End of training

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+base_model: cross-encoder/stsb-roberta-large
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+model-index:
+- name: ce-roberta-large
+  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. -->
+
+# ce-roberta-large
+
+This model is a fine-tuned version of [cross-encoder/stsb-roberta-large](https://huggingface.co/cross-encoder/stsb-roberta-large) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1713
+- Accuracy: 0.6869
+- Precision: 0.8654
+- Recall: 0.6522
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|
+| 0.7081        | 1.0   | 56   | 0.6788          | 0.5960   | 0.8372    | 0.5217 |
+| 0.2275        | 2.0   | 112  | 0.2457          | 0.6667   | 0.8333    | 0.6522 |
+| 0.2263        | 3.0   | 168  | 0.1814          | 0.5455   | 0.9286    | 0.3768 |
+| 0.2249        | 4.0   | 224  | 0.1833          | 0.5657   | 0.9062    | 0.4203 |
+| 0.1803        | 5.0   | 280  | 0.1999          | 0.6768   | 0.7937    | 0.7246 |
+| 0.1708        | 6.0   | 336  | 0.1956          | 0.6566   | 0.8302    | 0.6377 |
+| 0.2091        | 7.0   | 392  | 0.1789          | 0.5556   | 0.9310    | 0.3913 |
+| 0.186         | 8.0   | 448  | 0.1845          | 0.6364   | 0.9231    | 0.5217 |
+| 0.2133        | 9.0   | 504  | 0.1755          | 0.6162   | 0.9189    | 0.4928 |
+| 0.1982        | 10.0  | 560  | 0.1713          | 0.6869   | 0.8654    | 0.6522 |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.2.1
+- Datasets 2.14.6
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "cross-encoder/stsb-roberta-large",
+  "_num_labels": 3,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "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": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efaf8148d9f5595bd7d57677c9206384d650af8647d108e45065a3b218257746
+size 1421491316

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "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>",
+  "errors": "replace",
+  "full_tokenizer_file": null,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ea7c9ecd2142b28426acceeb0004d641e83d7de3b011e2702569a27745124d
+size 4664