Add files using upload-large-folder tool

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: transformers
+model_name: Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1
+
+This model is a fine-tuned version of [Qwen/Qwen3-14B-Base](https://huggingface.co/Qwen/Qwen3-14B-Base).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/katriin-kukk/Cross_lingual_morphological_generalization/runs/rutorgw2) 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.29.0
+- Transformers: 5.5.4
+- Pytorch: 2.10.0
+- Datasets: 4.6.1
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: transformers
+model_name: Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2
+
+This model is a fine-tuned version of [Qwen/Qwen3-14B-Base](https://huggingface.co/Qwen/Qwen3-14B-Base).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/katriin-kukk/Cross_lingual_morphological_generalization/runs/hj2m59ad) 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.29.0
+- Transformers: 5.5.4
+- Pytorch: 2.10.0
+- Datasets: 4.6.1
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-1284/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.19.1

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-1284/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-Base",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.030195310029781444,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-1284/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-1284/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-1284/trainer_state.json

@@ -0,0 +1,317 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1284,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6439054441452026,
+      "epoch": 0.11682242990654206,
+      "grad_norm": 0.49546942114830017,
+      "learning_rate": 1.7676515353317202e-05,
+      "loss": 1.6080712890625,
+      "mean_token_accuracy": 0.6552277088165284,
+      "num_tokens": 162248.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8895833045244217,
+      "epoch": 0.2336448598130841,
+      "grad_norm": 0.6087712645530701,
+      "learning_rate": 3.571377591792659e-05,
+      "loss": 0.8471942138671875,
+      "mean_token_accuracy": 0.7710993754863739,
+      "num_tokens": 327614.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7270394039154052,
+      "epoch": 0.35046728971962615,
+      "grad_norm": 0.4936729371547699,
+      "learning_rate": 5.375103648253598e-05,
+      "loss": 0.6940426635742187,
+      "mean_token_accuracy": 0.7985459506511688,
+      "num_tokens": 494582.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6873268783092499,
+      "epoch": 0.4672897196261682,
+      "grad_norm": 0.5290274620056152,
+      "learning_rate": 7.178829704714537e-05,
+      "loss": 0.6487248229980469,
+      "mean_token_accuracy": 0.8118354797363281,
+      "num_tokens": 653981.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6600921255350113,
+      "epoch": 0.5841121495327103,
+      "grad_norm": 0.3852632939815521,
+      "learning_rate": 8.982555761175476e-05,
+      "loss": 0.6241029357910156,
+      "mean_token_accuracy": 0.8171858608722686,
+      "num_tokens": 814840.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.6286565268039703,
+      "epoch": 0.7009345794392523,
+      "grad_norm": 0.44116389751434326,
+      "learning_rate": 0.00010786281817636416,
+      "loss": 0.5951404190063476,
+      "mean_token_accuracy": 0.8241004174947739,
+      "num_tokens": 979542.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6199766182899475,
+      "epoch": 0.8177570093457944,
+      "grad_norm": 0.38574621081352234,
+      "learning_rate": 0.00012590007874097354,
+      "loss": 0.5904315948486328,
+      "mean_token_accuracy": 0.8250177747011185,
+      "num_tokens": 1147400.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.5950348073244095,
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.41016682982444763,
+      "learning_rate": 0.0001439373393055829,
+      "loss": 0.5652639389038085,
+      "mean_token_accuracy": 0.83076107442379,
+      "num_tokens": 1310490.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.7618740917026222,
+      "eval_loss": 0.6691045761108398,
+      "eval_mean_token_accuracy": 0.8110752314716191,
+      "eval_num_tokens": 1399670.0,
+      "eval_runtime": 45.674,
+      "eval_samples_per_second": 26.952,
+      "eval_steps_per_second": 3.372,
+      "step": 428
+    },
+    {
+      "entropy": 0.5888169056177139,
+      "epoch": 1.0514018691588785,
+      "grad_norm": 0.339750200510025,
+      "learning_rate": 0.00015438762800645052,
+      "loss": 0.5587311935424805,
+      "mean_token_accuracy": 0.832102472782135,
+      "num_tokens": 1471726.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.5644756412506103,
