136719, "grad_norm": 1.9140625, "learning_rate": 0.001, "train/total_time_seconds": 68.49352874606848, "train/time_per_step_avg": 0.6849352874606848, "train/epoch_time_elapsed": 106.50218157470226, "train/estimated_remaining_minutes": 10.274029311910272}
+{"step": 120, "epoch": 0.06470746832030197, "timestamp": 1786743242.2572048, "loss": 17.364892578125, "grad_norm": 3.109375, "learning_rate": 0.001, "train/total_time_seconds": 82.1613814868033, "train/time_per_step_avg": 0.6817037157714367, "train/epoch_time_elapsed": 127.84099610894918, "train/estimated_remaining_minutes": 10.041946626164847}
+{"step": 140, "epoch": 0.07549204637368563, "timestamp": 1786743263.472586, "loss": 16.395790100097656, "grad_norm": 1.6015625, "learning_rate": 0.001, "train/total_time_seconds": 95.80696863308549, "train/time_per_step_avg": 0.6821696999669075, "train/epoch_time_elapsed": 149.05637842416763, "train/estimated_remaining_minutes": 9.808808693387324}
+{"step": 160, "epoch": 0.08627662442706929, "timestamp": 1786743283.5837717, "loss": 15.567823791503907, "grad_norm": 1.5234375, "learning_rate": 0.001, "train/total_time_seconds": 108.37814669311047, "train/time_per_step_avg": 0.6715412119776011, "train/epoch_time_elapsed": 169.16756326332688, "train/estimated_remaining_minutes": 9.483087835647165}
+{"step": 180, "epoch": 0.09706120248045295, "timestamp": 1786743303.724438, "loss": 14.909393310546875, "grad_norm": 1.703125, "learning_rate": 0.001, "train/total_time_seconds": 120.95274137333035, "train/time_per_step_avg": 0.6604035978391767, "train/epoch_time_elapsed": 189.30822933092713, "train/estimated_remaining_minutes": 9.183448882049158}
+{"step": 200, "epoch": 0.10784578053383662, "timestamp": 1786743319.5532258, "loss": 14.338616943359375, "grad_norm": 2.4375, "learning_rate": 0.001, "train/total_time_seconds": 129.02139946818352, "train/time_per_step_avg": 0.6052787072211504, "train/epoch_time_elapsed": 205.13701867312193, "train/estimated_remaining_minutes": 8.601426631212234}