step 20 | val_ppl=inf

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": 768,
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "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": 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 +1,5 @@
+{
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "max_length": 1024
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c040e035fd82930a1751fc28ea40bacc318558aa14de35e483ebc74dfaf605a
+size 38831784

resume/ckpt.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae84dbd5823617e94e37bf899b4802136d0acfb287153d1ca325164f3749f26c
+size 119457051

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": 9.705,
+  "pushed_at": "2026-06-10T18:53:38.859252",
+  "tokens_seen": 20951040
+}