aapoliakova/bsf_cls

README.md

@@ -1,7 +1,5 @@
 ---
 library_name: transformers
-license: mit
-base_model: microsoft/deberta-v3-small
 tags:
 - generated_from_trainer
 model-index:
@@ -14,15 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # cls_level_bsf
 
-This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 1.5422
-- eval_accuracy: 0.4860
-- eval_runtime: 7.168
-- eval_samples_per_second: 39.899
-- eval_steps_per_second: 2.511
-- epoch: 3.2308
-- step: 1050
+This model was trained from scratch on an unknown dataset.
 
 ## Model description
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "microsoft/deberta-v3-small",
+  "_name_or_path": "/content/cls_level_bsf/checkpoint-300",
   "architectures": [
     "DebertaV2ForSequenceClassification"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05bce8b50732d5120a22c782d4131cade8617527addad6690966cd68097d9a63
+oid sha256:90dbba4ab23da6829b5f1f22e15e32cfeeb0fd4cc0ee51fce5fb9e22c0ea4112
 size 567601628

runs/Oct01_16-37-55_36a7c0a38235/events.out.tfevents.1727800683.36a7c0a38235.1511.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50eef6419a42ab65b9612683f844aee1182b9c5eee4862af320739295754819b
+size 409

special_tokens_map.json

@@ -1,10 +1,46 @@
 {
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "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,

tokenizer_config.json

@@ -47,12 +47,19 @@
   "do_lower_case": false,
   "eos_token": "[SEP]",
   "mask_token": "[MASK]",
+  "max_length": 512,
   "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
   "sp_model_kwargs": {},
   "split_by_punct": false,
+  "stride": 0,
   "tokenizer_class": "DebertaV2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]",
   "vocab_type": "spm"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a685d7ab4afbd2ef2ba2de5c90952fb016438bf574c829139c844bfa18dff28
+oid sha256:d7a9a2c81bfb516c6ca8ebe7b6e22456e6a784b3ddb8b01d3d1257bc4554dd6e
 size 5176