Training in progress, step 20000

README.md

@@ -1,462 +1,95 @@
 ---
-language: ne
-license: apache-2.0
-tags:
-- nepali
-- grammatical-error-detection
-- text-classification
-- roberta
-- sequence-classification
-- nlp
-datasets:
-- sumitaryal/nepali_grammatical_error_detection
+library_name: transformers
 base_model: IRIIS-RESEARCH/RoBERTa_Nepali_125M
+tags:
+- generated_from_trainer
 metrics:
 - accuracy
-- f1
 - precision
 - recall
-pipeline_tag: text-classification
-widget:
-- text: "म विद्यालय जान्छु।"
-  example_title: "Correct Nepali"
-- text: "म विद्यालय जान्छ।"
-  example_title: "Grammatical Error"
----
-
-# RoBERTa Nepali Grammatical Error Detection 
-
-This model is a fine-tuned version of [IRIIS-RESEARCH/RoBERTa_Nepali_125M](https://huggingface.co/IRIIS-RESEARCH/RoBERTa_Nepali_125M) specifically trained for detecting grammatical errors in Nepali text. The model was optimized and trained on NVIDIA H100 GPU with advanced optimization techniques.
-
-## Model Description
-
-- **Model Type:** Binary Text Classification (Sequence Classification)
-- **Language:** Nepali (ne)
-- **Base Model:** IRIIS-RESEARCH/RoBERTa_Nepali_125M (125M parameters)
-- **License:** Apache 2.0
-- **Training Infrastructure:** NVIDIA H100 (80GB)
-- **Training Time:** ~3.00 hours
-- **Fine-tuning Dataset:** [sumitaryal/nepali_grammatical_error_detection](https://huggingface.co/datasets/sumitaryal/nepali_grammatical_error_detection)
-
-## Performance Metrics
-
-Evaluated on validation set of 771,511 samples:
-
-| Metric | Score |
-|--------|-------|
-| Accuracy | 0.9234 |
-| F1 Score | 0.9156 |
-| Precision | 0.9087 |
-| Recall | 0.9226 |
-
-### Class-wise Performance
-
-| Class | Precision | Recall | F1-Score |
-|-------|-----------|--------|----------|
-| Correct | 0.9321 | 0.9145 | 0.9232 |
-| Incorrect | 0.8853 | 0.9307 | 0.9074 |
-
-## Training Details
-
-### Training Data
-
-- **Training Samples:** 10,082,804
-- **Validation Samples:** 771,511
-- **Total Dataset Size:** ~10.8M Nepali sentences
-- **Label Distribution:** Balanced mix of grammatically correct and incorrect sentences
-
-### Training Configuration
-
-- **GPU:** NVIDIA H100 (80GB VRAM)
-- **Precision:** BF16 (Brain Floating Point 16-bit)
-- **Batch Size:** 128 per device
-- **Gradient Accumulation:** 2 steps (effective batch size: 256)
-- **Learning Rate:** 2e-5 with 10% warmup
-- **Optimizer:** AdamW (Fused)
-- **Weight Decay:** 0.01
-- **Epochs:** 3
-- **Max Sequence Length:** 256 tokens
-- **Parallel Processing:** 26 CPU cores
-
-### Optimization Techniques
-
-- BF16 mixed precision training
-- Fused AdamW optimizer for faster updates
-- Group-by-length batching to minimize padding
-- Pin memory and prefetching for faster data loading
-- Multi-process tokenization (26 workers)
-
-## Usage
-
-### Quick Start
-
-```python
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
-import torch
-
-# Load model and tokenizer
-model_name = "DipeshChaudhary/roberta-nepali-sequence-ged"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForSequenceClassification.from_pretrained(model_name)
-
-# Function to check grammar
-def check_grammar(sentence):
-    inputs = tokenizer(sentence, return_tensors="pt", truncation=True, max_length=256)
-    
-    with torch.no_grad():
-        outputs = model(**inputs)
-        probs = torch.softmax(outputs.logits, dim=-1)
-    
-    pred_class = probs.argmax().item()
