Training in progress, step 31

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7283b98c743f1b0ba9a719cd1ce8e1c363851b8bf7b7b1a5f7476a507fa80711
+oid sha256:c921115a651f8ecdf1219cfde754cc4c2703587852746af51d695c577305067e
 size 80792456

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "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 sha256:06ac1b3ce51973f24197f88ba28a2b2dfe800461b531bdfe5c1b23066116d0f1
+size 2384234968

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0896d5e9f2f47338a1acae78d5fc02f6f0528b622a3c60e6ecc62b8e0122346c
+oid sha256:3fa4116eeb484f39ba5a81c1337ea2777bf84e9e5cc924100899e492667b1baa
 size 6609