Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+toponym_lora/checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+toponym_lora/checkpoint-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+toponym_lora/checkpoint-978/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+toponym_lora/tokenizer.json filter=lfs diff=lfs merge=lfs -text

toponym_lora/README.md

@@ -0,0 +1,93 @@
+---
+base_model: Qwen/Qwen3-4B-Instruct-2507
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- ner
+- named-entity-recognition
+- early-modern-english
+- historical-texts
+- toponym
+- lora
+- transformers
+language:
+- en
+license: mit
+---
+
+# EarlyModernNER - TOPONYM Adapter
+
+A LoRA adapter specialized for extracting **TOPONYM** (place name) entities from Early Modern English documents (1500-1800).
+
+## Entity Type: TOPONYM
+
+Extracts place names including:
+- Cities and towns (London, Bristol, Amsterdam)
+- Ports and harbors (Port Royal, Gravesend)
+- Regions and territories (New England, Virginia, West Indies)
+- Countries and kingdoms (France, Spain, Great Britain)
+- Islands (Jamaica, Barbados, Madagascar)
+- Rivers and bodies of water (Thames, Mediterranean)
+- Geographic features (Cape of Good Hope)
+
+## Performance
+
+Evaluated on 100 gold-standard annotated documents:
+
+| Metric | Score |
+|--------|-------|
+| Precision | 0.9286 |
+| Recall | 0.8176 |
+| F1 | 0.8696 |
+
+## Training Details
+
+- **Base Model:** Qwen/Qwen3-4B-Instruct-2507
+- **Method:** QLoRA (4-bit quantization)
+- **LoRA Rank:** 64
+- **Epochs:** 4
+- **Training Data:** Silver-standard annotations from Early Modern historical corpora
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+base_model = AutoModelForCausalLM.from_pretrained(
+    "Qwen/Qwen3-4B-Instruct-2507",
+    device_map="auto",
+    trust_remote_code=True,
+)
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
+model = PeftModel.from_pretrained(base_model, "path/to/toponym_lora")
+```
+
+Or use via the EarlyModernNER package:
+```bash
+python -m earlymodernner --input your_docs/ --output results.jsonl
+```
+
+## Limitations
+
+- Trained primarily on 17th-century English documents
+- May struggle with heavily abbreviated or damaged OCR text
+- Historical spelling variants may affect recognition
+
+## License
+
+MIT License
+
+## Author
+
+Jacob Polay, MA Student, University of Saskatchewan
+
+## Citation
+
+```bibtex
+@software{earlymodernner,
+  title = {EarlyModernNER: Named Entity Recognition for Early Modern English},
+  author = {Polay, Jacob},
+  year = {2026}
+}
+```

toponym_lora/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Instruct-2507",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

toponym_lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab09ae476a93470d85ac7605a032fcec7da71f201404ed566dfe5605abbad948
+size 528550256

toponym_lora/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

toponym_lora/checkpoint-800/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen3-4B-Instruct-2507
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Instruct-2507
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

toponym_lora/checkpoint-800/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Instruct-2507",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

toponym_lora/checkpoint-800/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:121108d40356cc5adf396b6d2f70357413cfb37f734a95c7ee980e1a309bcf09
+size 528550256

toponym_lora/checkpoint-800/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

toponym_lora/checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:371b2fa29651d9cd4df4627fbc9090104ae74eae082c5b503ab3e8640cc426cf
+size 1057390923

toponym_lora/checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22d5584e75db23faf39ed9de1c6bbf4deff0b298ef92fdf23a975597f2a4e57e
+size 14645

toponym_lora/checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c8833b467bb18ae9d86ba957a9976bfc149890ab204eaab3b6a6769002c7fc
+size 1465

toponym_lora/checkpoint-800/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

toponym_lora/checkpoint-800/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f1298e298f2fe0059aba46f037697a339ccba45a1908780ce8ca14b45582f23
+size 11422753

toponym_lora/checkpoint-800/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1010000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