-    confidence = probs[0][pred_class].item()
-    
-    return {
-        "label": "correct" if pred_class == 0 else "incorrect",
-        "confidence": confidence,
-        "probabilities": {
-            "correct": probs[0][0].item(),
-            "incorrect": probs[0][1].item()
-        }
-    }
-
-# Example usage
-result = check_grammar("म विद्यालय जान्छु।")
-print(result)
-# Output: {'label': 'correct', 'confidence': 0.9876, 'probabilities': {'correct': 0.9876, 'incorrect': 0.0124}}
-
-result = check_grammar("म विद्यालय जान्छ।")
-print(result)
-# Output: {'label': 'incorrect', 'confidence': 0.9543, 'probabilities': {'correct': 0.0457, 'incorrect': 0.9543}}
-```
-
-### Batch Processing
-
-```python
-def check_grammar_batch(sentences):
-    inputs = tokenizer(sentences, return_tensors="pt", truncation=True, 
-                      max_length=256, padding=True)
-    
-    with torch.no_grad():
-        outputs = model(**inputs)
-        probs = torch.softmax(outputs.logits, dim=-1)
-    
-    results = []
-    for i, sentence in enumerate(sentences):
-        pred_class = probs[i].argmax().item()
-        results.append({
-            "sentence": sentence,
-            "label": "correct" if pred_class == 0 else "incorrect",
-            "confidence": probs[i][pred_class].item()
-        })
-    
-    return results
-
-# Process multiple sentences
-sentences = [
-    "तिमी कस्तो छौ?",
-    "नेपाल सुन्दर देश हो।",
-    "उनीहरू काम गर्दछन्।"
-]
-
-results = check_grammar_batch(sentences)
-for result in results:
-    print(f"{result['sentence']} → {result['label']} ({result['confidence']:.4f})")
-```
-
-### Using Pipeline API
-
-```python
-from transformers import pipeline
-
-# Create classifier pipeline
-classifier = pipeline(
-    "text-classification",
-    model="DipeshChaudhary/roberta-nepali-sequence-ged",
-    device=0  # Use GPU if available
-)
-
-# Check grammar
-result = classifier("म विद्यालय जान्छु।")
-print(result)
-# Output: [{'label': 'correct', 'score': 0.9876}]
-```
-
-## Use Cases
-
-### 1. Writing Assistant for Nepali
-
-```python
-def writing_assistant(text):
-    # Check and highlight grammatical errors in Nepali text
-    sentences = text.split('।')  # Split by Nepali sentence delimiter
-    sentences = [s.strip() + '।' for s in sentences if s.strip()]
-    
-    results = check_grammar_batch(sentences)
-    
-    print("Grammar Check Results:")
-    print("=" * 60)
-    for i, result in enumerate(results, 1):
-        status = "✓" if result['label'] == 'correct' else "✗"
-        print(f"{status} Sentence {i}: {result['sentence']}")
-        if result['label'] == 'incorrect':
-            print(f"  └─ Potential grammar error (confidence: {result['confidence']:.2%})")
-    
-    error_count = sum(1 for r in results if r['label'] == 'incorrect')
-    print(f"\nSummary: {error_count}/{len(results)} sentences may contain errors")
-    
-    return results
-
-# Example
-text = "म विद्यालय जान्छु। तिमी कस्तो छौ? उनीहरू काम गर्दछन्।"
-writing_assistant(text)
-```
-
-### 2. Educational Application
-
-```python
-def nepali_grammar_quiz(student_answer, correct_answer):
-    result = check_grammar(student_answer)
-    
-    if result['label'] == 'correct':
-        print(f"✓ Excellent! Your sentence is grammatically correct.")
-        print(f"  Confidence: {result['confidence']:.2%}")
-    else:
-        print(f"✗ There might be a grammatical error.")
