Saving model gmra_crest-data-systems/gitlab-mr-analysis-default-model_07112024T153612

README.md

@@ -0,0 +1,75 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: crest-data-systems/gitlab-mr-analysis-default-model
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: gitlab-mr-analysis-default-model_07112024T153612
+  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. -->
+
+# gitlab-mr-analysis-default-model_07112024T153612
+
+This model is a fine-tuned version of [crest-data-systems/gitlab-mr-analysis-default-model](https://huggingface.co/crest-data-systems/gitlab-mr-analysis-default-model) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5457
+- F1: 0.5961
+- Learning Rate: 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use adamw_hf with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | F1     | Rate   |
+|:-------------:|:------:|:----:|:---------------:|:------:|:------:|
+| No log        | 0.9968 | 157  | 1.6043          | 0.5917 | 0.0000 |
+| No log        | 1.9952 | 314  | 1.6776          | 0.5892 | 0.0000 |
+| No log        | 2.9937 | 471  | 1.8240          | 0.5767 | 0.0000 |
+| 0.1764        | 3.9984 | 629  | 1.9399          | 0.5930 | 0.0000 |
+| 0.1764        | 4.9968 | 786  | 2.0195          | 0.5834 | 0.0000 |
+| 0.1764        | 5.9952 | 943  | 2.1140          | 0.5892 | 0.0000 |
+| 0.1109        | 6.9937 | 1100 | 2.3528          | 0.5971 | 0.0000 |
+| 0.1109        | 7.9984 | 1258 | 2.4072          | 0.5963 | 0.0000 |
+| 0.1109        | 8.9968 | 1415 | 2.5230          | 0.5901 | 0.0000 |
+| 0.0415        | 9.9825 | 1570 | 2.5457          | 0.5961 | 0.0    |
+
+
+### Framework versions
+
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "crest-data-systems/gitlab-mr-analysis-default-model",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "change_request",
+    "1": "discussion_participation",
+    "2": "discussion_trigger",
+    "3": "acknowledgement",
+    "4": "critical",
+    "5": "reference"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "acknowledgement": 3,
+    "change_request": 0,
+    "critical": 4,
+    "discussion_participation": 1,
+    "discussion_trigger": 2,
+    "reference": 5
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f292de737e9dc736fa5038a91aeda1a7ee2fbe0765ee1106a2006300381d12
+size 267844872

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfe999775114be6d61a501781dab91dac2d9a1a5b2022ef033454041b6b1695e
+size 5368