End of training

README.md

@@ -0,0 +1,72 @@
+---
+base_model: dianamihalache27/Twroberta-baseB_5epoch
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: ceva
+  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. -->
+
+# ceva
+
+This model is a fine-tuned version of [dianamihalache27/Twroberta-baseB_5epoch](https://huggingface.co/dianamihalache27/Twroberta-baseB_5epoch) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1932
+- Accuracy: 0.7714
+- F1: 0.2892
+- Precision: 0.2435
+- Recall: 0.3579
+- Precision Sarcastic: 0.3372
+- Recall Sarcastic: 0.4833
+- F1 Sarcastic: 0.3973
+
+## 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- 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     | Precision | Recall | Precision Sarcastic | Recall Sarcastic | F1 Sarcastic |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:-------------------:|:----------------:|:------------:|
+| No log        | 1.0   | 217  | 0.1618          | 0.7893   | 0.2947 | 0.2611    | 0.3395 | 0.3458              | 0.4611           | 0.3952       |
+| No log        | 2.0   | 434  | 0.1815          | 0.7629   | 0.3104 | 0.2560    | 0.4059 | 0.3299              | 0.5278           | 0.4060       |
+| 0.0559        | 3.0   | 651  | 0.1762          | 0.8      | 0.2957 | 0.2991    | 0.3173 | 0.3721              | 0.4444           | 0.4051       |
+| 0.0559        | 4.0   | 868  | 0.1811          | 0.7636   | 0.2933 | 0.2418    | 0.3727 | 0.3297              | 0.5111           | 0.4009       |
+| 0.0245        | 5.0   | 1085 | 0.1932          | 0.7714   | 0.2892 | 0.2435    | 0.3579 | 0.3372              | 0.4833           | 0.3973       |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "dianamihalache27/Twroberta-baseB_5epoch",
+  "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": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 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": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "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 sha256:46b85c26a6fd0dc7be42cd86e7fa6642470a0e40114856eec188aa729a912b2f
+size 498625128

runs/Jun12_16-30-36_df49488af18c/events.out.tfevents.1718209836.df49488af18c.2184.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28f9d907a1b9542c13ea69bf02043dc46a4f7cb95e30f79beccefa6b38488eaa
+size 9231

runs/Jun12_16-30-36_df49488af18c/events.out.tfevents.1718210857.df49488af18c.2184.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3e81b036dbf0308cb36bce321d1666aad4ef91f018cb22900653ed867b9cc96
+size 739

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 +1,64 @@
+{
+  "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>",
+  "max_length": 128,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:662ef7fc8e248d81c4d6b2de99904aad5f6640a0ba8a2b75f49c8ce1dbb852a9
+size 5048