Training in progress, step 500

adapter_config.json

@@ -1,14 +1,14 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "TheBloke/Mistral-7B-Instruct-v0.1-GPTQ",
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "modules_to_save": null,
   "peft_type": "LORA",
@@ -16,9 +16,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "o_proj",
+    "down_proj",
+    "gate_proj",
     "q_proj",
     "v_proj",
+    "lm_head",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM"

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a16d1835320918032a943f50fd0c8211338b2d371cd3abc0beafac05c2e8ac8
-size 54560368
+oid sha256:a11cf289d47404188b0531e2c999163f28e16e816c31f1e28c2744f93b23288e
+size 170142632

runs/Nov24_18-54-20_3bc1458b4f98/events.out.tfevents.1700852093.3bc1458b4f98.47.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089d37770be776df5b296c48f839335b06b2a479732fc2e82fbfbf568b3965a8
+size 5579

special_tokens_map.json

@@ -2,22 +2,22 @@
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
+  "pad_token": "<unk>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer.json

@@ -14,7 +14,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     },
     {
@@ -23,7 +23,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     },
     {
@@ -32,7 +32,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     }
   ],

tokenizer_config.json

@@ -5,7 +5,7 @@
     "0": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -13,7 +13,7 @@
     "1": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -21,7 +21,7 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -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:f266ba0171ccf1ee6b74490f4ab58c91eb0fd8d67f0955bf98fd35e1ad0c5614
-size 4664
+oid sha256:777f26419f4aaacfdfa7e4a0442de6a2e9fa2fe4128a52e0ea8e5dcb938ae924
+size 4219