End of training

README.md

@@ -0,0 +1,67 @@
+---
+base_model: finiteautomata/bertweet-base-sentiment-analysis
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: bertweet-olid
+  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. -->
+
+# bertweet-olid
+
+This model is a fine-tuned version of [finiteautomata/bertweet-base-sentiment-analysis](https://huggingface.co/finiteautomata/bertweet-base-sentiment-analysis) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0303
+- Accuracy: 0.8104
+- F1: 0.8082
+
+## 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: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| 0.3675        | 1.0   | 774  | 0.4257          | 0.8233   | 0.8217 |
+| 0.3006        | 2.0   | 1548 | 0.3651          | 0.8385   | 0.8383 |
+| 0.2461        | 3.0   | 2322 | 0.4812          | 0.8301   | 0.8298 |
+| 0.202         | 4.0   | 3096 | 0.6835          | 0.8324   | 0.8324 |
+| 0.1533        | 5.0   | 3870 | 1.0303          | 0.8104   | 0.8082 |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "finiteautomata/bertweet-base-sentiment-analysis",
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 130,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "BertweetTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b4ec2fb849edc666f93abb9d515d3d142abf899171aa856da855edc57cb91e1
+size 539630168

runs/Mar05_13-14-40_34334bcdfcbe/events.out.tfevents.1709644488.34334bcdfcbe.1172.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:592bb7b9c69baf5c7ab95b3fb68deb0485eac92ebfc3ba01d165c73ec5b5ee48
+size 12378

runs/Mar05_13-25-09_34334bcdfcbe/events.out.tfevents.1709645177.34334bcdfcbe.1172.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c22005787dacf626a67341021684cfe740b7a9b4fdeb9c6af36c22d55e901f
+size 14973

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tmp-checkpoint-3042/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

tmp-checkpoint-3042/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "finiteautomata/bertweet-base-sentiment-analysis",
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 130,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "BertweetTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

tmp-checkpoint-3042/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34d12a1d3e172c900db1557491bd3756bc1339a4219e2ff4cc90f307e4e781ae
+size 539630168

tmp-checkpoint-3042/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4854bf6136216469343fd822e1089289e8ad47c108f68c7e50fed717b5b1f278
+size 582702423

tmp-checkpoint-3042/special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tmp-checkpoint-3042/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 128,
+  "normalization": false,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BertweetTokenizer",
+  "unk_token": "<unk>"
+}

tmp-checkpoint-3042/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fb1ed0a390004ca7057ed3ef8c28d0ba44446f9b3923847000b0ad417af1d0d
+size 4920

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 128,
+  "normalization": false,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BertweetTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42b9f793c5ef7507e2a4c886de0dfdd11afdece09eb3681058c7da9d9c640e7c
+size 4920