Training in progress, epoch 0

adapter_config.json

@@ -16,13 +16,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "q_proj",
     "v_proj",
+    "k_proj",
+    "o_proj",
     "gate_proj",
     "down_proj",
-    "q_proj",
-    "up_proj",
-    "k_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0945457e16bc7d2d7d46d1b24f25049dda38761361d73beaee81c121203266cd
+oid sha256:89528fd6b144f76692ca40593f16e62a222fbcb02ddff905d85be7aa1b0ba62f
 size 500897101

config.json

@@ -34,7 +34,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.34.0.dev0",
+  "transformers_version": "4.35.0.dev0",
   "use_cache": false,
   "vocab_size": 32001
 }

tokenizer_config.json

@@ -4,25 +4,25 @@
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
       "content": "<s>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
     "2": {
       "content": "</s>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27419c3831cc26176ad9b5c3a3b530477238b8eedb7352fe2ef6e416bedf832c
+oid sha256:adde5ff0b9adefe6a47ac022b63675afdf9cc9d534fa59b88c21b15abd573a3c
 size 4475