iahlt/span-marker-alephbert-small-nemo-mt-he

README.md

@@ -1,93 +1,240 @@
 ---
-language:
-- he
+library_name: span-marker
 tags:
-- language model
-pipeline_tag: feature-extraction
+- span-marker
+- token-classification
+- ner
+- named-entity-recognition
+- generated_from_span_marker_trainer
+datasets:
+- imvladikon/nemo_corpus
+metrics:
+- precision
+- recall
+- f1
+widget:
+- text: אחר כך הצטרף ל דאלאס מאווריקס מ ה אנ.בי.איי ו חזר לשחק ב אירופה ב ספרד ב מדי
+    קאחה בילבאו ו חירונה
+- text: ב קיץ 1982 ניסה טל ברודי (אז עוזר ה מאמן) להחתימו, אבל בריאנט, ש סבתו יהודיה,
+    חתם אז ב פורד קאנטו ו זכה עמ היא ב אותה עונה ב גביע אירופה ל אלופות.
+- text: יו"ר ועדת ה נוער נתן סלובטיק אמר ש ה שחקנים של אנחנו לא משתלבים ב אירופה.
+- text: ב ה סגל ש יתכנס מחר אחר ה צהריים ל מחנה אימונים ב שפיים 17 שחקנים, כולל מוזמן
+    חדש שירן אדירי מ מכבי תל אביב.
+- text: 'תוצאות אחרות: טורינו 2 (מורלו עצמי, מולר) לצה 0; קאליארי 0 לאציו 1 (פסטה,
+    שער עצמי); פיורנטינה 2 (נאפי, פאציונה) גנואה 2 (אורלאנדו, שקוראווי).'
+pipeline_tag: token-classification
+model-index:
+- name: SpanMarker
+  results:
+  - task:
+      type: token-classification
+      name: Named Entity Recognition
+    dataset:
+      name: Unknown
+      type: imvladikon/nemo_corpus
+      split: test
+    metrics:
+    - type: f1
+      value: 0.7338129496402878
+      name: F1
+    - type: precision
+      value: 0.7577142857142857
+      name: Precision
+    - type: recall
+      value: 0.7113733905579399
+      name: Recall
 ---
 
