step 20 | val_ppl=inf

README.md

@@ -0,0 +1,40 @@
+---
+language: en
+tags:
+- causal-lm
+- gqa
+- rope
+- swiglu
+license: apache-2.0
+---
+
+# Experimenting
+
+Small language model (9.9M parameters) trained from scratch.
+
+## Architecture
+| Property | Value |
+|---|---|
+| Layers | 12 |
+| Hidden size | 256 |
+| Intermediate size | 704 |
+| Attention heads | 4 (GQA kv=2) |
+| Max sequence length | 1024 |
+| Vocab size | 4096 |
+| Tied embeddings | True |
+| Total parameters | 9.902M |
+
+## Training
+- Tokens seen: 47,139,840
+- Val loss: inf
+- Val PPL: inf
+
+## Usage
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("GODELEV/Experimenting")
+model = AutoModelForCausalLM.from_pretrained("GODELEV/Experimenting")
+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": 64,
+  "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": 4,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 4096
+}

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 sha256:8c254648c7f19f421b85438a070d6b1380143a7f24bd99aae4a1d9fc532a810e
+size 39621248

resume/ckpt.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:148ef93e3b1e298e2472e9611f5f9aa7ad165246c16ff41acd0535d60da1609a
+size 122094365

resume/latest_step.txt

@@ -0,0 +1 @@
+20

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|bos|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|eos|>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<|mask|>",
+  "model_max_length": 4096,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|unk|>"
+}

training_meta.json

@@ -0,0 +1,8 @@
+{
+  "step": 20,
+  "val_loss": Infinity,
+  "val_ppl": Infinity,
+  "params_M": 9.902,
+  "pushed_at": "2026-06-11T05:51:45.236788",
+  "tokens_seen": 47139840
+}