Training complete

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: FacebookAI/roberta-base
+base_model: intfloat/multilingual-e5-base
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # digidaw
 
-This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
+This model is a fine-tuned version of [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3618
-- Accuracy: 0.5941
-- Precision: 0.0743
-- Recall: 0.125
-- F1: 0.0932
+- Loss: 0.7597
+- Accuracy: 0.7770
+- Precision: 0.5252
+- Recall: 0.5221
+- F1: 0.5217
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 1.3939        | 1.0   | 110  | 1.3742          | 0.5941   | 0.0743    | 0.125  | 0.0932 |
-| 1.3769        | 2.0   | 220  | 1.3634          | 0.5941   | 0.0743    | 0.125  | 0.0932 |
-| 1.3696        | 3.0   | 330  | 1.3618          | 0.5941   | 0.0743    | 0.125  | 0.0932 |
+| 1.0326        | 1.0   | 110  | 0.7906          | 0.7557   | 0.5710    | 0.4468 | 0.4696 |
+| 0.6609        | 2.0   | 220  | 0.7697          | 0.7597   | 0.5234    | 0.4885 | 0.4999 |
+| 0.4276        | 3.0   | 330  | 0.7597          | 0.7770   | 0.5252    | 0.5221 | 0.5217 |
 
 
 ### Framework versions

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "FacebookAI/roberta-base",
+  "_name_or_path": "intfloat/multilingual-e5-base",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "XLMRobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
@@ -34,9 +34,10 @@
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
-  "model_type": "roberta",
+  "model_type": "xlm-roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
+  "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
@@ -44,5 +45,5 @@
   "transformers_version": "4.41.2",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 250002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a9896e330afc579e2de627b97a4d37f76b8ed28e7b5f34e8576d2e2b4b7b564
-size 498631280
+oid sha256:183dbc6aa046c43670b3014f8aae7298988e26d0181173ce39695db8087b1d73
+size 1112223464

runs/Jun06_12-35-37_8b985dd3eeed/events.out.tfevents.1717677646.8b985dd3eeed.2286.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bf34c149cdeb75e533c95670dccf485f64c603bc2518565323290ed8edb7a9d
+size 560

runs/Jun06_12-52-46_8b985dd3eeed/events.out.tfevents.1717678367.8b985dd3eeed.2286.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:236fdf012fd049acb273c1028b6683eb7c0e379e8e520b83e19b1dfa67643fb7
+size 7656

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -1,7 +1,25 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -9,7 +27,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,10 +1,9 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -12,7 +11,7 @@
     "1": {
       "content": "<pad>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -20,7 +19,7 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -28,12 +27,12 @@
     "3": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
+    "250001": {
       "content": "<mask>",
       "lstrip": true,
       "normalized": false,
@@ -46,12 +45,10 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "errors": "replace",
   "mask_token": "<mask>",
   "model_max_length": 128,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
+  "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dd5f3bd7087a11069e6556652177038dc260fb1a489c0754256ea10e11d5842
+oid sha256:36f6fe3f67175c1bd04d1a18164ca949487ba6ecab3a5d50be1fe4697059c77d
 size 5048