Evaluation result = 0.775

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 checkpoints/checkpoint-2550/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/checkpoint-2100/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoints/checkpoint-2100/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

checkpoints/checkpoint-2100/README.md

@@ -0,0 +1,917 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:7552
+- loss:CoSENTLoss
+base_model: intfloat/multilingual-e5-large-instruct
+widget:
+- source_sentence: How are calibration points linked to equipment?
+  sentences:
+  - 'How are flow computers and measurement systems related?
+
+    Flow computers can have multiple systems assigned to them. However, a measurement
+    system can only be assigned to one flow computer.
+
+
+    Database terminology:
+
+    In the database, this relationship is referred to as:
+
+    - Meter streams
+
+    - Meter runs
+
+    - Sections
+
+
+    Storage of the relationship:
+
+    The relationship between a flow computer and its assigned measurement system is
+    stored in a special table.
+
+
+    User context:
+
+    When a user refers to a "meter stream," they are indicating that they are searching
+    for a measurement system assigned to a specific flow computer.'
+  - "How does a flow computer generate and store reports?\nA flow computer generates\
+    \ daily or hourly reports to provide users with operational data. These reports\
+    \ are stored in the flow computer's memory in an organized format.\n\nReport structure:\n\
+    - Each report includes:\n- Date and time of the data recording.\n- Data recorded\
+    \ from flow computers.\n\nData storage in tables:\nThe reports are saved in two\
+    \ tables:\n1. Main table (Index):\n    - Stores the date, time, and flow computer\
+    \ identifier.\n2. Detail table:\n    - Stores the measured values associated with\
+    \ the report.\n\nConnection to the Modbus table:\nThe flow computer's reports\
+    \ are linked to a Modbus table. This table contains the names corresponding to\
+    \ each value in the reports, making it easier to interpret the data."
+  - "What is uncertainty?\nUncertainty is a measure of confidence in the precision\
+    \ and reliability of results obtained from equipment or measurement systems. It\
+    \ quantifies the potential error or margin of error in measurements.\n\nTypes\
+    \ of uncertainty:\nThere are two main types of uncertainty:\n1. Uncertainty of\
+    \ magnitudes (variables):\n    - Refers to the uncertainty of specific variables,\
+    \ such as temperature or pressure.\n    - It is calculated after calibrating a\
+    \ device or obtained from the equipment manufacturer's manual.\n    - This uncertainty\
+    \ serves as a starting point for further calculations related to the equipment.\n\
+    \n2. Uncertainty of the measurement system:\n    - Refers to the uncertainty calculated\
+    \ for the overall flow measurement.\n    - It depends on the uncertainties of\
+    \ the individual variables (magnitudes) and represents the combined margin of\
+    \ error for the entire system.\n\nKey points:\n- The uncertainties of magnitudes\
+    \ (variables) are the foundation for calculating the uncertainty of the measurement\
+    \ system. Think of them as the \"building blocks.\"\n- Do not confuse the two\
+    \ types of uncertainty:\n    - **Uncertainty of magnitudes/variables**: Specific\
+    \ to individual variables (e.g., temperature, pressure).\n    - **Uncertainty\
+    \ of the measurement system**: Specific to the overall flow measurement.\n\nDatabase\
+    \ storage for uncertainties:\nIn the database, uncertainty calculations are stored\
+    \ in two separate tables:\n1. Uncertainty of magnitudes (variables):\n    - Stores\
+    \ the uncertainty values for specific variables (e.g., temperature, pressure).\n\
+    \n2. Uncertainty of the measurement system:\n    - Stores the uncertainty values\
+    \ for the overall flow measurement system.\n\nHow to retrieve uncertainty data:\n\
+    - To find the uncertainty of the measurement system, join the measurement systems\
+    \ table with the uncertainty of the measurement system table.\n- To find the uncertainty\
+    \ of a specific variable (magnitude), join the measurement systems table with\
+    \ the uncertainty of magnitudes (variables) table.\n\nImportant note:\nDo not\
+    \ confuse the two types of uncertainty:\n- If the user requests the uncertainty\
+    \ of the measurement system, use the first join (measurement systems table + uncertainty\
+    \ of the measurement system table).\n- If the user requests the uncertainty of\
+    \ a specific variable (magnitude) in a report, use the second join (measurement\
+    \ systems table + uncertainty of magnitudes table)."
+- source_sentence: What is the primary key of the flow computer table?
+  sentences:
+  - 'What is equipment calibration?
+
+    Calibration is a metrological verification process used to ensure the accuracy
+    of measurement equipment. It is performed periodically, based on intervals set
+    by the company or a regulatory body.
+
+
+    Purpose of calibration:
+
+    The calibration process corrects any deviations in how the equipment measures
+    physical magnitudes (variables). This ensures the equipment provides accurate
+    and reliable data.
+
+
+    Calibration cycles:
+
+    There are two main calibration cycles:
+
+    1. As-found: Represents the equipment''s measurement accuracy before any adjustments
+    are made. This cycle is almost always implemented.
+
+    2. As-left: Represents the equipment''s measurement accuracy after adjustments
+    are made. This cycle is used depending on regulatory requirements.
+
+
+    Calibration uncertainty:
+
+    - Uncertainty is included in the results of a calibration.
+
+    - Calibration uncertainty refers to the margin of error in the device''s measurements,
+    which also affects the uncertainty of the measured variable or magnitude.'
+  - 'What is equipment calibration?
+
+    Calibration is a metrological verification process used to ensure the accuracy
+    of measurement equipment. It is performed periodically, based on intervals set
+    by the company or a regulatory body.
+
+
+    Purpose of calibration:
+
+    The calibration process corrects any deviations in how the equipment measures
+    physical magnitudes (variables). This ensures the equipment provides accurate
+    and reliable data.
+
+
+    Calibration cycles:
+
+    There are two main calibration cycles:
+
+    1. As-found: Represents the equipment''s measurement accuracy before any adjustments
+    are made. This cycle is almost always implemented.
+
+    2. As-left: Represents the equipment''s measurement accuracy after adjustments
+    are made. This cycle is used depending on regulatory requirements.
+
+
+    Calibration uncertainty:
+
+    - Uncertainty is included in the results of a calibration.
+
+    - Calibration uncertainty refers to the margin of error in the device''s measurements,
+    which also affects the uncertainty of the measured variable or magnitude.'
+  - "How does a flow computer generate and store reports?\nA flow computer generates\
+    \ daily or hourly reports to provide users with operational data. These reports\
+    \ are stored in the flow computer's memory in an organized format.\n\nReport structure:\n\
+    - Each report includes:\n- Date and time of the data recording.\n- Data recorded\
+    \ from flow computers.\n\nData storage in tables:\nThe reports are saved in two\
+    \ tables:\n1. Main table (Index):\n    - Stores the date, time, and flow computer\
+    \ identifier.\n2. Detail table:\n    - Stores the measured values associated with\
+    \ the report.\n\nConnection to the Modbus table:\nThe flow computer's reports\
+    \ are linked to a Modbus table. This table contains the names corresponding to\
+    \ each value in the reports, making it easier to interpret the data."
+- source_sentence: Can you provide a sample query to test the retrieval of the uncertainty
+    result for the specified tag and date?
+  sentences:
+  - 'What is equipment calibration?
+
+    Calibration is a metrological verification process used to ensure the accuracy
+    of measurement equipment. It is performed periodically, based on intervals set
+    by the company or a regulatory body.
+
+
+    Purpose of calibration:
+
+    The calibration process corrects any deviations in how the equipment measures
+    physical magnitudes (variables). This ensures the equipment provides accurate
+    and reliable data.
+
+
+    Calibration cycles:
+
+    There are two main calibration cycles:
+
+    1. As-found: Represents the equipment''s measurement accuracy before any adjustments
+    are made. This cycle is almost always implemented.
+
+    2. As-left: Represents the equipment''s measurement accuracy after adjustments
+    are made. This cycle is used depending on regulatory requirements.
+
+
+    Calibration uncertainty:
+
+    - Uncertainty is included in the results of a calibration.
+
+    - Calibration uncertainty refers to the margin of error in the device''s measurements,
+    which also affects the uncertainty of the measured variable or magnitude.'
+  - 'What kind of data store an equipment?
+
+    Equipments can capture meteorological data, such as pressure, temperature, and
+    volume (magnitudes). This data is essential for users to perform various calculations.
+
+
+    Data storage:
+
+    - The measured values are stored in a special table in the database for magnitudes.
+    This table contains the values of the variables captured by the equipments.
+
+    - These values are **direct measurements** from the fluid (e.g., raw pressure,
+    temperature, or volume readings). **They are not calculated values**, such as
+    uncertainty.
+
+    - The values stored in the variable values table are **different** from variable
+    uncertainty values, which are calculated separately and represent the margin of
+    error.
+
+
+    Accessing the data:
+
+    - Users typically access the data by referring to the readings from the measurement
+    system, not directly from the individual equipments.
+
+    - The readings are stored in a "variable values" table within the database.
+
+
+    Linking variable names:
+
+    If the user needs to know the name of a variable, they must link the data to another
+    table that stores information about the types of variables.'
+  - "What is uncertainty?\nUncertainty is a measure of confidence in the precision\
+    \ and reliability of results obtained from equipment or measurement systems. It\
+    \ quantifies the potential error or margin of error in measurements.\n\nTypes\
+    \ of uncertainty:\nThere are two main types of uncertainty:\n1. Uncertainty of\
+    \ magnitudes (variables):\n    - Refers to the uncertainty of specific variables,\
+    \ such as temperature or pressure.\n    - It is calculated after calibrating a\
+    \ device or obtained from the equipment manufacturer's manual.\n    - This uncertainty\
+    \ serves as a starting point for further calculations related to the equipment.\n\
+    \n2. Uncertainty of the measurement system:\n    - Refers to the uncertainty calculated\
+    \ for the overall flow measurement.\n    - It depends on the uncertainties of\
+    \ the individual variables (magnitudes) and represents the combined margin of\
+    \ error for the entire system.\n\nKey points:\n- The uncertainties of magnitudes\
+    \ (variables) are the foundation for calculating the uncertainty of the measurement\
+    \ system. Think of them as the \"building blocks.\"\n- Do not confuse the two\
+    \ types of uncertainty:\n    - **Uncertainty of magnitudes/variables**: Specific\
+    \ to individual variables (e.g., temperature, pressure).\n    - **Uncertainty\
+    \ of the measurement system**: Specific to the overall flow measurement.\n\nDatabase\
+    \ storage for uncertainties:\nIn the database, uncertainty calculations are stored\
+    \ in two separate tables:\n1. Uncertainty of magnitudes (variables):\n    - Stores\
+    \ the uncertainty values for specific variables (e.g., temperature, pressure).\n\
+    \n2. Uncertainty of the measurement system:\n    - Stores the uncertainty values\
+    \ for the overall flow measurement system.\n\nHow to retrieve uncertainty data:\n\
+    - To find the uncertainty of the measurement system, join the measurement systems\
+    \ table with the uncertainty of the measurement system table.\n- To find the uncertainty\
+    \ of a specific variable (magnitude), join the measurement systems table with\
+    \ the uncertainty of magnitudes (variables) table.\n\nImportant note:\nDo not\
+    \ confuse the two types of uncertainty:\n- If the user requests the uncertainty\
+    \ of the measurement system, use the first join (measurement systems table + uncertainty\
+    \ of the measurement system table).\n- If the user requests the uncertainty of\
+    \ a specific variable (magnitude) in a report, use the second join (measurement\
+    \ systems table + uncertainty of magnitudes table)."