toponym_lora/checkpoint-800/trainer_state.json

@@ -0,0 +1,826 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.8807339449541285,
+  "eval_steps": 100,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06116207951070336,
+      "grad_norm": 0.5065167546272278,
+      "learning_rate": 6e-05,
+      "loss": 0.4883,
+      "step": 10
+    },
+    {
+      "epoch": 0.12232415902140673,
+      "grad_norm": 0.28862252831459045,
+      "learning_rate": 0.00012666666666666666,
+      "loss": 0.2469,
+      "step": 20
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 0.1823580414056778,
+      "learning_rate": 0.00019333333333333333,
+      "loss": 0.1435,
+      "step": 30
+    },
+    {
+      "epoch": 0.24464831804281345,
+      "grad_norm": 0.2956920564174652,
+      "learning_rate": 0.00019995552602987827,
+      "loss": 0.1124,
+      "step": 40
+    },
+    {
+      "epoch": 0.3058103975535168,
+      "grad_norm": 0.15972661972045898,
+      "learning_rate": 0.00019980183963589504,
+      "loss": 0.1319,
+      "step": 50
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.2291875034570694,
+      "learning_rate": 0.00019953856048007652,
+      "loss": 0.089,
+      "step": 60
+    },
+    {
+      "epoch": 0.42813455657492355,
+      "grad_norm": 0.1270621418952942,
+      "learning_rate": 0.00019916597767021807,
+      "loss": 0.1027,
+      "step": 70
+    },
+    {
+      "epoch": 0.4892966360856269,
+      "grad_norm": 0.1719549000263214,
+      "learning_rate": 0.00019868450034085352,
+      "loss": 0.09,
+      "step": 80
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.11448629200458527,
+      "learning_rate": 0.0001980946572039834,
+      "loss": 0.0886,
+      "step": 90
+    },
+    {
+      "epoch": 0.6116207951070336,
+      "grad_norm": 0.1629963368177414,
+      "learning_rate": 0.00019739709596849417,
+      "loss": 0.0974,
+      "step": 100
+    },
+    {
+      "epoch": 0.6116207951070336,
+      "eval_loss": 0.0775158628821373,
+      "eval_runtime": 17.6163,
+      "eval_samples_per_second": 4.144,
+      "eval_steps_per_second": 2.1,
+      "step": 100
+    },
+    {
+      "eval_ner_f1": 0.26666666666666666,
+      "step": 100
+    },
+    {
+      "eval_ner_precision": 0.5263157894736842,
+      "step": 100
+    },
+    {
+      "eval_ner_recall": 0.17857142857142858,
+      "step": 100
+    },
+    {
+      "eval_ner_f1_toponym": 0.273972602739726,
+      "step": 100
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 100
+    },
+    {
+      "eval_ner_f1_organization": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.672782874617737,
+      "grad_norm": 0.07239006459712982,
+      "learning_rate": 0.00019659258262890683,
+      "loss": 0.0783,
+      "step": 110
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.18169932067394257,
+      "learning_rate": 0.00019568200062423555,
+      "loss": 0.079,
+      "step": 120
+    },
+    {
+      "epoch": 0.7951070336391437,
+      "grad_norm": 0.13822244107723236,
+      "learning_rate": 0.00019466634986788005,
+      "loss": 0.0711,
+      "step": 130
+    },
+    {
+      "epoch": 0.8562691131498471,
+      "grad_norm": 0.08978362381458282,
+      "learning_rate": 0.0001935467456496171,
+      "loss": 0.0809,
+      "step": 140
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 0.09890680760145187,
+      "learning_rate": 0.00019232441741089676,
+      "loss": 0.0745,
+      "step": 150
+    },
+    {
+      "epoch": 0.9785932721712538,
+      "grad_norm": 0.20916098356246948,
+      "learning_rate": 0.00019100070739478832,
+      "loss": 0.0755,
+      "step": 160
+    },
+    {
+      "epoch": 1.036697247706422,
+      "grad_norm": 0.11759505420923233,
+      "learning_rate": 0.0001895770691720582,
+      "loss": 0.0722,
+      "step": 170
+    },
+    {
+      "epoch": 1.0978593272171253,
+      "grad_norm": 0.0745391771197319,
+      "learning_rate": 0.0001880550660449988,
+      "loss": 0.0482,
+      "step": 180
+    },
+    {
+      "epoch": 1.1590214067278288,
+      "grad_norm": 0.1519857943058014,
+      "learning_rate": 0.0001864363693307604,
+      "loss": 0.045,
+      "step": 190
+    },
+    {
+      "epoch": 1.2201834862385321,
+      "grad_norm": 0.07725294679403305,
+      "learning_rate": 0.00018472275652607186,
+      "loss": 0.0476,
+      "step": 200
+    },
+    {
+      "epoch": 1.2201834862385321,
+      "eval_loss": 0.06860311329364777,
+      "eval_runtime": 16.2309,
+      "eval_samples_per_second": 4.498,
+      "eval_steps_per_second": 2.28,
+      "step": 200
+    },
+    {
+      "eval_ner_f1": 0.2894736842105263,
+      "step": 200
+    },
+    {
+      "eval_ner_precision": 0.55,
+      "step": 200
+    },
+    {
+      "eval_ner_recall": 0.19642857142857142,
+      "step": 200
+    },
+    {
+      "eval_ner_f1_toponym": 0.3142857142857143,
+      "step": 200
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.2813455657492354,
+      "grad_norm": 0.07129528373479843,
+      "learning_rate": 0.000182916109355365,
+      "loss": 0.0538,
+      "step": 210
+    },
+    {
+      "epoch": 1.3425076452599387,
+      "grad_norm": 0.07345232367515564,
+      "learning_rate": 0.00018101841170444616,
+      "loss": 0.0444,
+      "step": 220
+    },
+    {
+      "epoch": 1.4036697247706422,
+      "grad_norm": 0.1663370579481125,
+      "learning_rate": 0.000179031747441984,
+      "loss": 0.06,
+      "step": 230
+    },
+    {
+      "epoch": 1.4648318042813455,
+      "grad_norm": 0.0920317992568016,
+      "learning_rate": 0.0001769582981312057,
+      "loss": 0.036,
+      "step": 240
+    },
+    {
+      "epoch": 1.525993883792049,
+      "grad_norm": 0.15344829857349396,
+      "learning_rate": 0.00017480034063431477,
+      "loss": 0.0572,
+      "step": 250
+    },
+    {
+      "epoch": 1.5871559633027523,
+      "grad_norm": 0.11365994811058044,
+      "learning_rate": 0.00017256024461226001,
+      "loss": 0.0609,
+      "step": 260
+    },
+    {
+      "epoch": 1.6483180428134556,
+      "grad_norm": 0.11572407931089401,
+      "learning_rate": 0.00017024046992260237,
+      "loss": 0.0441,
+      "step": 270
+    },
+    {
+      "epoch": 1.709480122324159,
+      "grad_norm": 0.16469694674015045,
+      "learning_rate": 0.00016784356391833665,
+      "loss": 0.0432,
+      "step": 280
+    },
+    {
+      "epoch": 1.7706422018348624,
+      "grad_norm": 0.08726947009563446,
+      "learning_rate": 0.00016537215865063365,
+      "loss": 0.0483,
+      "step": 290
+    },
+    {
+      "epoch": 1.8318042813455657,
+      "grad_norm": 0.10488814115524292,
+      "learning_rate": 0.00016282896797857548,
+      "loss": 0.0486,
+      "step": 300
+    },
+    {
+      "epoch": 1.8318042813455657,
+      "eval_loss": 0.052874963730573654,
+      "eval_runtime": 16.301,
+      "eval_samples_per_second": 4.478,
+      "eval_steps_per_second": 2.27,
+      "step": 300
+    },
+    {
+      "eval_ner_f1": 0.2894736842105263,
+      "step": 300
+    },
+    {
+      "eval_ner_precision": 0.55,
+      "step": 300
+    },
+    {
+      "eval_ner_recall": 0.19642857142857142,
+      "step": 300
+    },
+    {
+      "eval_ner_f1_toponym": 0.3142857142857143,
+      "step": 300
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 1.8929663608562692,
+      "grad_norm": 0.10856537520885468,
+      "learning_rate": 0.00016021678458905684,
+      "loss": 0.0477,
+      "step": 310
+    },
+    {
+      "epoch": 1.9541284403669725,
+      "grad_norm": 0.10471344739198685,
+      "learning_rate": 0.00015753847693012566,
+      "loss": 0.0547,
+      "step": 320
+    },
+    {
+      "epoch": 2.0122324159021407,
+      "grad_norm": 0.07346905022859573,
+      "learning_rate": 0.0001547969860611297,
+      "loss": 0.0467,
+      "step": 330
+    },
+    {
+      "epoch": 2.073394495412844,
+      "grad_norm": 0.0847230851650238,
+      "learning_rate": 0.0001519953224231287,
+      "loss": 0.0186,
+      "step": 340
+    },
+    {
+      "epoch": 2.1345565749235473,
+      "grad_norm": 0.11084947735071182,
+      "learning_rate": 0.0001491365625331182,
+      "loss": 0.0268,
+      "step": 350
+    },
+    {
+      "epoch": 2.1957186544342506,
+      "grad_norm": 0.11435306072235107,
+      "learning_rate": 0.00014622384560569493,
+      "loss": 0.0324,
+      "step": 360
+    },
+    {
+      "epoch": 2.2568807339449544,
+      "grad_norm": 0.05882082134485245,
+      "learning_rate": 0.00014326037010587404,
+      "loss": 0.0279,
+      "step": 370
+    },
+    {
+      "epoch": 2.3180428134556577,
+      "grad_norm": 0.09373460710048676,
+      "learning_rate": 0.00014024939023684298,
+      "loss": 0.0256,
+      "step": 380
+    },
+    {
+      "epoch": 2.379204892966361,
+      "grad_norm": 0.16994407773017883,
+      "learning_rate": 0.0001371942123665092,
+      "loss": 0.0233,
+      "step": 390
+    },
+    {
+      "epoch": 2.4403669724770642,
+      "grad_norm": 0.23053932189941406,
+      "learning_rate": 0.0001340981913967656,
+      "loss": 0.0285,
+      "step": 400
+    },
+    {
+      "epoch": 2.4403669724770642,
+      "eval_loss": 0.0535120964050293,
+      "eval_runtime": 16.5169,
+      "eval_samples_per_second": 4.42,
+      "eval_steps_per_second": 2.24,
+      "step": 400
+    },
+    {
+      "eval_ner_f1": 0.3055555555555555,
+      "step": 400
+    },
+    {
+      "eval_ner_precision": 0.6875,
+      "step": 400
+    },
+    {
+      "eval_ner_recall": 0.19642857142857142,
+      "step": 400
+    },
+    {
+      "eval_ner_f1_toponym": 0.3142857142857143,
+      "step": 400
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 400
+    },
+    {
+      "eval_ner_f1_organization": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 2.5015290519877675,