-        print(f"  Confidence: {result['confidence']:.2%}")
-        print(f"  Hint: Compare with correct form: {correct_answer}")
-    
-    return result
-
-# Example quiz question
-nepali_grammar_quiz(
-    student_answer="म स्कूल जान्छ।",
-    correct_answer="म स्कूल जान्छु।"
-)
-```
-
-### 3. Content Quality Control
-
-```python
-def validate_nepali_content(content, threshold=0.85):
-    """Validate grammar quality of Nepali content"""
-    sentences = content.split('।')
-    sentences = [s.strip() + '।' for s in sentences if s.strip()]
-    
-    results = check_grammar_batch(sentences)
-    
-    # Calculate quality score
-    correct_count = sum(1 for r in results if r['label'] == 'correct')
-    quality_score = correct_count / len(results)
-    
-    return {
-        "passed": quality_score >= threshold,
-        "quality_score": quality_score,
-        "total_sentences": len(results),
-        "correct_sentences": correct_count,
-        "error_sentences": len(results) - correct_count,
-        "details": results
-    }
-
-# Example
-content = "नेपाल सुन्दर देश हो। यहाँ धेरै हिमाल छन्।"
-validation = validate_nepali_content(content)
-print(f"Quality Score: {validation['quality_score']:.2%}")
-print(f"Status: {'PASSED' if validation['passed'] else 'NEEDS REVIEW'}")
-```
-
-### 4. Real-time Text Editor Integration
-
-```python
-class NepaliGrammarChecker:
-    def __init__(self, model_name="DipeshChaudhary/roberta-nepali-sequence-ged"):
-        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
-        self.model = AutoModelForSequenceClassification.from_pretrained(model_name)
-        self.model.eval()
-    
-    def check_realtime(self, text, return_positions=True):
-        """Check grammar with error positions for highlighting"""
-        sentences = text.split('।')
-        sentences = [s.strip() for s in sentences if s.strip()]
-        
-        errors = []
-        position = 0
-        
-        for sentence in sentences:
-            result = check_grammar(sentence + '।')
-            
-            if result['label'] == 'incorrect':
-                errors.append({
-                    "sentence": sentence,
-                    "start": position,
-                    "end": position + len(sentence),
-                    "confidence": result['confidence']
-                })
-            
-            position += len(sentence) + 1  # +1 for '।'
-        
-        return errors
-
-# Example: Integrate with text editor
-checker = NepaliGrammarChecker()
-text = "म स्कूल जान्छ। तिमी कस्तो छौ?"
-errors = checker.check_realtime(text)
-print(f"Found {len(errors)} potential errors")
-```
-
-## Model Architecture
-
-```
-RoBERTa Base Architecture
-├── Embedding Layer (50,256 vocab size)
-├── 12 Transformer Layers
-│   ├── Multi-Head Self-Attention (12 heads)
-│   ├── Feed-Forward Network (3072 hidden)
-│   └── Layer Normalization
-└── Classification Head
-    ├── Dense Layer (768 → 768)
-    ├── Dropout (0.1)
-    └── Output Layer (768 → 2)
-
-Total Parameters: ~125M
-```
-
-## Intended Use
-
-### Primary Applications
-- **Writing Assistance:** Help writers identify grammatical errors in Nepali text
-- **Educational Tools:** Assist students learning Nepali grammar
-- **Content Quality Control:** Validate grammar in published content
-- **Language Learning Apps:** Provide instant feedback on grammar usage
-- **Translation Post-Editing:** Verify grammar correctness in translated text
-
-### Target Users
-- Nepali language learners
-- Content creators and writers
-- Educators and students
-- Publishing platforms
-- NLP researchers working on Nepali language
-
-## Limitations and Considerations
-
-### Known Limitations
-
-1. **Dialectal Variations:** The model is trained primarily on standard Nepali and may not perform optimally on regional dialects
-2. **Informal Language:** Performance may vary with colloquial or informal Nepali
-3. **Context Dependency:** Some grammatical errors require broader context beyond single sentences
-4. **Punctuation Sensitivity:** The model considers punctuation as part of grammar checking
-5. **Domain Specificity:** May not capture domain-specific grammar rules (legal, medical, etc.)