+- source_sentence: How are the secondary equipment and measurement system related?
+  sentences:
+  - 'What kind of data store an equipment?
+
+    Equipments can capture meteorological data, such as pressure, temperature, and
+    volume (magnitudes). This data is essential for users to perform various calculations.
+
+
+    Data storage:
+
+    - The measured values are stored in a special table in the database for magnitudes.
+    This table contains the values of the variables captured by the equipments.
+
+    - These values are **direct measurements** from the fluid (e.g., raw pressure,
+    temperature, or volume readings). **They are not calculated values**, such as
+    uncertainty.
+
+    - The values stored in the variable values table are **different** from variable
+    uncertainty values, which are calculated separately and represent the margin of
+    error.
+
+
+    Accessing the data:
+
+    - Users typically access the data by referring to the readings from the measurement
+    system, not directly from the individual equipments.
+
+    - The readings are stored in a "variable values" table within the database.
+
+
+    Linking variable names:
+
+    If the user needs to know the name of a variable, they must link the data to another
+    table that stores information about the types of variables.'
+  - 'What do measurement equipment measure?
+
+    Each equipment measures a physical magnitude, also known as a variable. Based
+    on the type of variable they measure, devices are classified into different categories.
+
+
+    Equipment classification:
+
+    - Primary meter: Assigned by default to equipments like orifice plates.
+
+    - Secondary meter: Assigned by default to equipments like transmitters.
+
+    - Tertiary meter: Used for other types of equipments.
+
+
+    Equipment types in the database:
+
+    The database includes a table listing all equipment types. Examples of equipment
+    types are:
+
+    - Differential pressure transmitters
+
+    - RTDs (Resistance Temperature Detectors)
+
+    - Orifice plates
+
+    - Multivariable transmitters
+
+    - Ultrasonic meters
+
+
+    Meteorological checks for equipments:
+
+    Each equipment type is assigned a meteorological check, which can be either:
+
+    - Calibration: To ensure measurement accuracy.
+
+    - Inspection: To verify proper functioning.
+
+
+    Data storage in tables:
+
+    The database also includes a separate table for equipment classifications, which
+    are:
+
+    - Primary meter
+
+    - Secondary meter
+
+    - Tertiary meter
+
+    So, an equipment has equipment types and this types has classifications.'
+  - 'What kind of data store an equipment?
+
+    Equipments can capture meteorological data, such as pressure, temperature, and
+    volume (magnitudes). This data is essential for users to perform various calculations.
+
+
+    Data storage:
+
+    - The measured values are stored in a special table in the database for magnitudes.
+    This table contains the values of the variables captured by the equipments.
+
+    - These values are **direct measurements** from the fluid (e.g., raw pressure,
+    temperature, or volume readings). **They are not calculated values**, such as
+    uncertainty.
+
+    - The values stored in the variable values table are **different** from variable
+    uncertainty values, which are calculated separately and represent the margin of
+    error.
+
+
+    Accessing the data:
+
+    - Users typically access the data by referring to the readings from the measurement
+    system, not directly from the individual equipments.
+
+    - The readings are stored in a "variable values" table within the database.
+
+
+    Linking variable names:
+
+    If the user needs to know the name of a variable, they must link the data to another
+    table that stores information about the types of variables.'
+- source_sentence: What is the table structure for secondary equipment?
+  sentences:
+  - 'What kind of data store an equipment?
+
+    Equipments can capture meteorological data, such as pressure, temperature, and
+    volume (magnitudes). This data is essential for users to perform various calculations.
+
+
+    Data storage:
+
+    - The measured values are stored in a special table in the database for magnitudes.
+    This table contains the values of the variables captured by the equipments.
+
+    - These values are **direct measurements** from the fluid (e.g., raw pressure,
+    temperature, or volume readings). **They are not calculated values**, such as
+    uncertainty.
+
+    - The values stored in the variable values table are **different** from variable
+    uncertainty values, which are calculated separately and represent the margin of
+    error.
+
+
+    Accessing the data:
+
+    - Users typically access the data by referring to the readings from the measurement
+    system, not directly from the individual equipments.
+
+    - The readings are stored in a "variable values" table within the database.
+
+
+    Linking variable names:
+
+    If the user needs to know the name of a variable, they must link the data to another
+    table that stores information about the types of variables.'
+  - 'How are flow computers and measurement systems related?
+
+    Flow computers can have multiple systems assigned to them. However, a measurement
+    system can only be assigned to one flow computer.
+
+
+    Database terminology:
+
+    In the database, this relationship is referred to as:
+
+    - Meter streams
+
+    - Meter runs
+
+    - Sections
+
+
+    Storage of the relationship:
+
+    The relationship between a flow computer and its assigned measurement system is
+    stored in a special table.
+
+
+    User context:
+
+    When a user refers to a "meter stream," they are indicating that they are searching
+    for a measurement system assigned to a specific flow computer.'
+  - 'How are flow computers and measurement systems related?
+
+    Flow computers can have multiple systems assigned to them. However, a measurement
+    system can only be assigned to one flow computer.
+
+
+    Database terminology:
+
+    In the database, this relationship is referred to as:
+
+    - Meter streams
+
+    - Meter runs
+
+    - Sections
+
+
+    Storage of the relationship:
+
+    The relationship between a flow computer and its assigned measurement system is
+    stored in a special table.
+
+
+    User context:
+
+    When a user refers to a "meter stream," they are indicating that they are searching
+    for a measurement system assigned to a specific flow computer.'
+datasets:
+- Lauther/measuring-embeddings-v3
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on intfloat/multilingual-e5-large-instruct
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-large-instruct](https://huggingface.co/intfloat/multilingual-e5-large-instruct) on the [measuring-embeddings-v3](https://huggingface.co/datasets/Lauther/measuring-embeddings-v3) dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [intfloat/multilingual-e5-large-instruct](https://huggingface.co/intfloat/multilingual-e5-large-instruct) <!-- at revision c9e87c786ffac96aeaeb42863276930883923ecb -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [measuring-embeddings-v3](https://huggingface.co/datasets/Lauther/measuring-embeddings-v3)
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'What is the table structure for secondary equipment?',
+    'How are flow computers and measurement systems related?\nFlow computers can have multiple systems assigned to them. However, a measurement system can only be assigned to one flow computer.\n\nDatabase terminology:\nIn the database, this relationship is referred to as:\n- Meter streams\n- Meter runs\n- Sections\n\nStorage of the relationship:\nThe relationship between a flow computer and its assigned measurement system is stored in a special table.\n\nUser context:\nWhen a user refers to a "meter stream," they are indicating that they are searching for a measurement system assigned to a specific flow computer.',
+    'What kind of data store an equipment?\nEquipments can capture meteorological data, such as pressure, temperature, and volume (magnitudes). This data is essential for users to perform various calculations.\n\nData storage:\n- The measured values are stored in a special table in the database for magnitudes. This table contains the values of the variables captured by the equipments.\n- These values are **direct measurements** from the fluid (e.g., raw pressure, temperature, or volume readings). **They are not calculated values**, such as uncertainty.\n- The values stored in the variable values table are **different** from variable uncertainty values, which are calculated separately and represent the margin of error.\n\nAccessing the data:\n- Users typically access the data by referring to the readings from the measurement system, not directly from the individual equipments.\n- The readings are stored in a "variable values" table within the database.\n\nLinking variable names:\nIf the user needs to know the name of a variable, they must link the data to another table that stores information about the types of variables.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</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 Dataset
+
+#### measuring-embeddings-v3
+
+* Dataset: [measuring-embeddings-v3](https://huggingface.co/datasets/Lauther/measuring-embeddings-v3) at [1b3cbbe](https://huggingface.co/datasets/Lauther/measuring-embeddings-v3/tree/1b3cbbeb70b63338110491cd3de2950fb40b4f87)
+* Size: 7,552 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                             | score                                                           |