+      "grad_norm": 0.4044734239578247,
+      "learning_rate": 0.00013096472707946056,
+      "loss": 0.0306,
+      "step": 410
+    },
+    {
+      "epoch": 2.562691131498471,
+      "grad_norm": 0.11446376889944077,
+      "learning_rate": 0.0001277972602831181,
+      "loss": 0.0188,
+      "step": 420
+    },
+    {
+      "epoch": 2.623853211009174,
+      "grad_norm": 0.16048116981983185,
+      "learning_rate": 0.0001245992692145078,
+      "loss": 0.0282,
+      "step": 430
+    },
+    {
+      "epoch": 2.6850152905198774,
+      "grad_norm": 0.10304035991430283,
+      "learning_rate": 0.00012137426559921316,
+      "loss": 0.0273,
+      "step": 440
+    },
+    {
+      "epoch": 2.746177370030581,
+      "grad_norm": 0.04728333652019501,
+      "learning_rate": 0.00011812579082539317,
+      "loss": 0.0205,
+      "step": 450
+    },
+    {
+      "epoch": 2.8073394495412844,
+      "grad_norm": 0.09207329899072647,
+      "learning_rate": 0.00011485741205497094,
+      "loss": 0.0211,
+      "step": 460
+    },
+    {
+      "epoch": 2.8685015290519877,
+      "grad_norm": 0.17346537113189697,
+      "learning_rate": 0.00011157271830652062,
+      "loss": 0.0326,
+      "step": 470
+    },
+    {
+      "epoch": 2.929663608562691,
+      "grad_norm": 0.07529453188180923,
+      "learning_rate": 0.00010827531651415266,
+      "loss": 0.0192,
+      "step": 480
+    },
+    {
+      "epoch": 2.9908256880733948,
+      "grad_norm": 0.10349865257740021,
+      "learning_rate": 0.00010496882756672666,
+      "loss": 0.0175,
+      "step": 490
+    },
+    {
+      "epoch": 3.0489296636085625,
+      "grad_norm": 0.06423936784267426,
+      "learning_rate": 0.00010165688233174017,
+      "loss": 0.0129,
+      "step": 500
+    },
+    {
+      "epoch": 3.0489296636085625,
+      "eval_loss": 0.05351715907454491,
+      "eval_runtime": 16.4745,
+      "eval_samples_per_second": 4.431,
+      "eval_steps_per_second": 2.246,
+      "step": 500
+    },
+    {
+      "eval_ner_f1": 0.34285714285714286,
+      "step": 500
+    },
+    {
+      "eval_ner_precision": 0.8571428571428571,
+      "step": 500
+    },
+    {
+      "eval_ner_recall": 0.21428571428571427,
+      "step": 500
+    },
+    {
+      "eval_ner_f1_toponym": 0.34285714285714286,
+      "step": 500
+    },
+    {
+      "epoch": 3.1100917431192663,
+      "grad_norm": 0.10966634750366211,
+      "learning_rate": 9.834311766825985e-05,
+      "loss": 0.0108,
+      "step": 510
+    },
+    {
+      "epoch": 3.1712538226299696,
+      "grad_norm": 0.03550288453698158,
+      "learning_rate": 9.503117243327337e-05,
+      "loss": 0.0082,
+      "step": 520
+    },
+    {
+      "epoch": 3.232415902140673,
+      "grad_norm": 0.07612079381942749,
+      "learning_rate": 9.172468348584739e-05,
+      "loss": 0.0073,
+      "step": 530
+    },
+    {
+      "epoch": 3.293577981651376,
+      "grad_norm": 0.10736043751239777,
+      "learning_rate": 8.842728169347939e-05,
+      "loss": 0.0095,
+      "step": 540
+    },
+    {
+      "epoch": 3.3547400611620795,
+      "grad_norm": 0.10124403238296509,
+      "learning_rate": 8.514258794502905e-05,
+      "loss": 0.0147,
+      "step": 550
+    },
+    {
+      "epoch": 3.4159021406727827,
+      "grad_norm": 0.08522272109985352,
+      "learning_rate": 8.187420917460686e-05,
+      "loss": 0.0143,
+      "step": 560
+    },
+    {
+      "epoch": 3.477064220183486,
+      "grad_norm": 0.10443105548620224,
+      "learning_rate": 7.862573440078686e-05,
+      "loss": 0.0109,
+      "step": 570
+    },
+    {
+      "epoch": 3.5382262996941893,
+      "grad_norm": 0.07868387550115585,
+      "learning_rate": 7.540073078549221e-05,
+      "loss": 0.0068,
+      "step": 580
+    },
+    {
+      "epoch": 3.599388379204893,
+      "grad_norm": 0.034807343035936356,
+      "learning_rate": 7.220273971688192e-05,
+      "loss": 0.0107,
+      "step": 590
+    },
+    {
+      "epoch": 3.6605504587155964,
+      "grad_norm": 0.020409688353538513,
+      "learning_rate": 6.903527292053942e-05,
+      "loss": 0.0101,
+      "step": 600
+    },
+    {
+      "epoch": 3.6605504587155964,
+      "eval_loss": 0.0602705255150795,
+      "eval_runtime": 15.876,
+      "eval_samples_per_second": 4.598,
+      "eval_steps_per_second": 2.331,
+      "step": 600
+    },
+    {
+      "eval_ner_f1": 0.30769230769230765,
+      "step": 600
+    },
+    {
+      "eval_ner_precision": 0.5454545454545454,
+      "step": 600
+    },
+    {
+      "eval_ner_recall": 0.21428571428571427,
+      "step": 600
+    },
+    {
+      "eval_ner_f1_toponym": 0.34782608695652173,
+      "step": 600
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 600
+    },
+    {
+      "eval_ner_f1_organization": 0.0,
+      "step": 600
+    },
+    {
+      "epoch": 3.7217125382262997,
+      "grad_norm": 0.04670476168394089,
+      "learning_rate": 6.59018086032344e-05,
+      "loss": 0.0101,
+      "step": 610
+    },
+    {
+      "epoch": 3.782874617737003,
+      "grad_norm": 0.01200962159782648,
+      "learning_rate": 6.280578763349078e-05,
+      "loss": 0.006,
+      "step": 620
+    },
+    {
+      "epoch": 3.8440366972477067,
+      "grad_norm": 0.05485844239592552,
+      "learning_rate": 5.975060976315703e-05,
+      "loss": 0.0109,
+      "step": 630
+    },
+    {
+      "epoch": 3.90519877675841,
+      "grad_norm": 0.09339557588100433,
+      "learning_rate": 5.673962989412599e-05,
+      "loss": 0.0057,
+      "step": 640
+    },
+    {
+      "epoch": 3.9663608562691133,
+      "grad_norm": 0.21686244010925293,
+      "learning_rate": 5.377615439430508e-05,
+      "loss": 0.0081,
+      "step": 650
+    },
+    {
+      "epoch": 4.0244648318042815,
+      "grad_norm": 0.04568672925233841,
+      "learning_rate": 5.0863437466881836e-05,
+      "loss": 0.0071,
+      "step": 660
+    },
+    {
+      "epoch": 4.085626911314985,
+      "grad_norm": 0.037828218191862106,
+      "learning_rate": 4.80046775768713e-05,
+      "loss": 0.0025,
+      "step": 670
+    },
+    {
+      "epoch": 4.146788990825688,
+      "grad_norm": 0.05333082377910614,
+      "learning_rate": 4.520301393887033e-05,
+      "loss": 0.0032,
+      "step": 680
+    },
+    {
+      "epoch": 4.207951070336391,
+      "grad_norm": 0.007903705351054668,
+      "learning_rate": 4.2461523069874346e-05,
+      "loss": 0.0027,
+      "step": 690
+    },
+    {
+      "epoch": 4.269113149847095,
+      "grad_norm": 0.007534786593168974,
+      "learning_rate": 3.9783215410943174e-05,
+      "loss": 0.0019,
+      "step": 700
+    },
+    {
+      "epoch": 4.269113149847095,
+      "eval_loss": 0.06749989837408066,
+      "eval_runtime": 16.1258,
+      "eval_samples_per_second": 4.527,
+      "eval_steps_per_second": 2.294,
+      "step": 700
+    },
+    {
+      "eval_ner_f1": 0.379746835443038,
+      "step": 700
+    },
+    {
+      "eval_ner_precision": 0.6521739130434783,
+      "step": 700
+    },
+    {
+      "eval_ner_recall": 0.26785714285714285,
+      "step": 700
+    },
+    {
+      "eval_ner_f1_toponym": 0.3896103896103896,
+      "step": 700
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 700
+    },
+    {
+      "epoch": 4.330275229357798,
+      "grad_norm": 0.046107176691293716,
+      "learning_rate": 3.717103202142457e-05,
+      "loss": 0.0028,
+      "step": 710
+    },
+    {
+      "epoch": 4.391437308868501,
+      "grad_norm": 0.022927094250917435,
+      "learning_rate": 3.462784134936636e-05,
+      "loss": 0.0047,
+      "step": 720
+    },
+    {
+      "epoch": 4.4525993883792045,
+      "grad_norm": 0.09270883351564407,
+      "learning_rate": 3.2156436081663356e-05,
+      "loss": 0.0035,
+      "step": 730
+    },
+    {
+      "epoch": 4.513761467889909,
+      "grad_norm": 0.2539561092853546,
+      "learning_rate": 2.9759530077397636e-05,
+      "loss": 0.0011,
+      "step": 740
+    },
+    {
+      "epoch": 4.574923547400612,
+      "grad_norm": 0.0036298525519669056,
+      "learning_rate": 2.743975538774002e-05,
+      "loss": 0.0041,
+      "step": 750
+    },
+    {
+      "epoch": 4.636085626911315,
+      "grad_norm": 0.005658215843141079,
+      "learning_rate": 2.5199659365685235e-05,
+      "loss": 0.0017,
+      "step": 760
+    },
+    {
+      "epoch": 4.697247706422019,
+      "grad_norm": 0.00670202262699604,
+      "learning_rate": 2.3041701868794287e-05,
+      "loss": 0.0053,
+      "step": 770
+    },
+    {
+      "epoch": 4.758409785932722,
+      "grad_norm": 0.0019507587421685457,
+      "learning_rate": 2.0968252558016055e-05,
+      "loss": 0.0029,
+      "step": 780
+    },
+    {
+      "epoch": 4.819571865443425,
+      "grad_norm": 0.01064695417881012,
+      "learning_rate": 1.8981588295553853e-05,
+      "loss": 0.0051,
+      "step": 790
+    },
+    {
+      "epoch": 4.8807339449541285,
+      "grad_norm": 0.007430676836520433,
+      "learning_rate": 1.7083890644635014e-05,
+      "loss": 0.0047,
+      "step": 800
+    },
+    {
+      "epoch": 4.8807339449541285,
+      "eval_loss": 0.07247484475374222,
+      "eval_runtime": 15.8563,
+      "eval_samples_per_second": 4.604,
+      "eval_steps_per_second": 2.333,
+      "step": 800
+    },
+    {
+      "eval_ner_f1": 0.3783783783783784,
+      "step": 800
+    },
+    {
+      "eval_ner_precision": 0.7777777777777778,
+      "step": 800
+    },
+    {
+      "eval_ner_recall": 0.25,
+      "step": 800
+    },
+    {
+      "eval_ner_f1_toponym": 0.3835616438356164,
+      "step": 800
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 978,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3337164677971251e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

