Training in progress, step 10

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
+  "base_model_name_or_path": "google/gemma-2b",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,10 +20,10 @@
   "revision": null,
   "target_modules": [
     "up_proj",
-    "down_proj",
-    "k_proj",
     "v_proj",
+    "down_proj",
     "q_proj",
+    "k_proj",
     "gate_proj",
     "o_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:028a7b622c821ef47bd5664328b730ca305cabe2f5d9afd5ee9d673cb755374a
-size 167832240
+oid sha256:eae2a5cd3f9d82e08b9ad32ed2b0ed78350ea70fbf6bdc09ef8beac994bfc28e
+size 39256960

special_tokens_map.json

@@ -1,20 +1,20 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "<bos>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "<eos>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "</s>",
+    "content": "<pad>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
-size 17477473
+oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
+size 17477553

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
-size 493443
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -1,10 +1,9 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -12,7 +11,7 @@
       "special": true
     },
     "1": {
-      "content": "<s>",
+      "content": "<eos>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -20,23 +19,15 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32000": {
-      "content": "<|im_end|>",
+      "content": "<bos>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32001": {
-      "content": "<|im_start|>",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -44,19 +35,15 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "legacy": true,
+  "eos_token": "<eos>",
+  "legacy": null,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
+  "pad_token": "<pad>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "trust_remote_code": false,
+  "tokenizer_class": "GemmaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": true,
-  "use_fast": true
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0272c36b89c6d1dc1e8598919ba84b64ca9ec71968c60a504bd64c59fe533278
+oid sha256:97a0cc18221eda00a76daa1ed78763c36ac640153d876f9e22410aa0f9c6c3e4
 size 4856