Training in progress, step 25

adapter_config.json

@@ -10,7 +10,7 @@
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
-  "inference_mode": true,
+  "inference_mode": false,
   "init_lora_weights": "gaussian",
   "layer_replication": null,
   "layers_pattern": null,
@@ -28,13 +28,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
     "gate_proj",
-    "k_proj",
-    "up_proj",
     "q_proj",
+    "v_proj",
+    "up_proj",
     "o_proj",
-    "down_proj",
-    "v_proj"
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a280ee08bf72045ab70d224011fc1b3fc6859690c7eba4c4d3816b35627c0ed
+oid sha256:5ff9019bcee40de45bd3170d33b4ab1180c01becfe1a6874571c2969c70bafb3
 size 12377496

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    49279,
+    49279
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.57.1"
+}

tokenizer.json

@@ -1,14 +1,7 @@
 {
   "version": "1.0",
   "truncation": null,
-  "padding": {
-    "strategy": "BatchLongest",
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 2,
-    "pad_type_id": 0,
-    "pad_token": "<|im_end|>"
-  },
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e02fa990081b94dcaa407b1eeacfb9e050d2858ea91ee23e9d6d7e692969d5b2
+oid sha256:06577f0734a1bc39bdd22d423302dc0b1125d39053e9b4041438b7ca7725f434
 size 5944