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

@@ -0,0 +1,84 @@
+---
+library_name: transformers
+base_model: Davidozito/zeroshot-classification
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: fewshot-CDW-CE-250-samples
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# fewshot-CDW-CE-250-samples
+
+This model is a fine-tuned version of [Davidozito/zeroshot-classification](https://huggingface.co/Davidozito/zeroshot-classification) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1342
+- Accuracy: 0.52
+- F1 Macro: 0.4567
+- F1 Weighted: 0.4859
+- Precision Macro: 0.4891
+- Recall Macro: 0.4833
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1 Macro | F1 Weighted | Precision Macro | Recall Macro |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:-----------:|:---------------:|:------------:|
+| 1.1607        | 0.2414 | 7    | 1.1334          | 0.48     | 0.4406   | 0.4664      | 0.48            | 0.45         |
+| 1.198         | 0.4828 | 14   | 1.1342          | 0.52     | 0.4567   | 0.4859      | 0.4891          | 0.4833       |
+| 1.0988        | 0.7241 | 21   | 1.1320          | 0.48     | 0.4405   | 0.4777      | 0.4678          | 0.4400       |
+| 1.0673        | 0.9655 | 28   | 1.1304          | 0.48     | 0.4405   | 0.4777      | 0.4678          | 0.4400       |
+| 1.2669        | 1.2069 | 35   | 1.1282          | 0.48     | 0.4405   | 0.4777      | 0.4678          | 0.4400       |
+| 1.0031        | 1.4483 | 42   | 1.1274          | 0.48     | 0.4405   | 0.4777      | 0.4678          | 0.4400       |
+| 1.264         | 1.6897 | 49   | 1.1288          | 0.48     | 0.4405   | 0.4777      | 0.4678          | 0.4400       |
+| 1.0977        | 1.9310 | 56   | 1.1292          | 0.48     | 0.4405   | 0.4777      | 0.4678          | 0.4400       |
+| 1.2181        | 2.1724 | 63   | 1.1300          | 0.48     | 0.4405   | 0.4777      | 0.4678          | 0.4400       |
+| 1.1506        | 2.4138 | 70   | 1.1310          | 0.48     | 0.4405   | 0.4777      | 0.4678          | 0.4400       |
+| 1.0379        | 2.6552 | 77   | 1.1300          | 0.48     | 0.4405   | 0.4777      | 0.4678          | 0.4400       |
+| 1.1612        | 2.8966 | 84   | 1.1277          | 0.48     | 0.4405   | 0.4777      | 0.4678          | 0.4400       |
+| 1.1059        | 3.1379 | 91   | 1.1273          | 0.48     | 0.4405   | 0.4777      | 0.4678          | 0.4400       |
+| 1.1636        | 3.3793 | 98   | 1.1267          | 0.48     | 0.4405   | 0.4777      | 0.4678          | 0.4400       |
+| 1.0985        | 3.6207 | 105  | 1.1266          | 0.48     | 0.4405   | 0.4777      | 0.4678          | 0.4400       |
+| 1.0929        | 3.8621 | 112  | 1.1267          | 0.48     | 0.4405   | 0.4777      | 0.4678          | 0.4400       |
+| 0.9983        | 4.1034 | 119  | 1.1266          | 0.48     | 0.4405   | 0.4777      | 0.4678          | 0.4400       |
+| 1.1553        | 4.3448 | 126  | 1.1266          | 0.48     | 0.4405   | 0.4777      | 0.4678          | 0.4400       |
+| 1.2561        | 4.5862 | 133  | 1.1270          | 0.48     | 0.4405   | 0.4777      | 0.4678          | 0.4400       |
+| 1.0976        | 4.8276 | 140  | 1.1271          | 0.48     | 0.4405   | 0.4777      | 0.4678          | 0.4400       |
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.7.1
+- Datasets 3.6.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,42 @@
+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "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": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf1dde100820816d07d04999829318491d0ef835ecc3b1e8a85478e91cbb6907
+size 1112214236

sentencepiece.bpe.model

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

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "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": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+size 17082832

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fbd1bf401a78c4ca66b7f8ac22615d825ad5ed6f6cf0aba76992eea186c407d
+size 5777