-
-### Important Considerations
-
-- **False Positives:** The model may occasionally flag correct sentences as incorrect
-- **False Negatives:** Some grammatical errors might not be detected
-- **Not a Grammar Corrector:** This model only detects errors; it does not suggest corrections
-- **Sentence-Level Only:** Designed for sentence-level classification, not word-level error detection
-- **Static Training Data:** Based on data available up to the training cutoff date
-
-### Best Practices
-
-- Use as an assistive tool, not as the sole authority on grammar
-- Combine with human review for critical content
-- Consider the confidence scores when making decisions
-- Test on your specific domain/use case before deployment
-- Provide user feedback mechanisms to improve over time
-
-## Technical Specifications
-
-### Input/Output Format
-
-- **Input:** Single Nepali sentence (max 256 tokens)
-- **Output:** Binary classification (correct/incorrect) with confidence scores
-- **Processing:** Tokenization using RoBERTa tokenizer with BPE
-
-### Performance Benchmarks
-
-On NVIDIA H100:
-- **Inference Speed:** ~500 sentences/second (batch size 32)
-- **Latency:** <5ms per sentence (single inference)
-- **Memory:** ~2GB GPU memory (FP16 inference)
-
-### Deployment Recommendations
-
-- **CPU:** 4+ cores recommended for production
-- **GPU:** Any CUDA-capable GPU (T4, V100, A100, H100)
-- **Memory:** 4GB+ RAM, 2GB+ VRAM
-- **Precision:** FP16 or BF16 for optimal speed/memory tradeoff
-
-## Training Infrastructure
-
-- **GPU:** NVIDIA H100 (80GB HBM3)
-- **CPU:** 26 cores
-- **RAM:** 200GB+
-- **Training Duration:** 3.00 hours
-- **Cost:** ~$8.97
-
-## Ethical Considerations
-
-### Bias and Fairness
-- The model reflects patterns in the training data, which may contain biases
-- Performance may vary across different writing styles, registers, and demographics
-- Users should be aware that "grammatically incorrect" is context-dependent
-
-### Privacy
-- The model processes text locally and doesn't store user inputs
-- For production deployments, implement appropriate data handling policies
-
-### Accessibility
-- This tool should support, not replace, language learning and education
-- Should not be used to discriminate against non-native speakers or learners
-
-## Citation
-
-If you use this model in your research or application, please cite:
-
-```bibtex
-@misc{roberta-nepali-ged-2024,
-  author = {Dipesh Chaudhary},
-  title = {RoBERTa Nepali Grammatical Error Detection},
-  year = {2024},
-  publisher = {Hugging Face},
-  howpublished = {\url{https://huggingface.co/DipeshChaudhary/roberta-nepali-sequence-ged}}
-}
-```
-
-Also cite the base model:
-
-```bibtex
-@misc{roberta-nepali-125m,
-  author = {IRIIS Research},
-  title = {RoBERTa Nepali 125M},
-  year = {2024},
-  publisher = {Hugging Face},
-  howpublished = {\url{https://huggingface.co/IRIIS-RESEARCH/RoBERTa_Nepali_125M}}
-}
-```
-
-## References
-
-1. **Base Model:** [IRIIS-RESEARCH/RoBERTa_Nepali_125M](https://huggingface.co/IRIIS-RESEARCH/RoBERTa_Nepali_125M)
-2. **Dataset:** [sumitaryal/nepali_grammatical_error_detection](https://huggingface.co/datasets/sumitaryal/nepali_grammatical_error_detection)
-3. **RoBERTa Paper:** [Liu et al., 2019 - RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://arxiv.org/abs/1907.11692)
-4. **Transformers Library:** [Hugging Face Transformers](https://github.com/huggingface/transformers)
-
-## Contact and Support
-
-- **Model Repository:** [https://huggingface.co/DipeshChaudhary/roberta-nepali-sequence-ged](https://huggingface.co/DipeshChaudhary/roberta-nepali-sequence-ged)
-- **Issues:** Please report issues on the model repository
-- **Updates:** Follow the repository for model updates and improvements
-
-## License
-
-This model is released under the Apache 2.0 License. See LICENSE for details.