toponym_lora/checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c264c52127e7b32e02112d53c064f4d314a786fd6b750d0d213bf34b45b4b318
+size 5713

toponym_lora/checkpoint-900/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen3-4B-Instruct-2507
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Instruct-2507
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

toponym_lora/checkpoint-900/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Instruct-2507",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

toponym_lora/checkpoint-900/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1d4c688a401e921f21d82817f37c4a539f741a691693aeaff8d5e5894a20c5a
+size 528550256

toponym_lora/checkpoint-900/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

toponym_lora/checkpoint-900/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f921768d6cd92db10def0283b54b57e2570797a36e970bc93f590cdffcc5053
+size 1057390923

toponym_lora/checkpoint-900/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45dcaba6c1a2ef8dee71f1978184382b0bbd716ea3230add10afb690542c2d31
+size 14645

toponym_lora/checkpoint-900/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44657118a69362ee43402d9e7710e19cbfc3cd352c1fbb5b10bc34529ad64e70
+size 1465

toponym_lora/checkpoint-900/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

toponym_lora/checkpoint-900/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f1298e298f2fe0059aba46f037697a339ccba45a1908780ce8ca14b45582f23
+size 11422753

toponym_lora/checkpoint-900/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1010000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

toponym_lora/checkpoint-900/trainer_state.json

@@ -0,0 +1,924 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.489296636085627,
+  "eval_steps": 100,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06116207951070336,
+      "grad_norm": 0.5065167546272278,
+      "learning_rate": 6e-05,
+      "loss": 0.4883,
+      "step": 10
+    },
+    {
+      "epoch": 0.12232415902140673,
+      "grad_norm": 0.28862252831459045,
+      "learning_rate": 0.00012666666666666666,
+      "loss": 0.2469,
+      "step": 20
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 0.1823580414056778,
+      "learning_rate": 0.00019333333333333333,
+      "loss": 0.1435,
+      "step": 30
+    },
+    {
+      "epoch": 0.24464831804281345,
+      "grad_norm": 0.2956920564174652,
+      "learning_rate": 0.00019995552602987827,
+      "loss": 0.1124,
+      "step": 40
+    },
+    {
+      "epoch": 0.3058103975535168,
+      "grad_norm": 0.15972661972045898,
+      "learning_rate": 0.00019980183963589504,
+      "loss": 0.1319,
+      "step": 50
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.2291875034570694,
+      "learning_rate": 0.00019953856048007652,
+      "loss": 0.089,
+      "step": 60
+    },
+    {
+      "epoch": 0.42813455657492355,
+      "grad_norm": 0.1270621418952942,
+      "learning_rate": 0.00019916597767021807,
+      "loss": 0.1027,
+      "step": 70
+    },
+    {
+      "epoch": 0.4892966360856269,
+      "grad_norm": 0.1719549000263214,
+      "learning_rate": 0.00019868450034085352,
+      "loss": 0.09,
+      "step": 80
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.11448629200458527,
+      "learning_rate": 0.0001980946572039834,
+      "loss": 0.0886,
+      "step": 90
+    },
+    {
+      "epoch": 0.6116207951070336,
+      "grad_norm": 0.1629963368177414,
+      "learning_rate": 0.00019739709596849417,
+      "loss": 0.0974,
+      "step": 100
+    },
+    {
+      "epoch": 0.6116207951070336,
+      "eval_loss": 0.0775158628821373,
+      "eval_runtime": 17.6163,
+      "eval_samples_per_second": 4.144,
+      "eval_steps_per_second": 2.1,
+      "step": 100
+    },
+    {
+      "eval_ner_f1": 0.26666666666666666,
+      "step": 100
+    },
+    {
+      "eval_ner_precision": 0.5263157894736842,
+      "step": 100
+    },
+    {
+      "eval_ner_recall": 0.17857142857142858,
+      "step": 100
+    },
+    {
+      "eval_ner_f1_toponym": 0.273972602739726,
+      "step": 100
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 100
+    },
+    {
+      "eval_ner_f1_organization": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.672782874617737,
+      "grad_norm": 0.07239006459712982,
+      "learning_rate": 0.00019659258262890683,
+      "loss": 0.0783,
+      "step": 110
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.18169932067394257,
+      "learning_rate": 0.00019568200062423555,
+      "loss": 0.079,
+      "step": 120
+    },
+    {
+      "epoch": 0.7951070336391437,
+      "grad_norm": 0.13822244107723236,
+      "learning_rate": 0.00019466634986788005,
+      "loss": 0.0711,
+      "step": 130
+    },
+    {
+      "epoch": 0.8562691131498471,
+      "grad_norm": 0.08978362381458282,
+      "learning_rate": 0.0001935467456496171,
+      "loss": 0.0809,
+      "step": 140
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 0.09890680760145187,
+      "learning_rate": 0.00019232441741089676,
+      "loss": 0.0745,
+      "step": 150
+    },
+    {
+      "epoch": 0.9785932721712538,
+      "grad_norm": 0.20916098356246948,
+      "learning_rate": 0.00019100070739478832,
+      "loss": 0.0755,
+      "step": 160
+    },
+    {
+      "epoch": 1.036697247706422,
+      "grad_norm": 0.11759505420923233,
+      "learning_rate": 0.0001895770691720582,
+      "loss": 0.0722,
+      "step": 170
+    },
+    {
+      "epoch": 1.0978593272171253,
+      "grad_norm": 0.0745391771197319,
+      "learning_rate": 0.0001880550660449988,
+      "loss": 0.0482,
+      "step": 180
+    },
+    {
+      "epoch": 1.1590214067278288,
+      "grad_norm": 0.1519857943058014,
+      "learning_rate": 0.0001864363693307604,
+      "loss": 0.045,
+      "step": 190
+    },
+    {
+      "epoch": 1.2201834862385321,
+      "grad_norm": 0.07725294679403305,
+      "learning_rate": 0.00018472275652607186,
+      "loss": 0.0476,
+      "step": 200
+    },
+    {
+      "epoch": 1.2201834862385321,
+      "eval_loss": 0.06860311329364777,
+      "eval_runtime": 16.2309,
+      "eval_samples_per_second": 4.498,
+      "eval_steps_per_second": 2.28,
+      "step": 200
+    },
+    {
+      "eval_ner_f1": 0.2894736842105263,
+      "step": 200
+    },
+    {
+      "eval_ner_precision": 0.55,
+      "step": 200
+    },
+    {
+      "eval_ner_recall": 0.19642857142857142,
+      "step": 200
+    },
+    {
+      "eval_ner_f1_toponym": 0.3142857142857143,
+      "step": 200
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.2813455657492354,
+      "grad_norm": 0.07129528373479843,
+      "learning_rate": 0.000182916109355365,
+      "loss": 0.0538,
+      "step": 210
+    },
+    {
+      "epoch": 1.3425076452599387,
+      "grad_norm": 0.07345232367515564,
+      "learning_rate": 0.00018101841170444616,
+      "loss": 0.0444,
+      "step": 220
+    },
+    {
+      "epoch": 1.4036697247706422,
+      "grad_norm": 0.1663370579481125,
+      "learning_rate": 0.000179031747441984,
+      "loss": 0.06,
+      "step": 230
+    },
+    {
+      "epoch": 1.4648318042813455,
+      "grad_norm": 0.0920317992568016,
+      "learning_rate": 0.0001769582981312057,
+      "loss": 0.036,
+      "step": 240
+    },
+    {
+      "epoch": 1.525993883792049,
+      "grad_norm": 0.15344829857349396,
+      "learning_rate": 0.00017480034063431477,
+      "loss": 0.0572,
+      "step": 250
+    },
+    {
+      "epoch": 1.5871559633027523,
+      "grad_norm": 0.11365994811058044,
+      "learning_rate": 0.00017256024461226001,
+      "loss": 0.0609,
+      "step": 260
+    },
+    {
+      "epoch": 1.6483180428134556,
+      "grad_norm": 0.11572407931089401,
+      "learning_rate": 0.00017024046992260237,
+      "loss": 0.0441,
+      "step": 270
+    },
+    {
+      "epoch": 1.709480122324159,
+      "grad_norm": 0.16469694674015045,
+      "learning_rate": 0.00016784356391833665,
+      "loss": 0.0432,
+      "step": 280
+    },
+    {
+      "epoch": 1.7706422018348624,
+      "grad_norm": 0.08726947009563446,
+      "learning_rate": 0.00016537215865063365,
+      "loss": 0.0483,
+      "step": 290
+    },
+    {
+      "epoch": 1.8318042813455657,
+      "grad_norm": 0.10488814115524292,
+      "learning_rate": 0.00016282896797857548,
+      "loss": 0.0486,
+      "step": 300
+    },
+    {
+      "epoch": 1.8318042813455657,
+      "eval_loss": 0.052874963730573654,
+      "eval_runtime": 16.301,
+      "eval_samples_per_second": 4.478,
+      "eval_steps_per_second": 2.27,
+      "step": 300
+    },
+    {
+      "eval_ner_f1": 0.2894736842105263,
+      "step": 300
+    },
+    {
+      "eval_ner_precision": 0.55,
+      "step": 300
+    },
+    {
+      "eval_ner_recall": 0.19642857142857142,
+      "step": 300
+    },
+    {
+      "eval_ner_f1_toponym": 0.3142857142857143,
+      "step": 300
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 1.8929663608562692,
+      "grad_norm": 0.10856537520885468,
+      "learning_rate": 0.00016021678458905684,
+      "loss": 0.0477,
+      "step": 310
+    },
+    {
+      "epoch": 1.9541284403669725,
+      "grad_norm": 0.10471344739198685,
+      "learning_rate": 0.00015753847693012566,
+      "loss": 0.0547,
+      "step": 320
+    },
+    {
+      "epoch": 2.0122324159021407,
+      "grad_norm": 0.07346905022859573,
+      "learning_rate": 0.0001547969860611297,
+      "loss": 0.0467,
+      "step": 330
+    },
+    {
+      "epoch": 2.073394495412844,
+      "grad_norm": 0.0847230851650238,
+      "learning_rate": 0.0001519953224231287,
+      "loss": 0.0186,
+      "step": 340
+    },
+    {
+      "epoch": 2.1345565749235473,
+      "grad_norm": 0.11084947735071182,
+      "learning_rate": 0.0001491365625331182,
+      "loss": 0.0268,
+      "step": 350
+    },
+    {
+      "epoch": 2.1957186544342506,
+      "grad_norm": 0.11435306072235107,
+      "learning_rate": 0.00014622384560569493,
+      "loss": 0.0324,
+      "step": 360
+    },
+    {
+      "epoch": 2.2568807339449544,
+      "grad_norm": 0.05882082134485245,
+      "learning_rate": 0.00014326037010587404,
+      "loss": 0.0279,
+      "step": 370
+    },
+    {
+      "epoch": 2.3180428134556577,
+      "grad_norm": 0.09373460710048676,
+      "learning_rate": 0.00014024939023684298,
+      "loss": 0.0256,
+      "step": 380
+    },
+    {
+      "epoch": 2.379204892966361,
+      "grad_norm": 0.16994407773017883,
+      "learning_rate": 0.0001371942123665092,
+      "loss": 0.0233,
+      "step": 390
+    },
+    {
+      "epoch": 2.4403669724770642,
+      "grad_norm": 0.23053932189941406,
+      "learning_rate": 0.0001340981913967656,
+      "loss": 0.0285,
+      "step": 400
+    },
+    {
+      "epoch": 2.4403669724770642,
+      "eval_loss": 0.0535120964050293,
+      "eval_runtime": 16.5169,
+      "eval_samples_per_second": 4.42,
+      "eval_steps_per_second": 2.24,
+      "step": 400
+    },
+    {
+      "eval_ner_f1": 0.3055555555555555,
+      "step": 400
+    },
+    {
+      "eval_ner_precision": 0.6875,
+      "step": 400
+    },
+    {
+      "eval_ner_recall": 0.19642857142857142,
+      "step": 400
+    },
+    {
+      "eval_ner_f1_toponym": 0.3142857142857143,
+      "step": 400
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 400
+    },
+    {
+      "eval_ner_f1_organization": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 2.5015290519877675,
+      "grad_norm": 0.4044734239578247,
+      "learning_rate": 0.00013096472707946056,
+      "loss": 0.0306,
+      "step": 410
+    },
+    {
+      "epoch": 2.562691131498471,
+      "grad_norm": 0.11446376889944077,
+      "learning_rate": 0.0001277972602831181,
+      "loss": 0.0188,
+      "step": 420
+    },
+    {
+      "epoch": 2.623853211009174,
