Initial Commit

README.md

@@ -0,0 +1,85 @@
+---
+library_name: transformers
+license: mit
+base_model: haryoaw/scenario-TCR-NER_data-univner_half
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: scenario-kd-scr-ner-full-xlmr_data-univner_half55
+  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. -->
+
+# scenario-kd-scr-ner-full-xlmr_data-univner_half55
+
+This model is a fine-tuned version of [haryoaw/scenario-TCR-NER_data-univner_half](https://huggingface.co/haryoaw/scenario-TCR-NER_data-univner_half) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 239.5321
+- Precision: 0.3634
+- Recall: 0.2698
+- F1: 0.3097
+- Accuracy: 0.9371
+
+## 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: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 32
+- seed: 55
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 443.8944      | 0.5828 | 500  | 368.5827        | 1.0       | 0.0003 | 0.0006 | 0.9241   |
+| 344.6514      | 1.1655 | 1000 | 338.3108        | 0.4198    | 0.0238 | 0.0451 | 0.9249   |
+| 317.7911      | 1.7483 | 1500 | 323.1518        | 0.3373    | 0.0781 | 0.1268 | 0.9266   |
+| 295.7283      | 2.3310 | 2000 | 304.1432        | 0.3776    | 0.0879 | 0.1426 | 0.9282   |
+| 279.1692      | 2.9138 | 2500 | 298.1003        | 0.3030    | 0.1619 | 0.2110 | 0.9301   |
+| 265.46        | 3.4965 | 3000 | 283.4411        | 0.3299    | 0.1756 | 0.2292 | 0.9326   |
+| 253.3522      | 4.0793 | 3500 | 276.4803        | 0.3419    | 0.1991 | 0.2517 | 0.9335   |
+| 243.6295      | 4.6620 | 4000 | 268.1132        | 0.3623    | 0.2144 | 0.2694 | 0.9355   |
+| 235.7751      | 5.2448 | 4500 | 260.5050        | 0.3808    | 0.1952 | 0.2581 | 0.9358   |
+| 229.31        | 5.8275 | 5000 | 255.4243        | 0.3822    | 0.2135 | 0.2740 | 0.9358   |
+| 222.7415      | 6.4103 | 5500 | 253.6783        | 0.3210    | 0.2489 | 0.2804 | 0.9345   |
+| 218.7321      | 6.9930 | 6000 | 250.1186        | 0.3372    | 0.2663 | 0.2976 | 0.9354   |
+| 213.8638      | 7.5758 | 6500 | 245.7943        | 0.3533    | 0.2519 | 0.2941 | 0.9362   |
+| 211.1232      | 8.1585 | 7000 | 241.6974        | 0.3942    | 0.2450 | 0.3022 | 0.9382   |
+| 208.2374      | 8.7413 | 7500 | 241.2330        | 0.3854    | 0.2630 | 0.3127 | 0.9375   |
+| 206.2932      | 9.3240 | 8000 | 240.2229        | 0.3769    | 0.2672 | 0.3127 | 0.9373   |
+| 205.5458      | 9.9068 | 8500 | 239.5321        | 0.3634    | 0.2698 | 0.3097 | 0.9371   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.5
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "haryoaw/scenario-TCR-NER_data-univner_half",
+  "architectures": [
+    "XLMRobertaForTokenClassificationKD"
+  ],
+  "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": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "output_past": true,
+  "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": 250002
+}

eval_result_ner.json

@@ -0,0 +1 @@
+{"ceb_gja": {"precision": 0.5172413793103449, "recall": 0.30612244897959184, "f1": 0.38461538461538464, "accuracy": 0.9598455598455599}, "en_pud": {"precision": 0.35255570117955437, "recall": 0.2502325581395349, "f1": 0.2927094668117519, "accuracy": 0.9383264072534945}, "de_pud": {"precision": 0.12743506493506493, "recall": 0.15110683349374399, "f1": 0.13826508146191105, "accuracy": 0.8964417983216915}, "pt_pud": {"precision": 0.2789598108747045, "recall": 0.10737033666969972, "f1": 0.15505913272010513, "accuracy": 0.9329260477634895}, "ru_pud": {"precision": 0.024163568773234202, "recall": 0.012548262548262547, "f1": 0.01651842439644219, "accuracy": 0.893050891242573}, "sv_pud": {"precision": 0.23941068139963168, "recall": 0.12633624878522837, "f1": 0.1653944020356234, "accuracy": 0.9243027888446215}, "tl_trg": {"precision": 0.3, "recall": 0.2608695652173913, "f1": 0.27906976744186046, "accuracy": 0.9618528610354223}, "tl_ugnayan": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.9361896080218779}, "zh_gsd": {"precision": 0.3411764705882353, "recall": 0.18904823989569752, "f1": 0.24328859060402686, "accuracy": 0.9061771561771562}, "zh_gsdsimp": {"precision": 0.3480392156862745, "recall": 0.18610747051114024, "f1": 0.2425277540563621, "accuracy": 0.908008658008658}, "hr_set": {"precision": 0.5507246376811594, "recall": 0.5958660014255167, "f1": 0.5724067100308112, "accuracy": 0.9563066776586975}, "da_ddt": {"precision": 0.2681564245810056, "recall": 0.10738255033557047, "f1": 0.15335463258785942, "accuracy": 0.9395390601616282}, "en_ewt": {"precision": 0.4677777777777778, "recall": 0.3869485294117647, "f1": 0.4235412474849094, "accuracy": 0.9509503127863889}, "pt_bosque": {"precision": 0.1973392461197339, "recall": 0.07325102880658436, "f1": 0.10684273709483794, "accuracy": 0.9245761483842921}, "sr_set": {"precision": 0.5396270396270396, "recall": 0.5466351829988194, "f1": 0.543108504398827, "accuracy": 0.9387093949741704}, "sk_snk": {"precision": 0.17154811715481172, "recall": 0.08961748633879782, "f1": 0.11773151471643936, "accuracy": 0.8871702261306532}, "sv_talbanken": {"precision": 0.11979166666666667, "recall": 0.11734693877551021, "f1": 0.11855670103092784, "accuracy": 0.9813024488393778}}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b65073d7d34211e0691874aaecdea21283b413ed8249b721c60253c70eee119f
+size 939737140

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ac1b3f2f31ca800467c1e7944c686fcaf3762734df6031de411f4599d9667be
+size 5304