Initial Commit

README.md

@@ -0,0 +1,94 @@
+---
+license: mit
+base_model: facebook/xlm-v-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: scenario-TCR-XLMV-XCOPA-4_data-xcopa_all
+  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. -->
+
+# scenario-TCR-XLMV-XCOPA-4_data-xcopa_all
+
+This model is a fine-tuned version of [facebook/xlm-v-base](https://huggingface.co/facebook/xlm-v-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6931
+- Accuracy: 0.5017
+- F1: 0.4736
+
+## 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 4824
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 500
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 0.38  | 5    | 0.6931          | 0.4967   | 0.4711 |
+| No log        | 0.77  | 10   | 0.6931          | 0.5258   | 0.5133 |
+| No log        | 1.15  | 15   | 0.6931          | 0.5433   | 0.5456 |
+| No log        | 1.54  | 20   | 0.6931          | 0.5267   | 0.5145 |
+| No log        | 1.92  | 25   | 0.6931          | 0.5208   | 0.4987 |
+| No log        | 2.31  | 30   | 0.6931          | 0.5183   | 0.4921 |
+| No log        | 2.69  | 35   | 0.6931          | 0.5242   | 0.4987 |
+| No log        | 3.08  | 40   | 0.6931          | 0.5308   | 0.5151 |
+| No log        | 3.46  | 45   | 0.6931          | 0.53     | 0.5138 |
+| No log        | 3.85  | 50   | 0.6931          | 0.4833   | 0.4737 |
+| No log        | 4.23  | 55   | 0.6931          | 0.51     | 0.4922 |
+| No log        | 4.62  | 60   | 0.6931          | 0.5008   | 0.4759 |
+| No log        | 5.0   | 65   | 0.6931          | 0.4817   | 0.4591 |
+| No log        | 5.38  | 70   | 0.6931          | 0.5133   | 0.4859 |
+| No log        | 5.77  | 75   | 0.6932          | 0.4642   | 0.4305 |
+| No log        | 6.15  | 80   | 0.6932          | 0.4783   | 0.4360 |
+| No log        | 6.54  | 85   | 0.6932          | 0.4658   | 0.4282 |
+| No log        | 6.92  | 90   | 0.6932          | 0.455    | 0.4303 |
+| No log        | 7.31  | 95   | 0.6932          | 0.4808   | 0.4578 |
+| No log        | 7.69  | 100  | 0.6931          | 0.4967   | 0.4784 |
+| No log        | 8.08  | 105  | 0.6931          | 0.5208   | 0.5081 |
+| No log        | 8.46  | 110  | 0.6931          | 0.555    | 0.5444 |
+| No log        | 8.85  | 115  | 0.6931          | 0.5508   | 0.5397 |
+| No log        | 9.23  | 120  | 0.6931          | 0.5567   | 0.5430 |
+| No log        | 9.62  | 125  | 0.6931          | 0.5458   | 0.5338 |
+| No log        | 10.0  | 130  | 0.6931          | 0.5267   | 0.5044 |
+| No log        | 10.38 | 135  | 0.6931          | 0.5175   | 0.4961 |
+| No log        | 10.77 | 140  | 0.6931          | 0.5325   | 0.5185 |
+| No log        | 11.15 | 145  | 0.6931          | 0.5283   | 0.5104 |
+| No log        | 11.54 | 150  | 0.6931          | 0.5217   | 0.5    |
+| No log        | 11.92 | 155  | 0.6931          | 0.5058   | 0.4812 |
+| No log        | 12.31 | 160  | 0.6932          | 0.5      | 0.4792 |
+| No log        | 12.69 | 165  | 0.6931          | 0.5017   | 0.4736 |
+
+
+### Framework versions
+
+- Transformers 4.33.3
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.5
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "facebook/xlm-v-base",
+  "architectures": [
+    "XLMRobertaForMultipleChoice"
+  ],
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 901629
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:062b49ff5f54b5deaa7fa254d8a76aba186979cbf6178e3f96451b4b29c43349
+size 3114045230

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:714325961e1308f2b4080e783f2d312629d98a7627f510291e612637f70e2bdf
+size 4536