-## AlephBertGimmel
-Modern Hebrew pretrained BERT model with a 128K token vocabulary.
-
-
-[Checkpoint](https://github.com/Dicta-Israel-Center-for-Text-Analysis/alephbertgimmel/tree/main/alephbertgimmel-small/ckpt_29400--Max128Seq) of the alephbertgimmel-small-128 from [alephbertgimmel](https://github.com/Dicta-Israel-Center-for-Text-Analysis/alephbertgimmel)
-
+# SpanMarker
+
+This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model trained on the [imvladikon/nemo_corpus](https://huggingface.co/datasets/imvladikon/nemo_corpus) dataset that can be used for Named Entity Recognition.
+
+## Model Details
+
+### Model Description
+- **Model Type:** SpanMarker
+<!-- - **Encoder:** [Unknown](https://huggingface.co/unknown) -->
+- **Maximum Sequence Length:** 512 tokens
+- **Maximum Entity Length:** 100 words
+- **Training Dataset:** [imvladikon/nemo_corpus](https://huggingface.co/datasets/imvladikon/nemo_corpus)
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Repository:** [SpanMarker on GitHub](https://github.com/tomaarsen/SpanMarkerNER)
+- **Thesis:** [SpanMarker For Named Entity Recognition](https://raw.githubusercontent.com/tomaarsen/SpanMarkerNER/main/thesis.pdf)
+
+### Model Labels
+| Label | Examples                                        |
+|:------|:------------------------------------------------|
+| ANG   | "יידיש", "גרמנית", "אנגלית"                     |
+| DUC   | "דינמיט", "סובארו", "מרצדס"                     |
+| EVE   | "מצדה", "הצהרת בלפור", "ה שואה"                 |
+| FAC   | "ברזילי", "כלא עזה", "תל - ה שומר"              |
+| GPE   | "ה שטחים", "שפרעם", "רצועת עזה"                 |
+| LOC   | "שייח רדואן", "גיבאליה", "חאן יונס"             |
+| ORG   | "כך", "ה ארץ", "מרחב ה גליל"                    |
+| PER   | "רמי רהב", "נימר חוסיין", "איברהים נימר חוסיין" |
+| WOA   | "קיטש ו מוות", "קדיש", "ה ארץ"                  |
+
+## Evaluation
+
+### Metrics
+| Label   | Precision | Recall | F1     |
+|:--------|:----------|:-------|:-------|
+| **all** | 0.7577    | 0.7114 | 0.7338 |
+| ANG     | 0.0       | 0.0    | 0.0    |
+| DUC     | 0.0       | 0.0    | 0.0    |
+| FAC     | 0.0       | 0.0    | 0.0    |
+| GPE     | 0.7085    | 0.8103 | 0.7560 |
+| LOC     | 0.5714    | 0.1951 | 0.2909 |
+| ORG     | 0.7460    | 0.6912 | 0.7176 |
+| PER     | 0.8301    | 0.8052 | 0.8175 |
+| WOA     | 0.0       | 0.0    | 0.0    |
+
+## Uses
+
+### Direct Use for Inference
 
 ```python
-from transformers import AutoTokenizer, AutoModelForMaskedLM
-
-
-import torch
-from transformers import AutoModelForMaskedLM, AutoTokenizer
-
-model = AutoModelForMaskedLM.from_pretrained("imvladikon/alephbertgimmel-small-128")
-tokenizer = AutoTokenizer.from_pretrained("imvladikon/alephbertgimmel-small-128")
-
-text = "{} היא מטרופולין המהווה את מרכז הכלכלה"
-
-input = tokenizer.encode(text.format("[MASK]"), return_tensors="pt")
-mask_token_index = torch.where(input == tokenizer.mask_token_id)[1]
-
-token_logits = model(input).logits
-mask_token_logits = token_logits[0, mask_token_index, :]
-top_5_tokens = torch.topk(mask_token_logits, 5, dim=1).indices[0].tolist()
-
-for token in top_5_tokens:
-    print(text.format(tokenizer.decode([token])))
+from span_marker import SpanMarkerModel
 
-# ישראל היא מטרופולין המהווה את מרכז הכלכלה
-# ירושלים היא מטרופולין המהווה את מרכז הכלכלה
-# חיפה היא מטרופולין המהווה את מרכז הכלכלה
-# אילת היא מטרופולין המהווה את מרכז הכלכלה
-# אשדוד היא מטרופולין המהווה את מרכז הכלכלה
+# Download from the 🤗 Hub
+model = SpanMarkerModel.from_pretrained("span_marker_model_id")
+# Run inference
+entities = model.predict("יו\"ר ועדת ה נוער נתן סלובטיק אמר ש ה שחקנים של אנחנו לא משתלבים ב אירופה.")
 ```
 
-```python 
-def ppl_naive(text, model, tokenizer):
-    input = tokenizer.encode(text, return_tensors="pt")
-    loss = model(input, labels=input)[0]
-    return torch.exp(loss).item()
+### Downstream Use
+You can finetune this model on your own dataset.
 
-text = """{} היא עיר הבירה של מדינת ישראל, והעיר הגדולה ביותר בישראל בגודל האוכלוסייה"""
+<details><summary>Click to expand</summary>
 
