Auto upload zain 2026-08-14T20:53:52.460056 (part 2)

zain/Activation/out/glu-waleed-9L_run/checkpoint-100/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "waleed",
+  "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": 9,
+  "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-waleed-9L_run/checkpoint-100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eac72fa8cfdc95c3d7f36484c77e3f200d92928821de2b53cf1eefb6b78cc04
+size 4011496

zain/Activation/out/glu-waleed-9L_run/checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e19e2f3d58517afc374d39494ce93843828c818777a3054f583e9f87552915f
+size 8074746

zain/Activation/out/glu-waleed-9L_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-waleed-9L_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-waleed-9L_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-waleed-9L_run/checkpoint-100/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.05390835579514825,
+  "eval_steps": 60000,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01078167115902965,
+      "grad_norm": 0.9765625,
+      "learning_rate": 0.001,
+      "loss": 7.1419013977050785,
+      "step": 20
+    },
+    {
+      "epoch": 0.0215633423180593,
+      "grad_norm": 0.59375,
+      "learning_rate": 0.001,
+      "loss": 5.897165298461914,
+      "step": 40
+    },
+    {
+      "epoch": 0.03234501347708895,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.001,
+      "loss": 5.307088088989258,
+      "step": 60
+    },
+    {
+      "epoch": 0.0431266846361186,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.001,
+      "loss": 4.752142333984375,
+      "step": 80
+    },
+    {
+      "epoch": 0.05390835579514825,
+      "grad_norm": 0.357421875,
+      "learning_rate": 0.001,
+      "loss": 4.355420684814453,
+      "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": 232310754508800.0,
+  "train_batch_size": 512,
+  "trial_name": null,
+  "trial_params": null
+}

zain/Activation/out/glu-waleed-9L_run/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87bce8ade72476666206bb73e6353f17ce4c3746e58ce58ffd65d562b25eb55d
+size 4920

zain/Activation/out/glu-waleed-9L_run/training_log.jsonl

@@ -0,0 +1,10 @@
+{"step": 20, "epoch": 0.01078167115902965, "timestamp": 1786740710.299719, "loss": 7.1419013977050785, "grad_norm": 0.9765625, "learning_rate": 0.001, "train/total_time_seconds": 6.529780384153128, "train/time_per_step_avg": 0.3264890192076564, "train/epoch_time_elapsed": 14.558187425136566, "train/estimated_remaining_minutes": 5.332653980391721}
+{"step": 40, "epoch": 0.0215633423180593, "timestamp": 1786740724.3288724, "loss": 5.897165298461914, "grad_norm": 0.59375, "learning_rate": 0.001, "train/total_time_seconds": 13.063349019736052, "train/time_per_step_avg": 0.3265837254934013, "train/epoch_time_elapsed": 28.587341722100973, "train/estimated_remaining_minutes": 5.225339607894421}
+{"step": 60, "epoch": 0.03234501347708895, "timestamp": 1786740738.2896268, "loss": 5.307088088989258, "grad_norm": 0.55859375, "learning_rate": 0.001, "train/total_time_seconds": 19.519845563918352, "train/time_per_step_avg": 0.3253307593986392, "train/epoch_time_elapsed": 42.54809567332268, "train/estimated_remaining_minutes": 5.0968485639120145}
+{"step": 80, "epoch": 0.0431266846361186, "timestamp": 1786740752.4787056, "loss": 4.752142333984375, "grad_norm": 0.54296875, "learning_rate": 0.001, "train/total_time_seconds": 26.229080442339182, "train/time_per_step_avg": 0.32786350552923976, "train/epoch_time_elapsed": 56.73717471957207, "train/estimated_remaining_minutes": 5.02724041811501}
+{"step": 100, "epoch": 0.05390835579514825, "timestamp": 1786740766.493271, "loss": 4.355420684814453, "grad_norm": 0.357421875, "learning_rate": 0.001, "train/total_time_seconds": 32.80325895175338, "train/time_per_step_avg": 0.3280325895175338, "train/epoch_time_elapsed": 70.75174043700099, "train/estimated_remaining_minutes": 4.920488842763007}
+{"step": 120, "epoch": 0.0646900269541779, "timestamp": 1786740781.149797, "loss": 4.1065021514892575, "grad_norm": 1.5, "learning_rate": 0.001, "train/total_time_seconds": 39.68944124504924, "train/time_per_step_avg": 0.3315966086089611, "train/epoch_time_elapsed": 85.40826620161533, "train/estimated_remaining_minutes": 4.85093170772824}
+{"step": 140, "epoch": 0.07547169811320754, "timestamp": 1786740795.2345626, "loss": 3.8953704833984375, "grad_norm": 0.85546875, "learning_rate": 0.001, "train/total_time_seconds": 46.17903455346823, "train/time_per_step_avg": 0.33115685533732175, "train/epoch_time_elapsed": 99.49303134158254, "train/estimated_remaining_minutes": 4.727853537616985}
+{"step": 160, "epoch": 0.0862533692722372, "timestamp": 1786740809.5376456, "loss": 3.7184146881103515, "grad_norm": 0.490234375, "learning_rate": 0.001, "train/total_time_seconds": 52.95672606676817, "train/time_per_step_avg": 0.3343688050284982, "train/epoch_time_elapsed": 113.79611469060183, "train/estimated_remaining_minutes": 4.633713530842215}
+{"step": 180, "epoch": 0.09703504043126684, "timestamp": 1786740823.3313231, "loss": 3.5632476806640625, "grad_norm": 0.59765625, "learning_rate": 0.001, "train/total_time_seconds": 59.206629388034344, "train/time_per_step_avg": 0.3297754894569516, "train/epoch_time_elapsed": 127.58979272097349, "train/estimated_remaining_minutes": 4.495318157239644}
+{"step": 200, "epoch": 0.1078167115902965, "timestamp": 1786740836.8899324, "loss": 3.4323970794677736, "grad_norm": 0.84375, "learning_rate": 0.001, "train/total_time_seconds": 65.02674689516425, "train/time_per_step_avg": 0.3222348794341087, "train/epoch_time_elapsed": 141.1484008654952, "train/estimated_remaining_minutes": 4.335116459677617}