Training in progress, step 903

adapter_config.json

@@ -10,16 +10,19 @@
   "layers_to_transform": null,
   "lora_alpha": 32,
   "lora_dropout": 0.05,
-  "modules_to_save": null,
+  "modules_to_save": [
+    "lm_head",
+    "embed_tokens"
+  ],
   "peft_type": "LORA",
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "k_proj",
-    "v_proj",
-    "o_proj"
+    "q_proj",
+    "o_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:601bbefb0e2a2c1ac1f974256b8007bd778fb4a19f352b8d66a7b1dd432f5c67
-size 54560368
+oid sha256:2190821174b6d4e9ddb7e164365e5fe12cab120856f8bab3d17fe3acff9c7119
+size 578881368

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -5,7 +5,7 @@
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 2,
+  "eos_token_id": 32000,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -38,5 +38,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.37.0.dev0",
   "use_cache": false,
-  "vocab_size": 32000
+  "vocab_size": 32002
 }

special_tokens_map.json

@@ -7,7 +7,7 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -25,12 +25,28 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
+  "eos_token": "<|im_end|>",
   "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1f1ff373e9dfcf6c236e1a1018b78ff531d44ce3d9d7ac16e0b3bca7e274864
+oid sha256:92afb8c3d8929f20b62ac94e493d71f8f07af64aaa477be85988ca22d0e1ded4
 size 5368