+      "grad_norm": 0.16048116981983185,
+      "learning_rate": 0.0001245992692145078,
+      "loss": 0.0282,
+      "step": 430
+    },
+    {
+      "epoch": 2.6850152905198774,
+      "grad_norm": 0.10304035991430283,
+      "learning_rate": 0.00012137426559921316,
+      "loss": 0.0273,
+      "step": 440
+    },
+    {
+      "epoch": 2.746177370030581,
+      "grad_norm": 0.04728333652019501,
+      "learning_rate": 0.00011812579082539317,
+      "loss": 0.0205,
+      "step": 450
+    },
+    {
+      "epoch": 2.8073394495412844,
+      "grad_norm": 0.09207329899072647,
+      "learning_rate": 0.00011485741205497094,
+      "loss": 0.0211,
+      "step": 460
+    },
+    {
+      "epoch": 2.8685015290519877,
+      "grad_norm": 0.17346537113189697,
+      "learning_rate": 0.00011157271830652062,
+      "loss": 0.0326,
+      "step": 470
+    },
+    {
+      "epoch": 2.929663608562691,
+      "grad_norm": 0.07529453188180923,
+      "learning_rate": 0.00010827531651415266,
+      "loss": 0.0192,
+      "step": 480
+    },
+    {
+      "epoch": 2.9908256880733948,
+      "grad_norm": 0.10349865257740021,
+      "learning_rate": 0.00010496882756672666,
+      "loss": 0.0175,
+      "step": 490
+    },
+    {
+      "epoch": 3.0489296636085625,
+      "grad_norm": 0.06423936784267426,
+      "learning_rate": 0.00010165688233174017,
+      "loss": 0.0129,
+      "step": 500
+    },
+    {
+      "epoch": 3.0489296636085625,
+      "eval_loss": 0.05351715907454491,
+      "eval_runtime": 16.4745,
+      "eval_samples_per_second": 4.431,
+      "eval_steps_per_second": 2.246,
+      "step": 500
+    },
+    {
+      "eval_ner_f1": 0.34285714285714286,
+      "step": 500
+    },
+    {
+      "eval_ner_precision": 0.8571428571428571,
+      "step": 500
+    },
+    {
+      "eval_ner_recall": 0.21428571428571427,
+      "step": 500
+    },
+    {
+      "eval_ner_f1_toponym": 0.34285714285714286,
+      "step": 500
+    },
+    {
+      "epoch": 3.1100917431192663,
+      "grad_norm": 0.10966634750366211,
+      "learning_rate": 9.834311766825985e-05,
+      "loss": 0.0108,
+      "step": 510
+    },
+    {
+      "epoch": 3.1712538226299696,
+      "grad_norm": 0.03550288453698158,
+      "learning_rate": 9.503117243327337e-05,
+      "loss": 0.0082,
+      "step": 520
+    },
+    {
+      "epoch": 3.232415902140673,
+      "grad_norm": 0.07612079381942749,
+      "learning_rate": 9.172468348584739e-05,
+      "loss": 0.0073,
+      "step": 530
+    },
+    {
+      "epoch": 3.293577981651376,
+      "grad_norm": 0.10736043751239777,
+      "learning_rate": 8.842728169347939e-05,
+      "loss": 0.0095,
+      "step": 540
+    },
+    {
+      "epoch": 3.3547400611620795,
+      "grad_norm": 0.10124403238296509,
+      "learning_rate": 8.514258794502905e-05,
+      "loss": 0.0147,
+      "step": 550
+    },
+    {
+      "epoch": 3.4159021406727827,
+      "grad_norm": 0.08522272109985352,
+      "learning_rate": 8.187420917460686e-05,
+      "loss": 0.0143,
+      "step": 560
+    },
+    {
+      "epoch": 3.477064220183486,
+      "grad_norm": 0.10443105548620224,
+      "learning_rate": 7.862573440078686e-05,
+      "loss": 0.0109,
+      "step": 570
+    },
+    {
+      "epoch": 3.5382262996941893,
+      "grad_norm": 0.07868387550115585,
+      "learning_rate": 7.540073078549221e-05,
+      "loss": 0.0068,
+      "step": 580
+    },
+    {
+      "epoch": 3.599388379204893,
+      "grad_norm": 0.034807343035936356,
+      "learning_rate": 7.220273971688192e-05,
+      "loss": 0.0107,
+      "step": 590
+    },
+    {
+      "epoch": 3.6605504587155964,
+      "grad_norm": 0.020409688353538513,
+      "learning_rate": 6.903527292053942e-05,
+      "loss": 0.0101,
+      "step": 600
+    },
+    {
+      "epoch": 3.6605504587155964,
+      "eval_loss": 0.0602705255150795,
+      "eval_runtime": 15.876,
+      "eval_samples_per_second": 4.598,
+      "eval_steps_per_second": 2.331,
+      "step": 600
+    },
+    {
+      "eval_ner_f1": 0.30769230769230765,
+      "step": 600
+    },
+    {
+      "eval_ner_precision": 0.5454545454545454,
+      "step": 600
+    },
+    {
+      "eval_ner_recall": 0.21428571428571427,
+      "step": 600
+    },
+    {
+      "eval_ner_f1_toponym": 0.34782608695652173,
+      "step": 600
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 600
+    },
+    {
+      "eval_ner_f1_organization": 0.0,
+      "step": 600
+    },
+    {
+      "epoch": 3.7217125382262997,
+      "grad_norm": 0.04670476168394089,
+      "learning_rate": 6.59018086032344e-05,
+      "loss": 0.0101,
+      "step": 610
+    },
+    {
+      "epoch": 3.782874617737003,
+      "grad_norm": 0.01200962159782648,
+      "learning_rate": 6.280578763349078e-05,
+      "loss": 0.006,
+      "step": 620
+    },
+    {
+      "epoch": 3.8440366972477067,
+      "grad_norm": 0.05485844239592552,
+      "learning_rate": 5.975060976315703e-05,
+      "loss": 0.0109,
+      "step": 630
+    },
+    {
+      "epoch": 3.90519877675841,
+      "grad_norm": 0.09339557588100433,
+      "learning_rate": 5.673962989412599e-05,
+      "loss": 0.0057,
+      "step": 640
+    },
+    {
+      "epoch": 3.9663608562691133,
+      "grad_norm": 0.21686244010925293,
+      "learning_rate": 5.377615439430508e-05,
+      "loss": 0.0081,
+      "step": 650
+    },
+    {
+      "epoch": 4.0244648318042815,
+      "grad_norm": 0.04568672925233841,
+      "learning_rate": 5.0863437466881836e-05,
+      "loss": 0.0071,
+      "step": 660
+    },
+    {
+      "epoch": 4.085626911314985,
+      "grad_norm": 0.037828218191862106,
+      "learning_rate": 4.80046775768713e-05,
+      "loss": 0.0025,
+      "step": 670
+    },
+    {
+      "epoch": 4.146788990825688,
+      "grad_norm": 0.05333082377910614,
+      "learning_rate": 4.520301393887033e-05,
+      "loss": 0.0032,
+      "step": 680
+    },
+    {
+      "epoch": 4.207951070336391,
+      "grad_norm": 0.007903705351054668,
+      "learning_rate": 4.2461523069874346e-05,
+      "loss": 0.0027,
+      "step": 690
+    },
+    {
+      "epoch": 4.269113149847095,
+      "grad_norm": 0.007534786593168974,
+      "learning_rate": 3.9783215410943174e-05,
+      "loss": 0.0019,
+      "step": 700
+    },
+    {
+      "epoch": 4.269113149847095,
+      "eval_loss": 0.06749989837408066,
+      "eval_runtime": 16.1258,
+      "eval_samples_per_second": 4.527,
+      "eval_steps_per_second": 2.294,
+      "step": 700
+    },
+    {
+      "eval_ner_f1": 0.379746835443038,
+      "step": 700
+    },
+    {
+      "eval_ner_precision": 0.6521739130434783,
+      "step": 700
+    },
+    {
+      "eval_ner_recall": 0.26785714285714285,
+      "step": 700
+    },
+    {
+      "eval_ner_f1_toponym": 0.3896103896103896,
+      "step": 700
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 700
+    },
+    {
+      "epoch": 4.330275229357798,
+      "grad_norm": 0.046107176691293716,
+      "learning_rate": 3.717103202142457e-05,
+      "loss": 0.0028,
+      "step": 710
+    },
+    {
+      "epoch": 4.391437308868501,
+      "grad_norm": 0.022927094250917435,
+      "learning_rate": 3.462784134936636e-05,
+      "loss": 0.0047,
+      "step": 720
+    },
+    {
+      "epoch": 4.4525993883792045,
+      "grad_norm": 0.09270883351564407,
+      "learning_rate": 3.2156436081663356e-05,
+      "loss": 0.0035,
+      "step": 730
+    },
+    {
+      "epoch": 4.513761467889909,
+      "grad_norm": 0.2539561092853546,
+      "learning_rate": 2.9759530077397636e-05,
+      "loss": 0.0011,
+      "step": 740
+    },
+    {
+      "epoch": 4.574923547400612,
+      "grad_norm": 0.0036298525519669056,
+      "learning_rate": 2.743975538774002e-05,
+      "loss": 0.0041,
+      "step": 750
+    },
+    {
+      "epoch": 4.636085626911315,
+      "grad_norm": 0.005658215843141079,
+      "learning_rate": 2.5199659365685235e-05,
+      "loss": 0.0017,
+      "step": 760
+    },
+    {
+      "epoch": 4.697247706422019,
+      "grad_norm": 0.00670202262699604,
+      "learning_rate": 2.3041701868794287e-05,
+      "loss": 0.0053,
+      "step": 770
+    },
+    {
+      "epoch": 4.758409785932722,
+      "grad_norm": 0.0019507587421685457,
+      "learning_rate": 2.0968252558016055e-05,
+      "loss": 0.0029,
+      "step": 780
+    },
+    {
+      "epoch": 4.819571865443425,
+      "grad_norm": 0.01064695417881012,
+      "learning_rate": 1.8981588295553853e-05,
+      "loss": 0.0051,
+      "step": 790
+    },
+    {
+      "epoch": 4.8807339449541285,
+      "grad_norm": 0.007430676836520433,
+      "learning_rate": 1.7083890644635014e-05,
+      "loss": 0.0047,
+      "step": 800
+    },
+    {
+      "epoch": 4.8807339449541285,
+      "eval_loss": 0.07247484475374222,
+      "eval_runtime": 15.8563,
+      "eval_samples_per_second": 4.604,
+      "eval_steps_per_second": 2.333,
+      "step": 800
+    },
+    {
+      "eval_ner_f1": 0.3783783783783784,
+      "step": 800
+    },
+    {
+      "eval_ner_precision": 0.7777777777777778,
+      "step": 800
+    },
+    {
+      "eval_ner_recall": 0.25,
+      "step": 800
+    },
+    {
+      "eval_ner_f1_toponym": 0.3835616438356164,
+      "step": 800
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 800
+    },
+    {
+      "epoch": 4.941896024464832,
+      "grad_norm": 0.04860910028219223,
+      "learning_rate": 1.527724347392815e-05,
+      "loss": 0.0039,
+      "step": 810
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.002881321357563138,
+      "learning_rate": 1.3563630669239624e-05,
+      "loss": 0.0031,
+      "step": 820
+    },
+    {
+      "epoch": 5.061162079510703,
+      "grad_norm": 0.07761278748512268,
+      "learning_rate": 1.1944933955001225e-05,
+      "loss": 0.0029,
+      "step": 830
+    },
+    {
+      "epoch": 5.122324159021407,
+      "grad_norm": 0.017536113038659096,
+      "learning_rate": 1.04229308279418e-05,
+      "loss": 0.0006,
+      "step": 840
+    },
+    {
+      "epoch": 5.18348623853211,
+      "grad_norm": 0.022405065596103668,
+      "learning_rate": 8.999292605211695e-06,
+      "loss": 0.0022,
+      "step": 850
+    },
+    {
+      "epoch": 5.244648318042813,
+      "grad_norm": 0.03178695961833,
+      "learning_rate": 7.675582589103247e-06,
+      "loss": 0.001,
+      "step": 860
+    },
+    {
+      "epoch": 5.3058103975535165,
+      "grad_norm": 0.011610076762735844,
+      "learning_rate": 6.45325435038292e-06,
+      "loss": 0.0009,
+      "step": 870
+    },
+    {
+      "epoch": 5.36697247706422,
+      "grad_norm": 0.05008087307214737,
+      "learning_rate": 5.3336501321199714e-06,
+      "loss": 0.0024,
+      "step": 880
+    },
+    {
+      "epoch": 5.428134556574924,
+      "grad_norm": 0.0026775060687214136,
+      "learning_rate": 4.317999375764459e-06,
+      "loss": 0.0025,
+      "step": 890
+    },
+    {
+      "epoch": 5.489296636085627,
+      "grad_norm": 0.022927429527044296,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0011,
+      "step": 900
+    },
+    {
+      "epoch": 5.489296636085627,
+      "eval_loss": 0.07354085147380829,
+      "eval_runtime": 16.7178,
+      "eval_samples_per_second": 4.367,
+      "eval_steps_per_second": 2.213,
+      "step": 900
+    },
+    {
+      "eval_ner_f1": 0.3783783783783784,
+      "step": 900
+    },
+    {
+      "eval_ner_precision": 0.7777777777777778,
+      "step": 900
+    },
+    {
+      "eval_ner_recall": 0.25,
+      "step": 900
+    },
+    {
+      "eval_ner_f1_toponym": 0.3835616438356164,
+      "step": 900
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 900
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 978,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5030508615370957e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

