step 400 | val_ppl=32.14

README.md

@@ -0,0 +1,40 @@
+---
+language: en
+tags:
+- causal-lm
+- gqa
+- rope
+- swiglu
+license: apache-2.0
+---
+
+# Exp-1
+
+Small language model (9.9M parameters) trained from scratch.
+
+## Architecture
+| Property | Value |
+|---|---|
+| Layers | 11 |
+| Hidden size | 256 |
+| Intermediate size | 704 |
+| Attention heads | 8 (GQA kv=2) |
+| Max sequence length | 1024 |
+| Vocab size | 8192 |
+| Tied embeddings | True |
+| Total parameters | 9.853M |
+
+## Training
+- Tokens seen: 419,020,800
+- Val loss: 3.4701
+- Val PPL: 32.14
+
+## Usage
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("GODELEV/Exp-1")
+model = AutoModelForCausalLM.from_pretrained("GODELEV/Exp-1")
+inputs = tokenizer("Hello", return_tensors="pt")
+output = model.generate(**inputs, max_new_tokens=50)
+print(tokenizer.decode(output[0], skip_special_tokens=True))
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 704,
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 11,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 50000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 8192
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "bos_token_id": 2,
+  "eos_token_id": 3
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b687f62f3f58daccffe6c0697badab591a4ecb542386537822f220a8ceefab5a
+size 39421616

resume/ckpt.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20e45cc79bac0b46a1db8188779d2ca1528781617101b6cbde5cf6d1f4fba09a
+size 119811943

resume/latest_step.txt

@@ -0,0 +1 @@
+400

tokenizer_config.json

@@ -0,0 +1,27 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|bos|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|eos|>",
+  "extra_special_tokens": [
+    "<|unk_text|>",
+    "<|sot|>",
+    "<|eot|>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|math|>",
+    "<|expr|>",
+    "<|answer|>",
+    "<|code|>",
+    "<|think|>",
+    "<|end_of_think|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<|mask|>",
+  "model_max_length": 8192,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|unk|>"
+}

training_meta.json

@@ -0,0 +1,8 @@
+{
+  "step": 400,
+  "val_loss": 3.4701391414642333,
+  "val_ppl": 32.14121430925628,
+  "params_M": 9.853,
+  "pushed_at": "2026-06-17T09:38:56.823655",
+  "tokens_seen": 419020800
+}