Training in progress, epoch 1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
+  "base_model_name_or_path": "Qwen/Qwen2-7B-Instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -11,19 +11,19 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
-  "lora_dropout": 0.3,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "k_proj",
     "q_proj",
-    "o_proj",
-    "v_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df15b611e7e64a99c4de4ce6013fc7c74556a6da6463b4fa3dac25756b3e0c84
-size 8676008
+oid sha256:42ea4001db909978958e3a00d3adc67d1e67db4dbfdeccfa207638a8a6475e0e
+size 161510984

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 256,
+    "max_length": 4096,
     "strategy": "LongestFirst",
     "stride": 0
   },

tokenizer_config.json

@@ -35,7 +35,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "model_max_length": 32768,
+  "model_max_length": 131072,
   "pad_token": "<|im_end|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18dcabf791b4cb3f0ad098a7aa11d08ffae4dce95bc8aef016dff302eb884c49
-size 5304
+oid sha256:422acc4b060de7d492f8119a8fb6858c4c46d29016e6f7a9f641f036bcc921db
+size 5368