Saving model gmra_distilbert/distilbert-base-uncased-distilled-squad_07112024T120722

README.md

@@ -0,0 +1,85 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased-distilled-squad
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: distilbert-base-uncased-distilled-squad_07112024T120722
+  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. -->
+
+# distilbert-base-uncased-distilled-squad_07112024T120722
+
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased-distilled-squad](https://huggingface.co/distilbert/distilbert-base-uncased-distilled-squad) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7930
+- F1: 0.7643
+- 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: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Rate   |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
+| No log        | 1.0   | 121  | 1.1749          | 0.5577 | 0.0000 |
+| No log        | 2.0   | 242  | 0.9801          | 0.6593 | 0.0000 |
+| No log        | 3.0   | 363  | 0.9184          | 0.6951 | 0.0000 |
+| No log        | 4.0   | 484  | 0.8064          | 0.7480 | 0.0000 |
+| 0.9941        | 5.0   | 605  | 0.7930          | 0.7643 | 0.0000 |
+| 0.9941        | 6.0   | 726  | 0.8313          | 0.7793 | 0.0000 |
+| 0.9941        | 7.0   | 847  | 0.8955          | 0.7814 | 0.0000 |
+| 0.9941        | 8.0   | 968  | 0.9010          | 0.7963 | 0.0000 |
+| 0.3299        | 9.0   | 1089 | 0.9855          | 0.7945 | 0.0000 |
+| 0.3299        | 10.0  | 1210 | 0.9753          | 0.8036 | 0.0000 |
+| 0.3299        | 11.0  | 1331 | 1.0115          | 0.8095 | 0.0000 |
+| 0.3299        | 12.0  | 1452 | 1.0508          | 0.8052 | 7e-06  |
+| 0.0991        | 13.0  | 1573 | 1.1102          | 0.8125 | 0.0000 |
+| 0.0991        | 14.0  | 1694 | 1.1321          | 0.8146 | 0.0000 |
+| 0.0991        | 15.0  | 1815 | 1.2166          | 0.8085 | 3e-06  |
+| 0.0991        | 16.0  | 1936 | 1.1935          | 0.8109 | 0.0000 |
+| 0.0349        | 17.0  | 2057 | 1.2277          | 0.8074 | 0.0000 |
+| 0.0349        | 18.0  | 2178 | 1.2145          | 0.8091 | 5e-07  |
+| 0.0349        | 19.0  | 2299 | 1.2306          | 0.8082 | 1e-07  |
+| 0.0349        | 20.0  | 2420 | 1.2334          | 0.8080 | 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": "distilbert/distilbert-base-uncased-distilled-squad",
+  "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": "4.44.2",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f26579a5b9a7db7b42113bd71130312eefe070088142e0814d7b5ceea3b3a4c3
+size 267844872

runs/Nov07_06-37-22_4e102b0d102a/events.out.tfevents.1730961450.4e102b0d102a.233.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:434f322a48c13e2549b81074dbfa366ddad20b982dc6a668a1afcc941f8afeb6
+size 14103

runs/Nov07_06-37-22_4e102b0d102a/events.out.tfevents.1730963874.4e102b0d102a.233.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35736211c7ab19fd21fbfcf9b1c56663b695cd6a447595af8fc4b8e61439126
+size 463

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:232aff71aec3ab311a0d2c92abfc89b5391f9baf0c15a133fee0b3f2d457183b
+size 5304