fine_tuned_rte_sloberta

README.md

@@ -1,6 +1,6 @@
 ---
-license: mit
-base_model: xlm-roberta-base
+license: cc-by-sa-4.0
+base_model: EMBEDDIA/sloberta
 tags:
 - generated_from_trainer
 metrics:
@@ -16,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # fine_tuned_rte_sloberta
 
-This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
+This model is a fine-tuned version of [EMBEDDIA/sloberta](https://huggingface.co/EMBEDDIA/sloberta) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4763
+- Loss: 0.6653
 - Accuracy: 0.6207
-- F1: 0.5951
+- F1: 0.5750
 
 ## Model description
 
@@ -51,14 +51,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
-| 0.7117        | 1.7241  | 50   | 0.7129          | 0.4138   | 0.2422 |
-| 0.7033        | 3.4483  | 100  | 0.6997          | 0.4138   | 0.2422 |
-| 0.6845        | 5.1724  | 150  | 0.6933          | 0.4828   | 0.4828 |
-| 0.6378        | 6.8966  | 200  | 0.8005          | 0.4828   | 0.4668 |
-| 0.4579        | 8.6207  | 250  | 0.9656          | 0.6207   | 0.5951 |
-| 0.2521        | 10.3448 | 300  | 1.2302          | 0.6552   | 0.6018 |
-| 0.1196        | 12.0690 | 350  | 1.4679          | 0.5862   | 0.5789 |
-| 0.0653        | 13.7931 | 400  | 1.4763          | 0.6207   | 0.5951 |
+| 0.6985        | 1.7241  | 50   | 0.7540          | 0.4138   | 0.2422 |
+| 0.7058        | 3.4483  | 100  | 0.6912          | 0.5862   | 0.4333 |
+| 0.6993        | 5.1724  | 150  | 0.6980          | 0.4138   | 0.2422 |
+| 0.7003        | 6.8966  | 200  | 0.6806          | 0.5862   | 0.4333 |
+| 0.6968        | 8.6207  | 250  | 0.6730          | 0.5862   | 0.4333 |
+| 0.6736        | 10.3448 | 300  | 0.6726          | 0.6897   | 0.6801 |
+| 0.6339        | 12.0690 | 350  | 0.6580          | 0.6207   | 0.6090 |
+| 0.6005        | 13.7931 | 400  | 0.6653          | 0.6207   | 0.5750 |
 
 
 ### Framework versions

config.json

@@ -1,12 +1,13 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "EMBEDDIA/sloberta",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "CamembertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
   "classifier_dropout": null,
   "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -22,10 +23,9 @@
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "model_type": "camembert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
@@ -33,5 +33,5 @@
   "transformers_version": "4.40.2",
   "type_vocab_size": 1,
   "use_cache": false,
-  "vocab_size": 250002
+  "vocab_size": 32005
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eabd24fea607f51753c670732cbff70b9cf98944aaa48ee857d18940d30c1c9
-size 1112205008
+oid sha256:29cb0af14d650db1d9f022cffc1845fc4ee8af8e2c6bd824f93d035c81ac5f10
+size 442518104

runs/May22_21-34-41_DESKTOP-22QTFDR/events.out.tfevents.1716406482.DESKTOP-22QTFDR.31040.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe348488623273d2b92678f632cd45a4aced49f915adc2c3118d093fcd6810b
+size 9852

runs/May22_21-34-41_DESKTOP-22QTFDR/events.out.tfevents.1716406562.DESKTOP-22QTFDR.31040.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8e5b2b62d16afb56caada7b0d341fc543d9a7ad788b066546df465d30c74e73
+size 457

sentencepiece.bpe.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
-size 5069051
+oid sha256:34b589385a2320549143ab23b0ccf82cc99a82685701cdabe0fad847bd0479ff
+size 800013

special_tokens_map.json

@@ -1,15 +1,55 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "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,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "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.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
-size 17082832
+oid sha256:93fac4365343b9e0d50ab7fb998411973d573aedb1e9ec11451f068bcfed35f2
+size 2336993

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "<s>NOTUSED",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": "</s>NOTUSED",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -32,23 +32,45 @@
       "single_word": false,
       "special": true
     },
-    "250001": {
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
       "content": "<mask>",
       "lstrip": true,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
+  "do_lower_case": false,
   "eos_token": "</s>",
   "mask_token": "<mask>",
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "CamembertTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36dd1dd9f5c346ceaa1b3d7782066fd60c5d48c515089da4fb6079288a85a7c7
+oid sha256:155f9f1a43bb9a38b5759a1c63194714c98d2cc3a2756b716edf37a9a228dacb
 size 5048