+  |:--------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:----------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                                | float                                                           |
+  | details | <ul><li>min: 9 tokens</li><li>mean: 15.96 tokens</li><li>max: 40 tokens</li></ul> | <ul><li>min: 120 tokens</li><li>mean: 255.56 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.22</li><li>max: 0.95</li></ul> |
+* Samples:
+  | sentence1                                                                                              | sentence2                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  | score             |
+  |:-------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------|
+  | <code>How can I combine the sub-query with the main query to fetch the last uncertainty report?</code> | <code>What do measurement equipment measure?<br>Each equipment measures a physical magnitude, also known as a variable. Based on the type of variable they measure, devices are classified into different categories.<br><br>Equipment classification:<br>- Primary meter: Assigned by default to equipments like orifice plates.<br>- Secondary meter: Assigned by default to equipments like transmitters.<br>- Tertiary meter: Used for other types of equipments.<br><br>Equipment types in the database:<br>The database includes a table listing all equipment types. Examples of equipment types are:<br>- Differential pressure transmitters<br>- RTDs (Resistance Temperature Detectors)<br>- Orifice plates<br>- Multivariable transmitters<br>- Ultrasonic meters<br><br>Meteorological checks for equipments:<br>Each equipment type is assigned a meteorological check, which can be either:<br>- Calibration: To ensure measurement accuracy.<br>- Inspection: To verify proper functioning.<br><br>Data storage in tables:<br>The database also includes a separate table for equipment classific...</code> | <code>0.1</code>  |
+  | <code>What is the column name for the calibration date in the calibration table?</code>                | <code>How are flow computers and measurement systems related?<br>Flow computers can have multiple systems assigned to them. However, a measurement system can only be assigned to one flow computer.<br><br>Database terminology:<br>In the database, this relationship is referred to as:<br>- Meter streams<br>- Meter runs<br>- Sections<br><br>Storage of the relationship:<br>The relationship between a flow computer and its assigned measurement system is stored in a special table.<br><br>User context:<br>When a user refers to a "meter stream," they are indicating that they are searching for a measurement system assigned to a specific flow computer.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                            | <code>0.1</code>  |
+  | <code>What is the name of the table that contains the flow computer tags?</code>                       | <code>What is equipment calibration?<br>Calibration is a metrological verification process used to ensure the accuracy of measurement equipment. It is performed periodically, based on intervals set by the company or a regulatory body.<br><br>Purpose of calibration:<br>The calibration process corrects any deviations in how the equipment measures physical magnitudes (variables). This ensures the equipment provides accurate and reliable data.<br><br>Calibration cycles:<br>There are two main calibration cycles:<br>1. As-found: Represents the equipment's measurement accuracy before any adjustments are made. This cycle is almost always implemented.<br>2. As-left: Represents the equipment's measurement accuracy after adjustments are made. This cycle is used depending on regulatory requirements.<br><br>Calibration uncertainty:<br>- Uncertainty is included in the results of a calibration.<br>- Calibration uncertainty refers to the margin of error in the device's measurements, which also affects the uncertainty of the measured variable or ...</code>                            | <code>0.05</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### measuring-embeddings-v3
+
+* Dataset: [measuring-embeddings-v3](https://huggingface.co/datasets/Lauther/measuring-embeddings-v3) at [1b3cbbe](https://huggingface.co/datasets/Lauther/measuring-embeddings-v3/tree/1b3cbbeb70b63338110491cd3de2950fb40b4f87)
+* Size: 1,618 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                             | score                                                           |
+  |:--------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:----------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                                | float                                                           |
+  | details | <ul><li>min: 9 tokens</li><li>mean: 15.83 tokens</li><li>max: 40 tokens</li></ul> | <ul><li>min: 120 tokens</li><li>mean: 250.41 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.23</li><li>max: 0.95</li></ul> |
+* Samples:
+  | sentence1                                                                                               | sentence2                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       | score            |
+  |:--------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
+  | <code>Identify any additional tables or columns that might be needed for the query.</code>              | <code>How are flow computers and measurement systems related?<br>Flow computers can have multiple systems assigned to them. However, a measurement system can only be assigned to one flow computer.<br><br>Database terminology:<br>In the database, this relationship is referred to as:<br>- Meter streams<br>- Meter runs<br>- Sections<br><br>Storage of the relationship:<br>The relationship between a flow computer and its assigned measurement system is stored in a special table.<br><br>User context:<br>When a user refers to a "meter stream," they are indicating that they are searching for a measurement system assigned to a specific flow computer.</code>                                                                                                                                                                                                                                                                                                                                                                                                                 | <code>0.2</code> |
+  | <code>What columns in these tables contain the measurement system tag and the flow computer tag?</code> | <code>How does a flow computer generate and store reports?<br>A flow computer generates daily or hourly reports to provide users with operational data. These reports are stored in the flow computer's memory in an organized format.<br><br>Report structure:<br>- Each report includes:<br>- Date and time of the data recording.<br>- Data recorded from flow computers.<br><br>Data storage in tables:<br>The reports are saved in two tables:<br>1. Main table (Index):<br>    - Stores the date, time, and flow computer identifier.<br>2. Detail table:<br>    - Stores the measured values associated with the report.<br><br>Connection to the Modbus table:<br>The flow computer's reports are linked to a Modbus table. This table contains the names corresponding to each value in the reports, making it easier to interpret the data.</code>                                                                                                                                                                                                                                    | <code>0.1</code> |
+  | <code>Identify the column that stores the calibration number.</code>                                    | <code>What kind of data store an equipment?<br>Equipments can capture meteorological data, such as pressure, temperature, and volume (magnitudes). This data is essential for users to perform various calculations.<br><br>Data storage:<br>- The measured values are stored in a special table in the database for magnitudes. This table contains the values of the variables captured by the equipments.<br>- These values are **direct measurements** from the fluid (e.g., raw pressure, temperature, or volume readings). **They are not calculated values**, such as uncertainty.<br>- The values stored in the variable values table are **different** from variable uncertainty values, which are calculated separately and represent the margin of error.<br><br>Accessing the data:<br>- Users typically access the data by referring to the readings from the measurement system, not directly from the individual equipments.<br>- The readings are stored in a "variable values" table within the database.<br><br>Linking variable names:<br>If the user needs to kno...</code> | <code>0.1</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 7
+- `per_device_eval_batch_size`: 7
+- `gradient_accumulation_steps`: 4
+- `learning_rate`: 3e-05
+- `num_train_epochs`: 20
+- `warmup_ratio`: 0.1
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 7
+- `per_device_eval_batch_size`: 7
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 4
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 20
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+<details><summary>Click to expand</summary>
+
+| Epoch  | Step | Training Loss | Validation Loss |
+|:------:|:----:|:-------------:|:---------------:|
+| 3.9379 | 1060 | 8.5934        | -               |
+| 3.9750 | 1070 | 8.006         | -               |
+| 4.0148 | 1080 | 9.0081        | -               |
+| 4.0519 | 1090 | 8.6706        | -               |
