Training in progress, step 500

README.md

@@ -1,6 +1,6 @@
 ---
-library_name: transformers
-tags: []
+library_name: peft
+base_model: patrickvonplaten/bert2bert_cnn_daily_mail
 ---
 
 # Model Card for Model ID
@@ -15,7 +15,7 @@ tags: []
 
 <!-- Provide a longer summary of what this model is. -->
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
 
 - **Developed by:** [More Information Needed]
 - **Funded by [optional]:** [More Information Needed]
@@ -199,3 +199,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 
 
+### Framework versions
+
+- PEFT 0.10.1.dev0

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": 16,
+  "r": 4,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "value",
-    "query"
+    "q_proj",
+    "v_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 sha256:12e25b9a7a393ac18c9e176f76fb621be2e6733cb85439a7b5eb219ff4286691
-size 7099360
+oid sha256:c4b4a80d18fc6dcaa92e33648fdd85a5f4940cab1a819188105c221daaa4bb89
+size 894624

runs/Apr13_17-03-32_89a7766e7bdb/events.out.tfevents.1713027835.89a7766e7bdb.1873.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6d269e0c1d8450961ffe1c2d9f83786c3aff0ccdcadffc835deaf80eac43e96
-size 11439
+oid sha256:2b06d3ffaca2058e702bf99f1b4ec58b9e8ee6f952d8c1c1cc01810a15d64c98
+size 11793

runs/Apr13_17-03-32_89a7766e7bdb/events.out.tfevents.1713030946.89a7766e7bdb.1873.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7b312fe1009f653dce48fcd163aeb0d0f14c563efb510ee810bba9e83d92a5a
+size 359

runs/Apr13_18-15-34_89a7766e7bdb/events.out.tfevents.1713032135.89a7766e7bdb.1873.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4ca1ae0ad280af71c67ff4ff67305ff9f313393f6f075e910fdddc2bcc7d90e
+size 5854

runs/Apr13_18-16-06_89a7766e7bdb/events.out.tfevents.1713032171.89a7766e7bdb.1873.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dfc4371868898024a447a316dd666f14090008aa66da37b26e5a01e5fab820c
+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 sha256:7a8e39932266814530278f72b966e6ff504e81438b48e31aecb4ece5603c1699
+oid sha256:36c644b433f0c0e785d3bc10f899fc0ad9f7057eaf6e9012c85373f7af903cd9
 size 5112