Training in progress, epoch 1

adapter_config.json

@@ -21,7 +21,10 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "v_proj"
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:094a9f72ea61eb1f2062873c22d53bfa2426f10fcdad6f9dc3234ac3ebd76a18
-size 27280152
+oid sha256:d13cb9f4a0ec2a88a34f262c30263706a54a2d3da18e4aea32fbd511cdcc2ff3
+size 92317600

runs/May28_11-21-19_e6addf98c5a3/events.out.tfevents.1716895393.e6addf98c5a3.572.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:134ae7e104129c5ad9a1f454b75c7e765e067b782ccdbfe4944f53e6f78ada28
+size 4184

special_tokens_map.json

@@ -1,9 +1,4 @@
 {
-  "additional_special_tokens": [
-    "<unk>",
-    "<s>",
-    "</s>"
-  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,

tokenizer.json

@@ -1,7 +1,7 @@
 {
   "version": "1.0",
   "truncation": {
-    "direction": "Left",
+    "direction": "Right",
     "max_length": 1024,
     "strategy": "LongestFirst",
     "stride": 0
@@ -67,6 +67,12 @@
           "id": "A",
           "type_id": 0
         }
+      },
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 0
+        }
       }
     ],
     "pair": [
@@ -82,6 +88,12 @@
           "type_id": 0
         }
       },
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 0
+        }
+      },
       {
         "SpecialToken": {
           "id": "<s>",
@@ -93,9 +105,24 @@
           "id": "B",
           "type_id": 1
         }
+      },
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 1
+        }
       }
     ],
     "special_tokens": {
+      "</s>": {
+        "id": "</s>",
+        "ids": [
+          2
+        ],
+        "tokens": [
+          "</s>"
+        ]
+      },
       "<s>": {
         "id": "<s>",
         "ids": [

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
-  "add_eos_token": false,
+  "add_eos_token": true,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -27,21 +28,18 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<unk>",
-    "<s>",
-    "</s>"
-  ],
+  "additional_special_tokens": [],
   "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "pad_token": "</s>",
+  "padding_side": "right",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "truncation_side": "left",
   "unk_token": "<unk>",
   "use_default_system_prompt": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f20da8ec14c267bfbcd89d50c443481e66dd3e009b8785cfc1eb43ea62f931c
-size 4984
+oid sha256:81d2e914bbda72e796fb4e27d0c5854686f9898d29b24d616c5b1d6c9e08aeeb
+size 5112