Saving model gmra_crest-data-systems/gitlab-mr-analysis-default-model_07112024T172947

README.md

@@ -0,0 +1,80 @@
+---
+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_07112024T172947
+  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_07112024T172947
+
+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: 1.9438
+- F1: 0.5876
+- 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 15
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | F1     | Rate   |
+|:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
+| No log        | 0.9943  | 87   | 3.5342          | 0.1406 | 0.0000 |
+| No log        | 2.0     | 175  | 1.5958          | 0.2582 | 7e-06  |
+| No log        | 2.9943  | 262  | 1.2511          | 0.5414 | 0.0000 |
+| No log        | 4.0     | 350  | 1.1763          | 0.5725 | 0.0000 |
+| No log        | 4.9943  | 437  | 1.1890          | 0.5848 | 0.0000 |
+| 1.9832        | 6.0     | 525  | 1.2495          | 0.5913 | 0.0000 |
+| 1.9832        | 6.9943  | 612  | 1.3386          | 0.6015 | 0.0000 |
+| 1.9832        | 8.0     | 700  | 1.4233          | 0.6124 | 0.0000 |
+| 1.9832        | 8.9943  | 787  | 1.5144          | 0.5942 | 0.0000 |
+| 1.9832        | 10.0    | 875  | 1.6596          | 0.5924 | 0.0000 |
+| 1.9832        | 10.9943 | 962  | 1.7356          | 0.5980 | 0.0000 |
+| 0.3221        | 12.0    | 1050 | 1.8500          | 0.5796 | 0.0000 |
+| 0.3221        | 12.9943 | 1137 | 1.9288          | 0.5826 | 0.0000 |
+| 0.3221        | 14.0    | 1225 | 1.9396          | 0.5819 | 2e-06  |
+| 0.3221        | 14.9143 | 1305 | 1.9438          | 0.5876 | 0.0    |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.19.1

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": "acknowledgement",
+    "1": "change_request",
+    "2": "critical",
+    "3": "discussion_participation",
+    "4": "discussion_trigger",
+    "5": "reference"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "acknowledgement": 0,
+    "change_request": 1,
+    "critical": 2,
+    "discussion_participation": 3,
+    "discussion_trigger": 4,
+    "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": "4.44.2",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778d7b4bef4244ce3bf7a6254832fdaa07e749641ce78494037a187ce63c3f23
+size 267844872

runs/Nov07_11-59-47_f195c719d072/events.out.tfevents.1730980793.f195c719d072.192.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33548fb6321858f829d022e662bf443b8a2e45784f7e9add00165f5e6f7fe53d
+size 11880

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 sha256:0b9308667977f74c638c0251504ff4fa3ffa9e71fe1a9d35474eab3724f1beb4
+size 5304