End of training

.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

@@ -1,10 +1,10 @@
 ---
-license: apache-2.0
-base_model: distilbert-base-cased
+license: mit
+base_model: FacebookAI/xlm-roberta-base
 tags:
 - generated_from_trainer
 metrics:
-- accuracy
+- f1
 model-index:
 - name: L1-classifier-CopExp
   results: []
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # L1-classifier-CopExp
 
-This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset.
+This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3605
-- Accuracy: 0.8664
+- Loss: 0.4412
+- F1: 0.7117
 
 ## Model description
 
@@ -43,19 +43,22 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 75   | 0.4595          | 0.8046   |
-| No log        | 2.0   | 150  | 0.3605          | 0.8664   |
+| Training Loss | Epoch | Step | Validation Loss | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| No log        | 1.0   | 182  | 0.4110          | 0.6570 |
+| No log        | 2.0   | 364  | 0.3837          | 0.7136 |
+| 0.1347        | 3.0   | 546  | 0.4063          | 0.6975 |
+| 0.1347        | 4.0   | 728  | 0.3830          | 0.7240 |
+| 0.1347        | 5.0   | 910  | 0.4412          | 0.7117 |
 
 
 ### Framework versions
 
-- Transformers 4.38.2
+- Transformers 4.40.1
 - Pytorch 2.2.1+cu121
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -1,34 +1,37 @@
 {
-  "_name_or_path": "distilbert-base-cased",
-  "activation": "gelu",
+  "_name_or_path": "FacebookAI/xlm-roberta-base",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "XLMRobertaForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "Other",
     "1": "CopExp"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "CopExp": 1,
     "Other": 0
   },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "output_past": true,
-  "pad_token_id": 0,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
-  "vocab_size": 28996
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64e0b56f9526c62ace53938e1bc2df0c60eabccc65b3eced9062f19b120c093d
-size 263144680
+oid sha256:03a401275c0af16193e660162b81e88e65a2c7bf43fdb1e57c67be45dec55d8e
+size 1112205008

runs/May07_18-18-06_adaac59f58e7/events.out.tfevents.1715105887.adaac59f58e7.373.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:458702b83a40626d59c2a9fde9d835a164c7995414359db838f8e8f758cd8b7d
+size 7083

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 +1,15 @@
 {
-  "cls_token": "[CLS]",
-  "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": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,55 +1,54 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "mask_token": "[MASK]",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af81fac0dabfaf1aa0a52cf8e5faa2408990e7f1ccdb1e96ff49a5048e85bd13
-size 4920
+oid sha256:8a5e930923accab177e14f5899d46bfe6719fbc2c57d7d2ec7f9a9294ba5c5c2
+size 4984