End of training

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+base_model: facebook/bart-base
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- accuracy
+model-index:
+- name: bart_cause_classifier
+  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. -->
+
+# bart_cause_classifier
+
+This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2310
+- F1: 0.8139
+- Accuracy: 0.4022
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
+| No log        | 1.0   | 62   | 0.2882          | 0.7066 | 0.0444   |
+| No log        | 2.0   | 124  | 0.2538          | 0.7585 | 0.1643   |
+| No log        | 3.0   | 186  | 0.2338          | 0.7840 | 0.2581   |
+| No log        | 4.0   | 248  | 0.2202          | 0.8000 | 0.2954   |
+| No log        | 5.0   | 310  | 0.2218          | 0.7997 | 0.3306   |
+| No log        | 6.0   | 372  | 0.2146          | 0.8093 | 0.3488   |
+| No log        | 7.0   | 434  | 0.2157          | 0.8073 | 0.3498   |
+| No log        | 8.0   | 496  | 0.2146          | 0.8089 | 0.3629   |
+| 0.227         | 9.0   | 558  | 0.2223          | 0.8086 | 0.3972   |
+| 0.227         | 10.0  | 620  | 0.2215          | 0.8088 | 0.3639   |
+| 0.227         | 11.0  | 682  | 0.2191          | 0.8160 | 0.3982   |
+| 0.227         | 12.0  | 744  | 0.2227          | 0.8119 | 0.3821   |
+| 0.227         | 13.0  | 806  | 0.2293          | 0.8070 | 0.3790   |
+| 0.227         | 14.0  | 868  | 0.2310          | 0.8089 | 0.3780   |
+| 0.227         | 15.0  | 930  | 0.2267          | 0.8125 | 0.3982   |
+| 0.227         | 16.0  | 992  | 0.2275          | 0.8116 | 0.3851   |
+| 0.1282        | 17.0  | 1054 | 0.2289          | 0.8150 | 0.4052   |
+| 0.1282        | 18.0  | 1116 | 0.2320          | 0.8106 | 0.3891   |
+| 0.1282        | 19.0  | 1178 | 0.2321          | 0.8114 | 0.3942   |
+| 0.1282        | 20.0  | 1240 | 0.2310          | 0.8139 | 0.4022   |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 1.13.1+cu117
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,104 @@
+{
+  "_name_or_path": "facebook/bart-base",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "overall_complaint_0",
+    "1": "overall_complaint_1",
+    "2": "Complaint_Accusation",
+    "3": "Complaint_Blame",
+    "4": "Complaint_Disapproval",
+    "5": "Complaint_No explicit reproach",
+    "6": "Complaint_Non-Complaint",
+    "7": "Sentiment_negative",
+    "8": "Sentiment_neutral",
+    "9": "Sentiment_positive",
+    "10": "Emotion_anger",
+    "11": "Emotion_disgust",
+    "12": "Emotion_fear",
+    "13": "Emotion_happiness",
+    "14": "Emotion_other",
+    "15": "Emotion_sadness",
+    "16": "Emotion_surprise"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "Complaint_Accusation": 2,
+    "Complaint_Blame": 3,
+    "Complaint_Disapproval": 4,
+    "Complaint_No explicit reproach": 5,
+    "Complaint_Non-Complaint": 6,
+    "Emotion_anger": 10,
+    "Emotion_disgust": 11,
+    "Emotion_fear": 12,
+    "Emotion_happiness": 13,
+    "Emotion_other": 14,
+    "Emotion_sadness": 15,
+    "Emotion_surprise": 16,
+    "Sentiment_negative": 7,
+    "Sentiment_neutral": 8,
+    "Sentiment_positive": 9,
+    "overall_complaint_0": 0,
+    "overall_complaint_1": 1
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "problem_type": "multi_label_classification",
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d68c2a8473cd42d5176e936204c71cf9660095ac42534ee239e1e7eb5147e01a
+size 560126532

runs/Jun18_13-26-46_iit-p/events.out.tfevents.1718697409.iit-p.45260.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa2c23460a4c943e2aaef33de12837b0d1a243750d5779ae2e827674c34c865
+size 14943

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

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": true,
+      "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": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ada4c88c64225c91ba4ef39a05373cbd0d510b059630799d332e92f2beb78b04
+size 4667