Training in progress, epoch 0

adapter_config.json

@@ -8,7 +8,7 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "lora_alpha": 64,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "modules_to_save": null,
   "peft_type": "LORA",
@@ -16,14 +16,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj",
+    "gate_proj",
     "down_proj",
     "o_proj",
+    "lm_head",
+    "q_proj",
     "up_proj",
-    "v_proj",
-    "gate_proj",
-    "lm_head"
+    "k_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e67917e1cdd2b4a7f45536d2658c5cacdb802487ad3e26d89ed65ace4a542b65
+size 340327122

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b6a9a954f9bc591666f5989742125a871da8bb18a85536f2d697cab29681dd2
+oid sha256:aba9f81229b1a49bda3b709b6094fe82b65535814a967af23ea376fa906a2e37
 size 340225224

runs/Nov23_19-48-32_3c25d1b99ca3/events.out.tfevents.1700769027.3c25d1b99ca3.30755.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51344e6cd4abe2c9998ace26e349ea2a389fc68de11b99d69e92dbf2879cdbb1
+size 6873

special_tokens_map.json

@@ -13,7 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
+  "pad_token": "<unk>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -34,7 +34,7 @@
   "eos_token": "</s>",
   "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
+  "pad_token": "<unk>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9324d85ea97af71809e3d932082f96e3a4729f1c8bc6c7bfbe60944fe1d19003
+oid sha256:3b5400430031dd89c535c0b5c030a7e75d7ee21e6cc352fa45e0aaa09005f605
 size 4664