+| 4.0890 | 1100 | 9.6146        | -               |
+| 4.1260 | 1110 | 9.225         | -               |
+| 4.1631 | 1120 | 8.7522        | -               |
+| 4.2002 | 1130 | 9.0221        | -               |
+| 4.2373 | 1140 | 9.6458        | -               |
+| 4.2743 | 1150 | 8.7692        | -               |
+| 4.3114 | 1160 | 9.2874        | -               |
+| 4.3485 | 1170 | 8.9276        | -               |
+| 4.3855 | 1180 | 8.7444        | -               |
+| 4.4226 | 1190 | 8.7265        | -               |
+| 4.4597 | 1200 | 8.7642        | 2.6471          |
+| 4.4968 | 1210 | 8.8917        | -               |
+| 4.5338 | 1220 | 9.2155        | -               |
+| 4.5709 | 1230 | 8.6101        | -               |
+| 4.6080 | 1240 | 8.9904        | -               |
+| 4.6450 | 1250 | 9.3272        | -               |
+| 4.6821 | 1260 | 7.9367        | -               |
+| 4.7192 | 1270 | 8.5891        | -               |
+| 4.7563 | 1280 | 8.6286        | -               |
+| 4.7933 | 1290 | 7.9982        | -               |
+| 4.8304 | 1300 | 7.5587        | -               |
+| 4.8675 | 1310 | 7.9405        | -               |
+| 4.9045 | 1320 | 9.7092        | -               |
+| 4.9416 | 1330 | 8.1475        | -               |
+| 4.9787 | 1340 | 9.3603        | -               |
+| 5.0148 | 1350 | 7.6621        | 2.8309          |
+| 5.0519 | 1360 | 9.2301        | -               |
+| 5.0890 | 1370 | 9.7789        | -               |
+| 5.1260 | 1380 | 9.5359        | -               |
+| 5.1631 | 1390 | 10.8065       | -               |
+| 5.2002 | 1400 | 10.0149       | -               |
+| 5.2373 | 1410 | 10.2582       | -               |
+| 5.2743 | 1420 | 10.16         | -               |
+| 5.3114 | 1430 | 10.0763       | -               |
+| 5.3485 | 1440 | 9.5737        | -               |
+| 5.3855 | 1450 | 10.4816       | -               |
+| 5.4226 | 1460 | 8.6687        | -               |
+| 5.4597 | 1470 | 8.4066        | -               |
+| 5.4968 | 1480 | 9.386         | -               |
+| 5.5338 | 1490 | 8.3911        | -               |
+| 5.5709 | 1500 | 8.8025        | 2.5408          |
+| 5.6080 | 1510 | 8.7939        | -               |
+| 5.6450 | 1520 | 9.0903        | -               |
+| 5.6821 | 1530 | 8.9878        | -               |
+| 5.7192 | 1540 | 8.8642        | -               |
+| 5.7563 | 1550 | 8.8625        | -               |
+| 5.7933 | 1560 | 8.4105        | -               |
+| 5.8304 | 1570 | 9.0163        | -               |
+| 5.8675 | 1580 | 8.8947        | -               |
+| 5.9045 | 1590 | 8.5647        | -               |
+| 5.9416 | 1600 | 7.7047        | -               |
+| 5.9787 | 1610 | 8.1484        | -               |
+| 6.0148 | 1620 | 8.4079        | -               |
+| 6.0519 | 1630 | 8.5027        | -               |
+| 6.0890 | 1640 | 8.1805        | -               |
+| 6.1260 | 1650 | 8.4519        | 2.5901          |
+| 6.1631 | 1660 | 9.062         | -               |
+| 6.2002 | 1670 | 8.8499        | -               |
+| 6.2373 | 1680 | 8.6576        | -               |
+| 6.2743 | 1690 | 8.4652        | -               |
+| 6.3114 | 1700 | 9.0782        | -               |
+| 6.3485 | 1710 | 8.1532        | -               |
+| 6.3855 | 1720 | 8.5185        | -               |
+| 6.4226 | 1730 | 9.5908        | -               |
+| 6.4597 | 1740 | 8.4188        | -               |
+| 6.4968 | 1750 | 8.1885        | -               |
+| 6.5338 | 1760 | 8.7666        | -               |
+| 6.5709 | 1770 | 8.6105        | -               |
+| 6.6080 | 1780 | 8.664         | -               |
+| 6.6450 | 1790 | 8.5294        | -               |
+| 6.6821 | 1800 | 9.1857        | 2.4974          |
+| 6.7192 | 1810 | 8.7053        | -               |
+| 6.7563 | 1820 | 8.1428        | -               |
+| 6.7933 | 1830 | 8.4988        | -               |
+| 6.8304 | 1840 | 8.4147        | -               |
+| 6.8675 | 1850 | 9.069         | -               |
+| 6.9045 | 1860 | 8.4405        | -               |
+| 6.9416 | 1870 | 9.2157        | -               |
+| 6.9787 | 1880 | 9.5492        | -               |
+| 7.0148 | 1890 | 8.1325        | -               |
+| 7.0519 | 1900 | 8.324         | -               |
+| 7.0890 | 1910 | 7.7097        | -               |
+| 7.1260 | 1920 | 8.0982        | -               |
+| 7.1631 | 1930 | 7.7669        | -               |
+| 7.2002 | 1940 | 7.809         | -               |
+| 7.2373 | 1950 | 7.9729        | 2.6108          |
+| 7.2743 | 1960 | 8.2125        | -               |
+| 7.3114 | 1970 | 7.7403        | -               |
+| 7.3485 | 1980 | 7.5494        | -               |
+| 7.3855 | 1990 | 8.2821        | -               |
+| 7.4226 | 2000 | 8.1644        | -               |
+| 7.4597 | 2010 | 8.1664        | -               |
+| 7.4968 | 2020 | 8.5876        | -               |
+| 7.5338 | 2030 | 8.2753        | -               |
+| 7.5709 | 2040 | 9.2057        | -               |
+| 7.6080 | 2050 | 8.0052        | -               |
+| 7.6450 | 2060 | 8.4954        | -               |
+| 7.6821 | 2070 | 8.0325        | -               |
+| 7.7192 | 2080 | 8.2934        | -               |
+| 7.7563 | 2090 | 9.4019        | -               |
+| 7.7933 | 2100 | 8.874         | 2.4529          |
+
+</details>
+
+### Framework Versions
+- Python: 3.11.0
+- Sentence Transformers: 3.4.0
+- Transformers: 4.48.1
+- PyTorch: 2.5.1+cu124
+- Accelerate: 1.3.0
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### CoSENTLoss
+```bibtex
+@online{kexuefm-8847,
+    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
+    author={Su Jianlin},
+    year={2022},
+    month={Jan},
+    url={https://kexue.fm/archives/8847},
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

checkpoints/checkpoint-2100/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "intfloat/multilingual-e5-large-instruct",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoints/checkpoint-2100/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.0",
+    "transformers": "4.48.1",
+    "pytorch": "2.5.1+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

checkpoints/checkpoint-2100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:690def6d143892cb938c38666723b67e3fadc2c8742db467a85f87d3469cdf26
+size 2239607176

checkpoints/checkpoint-2100/modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

checkpoints/checkpoint-2100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee30b298b72c4d8c5e43844b1faaee343b6f8ceab6a05566df0669c706e128e4
+size 4471055801

checkpoints/checkpoint-2100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d20ac3073e25eec89f0d8cf5386459d4d2970de1ef20dcf48a7df197349309
+size 14244

checkpoints/checkpoint-2100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83ed6b752a686709c20beb6df24fd2b2f23ca8bc8f67bc7391af12aa2f7d9090
+size 1064

checkpoints/checkpoint-2100/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

checkpoints/checkpoint-2100/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoints/checkpoint-2100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

checkpoints/checkpoint-2100/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoints/checkpoint-2100/trainer_state.json

@@ -0,0 +1,1615 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.793327154772938,
+  "eval_steps": 150,
+  "global_step": 2100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03707136237256719,
+      "grad_norm": 53.36411666870117,
+      "learning_rate": 1.1152416356877324e-06,
+      "loss": 10.8165,
+      "step": 10
+    },
+    {
+      "epoch": 0.07414272474513438,
+      "grad_norm": 61.33858871459961,
+      "learning_rate": 2.2304832713754648e-06,
+      "loss": 10.8463,
+      "step": 20
+    },
+    {
+      "epoch": 0.11121408711770157,
+      "grad_norm": 67.16305541992188,
+      "learning_rate": 3.345724907063197e-06,
+      "loss": 10.821,
+      "step": 30
+    },
+    {
+      "epoch": 0.14828544949026876,
+      "grad_norm": 62.08958053588867,
+      "learning_rate": 4.4609665427509296e-06,
+      "loss": 10.4704,
+      "step": 40
+    },
+    {
+      "epoch": 0.18535681186283595,
+      "grad_norm": 53.839927673339844,
+      "learning_rate": 5.576208178438661e-06,
+      "loss": 10.8568,
+      "step": 50
+    },
+    {
+      "epoch": 0.22242817423540315,
+      "grad_norm": 57.02272033691406,
+      "learning_rate": 6.691449814126394e-06,
+      "loss": 10.3005,
+      "step": 60
+    },
+    {
+      "epoch": 0.2594995366079703,
+      "grad_norm": 88.16449737548828,
+      "learning_rate": 7.806691449814127e-06,
+      "loss": 9.6009,
+      "step": 70
+    },
+    {
+      "epoch": 0.2965708989805375,
+      "grad_norm": 84.35252380371094,
+      "learning_rate": 8.921933085501859e-06,
+      "loss": 9.7448,
+      "step": 80
+    },
+    {
+      "epoch": 0.3336422613531047,
+      "grad_norm": 77.93982696533203,
+      "learning_rate": 1.0037174721189593e-05,
+      "loss": 9.5922,
+      "step": 90
+    },
+    {
+      "epoch": 0.3707136237256719,
+      "grad_norm": 56.669166564941406,
+      "learning_rate": 1.1152416356877323e-05,
+      "loss": 10.0919,
+      "step": 100
+    },
+    {
+      "epoch": 0.4077849860982391,
+      "grad_norm": 56.652488708496094,
+      "learning_rate": 1.2267657992565056e-05,
+      "loss": 10.2733,
+      "step": 110
+    },
+    {
+      "epoch": 0.4448563484708063,
+      "grad_norm": 63.472042083740234,
+      "learning_rate": 1.3382899628252788e-05,
+      "loss": 9.4547,
+      "step": 120
+    },
+    {
+      "epoch": 0.4819277108433735,
+      "grad_norm": 78.0159912109375,
