Saving model gmra_crest-data-systems/gitlab-mr-analysis-default-model_07112024T123200

README.md

@@ -0,0 +1,85 @@
+---
+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_07112024T123200
+  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_07112024T123200
+
+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: 2.1618
+- F1: 0.6102
+- 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: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | F1     | Rate   |
+|:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
+| No log        | 0.9943  | 87   | 3.4729          | 0.1512 | 0.0000 |
+| No log        | 2.0     | 175  | 1.5854          | 0.2612 | 7e-06  |
+| No log        | 2.9943  | 262  | 1.3071          | 0.5194 | 0.0000 |
+| No log        | 4.0     | 350  | 1.1987          | 0.5696 | 0.0000 |
+| No log        | 4.9943  | 437  | 1.1969          | 0.5988 | 0.0000 |
+| 1.988         | 6.0     | 525  | 1.2367          | 0.6025 | 0.0000 |
+| 1.988         | 6.9943  | 612  | 1.2985          | 0.6065 | 0.0000 |
+| 1.988         | 8.0     | 700  | 1.3981          | 0.6012 | 0.0000 |
+| 1.988         | 8.9943  | 787  | 1.4878          | 0.6025 | 0.0000 |
+| 1.988         | 10.0    | 875  | 1.6375          | 0.6039 | 0.0000 |
+| 1.988         | 10.9943 | 962  | 1.6594          | 0.6116 | 0.0000 |
+| 0.3297        | 12.0    | 1050 | 1.7861          | 0.6165 | 0.0000 |
+| 0.3297        | 12.9943 | 1137 | 1.8770          | 0.6306 | 0.0000 |
+| 0.3297        | 14.0    | 1225 | 1.9764          | 0.6021 | 0.0000 |
+| 0.3297        | 14.9943 | 1312 | 2.0507          | 0.6134 | 0.0000 |
+| 0.3297        | 16.0    | 1400 | 2.1181          | 0.6007 | 0.0000 |
+| 0.3297        | 16.9943 | 1487 | 2.1135          | 0.6063 | 0.0000 |
+| 0.0529        | 18.0    | 1575 | 2.1483          | 0.6024 | 0.0000 |
+| 0.0529        | 18.9943 | 1662 | 2.1560          | 0.6138 | 0.0000 |
+| 0.0529        | 19.8857 | 1740 | 2.1618          | 0.6102 | 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 sha256:2b662a70e5cdaaf4d4ea965861240bec796ca5c212483053eec147707baa2462
+size 267844872

runs/Nov07_07-02-00_d525db3baeb7/events.out.tfevents.1730962925.d525db3baeb7.1204.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5161394ff3d5546699ea3267eb0c82fb4d204355bae1772451de069b2104d93f
+size 13979

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:c1571d4db10d86322fd9ea440091eb1cce0c29f2a65a09427ccb7e1512f93533
+size 5304