Training complete

README.md

@@ -0,0 +1,63 @@
+---
+library_name: transformers
+license: mit
+base_model: FacebookAI/roberta-base
+tags:
+- generated_from_trainer
+model-index:
+- name: RoBERTa-Base-full-finetuned-ner-multi-label
+  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. -->
+
+# RoBERTa-Base-full-finetuned-ner-multi-label
+
+This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0737
+- F1 Micro: 0.7893
+- Precision Micro: 0.8246
+- Recall Micro: 0.7569
+
+## 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
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1 Micro | Precision Micro | Recall Micro |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:------------:|
+| No log        | 1.0   | 105  | 0.0907          | 0.7538   | 0.8856          | 0.6562       |
+| No log        | 2.0   | 210  | 0.0763          | 0.7893   | 0.8398          | 0.7444       |
+| No log        | 3.0   | 315  | 0.0737          | 0.7893   | 0.8246          | 0.7569       |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "FacebookAI/roberta-base",
+  "architectures": [
+    "MultiLabelRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-SUBSTITUTE",
+    "2": "I-SUBSTITUTE",
+    "3": "B-EXPLAIN",
+    "4": "I-EXPLAIN",
+    "5": "B-GENERALIZE",
+    "6": "I-GENERALIZE",
+    "7": "B-EXEMPLIFY",
+    "8": "I-EXEMPLIFY",
+    "9": "B-OMIT",
+    "10": "I-OMIT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-EXEMPLIFY": 7,
+    "B-EXPLAIN": 3,
+    "B-GENERALIZE": 5,
+    "B-OMIT": 9,
+    "B-SUBSTITUTE": 1,
+    "I-EXEMPLIFY": 8,
+    "I-EXPLAIN": 4,
+    "I-GENERALIZE": 6,
+    "I-OMIT": 10,
+    "I-SUBSTITUTE": 2,
+    "O": 0
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "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 sha256:2e0d64a9ad29b8e6fdadc82f15f1e41efc8faadc74e5f3c1963682b718e39e1b
+size 496277924

runs/Sep20_09-22-10_0f0769814cfc/events.out.tfevents.1726824136.0f0769814cfc.1199.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71a82c9049025d342ee87b609501779973ef59a92b31f0a6ac20642b5ba4b8d3
+size 5504

runs/Sep20_09-23-37_0f0769814cfc/events.out.tfevents.1726824232.0f0769814cfc.1199.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd74b2d0ac5da8f2d1b809ee7f3ade08ac1844e43aa6afda6deb7b95d2db9dd2
+size 5504

runs/Sep20_09-33-32_0f0769814cfc/events.out.tfevents.1726824818.0f0769814cfc.1199.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81f87b48594459f6ecd0620c17ddab73d4f8a3dab39820eb7a2acd221351449e
+size 5504

runs/Sep20_09-38-58_0f0769814cfc/events.out.tfevents.1726825156.0f0769814cfc.1199.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:843d877273a46e986ddf3d47a0e0d28c57f84438105e6563cc89a6c6d043eac2
+size 5504

runs/Sep20_09-41-40_0f0769814cfc/events.out.tfevents.1726825308.0f0769814cfc.1199.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:726f8b9ddffdaf4716632a1287610074981fa97d2b7d3b3f0196cce097b895a7
+size 5504

runs/Sep20_09-58-37_0f0769814cfc/events.out.tfevents.1726826325.0f0769814cfc.1199.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcf86d06789aaddcd3dc58b02bacbdd15fd6a71c1558c07c98aed36f2149a75c
+size 5504

runs/Sep20_10-02-50_0f0769814cfc/events.out.tfevents.1726826574.0f0769814cfc.1199.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7f02740744582e11df968ad647067d358b925c9a40cb9586b91c98c22707dd2
+size 5504

runs/Sep20_10-12-26_0f0769814cfc/events.out.tfevents.1726827149.0f0769814cfc.1199.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec21fbb57d21e7c0b7a2da35293ce7399aa8fbbd19b7de5c46604eb3f9a50c8
+size 5504

runs/Sep20_10-23-46_0f0769814cfc/events.out.tfevents.1726827830.0f0769814cfc.1199.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63642901ac529cf51f2c01b0fcf2f7fc7ecf249fe5df6ed61e41fa941e0dbcc4
+size 5504

runs/Sep20_10-24-27_0f0769814cfc/events.out.tfevents.1726827871.0f0769814cfc.1199.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c11cab7cad6a464fc6f0d1a436cedc5a7374fbbf2d52a77198ce355f6bb08be
+size 5504

runs/Sep20_10-29-11_0f0769814cfc/events.out.tfevents.1726828153.0f0769814cfc.1199.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc22cc3a8bf59b00fbda6008ba86b5eb3db3b6a7e4e477ddee01113713377eb0
+size 5504

runs/Sep20_10-32-00_0f0769814cfc/events.out.tfevents.1726828322.0f0769814cfc.1199.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2879df2c94f5cfbbd17e3578e209054883802527d51d6af56f07aaa829437b9
+size 7164

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": true,
+  "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>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceabcd6d003515dd7be2f40085244723ad68ddd6c18b5fc0a0b93b4307ebcbef
+size 5240