+      "learning_rate": 1.4498141263940521e-05,
+      "loss": 9.1738,
+      "step": 130
+    },
+    {
+      "epoch": 0.5189990732159406,
+      "grad_norm": 68.1931381225586,
+      "learning_rate": 1.5613382899628255e-05,
+      "loss": 10.0876,
+      "step": 140
+    },
+    {
+      "epoch": 0.5560704355885079,
+      "grad_norm": 49.315216064453125,
+      "learning_rate": 1.6728624535315986e-05,
+      "loss": 10.3721,
+      "step": 150
+    },
+    {
+      "epoch": 0.5560704355885079,
+      "eval_loss": 2.559400796890259,
+      "eval_runtime": 34.304,
+      "eval_samples_per_second": 47.166,
+      "eval_steps_per_second": 6.763,
+      "step": 150
+    },
+    {
+      "epoch": 0.593141797961075,
+      "grad_norm": 34.1899528503418,
+      "learning_rate": 1.7843866171003718e-05,
+      "loss": 10.4711,
+      "step": 160
+    },
+    {
+      "epoch": 0.6302131603336423,
+      "grad_norm": 37.074134826660156,
+      "learning_rate": 1.895910780669145e-05,
+      "loss": 9.9383,
+      "step": 170
+    },
+    {
+      "epoch": 0.6672845227062094,
+      "grad_norm": 49.323158264160156,
+      "learning_rate": 2.0074349442379185e-05,
+      "loss": 10.0448,
+      "step": 180
+    },
+    {
+      "epoch": 0.7043558850787767,
+      "grad_norm": 53.07639694213867,
+      "learning_rate": 2.1189591078066917e-05,
+      "loss": 9.8467,
+      "step": 190
+    },
+    {
+      "epoch": 0.7414272474513438,
+      "grad_norm": 38.345916748046875,
+      "learning_rate": 2.2304832713754645e-05,
+      "loss": 9.9434,
+      "step": 200
+    },
+    {
+      "epoch": 0.7784986098239111,
+      "grad_norm": 47.55274963378906,
+      "learning_rate": 2.3420074349442377e-05,
+      "loss": 9.7912,
+      "step": 210
+    },
+    {
+      "epoch": 0.8155699721964782,
+      "grad_norm": 59.17176055908203,
+      "learning_rate": 2.4535315985130112e-05,
+      "loss": 9.7905,
+      "step": 220
+    },
+    {
+      "epoch": 0.8526413345690455,
+      "grad_norm": 52.57457733154297,
+      "learning_rate": 2.5650557620817844e-05,
+      "loss": 9.9412,
+      "step": 230
+    },
+    {
+      "epoch": 0.8897126969416126,
+      "grad_norm": 42.251304626464844,
+      "learning_rate": 2.6765799256505576e-05,
+      "loss": 10.0084,
+      "step": 240
+    },
+    {
+      "epoch": 0.9267840593141798,
+      "grad_norm": 46.63966369628906,
+      "learning_rate": 2.788104089219331e-05,
+      "loss": 10.0139,
+      "step": 250
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 27.772289276123047,
+      "learning_rate": 2.8996282527881043e-05,
+      "loss": 9.3794,
+      "step": 260
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 46.3179931640625,
+      "learning_rate": 2.9987608426270136e-05,
+      "loss": 9.5747,
+      "step": 270
+    },
+    {
+      "epoch": 1.0370713623725671,
+      "grad_norm": 45.746551513671875,
+      "learning_rate": 2.98636926889715e-05,
+      "loss": 9.6763,
+      "step": 280
+    },
+    {
+      "epoch": 1.0741427247451343,
+      "grad_norm": 49.50416564941406,
+      "learning_rate": 2.9739776951672864e-05,
+      "loss": 10.4789,
+      "step": 290
+    },
+    {
+      "epoch": 1.1112140871177016,
+      "grad_norm": 43.72733688354492,
+      "learning_rate": 2.9615861214374226e-05,
+      "loss": 9.7244,
+      "step": 300
+    },
+    {
+      "epoch": 1.1112140871177016,
+      "eval_loss": 2.6879734992980957,
+      "eval_runtime": 34.2522,
+      "eval_samples_per_second": 47.238,
+      "eval_steps_per_second": 6.773,
+      "step": 300
+    },
+    {
+      "epoch": 1.1482854494902688,
+      "grad_norm": 48.68376541137695,
+      "learning_rate": 2.9491945477075588e-05,
+      "loss": 9.9421,
+      "step": 310
+    },
+    {
+      "epoch": 1.185356811862836,
+      "grad_norm": 44.014747619628906,
+      "learning_rate": 2.9368029739776953e-05,
+      "loss": 9.5022,
+      "step": 320
+    },
+    {
+      "epoch": 1.222428174235403,
+      "grad_norm": 49.858642578125,
+      "learning_rate": 2.9244114002478315e-05,
+      "loss": 9.6801,
+      "step": 330
+    },
+    {
+      "epoch": 1.2594995366079704,
+      "grad_norm": 49.97459411621094,
+      "learning_rate": 2.9120198265179677e-05,
+      "loss": 9.25,
+      "step": 340
+    },
+    {
+      "epoch": 1.2965708989805376,
+      "grad_norm": 40.38698196411133,
+      "learning_rate": 2.8996282527881043e-05,
+      "loss": 10.2879,
+      "step": 350
+    },
+    {
+      "epoch": 1.3336422613531047,
+      "grad_norm": 29.797264099121094,
+      "learning_rate": 2.8872366790582405e-05,
+      "loss": 9.97,
+      "step": 360
+    },
+    {
+      "epoch": 1.3707136237256718,
+      "grad_norm": 43.83412551879883,
+      "learning_rate": 2.874845105328377e-05,
+      "loss": 9.3751,
+      "step": 370
+    },
+    {
+      "epoch": 1.407784986098239,
+      "grad_norm": 42.754154205322266,
+      "learning_rate": 2.8624535315985132e-05,
+      "loss": 9.8947,
+      "step": 380
+    },
+    {
+      "epoch": 1.4448563484708064,
+      "grad_norm": 50.08184051513672,
+      "learning_rate": 2.8500619578686494e-05,
+      "loss": 9.4987,
+      "step": 390
+    },
+    {
+      "epoch": 1.4819277108433735,
+      "grad_norm": 41.81029510498047,
+      "learning_rate": 2.8376703841387856e-05,
+      "loss": 10.1515,
+      "step": 400
+    },
+    {
+      "epoch": 1.5189990732159406,
+      "grad_norm": 44.03816223144531,
+      "learning_rate": 2.8252788104089218e-05,
+      "loss": 10.0098,
+      "step": 410
+    },
+    {
+      "epoch": 1.556070435588508,
+      "grad_norm": 42.871856689453125,
+      "learning_rate": 2.8128872366790583e-05,
+      "loss": 9.5566,
+      "step": 420
+    },
+    {
+      "epoch": 1.5931417979610751,
+      "grad_norm": 44.18041229248047,
+      "learning_rate": 2.8004956629491945e-05,
+      "loss": 10.1925,
+      "step": 430
+    },
+    {
+      "epoch": 1.6302131603336423,
+      "grad_norm": 30.012725830078125,
+      "learning_rate": 2.788104089219331e-05,
+      "loss": 9.7408,
+      "step": 440
+    },
+    {
+      "epoch": 1.6672845227062094,
+      "grad_norm": 38.104827880859375,
+      "learning_rate": 2.7757125154894673e-05,
+      "loss": 9.6873,
+      "step": 450
+    },
+    {
+      "epoch": 1.6672845227062094,
+      "eval_loss": 2.5061004161834717,
+      "eval_runtime": 34.2772,
+      "eval_samples_per_second": 47.203,
+      "eval_steps_per_second": 6.768,
+      "step": 450
+    },
+    {
+      "epoch": 1.7043558850787766,
+      "grad_norm": 42.93535232543945,
+      "learning_rate": 2.7633209417596035e-05,
+      "loss": 9.1932,
+      "step": 460
+    },
+    {
+      "epoch": 1.7414272474513437,
+      "grad_norm": 63.935279846191406,
+      "learning_rate": 2.75092936802974e-05,
+      "loss": 9.9204,
+      "step": 470
+    },
+    {
+      "epoch": 1.778498609823911,
+      "grad_norm": 30.906002044677734,
+      "learning_rate": 2.7385377942998762e-05,
+      "loss": 9.5151,
+      "step": 480
+    },
+    {
+      "epoch": 1.8155699721964782,
+      "grad_norm": 48.05679702758789,
+      "learning_rate": 2.7261462205700128e-05,
+      "loss": 9.8418,
+      "step": 490
+    },
+    {
+      "epoch": 1.8526413345690456,
+      "grad_norm": 56.36283874511719,
+      "learning_rate": 2.7137546468401486e-05,
+      "loss": 9.6943,
+      "step": 500
+    },
+    {
+      "epoch": 1.8897126969416127,
+      "grad_norm": 47.22933578491211,
+      "learning_rate": 2.7013630731102848e-05,
+      "loss": 9.6948,
+      "step": 510
+    },
+    {
+      "epoch": 1.9267840593141798,
+      "grad_norm": 36.110008239746094,
+      "learning_rate": 2.6889714993804214e-05,
+      "loss": 9.2274,
+      "step": 520
+    },
+    {
+      "epoch": 1.963855421686747,
+      "grad_norm": 37.13912582397461,
+      "learning_rate": 2.6765799256505576e-05,
+      "loss": 10.138,
+      "step": 530
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 51.37559509277344,
+      "learning_rate": 2.664188351920694e-05,
+      "loss": 8.7934,
+      "step": 540
+    },
+    {
+      "epoch": 2.037071362372567,
+      "grad_norm": 42.32170104980469,
+      "learning_rate": 2.6517967781908303e-05,
+      "loss": 8.8304,
+      "step": 550
+    },
+    {
+      "epoch": 2.0741427247451343,
+      "grad_norm": 42.406219482421875,
+      "learning_rate": 2.6394052044609665e-05,
+      "loss": 8.9593,
+      "step": 560
+    },
+    {
+      "epoch": 2.1112140871177014,
+      "grad_norm": 52.097023010253906,
+      "learning_rate": 2.627013630731103e-05,
+      "loss": 9.0051,
+      "step": 570
+    },
+    {
+      "epoch": 2.1482854494902686,
+      "grad_norm": 83.86861419677734,
+      "learning_rate": 2.6146220570012392e-05,
+      "loss": 9.2829,
+      "step": 580
+    },
+    {
+      "epoch": 2.185356811862836,
+      "grad_norm": 38.229949951171875,
+      "learning_rate": 2.6022304832713758e-05,
+      "loss": 9.785,
+      "step": 590
+    },
+    {
+      "epoch": 2.2224281742354033,
+      "grad_norm": 50.322513580322266,
+      "learning_rate": 2.5898389095415116e-05,
+      "loss": 9.6401,
+      "step": 600
+    },
+    {
+      "epoch": 2.2224281742354033,
+      "eval_loss": 2.448084592819214,
+      "eval_runtime": 34.2525,
+      "eval_samples_per_second": 47.237,
+      "eval_steps_per_second": 6.773,
+      "step": 600
+    },
+    {
+      "epoch": 2.266913809082484,
+      "grad_norm": 39.366676330566406,
+      "learning_rate": 2.5774473358116482e-05,
+      "loss": 8.7059,
+      "step": 610
+    },
+    {
+      "epoch": 2.303985171455051,
+      "grad_norm": 41.00213623046875,
+      "learning_rate": 2.5650557620817844e-05,
+      "loss": 9.1285,
