Saving model gmra_distilbert/distilbert-base-uncased-finetuned-sst-2-english_08112024T110433

README.md

@@ -0,0 +1,85 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased-finetuned-sst-2-english
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: distilbert-base-uncased-finetuned-sst-2-english_08112024T110433
+  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-finetuned-sst-2-english_08112024T110433
+
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert/distilbert-base-uncased-finetuned-sst-2-english) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4561
+- F1: 0.8591
+- 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: 1e-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: 600
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | F1     | Rate   |
+|:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
+| No log        | 0.9942  | 86   | 1.8025          | 0.1776 | 0.0000 |
+| No log        | 2.0     | 173  | 1.7296          | 0.1902 | 0.0000 |
+| No log        | 2.9942  | 259  | 1.6400          | 0.3649 | 0.0000 |
+| No log        | 4.0     | 346  | 1.4873          | 0.4157 | 0.0000 |
+| No log        | 4.9942  | 432  | 1.2812          | 0.5119 | 0.0000 |
+| 1.5846        | 6.0     | 519  | 1.0792          | 0.5668 | 0.0000 |
+| 1.5846        | 6.9942  | 605  | 0.9450          | 0.6226 | 1e-05  |
+| 1.5846        | 8.0     | 692  | 0.8238          | 0.6836 | 0.0000 |
+| 1.5846        | 8.9942  | 778  | 0.7274          | 0.7374 | 0.0000 |
+| 1.5846        | 10.0    | 865  | 0.6411          | 0.7734 | 0.0000 |
+| 1.5846        | 10.9942 | 951  | 0.6020          | 0.7822 | 0.0000 |
+| 0.7489        | 12.0    | 1038 | 0.5470          | 0.8157 | 0.0000 |
+| 0.7489        | 12.9942 | 1124 | 0.5161          | 0.8299 | 0.0000 |
+| 0.7489        | 14.0    | 1211 | 0.4952          | 0.8454 | 0.0000 |
+| 0.7489        | 14.9942 | 1297 | 0.4768          | 0.8518 | 0.0000 |
+| 0.7489        | 16.0    | 1384 | 0.4664          | 0.8546 | 0.0000 |
+| 0.7489        | 16.9942 | 1470 | 0.4665          | 0.8565 | 0.0000 |
+| 0.3329        | 18.0    | 1557 | 0.4561          | 0.8591 | 5e-07  |
+| 0.3329        | 18.9942 | 1643 | 0.4578          | 0.8585 | 1e-07  |
+| 0.3329        | 19.8844 | 1720 | 0.4579          | 0.8584 | 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 +1,43 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased-finetuned-sst-2-english",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "sst-2",
+  "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,
+  "output_past": true,
+  "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:a93da260d1e57d91a56faedd95d59b863ca045aff6be3cabf3981b111efa2755
+size 267844872

runs/Nov08_05-34-33_df5724cfcafd/events.out.tfevents.1731044080.df5724cfcafd.191.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a040c481a39fd5c31ae0f44bb58346b1fecfe742bc6deaa2d63557895d0d117
+size 13982

runs/Nov08_05-34-33_df5724cfcafd/events.out.tfevents.1731045669.df5724cfcafd.191.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c093d45261b5da0df0b1f338f7d48d8d88b7ce03ce5c37debfc0adecf9aa312
+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 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "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 sha256:92212ad59d6f673b54162f640cd5b3ea4fd32242956e65856a5b7185a56b13e7
+size 5304