Training in progress, step 978

adapter_config.json

@@ -8,21 +8,18 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
-  "modules_to_save": [
-    "lm_head",
-    "embed_tokens"
-  ],
+  "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "k_proj",
     "v_proj",
-    "q_proj"
+    "o_proj",
+    "q_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cd5967a8ac2c81f0aac85e9096e902bef2ae6c66578b268f4d287543897db66
-size 633407416
+oid sha256:41bc7bb18baf2c368e75550480c8a4346fcaec00edde9fe88c93f33883dbcafe
+size 54560368

config.json

@@ -5,7 +5,7 @@
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 32000,
+  "eos_token_id": 2,
   "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": 32002
+  "vocab_size": 32000
 }

special_tokens_map.json

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

tokenizer_config.json

@@ -25,28 +25,12 @@
       "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": "<|im_end|>",
+  "eos_token": "</s>",
   "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 sha256:7996fa7271f62490bcb7c0a548cad3b765ec648c70677f878ca28b39b86629fb
+oid sha256:b4b1fb46910fa7d2aa33f2def3676285a0b87052f84ab51d2c485ae9b6c899b7
 size 5368