Training in progress, epoch 0

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./Qwen2-0.5B-Instruct-SQL-generator",
+  "_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -12,7 +12,7 @@
   "intermediate_size": 4864,
   "max_position_embeddings": 32768,
   "max_window_layers": 24,
-  "model_type": "text-to-sql",
+  "model_type": "qwen2",
   "num_attention_heads": 14,
   "num_hidden_layers": 24,
   "num_key_value_heads": 2,
@@ -25,6 +25,5 @@
   "transformers_version": "4.46.3",
   "use_cache": true,
   "use_sliding_window": false,
-  "vocab_size": 151936,
-  "task": "text-generation"
-}
+  "vocab_size": 151936
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc6209e82b73f37c285d8796948d88fdeb793dd0fed71d739764072f6bcd17f9
+size 1976163472

runs/Apr12_16-16-36_lrz-hgx-h100-008/events.out.tfevents.1744467411.lrz-hgx-h100-008.91812.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce91e883119f3e1402db5fbad1aed9f72ea813cf2e99d8a06810fdb9ef78d848
+size 5476

runs/Apr12_16-21-32_lrz-hgx-h100-008/events.out.tfevents.1744467696.lrz-hgx-h100-008.125402.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b72ee358a2c4fc10f4f9d65c29dc42c0d1fc5124140d01dc8db624e448e1f6e
+size 5474

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
-size 11418266
+oid sha256:e49bebc2336dd0896ee055aa24e6bb65d80539b16751bb9798d6829db3ac4ea3
+size 11418365

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b520059249ff9ed617c65dca278c8e893cc523ec75ab428f1cadb97bff63a3
+size 5624