End of training

README.md

@@ -0,0 +1,57 @@
+---
+license: mit
+base_model: microsoft/deberta-base
+tags:
+- generated_from_trainer
+datasets:
+- events_classification_biotech
+model-index:
+- name: my_awesome_model
+  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. -->
+
+# my_awesome_model
+
+This model is a fine-tuned version of [microsoft/deberta-base](https://huggingface.co/microsoft/deberta-base) on the events_classification_biotech dataset.
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 0.01
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| No log        | 0.01  | 28   | 0.5194          | 0.9395   | 0.0029 | 0.0263    | 0.0015 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,97 @@
+{
+  "_name_or_path": "microsoft/deberta-base",
+  "architectures": [
+    "DebertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "event organization",
+    "1": "executive statement",
+    "2": "regulatory approval",
+    "3": "hiring",
+    "4": "foundation",
+    "5": "closing",
+    "6": "partnerships & alliances",
+    "7": "expanding industry",
+    "8": "new initiatives or programs",
+    "9": "m&a",
+    "10": "service & product providing",
+    "11": "event organisation",
+    "12": "new initiatives & programs",
+    "13": "subsidiary establishment",
+    "14": "product launching & presentation",
+    "15": "product updates",
+    "16": "executive appointment",
+    "17": "alliance & partnership",
+    "18": "ipo exit",
+    "19": "article publication",
+    "20": "clinical trial sponsorship",
+    "21": "company description",
+    "22": "investment in public company",
+    "23": "other",
+    "24": "expanding geography",
+    "25": "participation in an event",
+    "26": "support & philanthropy",
+    "27": "department establishment",
+    "28": "funding round",
+    "29": "patent publication"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "alliance & partnership": 17,
+    "article publication": 19,
+    "clinical trial sponsorship": 20,
+    "closing": 5,
+    "company description": 21,
+    "department establishment": 27,
+    "event organisation": 11,
+    "event organization": 0,
+    "executive appointment": 16,
+    "executive statement": 1,
+    "expanding geography": 24,
+    "expanding industry": 7,
+    "foundation": 4,
+    "funding round": 28,
+    "hiring": 3,
+    "investment in public company": 22,
+    "ipo exit": 18,
+    "m&a": 9,
+    "new initiatives & programs": 12,
+    "new initiatives or programs": 8,
+    "other": 23,
+    "participation in an event": 25,
+    "partnerships & alliances": 6,
+    "patent publication": 29,
+    "product launching & presentation": 14,
+    "product updates": 15,
+    "regulatory approval": 2,
+    "service & product providing": 10,
+    "subsidiary establishment": 13,
+    "support & philanthropy": 26
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "c2p",
+    "p2c"
+  ],
+  "position_biased_input": false,
+  "problem_type": "multi_label_classification",
+  "relative_attention": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 0,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:821d3339998a94528d6acb9206b0918b76d77791c0d3cbe8da6cf310306ae255
+size 556885696

runs/Mar07_17-26-02_085af4cb2a87/events.out.tfevents.1709832363.085af4cb2a87.1732.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3fce51e58087565ef7b497ed05c5c044e99f727d5366e27e91622ad645490e1
+size 7400

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "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
+    },
+    "50264": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "errors": "replace",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "DebertaTokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "gpt2"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e9497a819483e3a0711f0d98d4d70bcb2d4dc730a2569e77a1850f0e9d044ca
+size 4920