toponym_lora/checkpoint-900/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c264c52127e7b32e02112d53c064f4d314a786fd6b750d0d213bf34b45b4b318
+size 5713

toponym_lora/checkpoint-978/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen3-4B-Instruct-2507
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Instruct-2507
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

toponym_lora/checkpoint-978/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Instruct-2507",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

toponym_lora/checkpoint-978/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab09ae476a93470d85ac7605a032fcec7da71f201404ed566dfe5605abbad948
+size 528550256

toponym_lora/checkpoint-978/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

toponym_lora/checkpoint-978/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:283a6b5cce7a220132754a71a725119d99254b9961184469dd109144c9ebb61e
+size 1057390923

toponym_lora/checkpoint-978/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3582fd5d60e38ec10a13678c7fa264ec90203c191d12b4aef8ff3530910253ad
+size 14645

toponym_lora/checkpoint-978/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42fab66428211654c9b628855ba104bd5c5700f1c28e9af984e238eb2b63d3f5
+size 1465

toponym_lora/checkpoint-978/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

toponym_lora/checkpoint-978/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f1298e298f2fe0059aba46f037697a339ccba45a1908780ce8ca14b45582f23
+size 11422753

toponym_lora/checkpoint-978/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1010000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

toponym_lora/checkpoint-978/trainer_state.json

@@ -0,0 +1,973 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.966360856269113,
+  "eval_steps": 100,
+  "global_step": 978,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06116207951070336,
+      "grad_norm": 0.5065167546272278,
+      "learning_rate": 6e-05,
+      "loss": 0.4883,
+      "step": 10
+    },
+    {
+      "epoch": 0.12232415902140673,
+      "grad_norm": 0.28862252831459045,
+      "learning_rate": 0.00012666666666666666,
+      "loss": 0.2469,
+      "step": 20
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 0.1823580414056778,
+      "learning_rate": 0.00019333333333333333,
+      "loss": 0.1435,
+      "step": 30
+    },
+    {
+      "epoch": 0.24464831804281345,
+      "grad_norm": 0.2956920564174652,
+      "learning_rate": 0.00019995552602987827,
+      "loss": 0.1124,
+      "step": 40
+    },
+    {
+      "epoch": 0.3058103975535168,
+      "grad_norm": 0.15972661972045898,
+      "learning_rate": 0.00019980183963589504,
+      "loss": 0.1319,
+      "step": 50
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.2291875034570694,
+      "learning_rate": 0.00019953856048007652,
+      "loss": 0.089,
+      "step": 60
+    },
+    {
+      "epoch": 0.42813455657492355,
+      "grad_norm": 0.1270621418952942,
+      "learning_rate": 0.00019916597767021807,
+      "loss": 0.1027,
+      "step": 70
+    },
+    {
+      "epoch": 0.4892966360856269,
+      "grad_norm": 0.1719549000263214,
+      "learning_rate": 0.00019868450034085352,
+      "loss": 0.09,
+      "step": 80
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.11448629200458527,
+      "learning_rate": 0.0001980946572039834,
+      "loss": 0.0886,
+      "step": 90
+    },
+    {
+      "epoch": 0.6116207951070336,
+      "grad_norm": 0.1629963368177414,
+      "learning_rate": 0.00019739709596849417,
+      "loss": 0.0974,
+      "step": 100
+    },
+    {
+      "epoch": 0.6116207951070336,
+      "eval_loss": 0.0775158628821373,
+      "eval_runtime": 17.6163,
+      "eval_samples_per_second": 4.144,
+      "eval_steps_per_second": 2.1,
+      "step": 100
+    },
+    {
+      "eval_ner_f1": 0.26666666666666666,
+      "step": 100
+    },
+    {
+      "eval_ner_precision": 0.5263157894736842,
+      "step": 100
+    },
+    {
+      "eval_ner_recall": 0.17857142857142858,
+      "step": 100
+    },
+    {
+      "eval_ner_f1_toponym": 0.273972602739726,
+      "step": 100
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 100
+    },
+    {
+      "eval_ner_f1_organization": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.672782874617737,
+      "grad_norm": 0.07239006459712982,
+      "learning_rate": 0.00019659258262890683,
+      "loss": 0.0783,
+      "step": 110
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.18169932067394257,
+      "learning_rate": 0.00019568200062423555,
+      "loss": 0.079,
+      "step": 120
+    },
+    {
+      "epoch": 0.7951070336391437,
+      "grad_norm": 0.13822244107723236,
+      "learning_rate": 0.00019466634986788005,
+      "loss": 0.0711,
+      "step": 130
+    },
+    {
+      "epoch": 0.8562691131498471,
+      "grad_norm": 0.08978362381458282,
+      "learning_rate": 0.0001935467456496171,
+      "loss": 0.0809,
+      "step": 140
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 0.09890680760145187,
+      "learning_rate": 0.00019232441741089676,
+      "loss": 0.0745,
+      "step": 150
+    },
+    {
+      "epoch": 0.9785932721712538,
+      "grad_norm": 0.20916098356246948,
+      "learning_rate": 0.00019100070739478832,
+      "loss": 0.0755,
+      "step": 160
+    },
+    {
+      "epoch": 1.036697247706422,
+      "grad_norm": 0.11759505420923233,
+      "learning_rate": 0.0001895770691720582,
+      "loss": 0.0722,
+      "step": 170
+    },
+    {
+      "epoch": 1.0978593272171253,
+      "grad_norm": 0.0745391771197319,
+      "learning_rate": 0.0001880550660449988,
+      "loss": 0.0482,
+      "step": 180
+    },
+    {
+      "epoch": 1.1590214067278288,
+      "grad_norm": 0.1519857943058014,
+      "learning_rate": 0.0001864363693307604,
+      "loss": 0.045,
+      "step": 190
+    },
+    {
+      "epoch": 1.2201834862385321,
+      "grad_norm": 0.07725294679403305,
+      "learning_rate": 0.00018472275652607186,
+      "loss": 0.0476,
+      "step": 200
+    },
+    {
+      "epoch": 1.2201834862385321,
+      "eval_loss": 0.06860311329364777,
+      "eval_runtime": 16.2309,
+      "eval_samples_per_second": 4.498,
+      "eval_steps_per_second": 2.28,
+      "step": 200
+    },
+    {
+      "eval_ner_f1": 0.2894736842105263,
+      "step": 200
+    },
+    {
+      "eval_ner_precision": 0.55,
+      "step": 200
+    },
+    {
+      "eval_ner_recall": 0.19642857142857142,
+      "step": 200
+    },
+    {
+      "eval_ner_f1_toponym": 0.3142857142857143,
+      "step": 200
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.2813455657492354,
+      "grad_norm": 0.07129528373479843,
+      "learning_rate": 0.000182916109355365,
+      "loss": 0.0538,
+      "step": 210
+    },
+    {
+      "epoch": 1.3425076452599387,
+      "grad_norm": 0.07345232367515564,
+      "learning_rate": 0.00018101841170444616,
+      "loss": 0.0444,
+      "step": 220
+    },
+    {
+      "epoch": 1.4036697247706422,
+      "grad_norm": 0.1663370579481125,
+      "learning_rate": 0.000179031747441984,
+      "loss": 0.06,
+      "step": 230
+    },
+    {
+      "epoch": 1.4648318042813455,
+      "grad_norm": 0.0920317992568016,
+      "learning_rate": 0.0001769582981312057,
+      "loss": 0.036,
+      "step": 240
+    },
+    {
+      "epoch": 1.525993883792049,
+      "grad_norm": 0.15344829857349396,
+      "learning_rate": 0.00017480034063431477,
+      "loss": 0.0572,
+      "step": 250
+    },
+    {
+      "epoch": 1.5871559633027523,
+      "grad_norm": 0.11365994811058044,
+      "learning_rate": 0.00017256024461226001,
+      "loss": 0.0609,
+      "step": 260
+    },
+    {
+      "epoch": 1.6483180428134556,
+      "grad_norm": 0.11572407931089401,
+      "learning_rate": 0.00017024046992260237,
+      "loss": 0.0441,
+      "step": 270
+    },
+    {
+      "epoch": 1.709480122324159,
+      "grad_norm": 0.16469694674015045,
+      "learning_rate": 0.00016784356391833665,
+      "loss": 0.0432,
+      "step": 280
+    },
+    {
+      "epoch": 1.7706422018348624,
+      "grad_norm": 0.08726947009563446,
+      "learning_rate": 0.00016537215865063365,
+      "loss": 0.0483,
+      "step": 290
+    },
+    {
+      "epoch": 1.8318042813455657,
+      "grad_norm": 0.10488814115524292,
+      "learning_rate": 0.00016282896797857548,
+      "loss": 0.0486,
+      "step": 300
+    },
+    {
+      "epoch": 1.8318042813455657,
