Saving model gmra_distilbert/distilbert-base-uncased-finetuned-sst-2-english_07112024T125645

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_07112024T125645
+  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_07112024T125645
+
+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: 0.5776
+- F1: 0.8426
+- 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   | 141  | 1.1776          | 0.5721 | 0.0000 |
+| No log        | 2.0   | 282  | 0.9785          | 0.6619 | 0.0000 |
+| No log        | 3.0   | 423  | 0.8326          | 0.7194 | 0.0000 |
+| 1.1084        | 4.0   | 564  | 0.6920          | 0.7808 | 0.0000 |
+| 1.1084        | 5.0   | 705  | 0.6907          | 0.7973 | 0.0000 |
+| 1.1084        | 6.0   | 846  | 0.6107          | 0.8284 | 0.0000 |
+| 1.1084        | 7.0   | 987  | 0.5776          | 0.8426 | 0.0000 |
+| 0.4572        | 8.0   | 1128 | 0.6100          | 0.8523 | 0.0000 |
+| 0.4572        | 9.0   | 1269 | 0.6279          | 0.8570 | 0.0000 |
+| 0.4572        | 10.0  | 1410 | 0.6638          | 0.8587 | 0.0000 |
+| 0.1637        | 11.0  | 1551 | 0.7340          | 0.8568 | 0.0000 |
+| 0.1637        | 12.0  | 1692 | 0.7564          | 0.8596 | 7e-06  |
+| 0.1637        | 13.0  | 1833 | 0.8077          | 0.8568 | 0.0000 |
+| 0.1637        | 14.0  | 1974 | 0.7234          | 0.8667 | 0.0000 |
+| 0.069         | 15.0  | 2115 | 0.7535          | 0.8664 | 3e-06  |
+| 0.069         | 16.0  | 2256 | 0.7818          | 0.8659 | 0.0000 |
+| 0.069         | 17.0  | 2397 | 0.8064          | 0.8646 | 0.0000 |
+| 0.0376        | 18.0  | 2538 | 0.8203          | 0.8626 | 5e-07  |
+| 0.0376        | 19.0  | 2679 | 0.8233          | 0.8629 | 1e-07  |
+| 0.0376        | 20.0  | 2820 | 0.8235          | 0.8632 | 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": "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,
+  "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:b9de8c9c1395de9cdfdf2338d6460c3b648815572beb55b5d14efe8663b24f83
+size 267844872

runs/Nov07_07-26-45_4e102b0d102a/events.out.tfevents.1730964414.4e102b0d102a.233.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17ec53ac0d7c7ad7aec582852de8e8b001aaa7787725a7a153b27b7511ac6f2
+size 14411

runs/Nov07_07-26-45_4e102b0d102a/events.out.tfevents.1730967055.4e102b0d102a.233.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:833e139c43c34649e56c11addb387f0c011f7f40e36824fa323bc0c29a70bd85
+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 sha256:5caaf94573ac4b5d29a5ad1f4a88644d5d31ae4251969c6e7b4d7e4cbf4dd96f
+size 5304