Saving model gmra_cardiffnlp/twitter-roberta-base-sentiment-latest_12112024T123630

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_12112024T123630
+  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_12112024T123630
+
+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: 0.5160
+- F1: 0.8689
+- 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: 8
+- total_train_batch_size: 64
+- 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  | 43   | 1.7742          | 0.1656 | 7e-07  |
+| No log        | 1.9884  | 86   | 1.7368          | 0.2208 | 0.0000 |
+| No log        | 2.9827  | 129  | 1.6531          | 0.3182 | 0.0000 |
+| No log        | 4.0     | 173  | 1.5111          | 0.4169 | 0.0000 |
+| No log        | 4.9942  | 216  | 1.3427          | 0.4913 | 0.0000 |
+| No log        | 5.9884  | 259  | 1.1750          | 0.5379 | 0.0000 |
+| No log        | 6.9827  | 302  | 1.0970          | 0.5486 | 5e-06  |
+| No log        | 8.0     | 346  | 1.0081          | 0.5856 | 0.0000 |
+| No log        | 8.9942  | 389  | 0.9728          | 0.5991 | 0.0000 |
+| No log        | 9.9884  | 432  | 0.9005          | 0.6481 | 0.0000 |
+| No log        | 10.9827 | 475  | 0.8614          | 0.6640 | 0.0000 |
+| 1.2671        | 12.0    | 519  | 0.7905          | 0.7202 | 0.0000 |
+| 1.2671        | 12.9942 | 562  | 0.7560          | 0.7367 | 0.0000 |
+| 1.2671        | 13.9884 | 605  | 0.7399          | 0.7421 | 1e-05  |
+| 1.2671        | 14.9827 | 648  | 0.6596          | 0.7804 | 0.0000 |
+| 1.2671        | 16.0    | 692  | 0.6331          | 0.7966 | 0.0000 |
+| 1.2671        | 16.9942 | 735  | 0.6272          | 0.7994 | 0.0000 |
+| 1.2671        | 17.9884 | 778  | 0.5878          | 0.8249 | 0.0000 |
+| 1.2671        | 18.9827 | 821  | 0.5564          | 0.8386 | 0.0000 |
+| 1.2671        | 20.0    | 865  | 0.5482          | 0.8474 | 0.0000 |
+| 1.2671        | 20.9942 | 908  | 0.5523          | 0.8501 | 0.0000 |
+| 1.2671        | 21.9884 | 951  | 0.5309          | 0.8534 | 0.0000 |
+| 1.2671        | 22.9827 | 994  | 0.5364          | 0.8582 | 4e-06  |
+| 0.4473        | 24.0    | 1038 | 0.5176          | 0.8638 | 3e-06  |
+| 0.4473        | 24.9942 | 1081 | 0.5256          | 0.8663 | 0.0000 |
+| 0.4473        | 25.9884 | 1124 | 0.5182          | 0.8691 | 0.0000 |
+| 0.4473        | 26.9827 | 1167 | 0.5237          | 0.8680 | 8e-07  |
+| 0.4473        | 28.0    | 1211 | 0.5160          | 0.8689 | 3e-07  |
+| 0.4473        | 28.9942 | 1254 | 0.5216          | 0.8673 | 1e-07  |
+| 0.4473        | 29.8266 | 1290 | 0.5220          | 0.8670 | 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 sha256:28131c85930aa420055f5c666ef8959d3fa36914d58ff7477a64d35e78218665
+size 498625128

runs/Nov12_07-06-30_d87dcbccfa8e/events.out.tfevents.1731395198.d87dcbccfa8e.618.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dc814f7bc9719d4fc65063fed19631b000ce3d66de348fccb6cc5af2890508e
+size 17615

runs/Nov12_07-06-30_d87dcbccfa8e/events.out.tfevents.1731396584.d87dcbccfa8e.618.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:160b38c00ea224a98b6255555fb2daa9a365bb9dd16b140b146985da2e88c83a
+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:de058e623b11fe85959931a2158bdf8a68bfdc4b4a99bfefc5721982ac41345f
+size 5304