prompt_fine_tuned_rte_XLMroberta

.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 +1,71 @@
+---
+license: mit
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: xlm-roberta-base
+metrics:
+- accuracy
+- f1
+model-index:
+- name: prompt_fine_tuned_rte_XLMroberta
+  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. -->
+
+# prompt_fine_tuned_rte_XLMroberta
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7052
+- Accuracy: 0.3448
+- F1: 0.3399
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 400
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
+| 0.6899        | 1.7241  | 50   | 0.7067          | 0.4138   | 0.3957 |
+| 0.7066        | 3.4483  | 100  | 0.7054          | 0.4483   | 0.4221 |
+| 0.6996        | 5.1724  | 150  | 0.7054          | 0.4483   | 0.4221 |
+| 0.6876        | 6.8966  | 200  | 0.7056          | 0.4138   | 0.3957 |
+| 0.699         | 8.6207  | 250  | 0.7051          | 0.4138   | 0.3957 |
+| 0.6936        | 10.3448 | 300  | 0.7055          | 0.3448   | 0.3399 |
+| 0.6909        | 12.0690 | 350  | 0.7052          | 0.3448   | 0.3399 |
+| 0.69          | 13.7931 | 400  | 0.7052          | 0.3448   | 0.3399 |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,17 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "xlm-roberta-base",
+  "inference_mode": true,
+  "num_attention_heads": 12,
+  "num_layers": 12,
+  "num_transformer_submodules": 1,
+  "num_virtual_tokens": 12,
+  "peft_type": "PROMPT_TUNING",
+  "prompt_tuning_init": "RANDOM",
+  "prompt_tuning_init_text": null,
+  "revision": null,
+  "task_type": "SEQ_CLS",
+  "token_dim": 768,
+  "tokenizer_kwargs": null,
+  "tokenizer_name_or_path": "xlm-roberta-base"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0478f466dfe3fc8f5757353d54d49819febd0e2a1abfe96b2aa939f0701b0c76
+size 2405904

runs/May23_08-41-54_2e329e5d4728/events.out.tfevents.1716453715.2e329e5d4728.4382.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:879493fbdb93c0c7067f9bf0b04586f5ac76e05a973e600a6bb632c39ad8d7de
+size 10002

runs/May23_08-41-54_2e329e5d4728/events.out.tfevents.1716453757.2e329e5d4728.4382.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c1200b3f0fe71defc9af8ccd3e6bfc8f4fb09fc783213b484932e3bb48daf8d
+size 457

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 +1,15 @@
+{
+  "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28441c42281a1a69f29d3d283975da1328bf55c314af15116a6afa921b0a80cc
+size 5112