+      "eval_loss": 0.052874963730573654,
+      "eval_runtime": 16.301,
+      "eval_samples_per_second": 4.478,
+      "eval_steps_per_second": 2.27,
+      "step": 300
+    },
+    {
+      "eval_ner_f1": 0.2894736842105263,
+      "step": 300
+    },
+    {
+      "eval_ner_precision": 0.55,
+      "step": 300
+    },
+    {
+      "eval_ner_recall": 0.19642857142857142,
+      "step": 300
+    },
+    {
+      "eval_ner_f1_toponym": 0.3142857142857143,
+      "step": 300
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 1.8929663608562692,
+      "grad_norm": 0.10856537520885468,
+      "learning_rate": 0.00016021678458905684,
+      "loss": 0.0477,
+      "step": 310
+    },
+    {
+      "epoch": 1.9541284403669725,
+      "grad_norm": 0.10471344739198685,
+      "learning_rate": 0.00015753847693012566,
+      "loss": 0.0547,
+      "step": 320
+    },
+    {
+      "epoch": 2.0122324159021407,
+      "grad_norm": 0.07346905022859573,
+      "learning_rate": 0.0001547969860611297,
+      "loss": 0.0467,
+      "step": 330
+    },
+    {
+      "epoch": 2.073394495412844,
+      "grad_norm": 0.0847230851650238,
+      "learning_rate": 0.0001519953224231287,
+      "loss": 0.0186,
+      "step": 340
+    },
+    {
+      "epoch": 2.1345565749235473,
+      "grad_norm": 0.11084947735071182,
+      "learning_rate": 0.0001491365625331182,
+      "loss": 0.0268,
+      "step": 350
+    },
+    {
+      "epoch": 2.1957186544342506,
+      "grad_norm": 0.11435306072235107,
+      "learning_rate": 0.00014622384560569493,
+      "loss": 0.0324,
+      "step": 360
+    },
+    {
+      "epoch": 2.2568807339449544,
+      "grad_norm": 0.05882082134485245,
+      "learning_rate": 0.00014326037010587404,
+      "loss": 0.0279,
+      "step": 370
+    },
+    {
+      "epoch": 2.3180428134556577,
+      "grad_norm": 0.09373460710048676,
+      "learning_rate": 0.00014024939023684298,
+      "loss": 0.0256,
+      "step": 380
+    },
+    {
+      "epoch": 2.379204892966361,
+      "grad_norm": 0.16994407773017883,
+      "learning_rate": 0.0001371942123665092,
+      "loss": 0.0233,
+      "step": 390
+    },
+    {
+      "epoch": 2.4403669724770642,
+      "grad_norm": 0.23053932189941406,
+      "learning_rate": 0.0001340981913967656,
+      "loss": 0.0285,
+      "step": 400
+    },
+    {
+      "epoch": 2.4403669724770642,
+      "eval_loss": 0.0535120964050293,
+      "eval_runtime": 16.5169,
+      "eval_samples_per_second": 4.42,
+      "eval_steps_per_second": 2.24,
+      "step": 400
+    },
+    {
+      "eval_ner_f1": 0.3055555555555555,
+      "step": 400
+    },
+    {
+      "eval_ner_precision": 0.6875,
+      "step": 400
+    },
+    {
+      "eval_ner_recall": 0.19642857142857142,
+      "step": 400
+    },
+    {
+      "eval_ner_f1_toponym": 0.3142857142857143,
+      "step": 400
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 400
+    },
+    {
+      "eval_ner_f1_organization": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 2.5015290519877675,
+      "grad_norm": 0.4044734239578247,
+      "learning_rate": 0.00013096472707946056,
+      "loss": 0.0306,
+      "step": 410
+    },
+    {
+      "epoch": 2.562691131498471,
+      "grad_norm": 0.11446376889944077,
+      "learning_rate": 0.0001277972602831181,
+      "loss": 0.0188,
+      "step": 420
+    },
+    {
+      "epoch": 2.623853211009174,
+      "grad_norm": 0.16048116981983185,
+      "learning_rate": 0.0001245992692145078,
+      "loss": 0.0282,
+      "step": 430
+    },
+    {
+      "epoch": 2.6850152905198774,
+      "grad_norm": 0.10304035991430283,
+      "learning_rate": 0.00012137426559921316,
+      "loss": 0.0273,
+      "step": 440
+    },
+    {
+      "epoch": 2.746177370030581,
+      "grad_norm": 0.04728333652019501,
+      "learning_rate": 0.00011812579082539317,
+      "loss": 0.0205,
+      "step": 450
+    },
+    {
+      "epoch": 2.8073394495412844,
+      "grad_norm": 0.09207329899072647,
+      "learning_rate": 0.00011485741205497094,
+      "loss": 0.0211,
+      "step": 460
+    },
+    {
+      "epoch": 2.8685015290519877,
+      "grad_norm": 0.17346537113189697,
+      "learning_rate": 0.00011157271830652062,
+      "loss": 0.0326,
+      "step": 470
+    },
+    {
+      "epoch": 2.929663608562691,
+      "grad_norm": 0.07529453188180923,
+      "learning_rate": 0.00010827531651415266,
+      "loss": 0.0192,
+      "step": 480
+    },
+    {
+      "epoch": 2.9908256880733948,
+      "grad_norm": 0.10349865257740021,
+      "learning_rate": 0.00010496882756672666,
+      "loss": 0.0175,
+      "step": 490
+    },
+    {
+      "epoch": 3.0489296636085625,
+      "grad_norm": 0.06423936784267426,
+      "learning_rate": 0.00010165688233174017,
+      "loss": 0.0129,
+      "step": 500
+    },
+    {
+      "epoch": 3.0489296636085625,
+      "eval_loss": 0.05351715907454491,
+      "eval_runtime": 16.4745,
+      "eval_samples_per_second": 4.431,
+      "eval_steps_per_second": 2.246,
+      "step": 500
+    },
+    {
+      "eval_ner_f1": 0.34285714285714286,
+      "step": 500
+    },
+    {
+      "eval_ner_precision": 0.8571428571428571,
+      "step": 500
+    },
+    {
+      "eval_ner_recall": 0.21428571428571427,
+      "step": 500
+    },
+    {
+      "eval_ner_f1_toponym": 0.34285714285714286,
+      "step": 500
+    },
+    {
+      "epoch": 3.1100917431192663,
+      "grad_norm": 0.10966634750366211,
+      "learning_rate": 9.834311766825985e-05,
+      "loss": 0.0108,
+      "step": 510
+    },
+    {
+      "epoch": 3.1712538226299696,
+      "grad_norm": 0.03550288453698158,
+      "learning_rate": 9.503117243327337e-05,
+      "loss": 0.0082,
+      "step": 520
+    },
+    {
+      "epoch": 3.232415902140673,
+      "grad_norm": 0.07612079381942749,
+      "learning_rate": 9.172468348584739e-05,
+      "loss": 0.0073,
+      "step": 530
+    },
+    {
+      "epoch": 3.293577981651376,
+      "grad_norm": 0.10736043751239777,
+      "learning_rate": 8.842728169347939e-05,
+      "loss": 0.0095,
+      "step": 540
+    },
+    {
+      "epoch": 3.3547400611620795,
+      "grad_norm": 0.10124403238296509,
+      "learning_rate": 8.514258794502905e-05,
+      "loss": 0.0147,
+      "step": 550
+    },
+    {
+      "epoch": 3.4159021406727827,
+      "grad_norm": 0.08522272109985352,
+      "learning_rate": 8.187420917460686e-05,
+      "loss": 0.0143,
+      "step": 560
+    },
+    {
+      "epoch": 3.477064220183486,
+      "grad_norm": 0.10443105548620224,
+      "learning_rate": 7.862573440078686e-05,
+      "loss": 0.0109,
+      "step": 570
+    },
+    {
+      "epoch": 3.5382262996941893,
+      "grad_norm": 0.07868387550115585,
+      "learning_rate": 7.540073078549221e-05,
+      "loss": 0.0068,
+      "step": 580
+    },
+    {
+      "epoch": 3.599388379204893,
+      "grad_norm": 0.034807343035936356,
+      "learning_rate": 7.220273971688192e-05,
+      "loss": 0.0107,
+      "step": 590
+    },
+    {
+      "epoch": 3.6605504587155964,
+      "grad_norm": 0.020409688353538513,
+      "learning_rate": 6.903527292053942e-05,
+      "loss": 0.0101,
+      "step": 600
+    },
+    {
+      "epoch": 3.6605504587155964,
+      "eval_loss": 0.0602705255150795,
+      "eval_runtime": 15.876,
+      "eval_samples_per_second": 4.598,
+      "eval_steps_per_second": 2.331,
+      "step": 600
+    },
+    {
+      "eval_ner_f1": 0.30769230769230765,
+      "step": 600
+    },
+    {
+      "eval_ner_precision": 0.5454545454545454,
+      "step": 600
+    },
+    {
+      "eval_ner_recall": 0.21428571428571427,
+      "step": 600
+    },
+    {
+      "eval_ner_f1_toponym": 0.34782608695652173,
+      "step": 600
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 600
+    },
+    {
+      "eval_ner_f1_organization": 0.0,
+      "step": 600
+    },
+    {
+      "epoch": 3.7217125382262997,
+      "grad_norm": 0.04670476168394089,
+      "learning_rate": 6.59018086032344e-05,
+      "loss": 0.0101,
+      "step": 610
+    },
+    {
+      "epoch": 3.782874617737003,
+      "grad_norm": 0.01200962159782648,
+      "learning_rate": 6.280578763349078e-05,
+      "loss": 0.006,
+      "step": 620
+    },
+    {
+      "epoch": 3.8440366972477067,
+      "grad_norm": 0.05485844239592552,
+      "learning_rate": 5.975060976315703e-05,
+      "loss": 0.0109,
+      "step": 630
+    },
+    {
+      "epoch": 3.90519877675841,
