Training in progress, step 100

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "ModernLLMForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_modern_llm.ModernLLMConfig",
+    "AutoModelForCausalLM": "modeling_modern_llm.ModernLLMForCausalLM"
+  },
+  "bos_token_id": 151643,
+  "dtype": "float32",
+  "eos_token_id": 151643,
+  "hidden_size": 768,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 2048,
+  "model_type": "modern_llm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "transformers_version": "5.16.1",
+  "use_cache": false,
+  "vocab_size": 151936
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:430eb8774ac7076b8fb0f635c836cc19b9c14bc3c222ea191c7c7b8587d4205e
+size 1235573136

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21db9453d7d8ac6bfa4936e13632c57e87862815455df5498192c2b63e078d30
+size 5201