-for word in ["חיפה", "ירושלים", "תל אביב"]:
-  print(ppl_naive(text.format(word), model, tokenizer))
-
-# 9.825098991394043
-# 10.594215393066406
-# 9.536449432373047
-
-# I'd expect that for "ירושלים" should be the smallest value, but...
-
-@torch.inference_mode()
-def ppl_pseudo(text, model, tokenizer, ignore_idx=-100):
-    input = tokenizer.encode(text, return_tensors='pt')
-    mask = torch.ones(input.size(-1) - 1).diag(1)[:-2]
-    repeat_input = input.repeat(input.size(-1) - 2, 1)
-    input = repeat_input.masked_fill(mask == 1, tokenizer.mask_token_id)
-    labels = repeat_input.masked_fill(input != tokenizer.mask_token_id, ignore_idx)
-    loss = model(input, labels=labels)[0]
-    return torch.exp(loss).item()
+```python
+from span_marker import SpanMarkerModel, Trainer
+
+# Download from the 🤗 Hub
+model = SpanMarkerModel.from_pretrained("span_marker_model_id")
+
+# Specify a Dataset with "tokens" and "ner_tag" columns
+dataset = load_dataset("conll2003") # For example CoNLL2003
+
+# Initialize a Trainer using the pretrained model & dataset
+trainer = Trainer(
+    model=model,
+    train_dataset=dataset["train"],
+    eval_dataset=dataset["validation"],
+)
+trainer.train()
+trainer.save_model("span_marker_model_id-finetuned")
+```
+</details>
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Set Metrics
+| Training set          | Min | Median  | Max |
+|:----------------------|:----|:--------|:----|
+| Sentence length       | 1   | 25.4427 | 117 |
+| Entities per sentence | 0   | 1.2472  | 20  |
+
+### Training Hyperparameters
+- learning_rate: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training Results
+| Epoch  | Step | Validation Loss | Validation Precision | Validation Recall | Validation F1 | Validation Accuracy |
+|:------:|:----:|:---------------:|:--------------------:|:-----------------:|:-------------:|:-------------------:|
+| 0.4070 | 1000 | 0.0352          | 0.0                  | 0.0               | 0.0           | 0.8980              |
+| 0.8140 | 2000 | 0.0327          | 0.0                  | 0.0               | 0.0           | 0.8980              |
+| 1.2210 | 3000 | 0.0224          | 0.0                  | 0.0               | 0.0           | 0.8980              |
+| 1.6280 | 4000 | 0.0149          | 0.5874               | 0.2200            | 0.3201        | 0.9134              |
+| 2.0350 | 5000 | 0.0137          | 0.55                 | 0.3895            | 0.4560        | 0.9248              |
+| 2.4420 | 6000 | 0.0113          | 0.6204               | 0.4313            | 0.5089        | 0.9298              |
+| 2.8490 | 7000 | 0.0121          | 0.5733               | 0.5075            | 0.5384        | 0.9310              |
+| 3.2560 | 8000 | 0.0115          | 0.5782               | 0.5236            | 0.5495        | 0.9334              |
+| 3.6630 | 9000 | 0.0108          | 0.6100               | 0.5354            | 0.5703        | 0.9359              |
+| 0.4070 | 1000 | 0.0103          | 0.6321               | 0.5880            | 0.6092        | 0.9381              |
+| 0.8140 | 2000 | 0.0088          | 0.6968               | 0.6288            | 0.6610        | 0.9471              |
+| 1.2210 | 3000 | 0.0091          | 0.6790               | 0.6695            | 0.6742        | 0.9484              |
+| 1.6280 | 4000 | 0.0086          | 0.6845               | 0.6845            | 0.6845        | 0.9480              |
+| 2.0350 | 5000 | 0.0089          | 0.6802               | 0.6845            | 0.6824        | 0.9492              |
+| 2.4420 | 6000 | 0.0084          | 0.6938               | 0.6953            | 0.6945        | 0.9539              |
+| 2.8490 | 7000 | 0.0088          | 0.6884               | 0.7039            | 0.6960        | 0.9512              |
+| 3.2560 | 8000 | 0.0086          | 0.6895               | 0.7124            | 0.7008        | 0.9514              |
+| 3.6630 | 9000 | 0.0082          | 0.6989               | 0.7049            | 0.7019        | 0.9526              |
+| 0.4070 | 1000 | 0.0080          | 0.7109               | 0.7124            | 0.7117        | 0.9535              |
+| 0.8140 | 2000 | 0.0074          | 0.7577               | 0.7114            | 0.7338        | 0.9567              |
+| 1.2210 | 3000 | 0.0083          | 0.7183               | 0.7414            | 0.7297        | 0.9554              |
+| 1.6280 | 4000 | 0.0088          | 0.6987               | 0.7339            | 0.7159        | 0.9510              |
+| 2.0350 | 5000 | 0.0086          | 0.7135               | 0.7296            | 0.7215        | 0.9541              |
+| 2.4420 | 6000 | 0.0086          | 0.7167               | 0.7382            | 0.7273        | 0.9559              |
+| 2.8490 | 7000 | 0.0088          | 0.7133               | 0.7554            | 0.7337        | 0.9541              |
+| 3.2560 | 8000 | 0.0085          | 0.7165               | 0.7511            | 0.7334        | 0.9551              |
+| 3.6630 | 9000 | 0.0083          | 0.7263               | 0.7489            | 0.7375        | 0.9561              |
+
+### Framework Versions
+- Python: 3.10.12
+- SpanMarker: 1.5.0
+- Transformers: 4.35.2
+- PyTorch: 2.1.0+cu118
+- Datasets: 2.15.0
+- Tokenizers: 0.15.0
+
+## Citation
+
+### BibTeX
+```
+@software{Aarsen_SpanMarker,
+    author = {Aarsen, Tom},
+    license = {Apache-2.0},
+    title = {{SpanMarker for Named Entity Recognition}},
+    url = {https://github.com/tomaarsen/SpanMarkerNER}
+}
+```
 
