Training completed!

README.md

@@ -0,0 +1,78 @@
+---
+base_model: allenai/scibert_scivocab_cased
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: SOMD-train-scibert
+  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. -->
+
+# SOMD-train-scibert
+
+This model is a fine-tuned version of [allenai/scibert_scivocab_cased](https://huggingface.co/allenai/scibert_scivocab_cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0000
+- F1: 1.0
+
+## 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 256
+- 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     |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| No log        | 1.0   | 1243  | 0.0053          | 0.7304 |
+| No log        | 2.0   | 2486  | 0.0029          | 0.8024 |
+| No log        | 3.0   | 3729  | 0.0017          | 0.8700 |
+| No log        | 4.0   | 4972  | 0.0011          | 0.9302 |
+| No log        | 5.0   | 6215  | 0.0010          | 0.9305 |
+| No log        | 6.0   | 7458  | 0.0008          | 0.9545 |
+| No log        | 7.0   | 8701  | 0.0007          | 0.9629 |
+| No log        | 8.0   | 9944  | 0.0004          | 0.9698 |
+| No log        | 9.0   | 11187 | 0.0002          | 0.9854 |
+| No log        | 10.0  | 12430 | 0.0002          | 0.9871 |
+| No log        | 11.0  | 13673 | 0.0002          | 0.9934 |
+| No log        | 12.0  | 14916 | 0.0001          | 0.9898 |
+| No log        | 13.0  | 16159 | 0.0000          | 0.9985 |
+| No log        | 14.0  | 17402 | 0.0001          | 0.9940 |
+| No log        | 15.0  | 18645 | 0.0000          | 0.9986 |
+| No log        | 16.0  | 19888 | 0.0000          | 0.9966 |
+| No log        | 17.0  | 21131 | 0.0000          | 0.9994 |
+| No log        | 18.0  | 22374 | 0.0000          | 1.0    |
+| No log        | 19.0  | 23617 | 0.0000          | 1.0    |
+| No log        | 20.0  | 24860 | 0.0000          | 1.0    |
+
+
+### Framework versions
+
+- Transformers 4.37.0
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,83 @@
+{
+  "_name_or_path": "allenai/scibert_scivocab_cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "I-SoftwareCoreference_Deposition",
+    "2": "I-ProgrammingEnvironment_Usage",
+    "3": "I-ProgrammingEnvironment_Mention",
+    "4": "I-PlugIn_Usage",
+    "5": "I-PlugIn_Mention",
+    "6": "I-PlugIn_Deposition",
+    "7": "I-PlugIn_Creation",
+    "8": "I-OperatingSystem_Usage",
+    "9": "I-OperatingSystem_Mention",
+    "10": "I-Application_Usage",
+    "11": "I-Application_Mention",
+    "12": "I-Application_Deposition",
+    "13": "I-Application_Creation",
+    "14": "B-SoftwareCoreference_Deposition",
+    "15": "B-ProgrammingEnvironment_Usage",
+    "16": "B-ProgrammingEnvironment_Mention",
+    "17": "B-PlugIn_Usage",
+    "18": "B-PlugIn_Mention",
+    "19": "B-PlugIn_Deposition",
+    "20": "B-PlugIn_Creation",
+    "21": "B-OperatingSystem_Usage",
+    "22": "B-OperatingSystem_Mention",
+    "23": "B-Application_Usage",
+    "24": "B-Application_Mention",
+    "25": "B-Application_Deposition",
+    "26": "B-Application_Creation"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Application_Creation": 26,
+    "B-Application_Deposition": 25,
+    "B-Application_Mention": 24,
+    "B-Application_Usage": 23,
+    "B-OperatingSystem_Mention": 22,
+    "B-OperatingSystem_Usage": 21,
+    "B-PlugIn_Creation": 20,
+    "B-PlugIn_Deposition": 19,
+    "B-PlugIn_Mention": 18,
+    "B-PlugIn_Usage": 17,
+    "B-ProgrammingEnvironment_Mention": 16,
+    "B-ProgrammingEnvironment_Usage": 15,
+    "B-SoftwareCoreference_Deposition": 14,
+    "I-Application_Creation": 13,
+    "I-Application_Deposition": 12,
+    "I-Application_Mention": 11,
+    "I-Application_Usage": 10,
+    "I-OperatingSystem_Mention": 9,
+    "I-OperatingSystem_Usage": 8,
+    "I-PlugIn_Creation": 7,
+    "I-PlugIn_Deposition": 6,
+    "I-PlugIn_Mention": 5,
+    "I-PlugIn_Usage": 4,
+    "I-ProgrammingEnvironment_Mention": 3,
+    "I-ProgrammingEnvironment_Usage": 2,
+    "I-SoftwareCoreference_Deposition": 1,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31116
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1bc092fe2de316a3b28faae9207e85ffe5ed2819e0cf69e022647445bcbe107
+size 437497756

runs/Feb25_08-54-51_7a49a71b37c2/events.out.tfevents.1708851334.7a49a71b37c2.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bfbb22417b7f4aea0d050aa229cdf0df7890474f1d8b94c90d68479d915e7af
+size 12928

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cacd1865b6e969c1cb78f3c1171170e422f6a16addc400ef8b6660aaa12aad2
+size 4728