bif02/pair_classifier

README.md

@@ -0,0 +1,72 @@
+---
+library_name: transformers
+license: mit
+base_model: FacebookAI/roberta-large-mnli
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+model-index:
+- name: classifier_roberta
+  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. -->
+
+# classifier_roberta
+
+This model is a fine-tuned version of [FacebookAI/roberta-large-mnli](https://huggingface.co/FacebookAI/roberta-large-mnli) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6876
+- Accuracy: 0.5608
+- Precision: 0.0
+- Recall: 0.0
+
+## 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: 0.001
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 0
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: polynomial
+- num_epochs: 8
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|
+| No log        | 1.0   | 358  | 0.9513          | 0.4392   | 0.4392    | 1.0    |
+| 0.7615        | 2.0   | 716  | 0.9091          | 0.4392   | 0.4392    | 1.0    |
+| 0.739         | 3.0   | 1074 | 0.6890          | 0.5608   | 0.0       | 0.0    |
+| 0.739         | 4.0   | 1432 | 0.7166          | 0.5608   | 0.0       | 0.0    |
+| 0.732         | 5.0   | 1790 | 0.7337          | 0.5608   | 0.0       | 0.0    |
+| 0.7227        | 6.0   | 2148 | 0.7022          | 0.4392   | 0.4392    | 1.0    |
+| 0.7097        | 7.0   | 2506 | 0.6982          | 0.4392   | 0.4392    | 1.0    |
+| 0.7097        | 8.0   | 2864 | 0.6876          | 0.5608   | 0.0       | 0.0    |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "FacebookAI/roberta-large-mnli",
+  "_num_labels": 3,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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": 1024,
+  "id2label": {
+    "0": "CONTRADICTION",
+    "1": "NEUTRAL",
+    "2": "ENTAILMENT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "CONTRADICTION": 0,
+    "ENTAILMENT": 2,
+    "NEUTRAL": 1
+  },
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "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 sha256:5a982be8803c27a18c3a1f77f90cf979e23a2f7751228c3a9beba390e6c1ff73
+size 1421499516

runs/Nov02_22-20-22_1db9ed44b2cb/events.out.tfevents.1730586034.1db9ed44b2cb.15291.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c91d6de2917c6536d1375f3a516cc3b18fd0c486cb6ba176c646116afdfdf4c
+size 9971

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_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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "devic_map": "auto",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "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:ba46d5d4b17198c09c4a337b9575a1987496b86420d9aa07f80b835dc7dff462
+size 5240