Training in progress, step 500

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "patrickvonplaten/bert2bert_cnn_daily_mail",
+  "base_model_name_or_path": "facebook/bart-base",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -16,12 +16,12 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 4,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query",
-    "value"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "SEQ_2_SEQ_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97c646b4eb28beb7d2273e49e0d34f710ae868cb8dc2f5690336347ff08e31d3
-size 14177360
+oid sha256:8008c348445a22c11fde48a1480ae6493253328384138bd241a040b990c2c69a
+size 894624

runs/Apr13_17-04-33_ef033c8b66bb/events.out.tfevents.1713027875.ef033c8b66bb.375.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e44e1fa2dd121808898268e4c1c6d080a37ce411adef4800748d5acdd46b0ca
-size 11439
+oid sha256:ad53066bc7b2768851e1ee004fee54d6cd9a507966180565bb370df1acffce19
+size 11793

runs/Apr13_17-04-33_ef033c8b66bb/events.out.tfevents.1713031044.ef033c8b66bb.375.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:714017987bc1098f99aa8fdae36c86b0581d531aecf1078a74c7ccc16248e71a
+size 359

runs/Apr13_18-07-35_ef033c8b66bb/events.out.tfevents.1713031666.ef033c8b66bb.375.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab565a7cda2aea03b7deeb6ef9fe5ff6f11cb3b4855c3ec6d2161d9ff51ed21
+size 6336

special_tokens_map.json

@@ -1,9 +1,15 @@
 {
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,60 +1,58 @@
 {
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "[CLS]",
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
+  "cls_token": "<s>",
   "device_map": "auto",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73f1cb5bdd996ea2f49275203b73e73be2eb736ca9a553bd8faa7f8dad7261f5
+oid sha256:8643b4d962f39729fe1c7aff20bb36fc0615286f9c620f70f132d6b383c4b10e
 size 5112