Saving model gmra_cardiffnlp/twitter-roberta-base-sentiment-latest_12112024T120259

README.md

@@ -0,0 +1,94 @@
+---
+library_name: transformers
+base_model: cardiffnlp/twitter-roberta-base-sentiment-latest
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: twitter-roberta-base-sentiment-latest_12112024T120259
+  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. -->
+
+# twitter-roberta-base-sentiment-latest_12112024T120259
+
+This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-sentiment-latest](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment-latest) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4912
+- F1: 0.8803
+- 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: 30
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | F1     | Rate   |
+|:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
+| No log        | 0.9942  | 86   | 1.7812          | 0.1230 | 0.0000 |
+| No log        | 2.0     | 173  | 1.6480          | 0.3596 | 0.0000 |
+| No log        | 2.9942  | 259  | 1.3462          | 0.4748 | 0.0000 |
+| No log        | 4.0     | 346  | 1.1145          | 0.5480 | 0.0000 |
+| No log        | 4.9942  | 432  | 0.9935          | 0.5877 | 0.0000 |
+| 1.3977        | 6.0     | 519  | 0.9023          | 0.6390 | 0.0000 |
+| 1.3977        | 6.9942  | 605  | 0.8538          | 0.6798 | 1e-05  |
+| 1.3977        | 8.0     | 692  | 0.7381          | 0.7388 | 1e-05  |
+| 1.3977        | 8.9942  | 778  | 0.6558          | 0.7696 | 0.0000 |
+| 1.3977        | 10.0    | 865  | 0.6072          | 0.7963 | 0.0000 |
+| 1.3977        | 10.9942 | 951  | 0.5771          | 0.8139 | 0.0000 |
+| 0.6178        | 12.0    | 1038 | 0.5692          | 0.8270 | 0.0000 |
+| 0.6178        | 12.9942 | 1124 | 0.5208          | 0.8513 | 0.0000 |
+| 0.6178        | 14.0    | 1211 | 0.5416          | 0.8487 | 0.0000 |
+| 0.6178        | 14.9942 | 1297 | 0.5073          | 0.8655 | 0.0000 |
+| 0.6178        | 16.0    | 1384 | 0.5052          | 0.8740 | 0.0000 |
+| 0.6178        | 16.9942 | 1470 | 0.4912          | 0.8803 | 6e-06  |
+| 0.2205        | 18.0    | 1557 | 0.5557          | 0.8700 | 0.0000 |
+| 0.2205        | 18.9942 | 1643 | 0.5021          | 0.8845 | 0.0000 |
+| 0.2205        | 20.0    | 1730 | 0.5382          | 0.8837 | 0.0000 |
+| 0.2205        | 20.9942 | 1816 | 0.6147          | 0.8730 | 0.0000 |
+| 0.2205        | 22.0    | 1903 | 0.5978          | 0.8762 | 0.0000 |
+| 0.2205        | 22.9942 | 1989 | 0.6037          | 0.8756 | 0.0000 |
+| 0.0833        | 24.0    | 2076 | 0.6226          | 0.8755 | 0.0000 |
+| 0.0833        | 24.9942 | 2162 | 0.6136          | 0.8777 | 0.0000 |
+| 0.0833        | 26.0    | 2249 | 0.5938          | 0.8815 | 7e-07  |
+| 0.0833        | 26.9942 | 2335 | 0.6318          | 0.8766 | 4e-07  |
+| 0.0833        | 28.0    | 2422 | 0.6302          | 0.8783 | 2e-07  |
+| 0.0462        | 28.9942 | 2508 | 0.6325          | 0.8777 | 0.0    |
+| 0.0462        | 29.8266 | 2580 | 0.6322          | 0.8777 | 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 +1,45 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-roberta-base-sentiment-latest",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "acknowledgement",
+    "1": "change_request",
+    "2": "critical",
+    "3": "discussion_participation",
+    "4": "discussion_trigger",
+    "5": "reference"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "acknowledgement": 0,
+    "change_request": 1,
+    "critical": 2,
+    "discussion_participation": 3,
+    "discussion_trigger": 4,
+    "reference": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ef049698bc3cecd1e563b8e219d7e07643cdf39bc992d523661a4f8f9ecfd82
+size 498625128

runs/Nov12_06-32-59_3a042ea2665a/events.out.tfevents.1731393188.3a042ea2665a.662.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77b4a6300ffaaa23393b55b25a4ee0c495f5110614d4fb0fa53a04b07612fa9d
+size 18255

runs/Nov12_06-32-59_3a042ea2665a/events.out.tfevents.1731394658.3a042ea2665a.662.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:936226543b764a0c26930a3360983dff1ac4e6ce02522647b2d963d4825fa583
+size 463

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8744522d493a533d5b8b27147ed6a0f294c1766908987d4550067c0516c8490c
+size 5304