Training in progress, step 3

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1809e7cc2138e2e55d22ac1e96c24282fc7575e140ef40b9a19d3ac2a97451e0
+size 988097824

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb8724d29832b539122765619f4b5995ceff067c6718e7b3b92a69d1002f2035
+oid sha256:98f3e35eb736b80c3ad47c156689398ea28ccfbfd2363de6c60afd89e5e290c9
 size 5496