+      "step": 620
+    },
+    {
+      "epoch": 2.341056533827618,
+      "grad_norm": 63.442169189453125,
+      "learning_rate": 2.5526641883519206e-05,
+      "loss": 9.3277,
+      "step": 630
+    },
+    {
+      "epoch": 2.3781278962001853,
+      "grad_norm": 51.54194641113281,
+      "learning_rate": 2.540272614622057e-05,
+      "loss": 9.1577,
+      "step": 640
+    },
+    {
+      "epoch": 2.4151992585727524,
+      "grad_norm": 57.583885192871094,
+      "learning_rate": 2.5278810408921933e-05,
+      "loss": 9.6032,
+      "step": 650
+    },
+    {
+      "epoch": 2.4522706209453196,
+      "grad_norm": 60.13545227050781,
+      "learning_rate": 2.51548946716233e-05,
+      "loss": 8.5451,
+      "step": 660
+    },
+    {
+      "epoch": 2.489341983317887,
+      "grad_norm": 139.85794067382812,
+      "learning_rate": 2.503097893432466e-05,
+      "loss": 8.6601,
+      "step": 670
+    },
+    {
+      "epoch": 2.5264133456904543,
+      "grad_norm": 160.73171997070312,
+      "learning_rate": 2.4907063197026023e-05,
+      "loss": 9.522,
+      "step": 680
+    },
+    {
+      "epoch": 2.5634847080630214,
+      "grad_norm": 190.7194366455078,
+      "learning_rate": 2.4783147459727385e-05,
+      "loss": 10.0619,
+      "step": 690
+    },
+    {
+      "epoch": 2.6005560704355886,
+      "grad_norm": 172.5655517578125,
+      "learning_rate": 2.4659231722428747e-05,
+      "loss": 9.6444,
+      "step": 700
+    },
+    {
+      "epoch": 2.6376274328081557,
+      "grad_norm": 280.9183044433594,
+      "learning_rate": 2.4535315985130112e-05,
+      "loss": 10.7593,
+      "step": 710
+    },
+    {
+      "epoch": 2.674698795180723,
+      "grad_norm": 118.03450775146484,
+      "learning_rate": 2.4411400247831474e-05,
+      "loss": 10.4432,
+      "step": 720
+    },
+    {
+      "epoch": 2.71177015755329,
+      "grad_norm": 332.662353515625,
+      "learning_rate": 2.428748451053284e-05,
+      "loss": 9.6033,
+      "step": 730
+    },
+    {
+      "epoch": 2.748841519925857,
+      "grad_norm": 129.18788146972656,
+      "learning_rate": 2.41635687732342e-05,
+      "loss": 9.108,
+      "step": 740
+    },
+    {
+      "epoch": 2.7859128822984243,
+      "grad_norm": 350.5856628417969,
+      "learning_rate": 2.4039653035935564e-05,
+      "loss": 9.884,
+      "step": 750
+    },
+    {
+      "epoch": 2.7859128822984243,
+      "eval_loss": 2.599517583847046,
+      "eval_runtime": 34.0592,
+      "eval_samples_per_second": 47.506,
+      "eval_steps_per_second": 6.812,
+      "step": 750
+    },
+    {
+      "epoch": 2.822984244670992,
+      "grad_norm": 285.14862060546875,
+      "learning_rate": 2.391573729863693e-05,
+      "loss": 11.3952,
+      "step": 760
+    },
+    {
+      "epoch": 2.860055607043559,
+      "grad_norm": 185.5862579345703,
+      "learning_rate": 2.379182156133829e-05,
+      "loss": 10.6798,
+      "step": 770
+    },
+    {
+      "epoch": 2.897126969416126,
+      "grad_norm": 77.20765686035156,
+      "learning_rate": 2.3667905824039656e-05,
+      "loss": 9.9795,
+      "step": 780
+    },
+    {
+      "epoch": 2.9341983317886933,
+      "grad_norm": 88.75109100341797,
+      "learning_rate": 2.3543990086741015e-05,
+      "loss": 9.3694,
+      "step": 790
+    },
+    {
+      "epoch": 2.9712696941612604,
+      "grad_norm": 53.416690826416016,
+      "learning_rate": 2.3420074349442377e-05,
+      "loss": 8.4631,
+      "step": 800
+    },
+    {
+      "epoch": 3.0111214087117704,
+      "grad_norm": 72.12966918945312,
+      "learning_rate": 2.3296158612143742e-05,
+      "loss": 9.3903,
+      "step": 810
+    },
+    {
+      "epoch": 3.0481927710843375,
+      "grad_norm": 159.3909912109375,
+      "learning_rate": 2.3172242874845104e-05,
+      "loss": 8.9608,
+      "step": 820
+    },
+    {
+      "epoch": 3.0852641334569046,
+      "grad_norm": 161.03713989257812,
+      "learning_rate": 2.304832713754647e-05,
+      "loss": 9.623,
+      "step": 830
+    },
+    {
+      "epoch": 3.122335495829472,
+      "grad_norm": 136.50045776367188,
+      "learning_rate": 2.2924411400247832e-05,
+      "loss": 8.5958,
+      "step": 840
+    },
+    {
+      "epoch": 3.159406858202039,
+      "grad_norm": 60.785926818847656,
+      "learning_rate": 2.2800495662949197e-05,
+      "loss": 8.6278,
+      "step": 850
+    },
+    {
+      "epoch": 3.196478220574606,
+      "grad_norm": 115.2509536743164,
+      "learning_rate": 2.267657992565056e-05,
+      "loss": 8.661,
+      "step": 860
+    },
+    {
+      "epoch": 3.233549582947173,
+      "grad_norm": 144.38912963867188,
+      "learning_rate": 2.255266418835192e-05,
+      "loss": 9.5836,
+      "step": 870
+    },
+    {
+      "epoch": 3.2706209453197403,
+      "grad_norm": 239.74520874023438,
+      "learning_rate": 2.2428748451053287e-05,
+      "loss": 8.6221,
+      "step": 880
+    },
+    {
+      "epoch": 3.3076923076923075,
+      "grad_norm": 215.12789916992188,
+      "learning_rate": 2.2304832713754645e-05,
+      "loss": 9.1995,
+      "step": 890
+    },
+    {
+      "epoch": 3.344763670064875,
+      "grad_norm": 113.77183532714844,
+      "learning_rate": 2.218091697645601e-05,
+      "loss": 8.6909,
+      "step": 900
+    },
+    {
+      "epoch": 3.344763670064875,
+      "eval_loss": 2.4246325492858887,
+      "eval_runtime": 34.1351,
+      "eval_samples_per_second": 47.4,
+      "eval_steps_per_second": 6.797,
+      "step": 900
+    },
+    {
+      "epoch": 3.381835032437442,
+      "grad_norm": 175.02731323242188,
+      "learning_rate": 2.2057001239157373e-05,
+      "loss": 8.7632,
+      "step": 910
+    },
+    {
+      "epoch": 3.4189063948100094,
+      "grad_norm": 142.76580810546875,
+      "learning_rate": 2.1933085501858735e-05,
+      "loss": 8.5604,
+      "step": 920
+    },
+    {
+      "epoch": 3.4559777571825765,
+      "grad_norm": 163.0391387939453,
+      "learning_rate": 2.18091697645601e-05,
+      "loss": 9.3871,
+      "step": 930
+    },
+    {
+      "epoch": 3.4930491195551436,
+      "grad_norm": 386.4294738769531,
+      "learning_rate": 2.1685254027261462e-05,
+      "loss": 9.6445,
+      "step": 940
+    },
+    {
+      "epoch": 3.5301204819277108,
+      "grad_norm": 86.92581939697266,
+      "learning_rate": 2.1561338289962827e-05,
+      "loss": 9.635,
+      "step": 950
+    },
+    {
+      "epoch": 3.567191844300278,
+      "grad_norm": 80.94845581054688,
+      "learning_rate": 2.143742255266419e-05,
+      "loss": 8.8689,
+      "step": 960
+    },
+    {
+      "epoch": 3.6042632066728455,
+      "grad_norm": 69.99708557128906,
+      "learning_rate": 2.1313506815365555e-05,
+      "loss": 9.1411,
+      "step": 970
+    },
+    {
+      "epoch": 3.641334569045412,
+      "grad_norm": 80.53229522705078,
+      "learning_rate": 2.1189591078066917e-05,
+      "loss": 8.7552,
+      "step": 980
+    },
+    {
+      "epoch": 3.67840593141798,
+      "grad_norm": 53.3475341796875,
+      "learning_rate": 2.1065675340768275e-05,
+      "loss": 8.5697,
+      "step": 990
+    },
+    {
+      "epoch": 3.715477293790547,
+      "grad_norm": 54.19875717163086,
+      "learning_rate": 2.094175960346964e-05,
+      "loss": 8.9008,
+      "step": 1000
+    },
+    {
+      "epoch": 3.752548656163114,
+      "grad_norm": 52.96628952026367,
+      "learning_rate": 2.0817843866171003e-05,
+      "loss": 8.9415,
+      "step": 1010
+    },
+    {
+      "epoch": 3.789620018535681,
+      "grad_norm": 64.08312225341797,
+      "learning_rate": 2.0693928128872368e-05,
+      "loss": 8.1303,
+      "step": 1020
+    },
+    {
+      "epoch": 3.8266913809082483,
+      "grad_norm": 68.22163391113281,
+      "learning_rate": 2.057001239157373e-05,
+      "loss": 8.241,
+      "step": 1030
+    },
+    {
+      "epoch": 3.8637627432808155,
+      "grad_norm": 66.70902252197266,
+      "learning_rate": 2.0446096654275092e-05,
+      "loss": 8.6969,
+      "step": 1040
+    },
+    {
+      "epoch": 3.9008341056533826,
+      "grad_norm": 49.94658279418945,
+      "learning_rate": 2.0322180916976458e-05,
+      "loss": 9.8392,
+      "step": 1050
+    },
+    {
+      "epoch": 3.9008341056533826,
+      "eval_loss": 2.533297300338745,
+      "eval_runtime": 34.1106,
+      "eval_samples_per_second": 47.434,
+      "eval_steps_per_second": 6.801,
+      "step": 1050
+    },
+    {
+      "epoch": 3.93790546802595,
+      "grad_norm": 73.9527816772461,
+      "learning_rate": 2.6765799256505576e-05,
+      "loss": 8.5934,
+      "step": 1060
+    },
+    {
+      "epoch": 3.974976830398517,
+      "grad_norm": 76.90135955810547,
+      "learning_rate": 2.6703841387856257e-05,
+      "loss": 8.006,
+      "step": 1070
+    },
+    {
+      "epoch": 4.014828544949027,
+      "grad_norm": 85.86236572265625,
+      "learning_rate": 2.664188351920694e-05,
+      "loss": 9.0081,
+      "step": 1080
+    },
+    {
+      "epoch": 4.051899907321594,
+      "grad_norm": 106.57842254638672,
+      "learning_rate": 2.6579925650557622e-05,
+      "loss": 8.6706,
+      "step": 1090
+    },
+    {
+      "epoch": 4.088971269694161,
+      "grad_norm": 68.10344696044922,
+      "learning_rate": 2.6517967781908303e-05,
+      "loss": 9.6146,
+      "step": 1100
+    },
+    {
+      "epoch": 4.126042632066729,
+      "grad_norm": 67.02091217041016,
+      "learning_rate": 2.6456009913258984e-05,
+      "loss": 9.225,
+      "step": 1110
+    },
+    {
+      "epoch": 4.163113994439295,
+      "grad_norm": 67.66644287109375,
+      "learning_rate": 2.6394052044609665e-05,
+      "loss": 8.7522,
+      "step": 1120
+    },
+    {
+      "epoch": 4.200185356811863,