-
-## Acknowledgments
-
-- IRIIS Research for the pre-trained RoBERTa Nepali model
-- Sumit Aryal for the grammatical error detection dataset
-- Hugging Face for the Transformers library and model hosting
-- The Nepali NLP community for continued support and feedback
-
+- f1
+model-index:
+- name: roberta-nepali-sequence-ged
+  results: []
 ---
 
-*Last Updated: November 08, 2025*
+<!-- 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-nepali-sequence-ged
+
+This model is a fine-tuned version of [IRIIS-RESEARCH/RoBERTa_Nepali_125M](https://huggingface.co/IRIIS-RESEARCH/RoBERTa_Nepali_125M) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1973
+- Model Preparation Time: 0.002
+- Accuracy: 0.9231
+- Precision: 0.9222
+- Recall: 0.9326
+- F1: 0.9274
+- Precision Correct: 0.9242
+- Recall Correct: 0.9127
+- F1 Correct: 0.9184
+- Precision Incorrect: 0.9222
+- Recall Incorrect: 0.9326
+- F1 Incorrect: 0.9274
+
+## 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: 512
+- eval_batch_size: 1024
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 1024
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 2
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Model Preparation Time | Accuracy | Precision | Recall | F1     | Precision Correct | Recall Correct | F1 Correct | Precision Incorrect | Recall Incorrect | F1 Incorrect |
+|:-------------:|:------:|:-----:|:---------------:|:----------------------:|:--------:|:---------:|:------:|:------:|:-----------------:|:--------------:|:----------:|:-------------------:|:----------------:|:------------:|
+| 0.2734        | 0.1016 | 1000  | 0.2748          | 0.002                  | 0.8894   | 0.8951    | 0.8946 | 0.8949 | 0.8831            | 0.8836         | 0.8833     | 0.8951              | 0.8946           | 0.8949       |
+| 0.2302        | 0.2031 | 2000  | 0.2455          | 0.002                  | 0.9026   | 0.9049    | 0.9106 | 0.9078 | 0.9001            | 0.8937         | 0.8969     | 0.9049              | 0.9106           | 0.9078       |
+| 0.2169        | 0.3047 | 3000  | 0.2462          | 0.002                  | 0.9016   | 0.8918    | 0.9252 | 0.9082 | 0.9134            | 0.8753         | 0.8939     | 0.8918              | 0.9252           | 0.9082       |
+| 0.2101        | 0.4062 | 4000  | 0.2315          | 0.002                  | 0.9086   | 0.9047    | 0.9236 | 0.9140 | 0.9131            | 0.8920         | 0.9024     | 0.9047              | 0.9236           | 0.9140       |
+| 0.2052        | 0.5078 | 5000  | 0.2234          | 0.002                  | 0.9124   | 0.9131    | 0.9212 | 0.9171 | 0.9117            | 0.9026         | 0.9071     | 0.9131              | 0.9212           | 0.9171       |
+| 0.2003        | 0.6094 | 6000  | 0.2248          | 0.002                  | 0.9100   | 0.9024    | 0.9294 | 0.9157 | 0.9189            | 0.8885         | 0.9034     | 0.9024              | 0.9294           | 0.9157       |
+| 0.1987        | 0.7109 | 7000  | 0.2187          | 0.002                  | 0.9131   | 0.9074    | 0.9298 | 0.9184 | 0.9199            | 0.8946         | 0.9071     | 0.9074              | 0.9298           | 0.9184       |
+| 0.1965        | 0.8125 | 8000  | 0.2105          | 0.002                  | 0.9180   | 0.9189    | 0.9260 | 0.9224 | 0.9171            | 0.9092         | 0.9131     | 0.9189              | 0.9260           | 0.9224       |
+| 0.1939        | 0.9140 | 9000  | 0.2129          | 0.002                  | 0.9166   | 0.9126    | 0.9306 | 0.9215 | 0.9212            | 0.9010         | 0.9110     | 0.9126              | 0.9306           | 0.9215       |
