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 +1,94 @@
+---
+base_model: yihongLiu/furina
+tags:
+- generated_from_trainer
+model-index:
+- name: furina_afr_corr_5e-06
+  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. -->
+
+# furina_afr_corr_5e-06
+
+This model is a fine-tuned version of [yihongLiu/furina](https://huggingface.co/yihongLiu/furina) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0213
+- Spearman Corr: 0.7660
+
+## 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-06
+- train_batch_size: 32
+- eval_batch_size: 128
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 30
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Spearman Corr |
+|:-------------:|:-----:|:----:|:---------------:|:-------------:|
+| No log        | 0.85  | 200  | 0.0813          | 0.0483        |
+| No log        | 1.69  | 400  | 0.0439          | 0.3738        |
+| 0.1125        | 2.54  | 600  | 0.0360          | 0.6162        |
+| 0.1125        | 3.38  | 800  | 0.0287          | 0.6660        |
+| 0.035         | 4.23  | 1000 | 0.0271          | 0.6987        |
+| 0.035         | 5.07  | 1200 | 0.0248          | 0.7139        |
+| 0.035         | 5.92  | 1400 | 0.0252          | 0.7230        |
+| 0.026         | 6.77  | 1600 | 0.0246          | 0.7173        |
+| 0.026         | 7.61  | 1800 | 0.0230          | 0.7344        |
+| 0.0227        | 8.46  | 2000 | 0.0236          | 0.7361        |
+| 0.0227        | 9.3   | 2200 | 0.0223          | 0.7470        |
+| 0.0203        | 10.15 | 2400 | 0.0227          | 0.7462        |
+| 0.0203        | 10.99 | 2600 | 0.0224          | 0.7477        |
+| 0.0203        | 11.84 | 2800 | 0.0242          | 0.7483        |
+| 0.0186        | 12.68 | 3000 | 0.0218          | 0.7537        |
+| 0.0186        | 13.53 | 3200 | 0.0229          | 0.7528        |
+| 0.0175        | 14.38 | 3400 | 0.0227          | 0.7552        |
+| 0.0175        | 15.22 | 3600 | 0.0221          | 0.7602        |
+| 0.0163        | 16.07 | 3800 | 0.0216          | 0.7612        |
+| 0.0163        | 16.91 | 4000 | 0.0216          | 0.7619        |
+| 0.0163        | 17.76 | 4200 | 0.0217          | 0.7616        |
+| 0.0154        | 18.6  | 4400 | 0.0215          | 0.7612        |
+| 0.0154        | 19.45 | 4600 | 0.0212          | 0.7651        |
+| 0.0146        | 20.3  | 4800 | 0.0216          | 0.7634        |
+| 0.0146        | 21.14 | 5000 | 0.0213          | 0.7641        |
+| 0.0141        | 21.99 | 5200 | 0.0223          | 0.7629        |
+| 0.0141        | 22.83 | 5400 | 0.0213          | 0.7664        |
+| 0.0141        | 23.68 | 5600 | 0.0214          | 0.7635        |
+| 0.0134        | 24.52 | 5800 | 0.0214          | 0.7649        |
+| 0.0134        | 25.37 | 6000 | 0.0216          | 0.7637        |
+| 0.013         | 26.22 | 6200 | 0.0214          | 0.7644        |
+| 0.013         | 27.06 | 6400 | 0.0213          | 0.7656        |
+| 0.013         | 27.91 | 6600 | 0.0214          | 0.7661        |
+| 0.0127        | 28.75 | 6800 | 0.0212          | 0.7655        |
+| 0.0127        | 29.6  | 7000 | 0.0213          | 0.7660        |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.2.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "yihongLiu/furina",
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 401145
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9443cdba2d37d7d8714beb88c63d825ab55672bcd73ff6f0a2c5d3bae3cc2168
+size 1576513492

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": true,
+    "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 sha256:849984098c26f9b2f4a2d6104a148685f09571ecb72597422e478fb9309e50e8
+size 26885962

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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
+    },
+    "401144": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "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>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>",
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f56603f07f77c19495c1c0ae0e81d2a86ca1e5cfa356854203afb81cf88ecc4a
+size 4664