+      "grad_norm": 59.26814651489258,
+      "learning_rate": 2.633209417596035e-05,
+      "loss": 9.0221,
+      "step": 1130
+    },
+    {
+      "epoch": 4.23725671918443,
+      "grad_norm": 88.07310485839844,
+      "learning_rate": 2.627013630731103e-05,
+      "loss": 9.6458,
+      "step": 1140
+    },
+    {
+      "epoch": 4.274328081556997,
+      "grad_norm": 69.33895874023438,
+      "learning_rate": 2.620817843866171e-05,
+      "loss": 8.7692,
+      "step": 1150
+    },
+    {
+      "epoch": 4.311399443929565,
+      "grad_norm": 43.823951721191406,
+      "learning_rate": 2.6146220570012392e-05,
+      "loss": 9.2874,
+      "step": 1160
+    },
+    {
+      "epoch": 4.348470806302132,
+      "grad_norm": 63.590980529785156,
+      "learning_rate": 2.6084262701363077e-05,
+      "loss": 8.9276,
+      "step": 1170
+    },
+    {
+      "epoch": 4.385542168674699,
+      "grad_norm": 43.4519157409668,
+      "learning_rate": 2.6022304832713758e-05,
+      "loss": 8.7444,
+      "step": 1180
+    },
+    {
+      "epoch": 4.422613531047266,
+      "grad_norm": 72.1529312133789,
+      "learning_rate": 2.5960346964064435e-05,
+      "loss": 8.7265,
+      "step": 1190
+    },
+    {
+      "epoch": 4.459684893419833,
+      "grad_norm": 101.67008972167969,
+      "learning_rate": 2.5898389095415116e-05,
+      "loss": 8.7642,
+      "step": 1200
+    },
+    {
+      "epoch": 4.459684893419833,
+      "eval_loss": 2.6471314430236816,
+      "eval_runtime": 34.2723,
+      "eval_samples_per_second": 47.21,
+      "eval_steps_per_second": 6.769,
+      "step": 1200
+    },
+    {
+      "epoch": 4.4967562557924,
+      "grad_norm": 66.03606414794922,
+      "learning_rate": 2.5836431226765797e-05,
+      "loss": 8.8917,
+      "step": 1210
+    },
+    {
+      "epoch": 4.533827618164968,
+      "grad_norm": 60.01662826538086,
+      "learning_rate": 2.5774473358116482e-05,
+      "loss": 9.2155,
+      "step": 1220
+    },
+    {
+      "epoch": 4.570898980537534,
+      "grad_norm": 83.86510467529297,
+      "learning_rate": 2.5712515489467163e-05,
+      "loss": 8.6101,
+      "step": 1230
+    },
+    {
+      "epoch": 4.607970342910102,
+      "grad_norm": 64.35486602783203,
+      "learning_rate": 2.5650557620817844e-05,
+      "loss": 8.9904,
+      "step": 1240
+    },
+    {
+      "epoch": 4.645041705282669,
+      "grad_norm": 60.44017791748047,
+      "learning_rate": 2.5588599752168525e-05,
+      "loss": 9.3272,
+      "step": 1250
+    },
+    {
+      "epoch": 4.682113067655236,
+      "grad_norm": 56.501102447509766,
+      "learning_rate": 2.5526641883519206e-05,
+      "loss": 7.9367,
+      "step": 1260
+    },
+    {
+      "epoch": 4.719184430027804,
+      "grad_norm": 65.01017761230469,
+      "learning_rate": 2.546468401486989e-05,
+      "loss": 8.5891,
+      "step": 1270
+    },
+    {
+      "epoch": 4.7562557924003706,
+      "grad_norm": 63.42623519897461,
+      "learning_rate": 2.540272614622057e-05,
+      "loss": 8.6286,
+      "step": 1280
+    },
+    {
+      "epoch": 4.793327154772938,
+      "grad_norm": 58.96747589111328,
+      "learning_rate": 2.5340768277571252e-05,
+      "loss": 7.9982,
+      "step": 1290
+    },
+    {
+      "epoch": 4.830398517145505,
+      "grad_norm": 96.77368927001953,
+      "learning_rate": 2.5278810408921933e-05,
+      "loss": 7.5587,
+      "step": 1300
+    },
+    {
+      "epoch": 4.867469879518072,
+      "grad_norm": 85.92269897460938,
+      "learning_rate": 2.5216852540272614e-05,
+      "loss": 7.9405,
+      "step": 1310
+    },
+    {
+      "epoch": 4.904541241890639,
+      "grad_norm": 86.37085723876953,
+      "learning_rate": 2.51548946716233e-05,
+      "loss": 9.7092,
+      "step": 1320
+    },
+    {
+      "epoch": 4.941612604263207,
+      "grad_norm": 65.88274383544922,
+      "learning_rate": 2.509293680297398e-05,
+      "loss": 8.1475,
+      "step": 1330
+    },
+    {
+      "epoch": 4.978683966635774,
+      "grad_norm": 53.252742767333984,
+      "learning_rate": 2.503097893432466e-05,
+      "loss": 9.3603,
+      "step": 1340
+    },
+    {
+      "epoch": 5.014828544949027,
+      "grad_norm": 182.35781860351562,
+      "learning_rate": 2.4969021065675342e-05,
+      "loss": 7.6621,
+      "step": 1350
+    },
+    {
+      "epoch": 5.014828544949027,
+      "eval_loss": 2.8308892250061035,
+      "eval_runtime": 34.1063,
+      "eval_samples_per_second": 47.44,
+      "eval_steps_per_second": 6.802,
+      "step": 1350
+    },
+    {
+      "epoch": 5.051899907321594,
+      "grad_norm": 324.6659240722656,
+      "learning_rate": 2.4907063197026023e-05,
+      "loss": 9.2301,
+      "step": 1360
+    },
+    {
+      "epoch": 5.088971269694161,
+      "grad_norm": 4839.4453125,
+      "learning_rate": 2.4845105328376707e-05,
+      "loss": 9.7789,
+      "step": 1370
+    },
+    {
+      "epoch": 5.126042632066729,
+      "grad_norm": 408588.40625,
+      "learning_rate": 2.4783147459727385e-05,
+      "loss": 9.5359,
+      "step": 1380
+    },
+    {
+      "epoch": 5.163113994439295,
+      "grad_norm": 932.5144653320312,
+      "learning_rate": 2.4721189591078066e-05,
+      "loss": 10.8065,
+      "step": 1390
+    },
+    {
+      "epoch": 5.200185356811863,
+      "grad_norm": 148.0634765625,
+      "learning_rate": 2.4659231722428747e-05,
+      "loss": 10.0149,
+      "step": 1400
+    },
+    {
+      "epoch": 5.23725671918443,
+      "grad_norm": 1214.7279052734375,
+      "learning_rate": 2.459727385377943e-05,
+      "loss": 10.2582,
+      "step": 1410
+    },
+    {
+      "epoch": 5.274328081556997,
+      "grad_norm": 188.14292907714844,
+      "learning_rate": 2.4535315985130112e-05,
+      "loss": 10.16,
+      "step": 1420
+    },
+    {
+      "epoch": 5.311399443929565,
+      "grad_norm": 388.7134094238281,
+      "learning_rate": 2.4473358116480793e-05,
+      "loss": 10.0763,
+      "step": 1430
+    },
+    {
+      "epoch": 5.348470806302132,
+      "grad_norm": 270.61279296875,
+      "learning_rate": 2.4411400247831474e-05,
+      "loss": 9.5737,
+      "step": 1440
+    },
+    {
+      "epoch": 5.385542168674699,
+      "grad_norm": 1637.854736328125,
+      "learning_rate": 2.4349442379182155e-05,
+      "loss": 10.4816,
+      "step": 1450
+    },
+    {
+      "epoch": 5.422613531047266,
+      "grad_norm": 1118.7012939453125,
+      "learning_rate": 2.428748451053284e-05,
+      "loss": 8.6687,
+      "step": 1460
+    },
+    {
+      "epoch": 5.459684893419833,
+      "grad_norm": 788.9707641601562,
+      "learning_rate": 2.422552664188352e-05,
+      "loss": 8.4066,
+      "step": 1470
+    },
+    {
+      "epoch": 5.4967562557924,
+      "grad_norm": 185.22950744628906,
+      "learning_rate": 2.41635687732342e-05,
+      "loss": 9.386,
+      "step": 1480
+    },
+    {
+      "epoch": 5.533827618164968,
+      "grad_norm": 257.726806640625,
+      "learning_rate": 2.4101610904584883e-05,
+      "loss": 8.3911,
+      "step": 1490
+    },
+    {
+      "epoch": 5.570898980537534,
+      "grad_norm": 867.30908203125,
+      "learning_rate": 2.4039653035935564e-05,
+      "loss": 8.8025,
+      "step": 1500
+    },
+    {
+      "epoch": 5.570898980537534,
+      "eval_loss": 2.5407650470733643,
+      "eval_runtime": 34.0934,
+      "eval_samples_per_second": 47.458,
+      "eval_steps_per_second": 6.805,
+      "step": 1500
+    },
+    {
+      "epoch": 5.607970342910102,
+      "grad_norm": 68.35711669921875,
+      "learning_rate": 2.3977695167286248e-05,
+      "loss": 8.7939,
+      "step": 1510
+    },
+    {
+      "epoch": 5.645041705282669,
+      "grad_norm": 1419.1650390625,
+      "learning_rate": 2.391573729863693e-05,
+      "loss": 9.0903,
+      "step": 1520
+    },
+    {
+      "epoch": 5.682113067655236,
+      "grad_norm": 60.88732147216797,
+      "learning_rate": 2.385377942998761e-05,
+      "loss": 8.9878,
+      "step": 1530
+    },
+    {
+      "epoch": 5.719184430027804,
+      "grad_norm": 61.50148010253906,
+      "learning_rate": 2.379182156133829e-05,
+      "loss": 8.8642,
+      "step": 1540
+    },
+    {
+      "epoch": 5.7562557924003706,
+      "grad_norm": 73.9307861328125,
+      "learning_rate": 2.3729863692688972e-05,
+      "loss": 8.8625,
+      "step": 1550
+    },
+    {
+      "epoch": 5.793327154772938,
+      "grad_norm": 82.28329467773438,
+      "learning_rate": 2.3667905824039656e-05,
+      "loss": 8.4105,
+      "step": 1560
+    },
+    {
+      "epoch": 5.830398517145505,
+      "grad_norm": 83.54141235351562,
+      "learning_rate": 2.3605947955390337e-05,
+      "loss": 9.0163,
+      "step": 1570
+    },
+    {
+      "epoch": 5.867469879518072,
+      "grad_norm": 66.59397888183594,
+      "learning_rate": 2.3543990086741015e-05,
+      "loss": 8.8947,
+      "step": 1580
+    },
+    {
+      "epoch": 5.904541241890639,
+      "grad_norm": 55.8841667175293,
+      "learning_rate": 2.3482032218091696e-05,
+      "loss": 8.5647,
+      "step": 1590
+    },
+    {
+      "epoch": 5.941612604263207,
+      "grad_norm": 74.56892395019531,
+      "learning_rate": 2.3420074349442377e-05,
+      "loss": 7.7047,
+      "step": 1600
+    },
+    {
+      "epoch": 5.978683966635774,
+      "grad_norm": 106.54405212402344,
+      "learning_rate": 2.335811648079306e-05,
+      "loss": 8.1484,
+      "step": 1610
+    },
+    {
+      "epoch": 6.014828544949027,
+      "grad_norm": 107.8216781616211,
+      "learning_rate": 2.3296158612143742e-05,
+      "loss": 8.4079,
+      "step": 1620
+    },
+    {
+      "epoch": 6.051899907321594,
+      "grad_norm": 100.98133087158203,
+      "learning_rate": 2.3234200743494423e-05,
