Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "KennethEnevoldsen/dfm-sentence-encoder-large-exp2-no-lang-align",
+  "_name_or_path": "KennethEnevoldsen/dfm-sentence-encoder-large",
   "architectures": [
     "BertForSequenceClassification"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5c9dcca15787e8a5453d11c960f87e0e0bd373f6f6b140c8a70960ab7303896
+oid sha256:c80d8b2bd16256d518406d562e67fdf635072ddc63471540e02ade2a8a604dfc
 size 1420404704

runs/Jun12_14-56-37_58029a0bd48e/events.out.tfevents.1718204313.58029a0bd48e.1107.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7804e121a81b2e5951618dc34f442cb05643c46beef3e846f65af10d01ab3b3c
+size 5270

special_tokens_map.json

@@ -1,37 +1,7 @@
 {
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -46,19 +46,12 @@
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "max_length": 256,
   "model_max_length": 512,
   "never_split": null,
-  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "[SEP]",
-  "stride": 0,
   "strip_accents": false,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d27a74c8da4a5cd2b2c77a0764d75f13c50ed0c7d71b65f28df82d09437abed
+oid sha256:934d7f3d763472917ed97750a19274998340a59f4e1ed4b696cc53fac003413a
 size 5176