+      "grad_norm": 0.09339557588100433,
+      "learning_rate": 5.673962989412599e-05,
+      "loss": 0.0057,
+      "step": 640
+    },
+    {
+      "epoch": 3.9663608562691133,
+      "grad_norm": 0.21686244010925293,
+      "learning_rate": 5.377615439430508e-05,
+      "loss": 0.0081,
+      "step": 650
+    },
+    {
+      "epoch": 4.0244648318042815,
+      "grad_norm": 0.04568672925233841,
+      "learning_rate": 5.0863437466881836e-05,
+      "loss": 0.0071,
+      "step": 660
+    },
+    {
+      "epoch": 4.085626911314985,
+      "grad_norm": 0.037828218191862106,
+      "learning_rate": 4.80046775768713e-05,
+      "loss": 0.0025,
+      "step": 670
+    },
+    {
+      "epoch": 4.146788990825688,
+      "grad_norm": 0.05333082377910614,
+      "learning_rate": 4.520301393887033e-05,
+      "loss": 0.0032,
+      "step": 680
+    },
+    {
+      "epoch": 4.207951070336391,
+      "grad_norm": 0.007903705351054668,
+      "learning_rate": 4.2461523069874346e-05,
+      "loss": 0.0027,
+      "step": 690
+    },
+    {
+      "epoch": 4.269113149847095,
+      "grad_norm": 0.007534786593168974,
+      "learning_rate": 3.9783215410943174e-05,
+      "loss": 0.0019,
+      "step": 700
+    },
+    {
+      "epoch": 4.269113149847095,
+      "eval_loss": 0.06749989837408066,
+      "eval_runtime": 16.1258,
+      "eval_samples_per_second": 4.527,
+      "eval_steps_per_second": 2.294,
+      "step": 700
+    },
+    {
+      "eval_ner_f1": 0.379746835443038,
+      "step": 700
+    },
+    {
+      "eval_ner_precision": 0.6521739130434783,
+      "step": 700
+    },
+    {
+      "eval_ner_recall": 0.26785714285714285,
+      "step": 700
+    },
+    {
+      "eval_ner_f1_toponym": 0.3896103896103896,
+      "step": 700
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 700
+    },
+    {
+      "epoch": 4.330275229357798,
+      "grad_norm": 0.046107176691293716,
+      "learning_rate": 3.717103202142457e-05,
+      "loss": 0.0028,
+      "step": 710
+    },
+    {
+      "epoch": 4.391437308868501,
+      "grad_norm": 0.022927094250917435,
+      "learning_rate": 3.462784134936636e-05,
+      "loss": 0.0047,
+      "step": 720
+    },
+    {
+      "epoch": 4.4525993883792045,
+      "grad_norm": 0.09270883351564407,
+      "learning_rate": 3.2156436081663356e-05,
+      "loss": 0.0035,
+      "step": 730
+    },
+    {
+      "epoch": 4.513761467889909,
+      "grad_norm": 0.2539561092853546,
+      "learning_rate": 2.9759530077397636e-05,
+      "loss": 0.0011,
+      "step": 740
+    },
+    {
+      "epoch": 4.574923547400612,
+      "grad_norm": 0.0036298525519669056,
+      "learning_rate": 2.743975538774002e-05,
+      "loss": 0.0041,
+      "step": 750
+    },
+    {
+      "epoch": 4.636085626911315,
+      "grad_norm": 0.005658215843141079,
+      "learning_rate": 2.5199659365685235e-05,
+      "loss": 0.0017,
+      "step": 760
+    },
+    {
+      "epoch": 4.697247706422019,
+      "grad_norm": 0.00670202262699604,
+      "learning_rate": 2.3041701868794287e-05,
+      "loss": 0.0053,
+      "step": 770
+    },
+    {
+      "epoch": 4.758409785932722,
+      "grad_norm": 0.0019507587421685457,
+      "learning_rate": 2.0968252558016055e-05,
+      "loss": 0.0029,
+      "step": 780
+    },
+    {
+      "epoch": 4.819571865443425,
+      "grad_norm": 0.01064695417881012,
+      "learning_rate": 1.8981588295553853e-05,
+      "loss": 0.0051,
+      "step": 790
+    },
+    {
+      "epoch": 4.8807339449541285,
+      "grad_norm": 0.007430676836520433,
+      "learning_rate": 1.7083890644635014e-05,
+      "loss": 0.0047,
+      "step": 800
+    },
+    {
+      "epoch": 4.8807339449541285,
+      "eval_loss": 0.07247484475374222,
+      "eval_runtime": 15.8563,
+      "eval_samples_per_second": 4.604,
+      "eval_steps_per_second": 2.333,
+      "step": 800
+    },
+    {
+      "eval_ner_f1": 0.3783783783783784,
+      "step": 800
+    },
+    {
+      "eval_ner_precision": 0.7777777777777778,
+      "step": 800
+    },
+    {
+      "eval_ner_recall": 0.25,
+      "step": 800
+    },
+    {
+      "eval_ner_f1_toponym": 0.3835616438356164,
+      "step": 800
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 800
+    },
+    {
+      "epoch": 4.941896024464832,
+      "grad_norm": 0.04860910028219223,
+      "learning_rate": 1.527724347392815e-05,
+      "loss": 0.0039,
+      "step": 810
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.002881321357563138,
+      "learning_rate": 1.3563630669239624e-05,
+      "loss": 0.0031,
+      "step": 820
+    },
+    {
+      "epoch": 5.061162079510703,
+      "grad_norm": 0.07761278748512268,
+      "learning_rate": 1.1944933955001225e-05,
+      "loss": 0.0029,
+      "step": 830
+    },
+    {
+      "epoch": 5.122324159021407,
+      "grad_norm": 0.017536113038659096,
+      "learning_rate": 1.04229308279418e-05,
+      "loss": 0.0006,
+      "step": 840
+    },
+    {
+      "epoch": 5.18348623853211,
+      "grad_norm": 0.022405065596103668,
+      "learning_rate": 8.999292605211695e-06,
+      "loss": 0.0022,
+      "step": 850
+    },
+    {
+      "epoch": 5.244648318042813,
+      "grad_norm": 0.03178695961833,
+      "learning_rate": 7.675582589103247e-06,
+      "loss": 0.001,
+      "step": 860
+    },
+    {
+      "epoch": 5.3058103975535165,
+      "grad_norm": 0.011610076762735844,
+      "learning_rate": 6.45325435038292e-06,
+      "loss": 0.0009,
+      "step": 870
+    },
+    {
+      "epoch": 5.36697247706422,
+      "grad_norm": 0.05008087307214737,
+      "learning_rate": 5.3336501321199714e-06,
+      "loss": 0.0024,
+      "step": 880
+    },
+    {
+      "epoch": 5.428134556574924,
+      "grad_norm": 0.0026775060687214136,
+      "learning_rate": 4.317999375764459e-06,
+      "loss": 0.0025,
+      "step": 890
+    },
+    {
+      "epoch": 5.489296636085627,
+      "grad_norm": 0.022927429527044296,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0011,
+      "step": 900
+    },
+    {
+      "epoch": 5.489296636085627,
+      "eval_loss": 0.07354085147380829,
+      "eval_runtime": 16.7178,
+      "eval_samples_per_second": 4.367,
+      "eval_steps_per_second": 2.213,
+      "step": 900
+    },
+    {
+      "eval_ner_f1": 0.3783783783783784,
+      "step": 900
+    },
+    {
+      "eval_ner_precision": 0.7777777777777778,
+      "step": 900
+    },
+    {
+      "eval_ner_recall": 0.25,
+      "step": 900
+    },
+    {
+      "eval_ner_f1_toponym": 0.3835616438356164,
+      "step": 900
+    },
+    {
+      "eval_ner_f1_person": 0.0,
+      "step": 900
+    },
+    {
+      "epoch": 5.5504587155963305,
+      "grad_norm": 0.012552715837955475,
+      "learning_rate": 2.6029040315058485e-06,
+      "loss": 0.0004,
+      "step": 910
+    },
+    {
+      "epoch": 5.611620795107034,
+      "grad_norm": 0.007489943876862526,
+      "learning_rate": 1.9053427960166182e-06,
+      "loss": 0.0022,
+      "step": 920
+    },
+    {
+      "epoch": 5.672782874617737,
+      "grad_norm": 0.05042216554284096,
+      "learning_rate": 1.3154996591464908e-06,
+      "loss": 0.0026,
+      "step": 930
+    },
+    {
+      "epoch": 5.73394495412844,
+      "grad_norm": 0.13189654052257538,
+      "learning_rate": 8.340223297819471e-07,
+      "loss": 0.0025,
+      "step": 940
+    },
+    {
+      "epoch": 5.795107033639144,
+      "grad_norm": 0.0027829280588775873,
+      "learning_rate": 4.614395199234678e-07,
+      "loss": 0.0005,
+      "step": 950
+    },
+    {
+      "epoch": 5.856269113149847,
+      "grad_norm": 0.01883106864988804,
+      "learning_rate": 1.9816036410499338e-07,
+      "loss": 0.0016,
+      "step": 960
+    },
+    {
+      "epoch": 5.91743119266055,
+      "grad_norm": 0.013132578693330288,
+      "learning_rate": 4.447397012177224e-08,
+      "loss": 0.0006,
+      "step": 970
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 978,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.632962471945687e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

toponym_lora/checkpoint-978/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c264c52127e7b32e02112d53c064f4d314a786fd6b750d0d213bf34b45b4b318
+size 5713

toponym_lora/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

toponym_lora/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f1298e298f2fe0059aba46f037697a339ccba45a1908780ce8ca14b45582f23
+size 11422753