+      "loss": 8.5027,
+      "step": 1630
+    },
+    {
+      "epoch": 6.088971269694161,
+      "grad_norm": 67.31327819824219,
+      "learning_rate": 2.3172242874845104e-05,
+      "loss": 8.1805,
+      "step": 1640
+    },
+    {
+      "epoch": 6.126042632066729,
+      "grad_norm": 61.10900115966797,
+      "learning_rate": 2.311028500619579e-05,
+      "loss": 8.4519,
+      "step": 1650
+    },
+    {
+      "epoch": 6.126042632066729,
+      "eval_loss": 2.590090036392212,
+      "eval_runtime": 34.1392,
+      "eval_samples_per_second": 47.394,
+      "eval_steps_per_second": 6.796,
+      "step": 1650
+    },
+    {
+      "epoch": 6.163113994439295,
+      "grad_norm": 60.91183090209961,
+      "learning_rate": 2.304832713754647e-05,
+      "loss": 9.062,
+      "step": 1660
+    },
+    {
+      "epoch": 6.200185356811863,
+      "grad_norm": 76.2873306274414,
+      "learning_rate": 2.298636926889715e-05,
+      "loss": 8.8499,
+      "step": 1670
+    },
+    {
+      "epoch": 6.23725671918443,
+      "grad_norm": 74.2361068725586,
+      "learning_rate": 2.2924411400247832e-05,
+      "loss": 8.6576,
+      "step": 1680
+    },
+    {
+      "epoch": 6.274328081556997,
+      "grad_norm": 84.99951934814453,
+      "learning_rate": 2.2862453531598513e-05,
+      "loss": 8.4652,
+      "step": 1690
+    },
+    {
+      "epoch": 6.311399443929565,
+      "grad_norm": 86.40947723388672,
+      "learning_rate": 2.2800495662949197e-05,
+      "loss": 9.0782,
+      "step": 1700
+    },
+    {
+      "epoch": 6.348470806302132,
+      "grad_norm": 75.45568084716797,
+      "learning_rate": 2.2738537794299878e-05,
+      "loss": 8.1532,
+      "step": 1710
+    },
+    {
+      "epoch": 6.385542168674699,
+      "grad_norm": 86.65908813476562,
+      "learning_rate": 2.267657992565056e-05,
+      "loss": 8.5185,
+      "step": 1720
+    },
+    {
+      "epoch": 6.422613531047266,
+      "grad_norm": 62.620758056640625,
+      "learning_rate": 2.261462205700124e-05,
+      "loss": 9.5908,
+      "step": 1730
+    },
+    {
+      "epoch": 6.459684893419833,
+      "grad_norm": 73.63095092773438,
+      "learning_rate": 2.255266418835192e-05,
+      "loss": 8.4188,
+      "step": 1740
+    },
+    {
+      "epoch": 6.4967562557924,
+      "grad_norm": 55.175045013427734,
+      "learning_rate": 2.2490706319702606e-05,
+      "loss": 8.1885,
+      "step": 1750
+    },
+    {
+      "epoch": 6.533827618164968,
+      "grad_norm": 47.647621154785156,
+      "learning_rate": 2.2428748451053287e-05,
+      "loss": 8.7666,
+      "step": 1760
+    },
+    {
+      "epoch": 6.570898980537534,
+      "grad_norm": 191.0419158935547,
+      "learning_rate": 2.2366790582403964e-05,
+      "loss": 8.6105,
+      "step": 1770
+    },
+    {
+      "epoch": 6.607970342910102,
+      "grad_norm": 57.81939697265625,
+      "learning_rate": 2.2304832713754645e-05,
+      "loss": 8.664,
+      "step": 1780
+    },
+    {
+      "epoch": 6.645041705282669,
+      "grad_norm": 85.04927825927734,
+      "learning_rate": 2.2242874845105326e-05,
+      "loss": 8.5294,
+      "step": 1790
+    },
+    {
+      "epoch": 6.682113067655236,
+      "grad_norm": 55.604122161865234,
+      "learning_rate": 2.218091697645601e-05,
+      "loss": 9.1857,
+      "step": 1800
+    },
+    {
+      "epoch": 6.682113067655236,
+      "eval_loss": 2.497358560562134,
+      "eval_runtime": 34.0441,
+      "eval_samples_per_second": 47.527,
+      "eval_steps_per_second": 6.815,
+      "step": 1800
+    },
+    {
+      "epoch": 6.719184430027804,
+      "grad_norm": 75.21812438964844,
+      "learning_rate": 2.211895910780669e-05,
+      "loss": 8.7053,
+      "step": 1810
+    },
+    {
+      "epoch": 6.7562557924003706,
+      "grad_norm": 85.76676940917969,
+      "learning_rate": 2.2057001239157373e-05,
+      "loss": 8.1428,
+      "step": 1820
+    },
+    {
+      "epoch": 6.793327154772938,
+      "grad_norm": 69.85575866699219,
+      "learning_rate": 2.1995043370508054e-05,
+      "loss": 8.4988,
+      "step": 1830
+    },
+    {
+      "epoch": 6.830398517145505,
+      "grad_norm": 66.85325622558594,
+      "learning_rate": 2.1933085501858735e-05,
+      "loss": 8.4147,
+      "step": 1840
+    },
+    {
+      "epoch": 6.867469879518072,
+      "grad_norm": 60.645294189453125,
+      "learning_rate": 2.187112763320942e-05,
+      "loss": 9.069,
+      "step": 1850
+    },
+    {
+      "epoch": 6.904541241890639,
+      "grad_norm": 77.59921264648438,
+      "learning_rate": 2.18091697645601e-05,
+      "loss": 8.4405,
+      "step": 1860
+    },
+    {
+      "epoch": 6.941612604263207,
+      "grad_norm": 56.27996826171875,
+      "learning_rate": 2.174721189591078e-05,
+      "loss": 9.2157,
+      "step": 1870
+    },
+    {
+      "epoch": 6.978683966635774,
+      "grad_norm": 64.18400573730469,
+      "learning_rate": 2.1685254027261462e-05,
+      "loss": 9.5492,
+      "step": 1880
+    },
+    {
+      "epoch": 7.014828544949027,
+      "grad_norm": 76.78484344482422,
+      "learning_rate": 2.1623296158612143e-05,
+      "loss": 8.1325,
+      "step": 1890
+    },
+    {
+      "epoch": 7.051899907321594,
+      "grad_norm": 77.69871520996094,
+      "learning_rate": 2.1561338289962827e-05,
+      "loss": 8.324,
+      "step": 1900
+    },
+    {
+      "epoch": 7.088971269694161,
+      "grad_norm": 102.43340301513672,
+      "learning_rate": 2.149938042131351e-05,
+      "loss": 7.7097,
+      "step": 1910
+    },
+    {
+      "epoch": 7.126042632066729,
+      "grad_norm": 114.0189208984375,
+      "learning_rate": 2.143742255266419e-05,
+      "loss": 8.0982,
+      "step": 1920
+    },
+    {
+      "epoch": 7.163113994439295,
+      "grad_norm": 66.60838317871094,
+      "learning_rate": 2.137546468401487e-05,
+      "loss": 7.7669,
+      "step": 1930
+    },
+    {
+      "epoch": 7.200185356811863,
+      "grad_norm": 252.72503662109375,
+      "learning_rate": 2.1313506815365555e-05,
+      "loss": 7.809,
+      "step": 1940
+    },
+    {
+      "epoch": 7.23725671918443,
+      "grad_norm": 91.0379409790039,
+      "learning_rate": 2.1251548946716236e-05,
+      "loss": 7.9729,
+      "step": 1950
+    },
+    {
+      "epoch": 7.23725671918443,
+      "eval_loss": 2.610764741897583,
+      "eval_runtime": 34.0774,
+      "eval_samples_per_second": 47.48,
+      "eval_steps_per_second": 6.808,
+      "step": 1950
+    },
+    {
+      "epoch": 7.274328081556997,
+      "grad_norm": 96.09555053710938,
+      "learning_rate": 2.1189591078066917e-05,
+      "loss": 8.2125,
+      "step": 1960
+    },
+    {
+      "epoch": 7.311399443929565,
+      "grad_norm": 68.51132202148438,
+      "learning_rate": 2.1127633209417594e-05,
+      "loss": 7.7403,
+      "step": 1970
+    },
+    {
+      "epoch": 7.348470806302132,
+      "grad_norm": 94.45308685302734,
+      "learning_rate": 2.1065675340768275e-05,
+      "loss": 7.5494,
+      "step": 1980
+    },
+    {
+      "epoch": 7.385542168674699,
+      "grad_norm": 56.785587310791016,
+      "learning_rate": 2.100371747211896e-05,
+      "loss": 8.2821,
+      "step": 1990
+    },
+    {
+      "epoch": 7.422613531047266,
+      "grad_norm": 91.59173583984375,
+      "learning_rate": 2.094175960346964e-05,
+      "loss": 8.1644,
+      "step": 2000
+    },
+    {
+      "epoch": 7.459684893419833,
+      "grad_norm": 78.57572174072266,
+      "learning_rate": 2.0879801734820322e-05,
+      "loss": 8.1664,
+      "step": 2010
+    },
+    {
+      "epoch": 7.4967562557924,
+      "grad_norm": 71.83062744140625,
+      "learning_rate": 2.0817843866171003e-05,
+      "loss": 8.5876,
+      "step": 2020
+    },
+    {
+      "epoch": 7.533827618164968,
+      "grad_norm": 74.75129699707031,
+      "learning_rate": 2.0755885997521684e-05,
+      "loss": 8.2753,
+      "step": 2030
+    },
+    {
+      "epoch": 7.570898980537534,
+      "grad_norm": 96.26950073242188,
+      "learning_rate": 2.0693928128872368e-05,
+      "loss": 9.2057,
+      "step": 2040
+    },
+    {
+      "epoch": 7.607970342910102,
+      "grad_norm": 96.87144470214844,
+      "learning_rate": 2.063197026022305e-05,
+      "loss": 8.0052,
+      "step": 2050
+    },
+    {
+      "epoch": 7.645041705282669,
+      "grad_norm": 83.44422912597656,
+      "learning_rate": 2.057001239157373e-05,
+      "loss": 8.4954,
+      "step": 2060
+    },
+    {
+      "epoch": 7.682113067655236,
+      "grad_norm": 86.1534194946289,
+      "learning_rate": 2.050805452292441e-05,
+      "loss": 8.0325,
+      "step": 2070
+    },
+    {
+      "epoch": 7.719184430027804,
+      "grad_norm": 89.11744689941406,
+      "learning_rate": 2.0446096654275092e-05,
+      "loss": 8.2934,
+      "step": 2080
+    },
+    {
+      "epoch": 7.7562557924003706,
+      "grad_norm": 60.81666946411133,
+      "learning_rate": 2.0384138785625777e-05,
+      "loss": 9.4019,
+      "step": 2090
+    },
+    {
+      "epoch": 7.793327154772938,
+      "grad_norm": 82.93228912353516,
+      "learning_rate": 2.0322180916976458e-05,
+      "loss": 8.874,
+      "step": 2100
+    },
+    {
+      "epoch": 7.793327154772938,
+      "eval_loss": 2.452894926071167,
+      "eval_runtime": 34.0684,
+      "eval_samples_per_second": 47.493,
+      "eval_steps_per_second": 6.81,
+      "step": 2100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5380,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 150,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 7,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-2100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cdcceaae6653fb2ddf52aed92e50c566c84ffbec2efeda566b6d2719f722937
+size 5624