+| 0.1896        | 1.0155 | 10000 | 0.2055          | 0.002                  | 0.9198   | 0.9206    | 0.9277 | 0.9241 | 0.9190            | 0.9111         | 0.9150     | 0.9206              | 0.9277           | 0.9241       |
+| 0.1796        | 1.1171 | 11000 | 0.2065          | 0.002                  | 0.9188   | 0.9169    | 0.9301 | 0.9234 | 0.9211            | 0.9064         | 0.9137     | 0.9169              | 0.9301           | 0.9234       |
+| 0.1788        | 1.2187 | 12000 | 0.2058          | 0.002                  | 0.9192   | 0.9164    | 0.9314 | 0.9238 | 0.9224            | 0.9056         | 0.9139     | 0.9164              | 0.9314           | 0.9238       |
+| 0.1787        | 1.3202 | 13000 | 0.2018          | 0.002                  | 0.9212   | 0.9204    | 0.9307 | 0.9255 | 0.9221            | 0.9106         | 0.9163     | 0.9204              | 0.9307           | 0.9255       |
+| 0.1774        | 1.4218 | 14000 | 0.2038          | 0.002                  | 0.9206   | 0.9177    | 0.9328 | 0.9252 | 0.9240            | 0.9072         | 0.9155     | 0.9177              | 0.9328           | 0.9252       |
+| 0.1767        | 1.5233 | 15000 | 0.1940          | 0.002                  | 0.9251   | 0.9309    | 0.9263 | 0.9286 | 0.9186            | 0.9237         | 0.9211     | 0.9309              | 0.9263           | 0.9286       |
+| 0.1785        | 1.6249 | 16000 | 0.1943          | 0.002                  | 0.9245   | 0.9283    | 0.9282 | 0.9283 | 0.9203            | 0.9204         | 0.9204     | 0.9283              | 0.9282           | 0.9283       |
+| 0.1761        | 1.7265 | 17000 | 0.1957          | 0.002                  | 0.9237   | 0.9253    | 0.9301 | 0.9277 | 0.9220            | 0.9166         | 0.9193     | 0.9253              | 0.9301           | 0.9277       |
+| 0.176         | 1.8280 | 18000 | 0.1960          | 0.002                  | 0.9240   | 0.9253    | 0.9307 | 0.9280 | 0.9225            | 0.9165         | 0.9195     | 0.9253              | 0.9307           | 0.9280       |
+| 0.1761        | 1.9296 | 19000 | 0.1973          | 0.002                  | 0.9231   | 0.9222    | 0.9326 | 0.9274 | 0.9242            | 0.9127         | 0.9184     | 0.9222              | 0.9326           | 0.9274       |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.8.0+cu128
+- Datasets 4.4.1
+- Tokenizers 0.22.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8093edfb19ed3b19d6c9432977e8120fc673a07c82522e76d4cc51ab6046c5f
+oid sha256:3135c543cbee8ced633a4aa5ab8f697ad254757b6ac93a80f3aa0b9a530922af
 size 498585176

runs/Nov08_16-52-16_192-222-52-54/events.out.tfevents.1762620831.192-222-52-54.6829.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c432bccba24462a0d5a9f13c2cd8a3b9a4b4370e33d50fb15ebdffecb0b1ad1
+size 5618

runs/Nov08_16-59-39_192-222-52-54/events.out.tfevents.1762621188.192-222-52-54.6829.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3879cd2b4ded555a76748cd933c8a66c8c5c3d3c150b13f0e77936c00a5917
+size 5273

runs/Nov08_17-02-08_192-222-52-54/events.out.tfevents.1762621331.192-222-52-54.6829.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2cd49ac314676e507d681e49e927458a9aa67caf349e347e9590112fa56e91
+size 5272

runs/Nov08_17-03-01_192-222-52-54/events.out.tfevents.1762621515.192-222-52-54.6829.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd667e2f3669a6129dfa79bf11ca98127151e593830897a5047f1b29f37d2444
+size 5632

runs/Nov08_17-06-03_192-222-52-54/events.out.tfevents.1762621569.192-222-52-54.6829.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0866006b75113baba648956bb93673b01e9e03642a092eb8275ee6579bc74fdb
+size 5487

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f459c9b427a544ee2bf4d9385b392338c599e2c2cb6e5b7dd8714d246e41e30a
+oid sha256:95b36cd54d1ba2203f0fa90fc777ed7cf1bb94f9720246f2b7bbed2dd99b6ba6
 size 5841