dandankim/token_classifier2

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: distilbert-base-uncased
+license: mit
+base_model: FacebookAI/roberta-base
 tags:
 - generated_from_trainer
 metrics:
@@ -19,13 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilbert-token-classifier
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
+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: 0.0738
-- Precision: 0.9657
-- Recall: 0.9761
-- F1: 0.9709
-- Accuracy: 0.9845
+- Loss: 0.0728
+- Precision: 0.9694
+- Recall: 0.9767
+- F1: 0.9730
+- Accuracy: 0.9846
 
 ## Model description
 
@@ -44,27 +44,28 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 1e-05
+- train_batch_size: 20
+- eval_batch_size: 20
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.1
+- lr_scheduler_warmup_ratio: 0.2
 - num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.898         | 1.0   | 149  | 0.1613          | 0.8995    | 0.8729 | 0.8860 | 0.9637   |
-| 0.1161        | 2.0   | 298  | 0.0749          | 0.9682    | 0.9501 | 0.9591 | 0.9790   |
-| 0.0717        | 3.0   | 447  | 0.0762          | 0.9723    | 0.9630 | 0.9676 | 0.9814   |
-| 0.0412        | 4.0   | 596  | 0.0661          | 0.9699    | 0.9694 | 0.9697 | 0.9845   |
-| 0.0295        | 5.0   | 745  | 0.0630          | 0.9596    | 0.9739 | 0.9667 | 0.9835   |
-| 0.0262        | 6.0   | 894  | 0.0658          | 0.9696    | 0.9732 | 0.9714 | 0.9851   |
-| 0.0191        | 7.0   | 1043 | 0.0695          | 0.9696    | 0.9707 | 0.9702 | 0.9846   |
-| 0.0165        | 8.0   | 1192 | 0.0738          | 0.9657    | 0.9761 | 0.9709 | 0.9845   |
+| 1.0798        | 1.0   | 119  | 0.5221          | 0.5989    | 0.3881 | 0.4710 | 0.8427   |
+| 0.2561        | 2.0   | 238  | 0.1148          | 0.9162    | 0.9214 | 0.9188 | 0.9716   |
+| 0.0901        | 3.0   | 357  | 0.0863          | 0.9729    | 0.9584 | 0.9656 | 0.9799   |
+| 0.0735        | 4.0   | 476  | 0.0699          | 0.9658    | 0.9701 | 0.9680 | 0.9827   |
+| 0.0528        | 5.0   | 595  | 0.0674          | 0.9545    | 0.9761 | 0.9652 | 0.9831   |
+| 0.0505        | 6.0   | 714  | 0.0659          | 0.9689    | 0.9757 | 0.9723 | 0.9841   |
+| 0.0394        | 7.0   | 833  | 0.0696          | 0.9633    | 0.9771 | 0.9701 | 0.9839   |
+| 0.0278        | 8.0   | 952  | 0.0728          | 0.9640    | 0.9772 | 0.9706 | 0.9837   |
+| 0.0241        | 9.0   | 1071 | 0.0728          | 0.9694    | 0.9767 | 0.9730 | 0.9846   |
 
 
 ### Framework versions

config.json

@@ -1,13 +1,15 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "FacebookAI/roberta-base",
   "architectures": [
-    "DistilBertForTokenClassification"
+    "RobertaForTokenClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "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-BASE_TOKEN",
@@ -28,6 +30,7 @@
     "16": "I-LEVERAGE"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "B-ACTION": 5,
     "B-BASE_TOKEN": 1,
@@ -47,16 +50,16 @@
     "I-TARGET_SELL_PRICE": 10,
     "O": 0
   },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "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": "4.48.3",
-  "vocab_size": 30522
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b21e75c082fe70716c9e78e7ac9075627dd6dcc9c27b08c05ece728bd4287d78
-size 265516156
+oid sha256:bbabdbdc4ff986f2b2cc36998af941e433cdbd5cce644f6a494fd47a325dc7ed
+size 496296380

runs/Feb27_13-41-58_db74930b30d9/events.out.tfevents.1740663720.db74930b30d9.911.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02c804e0537ffbb3c81d2e9fe51e5c9b398a83cc59c673b7dc69e39b5da30830
+size 6268

runs/Feb27_13-44-28_db74930b30d9/events.out.tfevents.1740663868.db74930b30d9.911.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1378fe2a31bcb98abc09af566e6e27d6130abae04527a11fc01eb612d80ceda
+size 13724

runs/Feb27_13-54-15_db74930b30d9/events.out.tfevents.1740664455.db74930b30d9.911.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:693334c44f3bc157cc75601cba18bf98c0b9c0b9c24637a9f57501700f513f0c
+size 10871

runs/Feb27_13-56-26_db74930b30d9/events.out.tfevents.1740664586.db74930b30d9.911.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b22b62145da73f857f38e570743a01edbe1eafb748c5cb1eb82d24f44ce2a6f3
+size 13976

runs/Feb27_13-58-49_db74930b30d9/events.out.tfevents.1740664729.db74930b30d9.911.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee1b259c4e382f83d580fc207bf01eee4e3edf7e34e75aacbf233c4c61613b4d
+size 7154

runs/Feb27_13-59-45_db74930b30d9/events.out.tfevents.1740664786.db74930b30d9.911.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52ce82e251f839e376efe66569d3ace925bffb3340a39eba6391557b456c844c
+size 14871

runs/Feb27_14-04-10_db74930b30d9/events.out.tfevents.1740665051.db74930b30d9.911.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4479d29a5c8d62f7e9e16369c48f1e63bc4bb2d71e1dd4a0595f14f66f4bf8d
+size 16540

runs/Feb27_14-12-12_db74930b30d9/events.out.tfevents.1740665532.db74930b30d9.911.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:933617470ce9c5c109b22a0e2d9eae51ee436803c1e447d1e44a5e344b98613b
+size 9756

runs/Feb27_14-14-07_db74930b30d9/events.out.tfevents.1740665648.db74930b30d9.911.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34bc05bfb5bd99c99855eb6cb6087bc31d2c3ca5187689c184380fca18bc35ea
+size 15002

special_tokens_map.json

@@ -1,7 +1,15 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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

@@ -1,56 +1,58 @@
 {
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
   "extra_special_tokens": {},
-  "mask_token": "[MASK]",
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7787e2f7d843089369530f9da3cbba46eb271f002f6deb2d26ddbced101d2372
+oid sha256:8a6647940cf51d5452e3002f44c907fd51093c4f0d0208669a7d09ee4aa86113
 size 5368