Training in progress, step 500

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
+    "k_proj",
     "q_proj",
+    "up_proj",
     "o_proj",
-    "k_proj",
     "down_proj",
-    "gate_proj"
+    "gate_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7796a8b8b48c8a65dd69eaa720ca767ce8793f9c21b27bee282ae5a9c1fd9103
+oid sha256:852d0f7f85615da468c797ef1ec1f1f8660fe222c480cbfee2ffb2f35e3cb625
 size 167832240

runs/Jul14_15-27-22_ml-cluster/events.out.tfevents.1720970846.ml-cluster

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c35b537b4fe060729f5b1a15ef0f29a9aafc548e3b6ba667cc56860656a7e10d
+size 5702

runs/Jul14_15-30-21_ml-cluster/events.out.tfevents.1720971025.ml-cluster

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc559b59082c869748e1d9e482c0cedac80595444b17e0503ac4549446d2fb87
+size 5702

special_tokens_map.json

@@ -13,5 +13,11 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|end_of_text|>"
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -2311,6 +2311,15 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 128256,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -2047,6 +2047,14 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "128256": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "bos_token": "<|begin_of_text|>",
@@ -2057,6 +2065,6 @@
     "attention_mask"
   ],
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|end_of_text|>",
+  "pad_token": "[PAD]",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ecda7d7300bb607ef09690b066dcf6aa108dfb72fad4082997b8645b12578b6
+oid sha256:2e2008df619968f860bea0ef68062b4745c3ab9910343223e27015d96b4ec03d
 size 5432