Training in progress, epoch 1

adapter_config.json

@@ -1,6 +1,6 @@
 {
   "auto_mapping": null,
-  "base_model_name_or_path": "roberta-large",
+  "base_model_name_or_path": "tiiuae/falcon-7b",
   "bias": "all",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -14,8 +14,7 @@
   "r": 16,
   "revision": null,
   "target_modules": [
-    "query",
-    "value"
+    "query_key_value"
   ],
   "task_type": "TOKEN_CLS"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88d1cbb097030b923bc1460e474e390df25ce6d6cc5b7f0991c29c420f780406
-size 7519645
+oid sha256:af8efa9ac20d1fdd156f95a4bde03b91369a937a9ed4a01250704bf3a41b2fe8
+size 19674013

special_tokens_map.json

@@ -1,9 +1,17 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
 }

tokenizer_config.json

@@ -2,7 +2,7 @@
   "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": ">>TITLE<<",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -10,7 +10,7 @@
       "special": true
     },
     "1": {
-      "content": "<pad>",
+      "content": ">>ABSTRACT<<",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -18,7 +18,7 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": ">>INTRODUCTION<<",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -26,35 +26,99 @@
       "special": true
     },
     "3": {
-      "content": "<unk>",
+      "content": ">>SUMMARY<<",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
-      "content": "<mask>",
-      "lstrip": true,
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": ">>DOMAIN<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": ">>PREFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": ">>SUFFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": ">>MIDDLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
-  "model_max_length": 512,
-  "pad_token": "<pad>",
+  "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
   "padding": true,
-  "sep_token": "</s>",
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
-  "truncation": true,
-  "unk_token": "<unk>"
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dc0f25f4e2407d6a5844e129e433aa281b282ff0acb3a2290aa17c437bbf35f
-size 4091
+oid sha256:85240e81f811d6259a6fca94ea9183d22d24ef13d708e7a31f69e709aaaddba1
+size 4155