+<!--
+## Glossary
 
-for word in ["חיפה", "ירושלים", "תל אביב"]:
-    print(ppl_pseudo(text.format(word), model, tokenizer))
-# 4.346900939941406
-# 3.292382001876831
-# 2.732590913772583
-```
+*Clearly define terms in order to be accessible across audiences.*
+-->
 
-When using AlephBertGimmel, please reference:
+<!--
+## Model Card Authors
 
-```bibtex
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
 
-@misc{guetta2022large,
-      title={Large Pre-Trained Models with Extra-Large Vocabularies: A Contrastive Analysis of Hebrew BERT Models and a New One to Outperform Them All}, 
-      author={Eylon Guetta and Avi Shmidman and Shaltiel Shmidman and Cheyn Shmuel Shmidman and Joshua Guedalia and Moshe Koppel and Dan Bareket and Amit Seker and Reut Tsarfaty},
-      year={2022},
-      eprint={2211.15199},
-      archivePrefix={arXiv},
-      primaryClass={cs.CL}
-}
+<!--
+## Model Card Contact
 
-```
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<end>": 128001,
+  "<start>": 128000
+}

config.json

@@ -1,25 +1,231 @@
 {
-  "_name_or_path": "/content/alephbertgimmel/alephbertgimmel-small/ckpt_29400--Max128Seq",
   "architectures": [
-    "BertModel"
+    "SpanMarkerModel"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 512,
-  "initializer_range": 0.02,
-  "intermediate_size": 2048,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 4,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "encoder": {
+    "_name_or_path": "imvladikon/alephbertgimmel-small-128",
+    "add_cross_attention": false,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 512,
+    "id2label": {
+      "0": "S-ANG",
+      "1": "B-ANG",
+      "2": "I-ANG",
+      "3": "E-ANG",
+      "4": "S-DUC",
+      "5": "B-DUC",
+      "6": "I-DUC",
+      "7": "E-DUC",
+      "8": "B-EVE",
+      "9": "E-EVE",
+      "10": "S-EVE",
+      "11": "I-EVE",
+      "12": "S-FAC",
+      "13": "B-FAC",
+      "14": "E-FAC",
+      "15": "I-FAC",
+      "16": "S-GPE",
+      "17": "B-GPE",
+      "18": "E-GPE",
+      "19": "I-GPE",
+      "20": "S-LOC",
+      "21": "B-LOC",
+      "22": "E-LOC",
+      "23": "I-LOC",
+      "24": "O",
+      "25": "S-ORG",
+      "26": "B-ORG",
+      "27": "E-ORG",
+      "28": "I-ORG",
+      "29": "B-PER",
+      "30": "I-PER",
+      "31": "E-PER",
+      "32": "S-PER",
+      "33": "B-WOA",
+      "34": "E-WOA",
+      "35": "I-WOA",
+      "36": "S-WOA"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "B-ANG": 1,
+      "B-DUC": 5,
+      "B-EVE": 8,
+      "B-FAC": 13,
+      "B-GPE": 17,
+      "B-LOC": 21,
+      "B-ORG": 26,
+      "B-PER": 29,
+      "B-WOA": 33,
+      "E-ANG": 3,
+      "E-DUC": 7,
+      "E-EVE": 9,
+      "E-FAC": 14,
+      "E-GPE": 18,
+      "E-LOC": 22,
+      "E-ORG": 27,
+      "E-PER": 31,
+      "E-WOA": 34,
+      "I-ANG": 2,
+      "I-DUC": 6,
+      "I-EVE": 11,
+      "I-FAC": 15,
+      "I-GPE": 19,
+      "I-LOC": 23,
+      "I-ORG": 28,
+      "I-PER": 30,
+      "I-WOA": 35,
+      "O": 24,
+      "S-ANG": 0,
+      "S-DUC": 4,
+      "S-EVE": 10,
+      "S-FAC": 12,
+      "S-GPE": 16,
+      "S-LOC": 20,
+      "S-ORG": 25,
+      "S-PER": 32,
+      "S-WOA": 36
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 8,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "transformers_version": "4.35.2",
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 128008
+  },
+  "entity_max_length": 100,
