Training in progress, step 15

README.md

@@ -4,9 +4,9 @@ library_name: transformers
 model_name: demo-sft-model
 tags:
 - generated_from_trainer
-- trl
-- sft
 - hf_jobs
+- sft
+- trl
 licence: license
 ---
 

adapter_config.json

@@ -1,6 +1,9 @@
 {
   "alpha_pattern": {},
-  "auto_mapping": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2"
+  },
   "base_model_name_or_path": "Qwen/Qwen2.5-0.5B",
   "bias": "none",
   "corda_config": null,
@@ -15,7 +18,7 @@
   "loftq_config": {},
   "lora_alpha": 32,
   "lora_bias": false,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -25,13 +28,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "q_proj",
     "k_proj",
-    "v_proj"
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj"
   ],
   "target_parameters": null,
-  "task_type": "CAUSAL_LM",
+  "task_type": null,
   "trainable_token_indices": null,
   "use_dora": false,
   "use_qalora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee174a940ceabb73302d4a05b517b5e480c863834a3092af4cd5d5e2d971584e
-size 8676008
+oid sha256:301c0bce367650466eb6e57557befeb8917d6da7342fdf63328836dca55beef0
+size 35237104

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d08a814626e83aa8a488bd2b3a6181d97f25c294d1e3d6b2691b382759e0aa75
+oid sha256:e46454bfd9a6ebc1c42ffa624b97baa567feb3bacd09d3f186e862ead85ec9e7
 size 6289