+  "id2label": {
+    "0": "O",
+    "1": "ANG",
+    "2": "DUC",
+    "3": "EVE",
+    "4": "FAC",
+    "5": "GPE",
+    "6": "LOC",
+    "7": "ORG",
+    "8": "PER",
+    "9": "WOA"
+  },
+  "id2reduced_id": {
+    "0": 1,
+    "1": 1,
+    "2": 1,
+    "3": 1,
+    "4": 2,
+    "5": 2,
+    "6": 2,
+    "7": 2,
+    "8": 3,
+    "9": 3,
+    "10": 3,
+    "11": 3,
+    "12": 4,
+    "13": 4,
+    "14": 4,
+    "15": 4,
+    "16": 5,
+    "17": 5,
+    "18": 5,
+    "19": 5,
+    "20": 6,
+    "21": 6,
+    "22": 6,
+    "23": 6,
+    "24": 0,
+    "25": 7,
+    "26": 7,
+    "27": 7,
+    "28": 7,
+    "29": 8,
+    "30": 8,
+    "31": 8,
+    "32": 8,
+    "33": 9,
+    "34": 9,
+    "35": 9,
+    "36": 9
+  },
+  "label2id": {
+    "ANG": 1,
+    "DUC": 2,
+    "EVE": 3,
+    "FAC": 4,
+    "GPE": 5,
+    "LOC": 6,
+    "O": 0,
+    "ORG": 7,
+    "PER": 8,
+    "WOA": 9
+  },
+  "marker_max_length": 128,
+  "max_next_context": null,
+  "max_prev_context": null,
+  "model_max_length": 512,
+  "model_max_length_default": 512,
+  "model_type": "span-marker",
+  "span_marker_version": "1.5.0",
   "torch_dtype": "float32",
+  "trained_with_document_context": false,
   "transformers_version": "4.35.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 128000
+  "vocab_size": 128008
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3b26e839690ccd14b72f6959e99a39c0d4da600f8cde12639e72825daf2f9c4
-size 314697456
+oid sha256:0921ec8eacb9a71752105455edf2ab73e2500a3e106180fc2cdf0754aa6633aa
+size 314755568

runs/Nov23_23-23-18_25de05a58e1f/events.out.tfevents.1700781874.25de05a58e1f.158.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96310a7617981ee7a98c9e2be884c0fefc9ff76ca72c4e428992d788a8fee9a0
+size 44099

runs/Nov23_23-23-18_25de05a58e1f/events.out.tfevents.1700783199.25de05a58e1f.158.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b59a34a4d7694c50608a11b8e520c2bf1850a0f4102beaea47bd765fcd90bb4a
+size 1096

runs/Nov23_23-23-18_25de05a58e1f/events.out.tfevents.1700784030.25de05a58e1f.158.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99d21bf28512cf124e7bf020803b5cb2db40586af57cc9f7ab630f44512512de
+size 44175

runs/Nov23_23-23-18_25de05a58e1f/events.out.tfevents.1700785412.25de05a58e1f.158.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92a7ee30a4ab77f11210ed6b17eb05026189558960483cdc2cac5a0c7192752a
+size 44175

runs/Nov23_23-23-18_25de05a58e1f/events.out.tfevents.1700786721.25de05a58e1f.158.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:435ec24d374619881085d6d3dc931ff8d3dbc0020e1977189324220d9f2ac72a
+size 1096

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 512
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 3,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,
@@ -47,6 +61,24 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 128000,
+      "content": "<start>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 128001,
+      "content": "<end>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "[UNK]",
@@ -39,14 +40,31 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "128000": {
+      "content": "<start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<end>",
+      "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,
+  "entity_max_length": 100,
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5cd46ec2a8cfe36fcb897224363cd1797644a2c2f91178322ebc1298747396f
+size 4600