+      "epoch": 1.1682242990654206,
+      "grad_norm": 0.32897934317588806,
+      "learning_rate": 0.00015426955859477223,
+      "loss": 0.5355723571777343,
+      "mean_token_accuracy": 0.8378035259246827,
+      "num_tokens": 1638060.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.5603723293542862,
+      "epoch": 1.2850467289719627,
+      "grad_norm": 0.3474414646625519,
+      "learning_rate": 0.00015402334678635756,
+      "loss": 0.5328482437133789,
+      "mean_token_accuracy": 0.8384119784832,
+      "num_tokens": 1802005.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.551156692802906,
+      "epoch": 1.4018691588785046,
+      "grad_norm": 0.21533823013305664,
+      "learning_rate": 0.00015364940195109232,
+      "loss": 0.5259516525268555,
+      "mean_token_accuracy": 0.8401002615690232,
+      "num_tokens": 1969267.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.5456148293614388,
+      "epoch": 1.5186915887850467,
+      "grad_norm": 0.3005809485912323,
+      "learning_rate": 0.0001531483458372002,
+      "loss": 0.5163665008544922,
+      "mean_token_accuracy": 0.8423654067516327,
+      "num_tokens": 2134793.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.540266016125679,
+      "epoch": 1.6355140186915889,
+      "grad_norm": 0.2895597815513611,
+      "learning_rate": 0.00015252101153747827,
+      "loss": 0.5159417343139648,
+      "mean_token_accuracy": 0.8422912752628327,
+      "num_tokens": 2300672.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5450576081871986,
+      "epoch": 1.7523364485981308,
+      "grad_norm": 0.26751118898391724,
+      "learning_rate": 0.00015176844210413562,
+      "loss": 0.5150370788574219,
+      "mean_token_accuracy": 0.8433581227064133,
+      "num_tokens": 2459315.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.540363709628582,
+      "epoch": 1.8691588785046729,
+      "grad_norm": 0.25945547223091125,
+      "learning_rate": 0.0001508918888145379,
+      "loss": 0.5133833312988281,
+      "mean_token_accuracy": 0.8442667639255523,
+      "num_tokens": 2616878.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5406239181756973,
+      "epoch": 1.985981308411215,
+      "grad_norm": 0.2768362760543823,
+      "learning_rate": 0.0001498928090907414,
+      "loss": 0.5116788864135742,
+      "mean_token_accuracy": 0.8440770989656449,
+      "num_tokens": 2778909.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.6602114913138476,
+      "eval_loss": 0.6344706416130066,
+      "eval_mean_token_accuracy": 0.8167721358212557,
+      "eval_num_tokens": 2799340.0,
+      "eval_runtime": 45.6608,
+      "eval_samples_per_second": 26.96,
+      "eval_steps_per_second": 3.373,
+      "step": 856
+    },
+    {
+      "entropy": 0.47262389928102494,
+      "epoch": 2.102803738317757,
+      "grad_norm": 0.2535194158554077,
+      "learning_rate": 0.00014877286407627584,
+      "loss": 0.4428855514526367,
+      "mean_token_accuracy": 0.8600562286376953,
+      "num_tokens": 2951115.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.47976606965065005,
+      "epoch": 2.2196261682242993,
+      "grad_norm": 0.30369797348976135,
+      "learning_rate": 0.00014753391587420475,
+      "loss": 0.44907299041748044,
+      "mean_token_accuracy": 0.8582676541805268,
+      "num_tokens": 3115016.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.47275764375925067,
+      "epoch": 2.336448598130841,
+      "grad_norm": 0.3171652853488922,
+      "learning_rate": 0.0001461780244510558,
+      "loss": 0.44435993194580076,
+      "mean_token_accuracy": 0.8601345640420913,
+      "num_tokens": 3274313.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.4735608258843422,
+      "epoch": 2.453271028037383,
+      "grad_norm": 0.29764947295188904,
+      "learning_rate": 0.00014470744421176885,
+      "loss": 0.44539962768554686,
+      "mean_token_accuracy": 0.8607082539796829,
+      "num_tokens": 3440379.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.4744651636481285,
+      "epoch": 2.5700934579439254,
+      "grad_norm": 0.23777751624584198,
+      "learning_rate": 0.00014312462025135595,
+      "loss": 0.44422054290771484,
+      "mean_token_accuracy": 0.859566843509674,
+      "num_tokens": 3606755.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.47177853137254716,
+      "epoch": 2.6869158878504673,
+      "grad_norm": 0.28442806005477905,
+      "learning_rate": 0.00014143218428950668,
+      "loss": 0.4431512069702148,
+      "mean_token_accuracy": 0.8603039968013764,
+      "num_tokens": 3766555.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.4803256571292877,
+      "epoch": 2.803738317757009,
+      "grad_norm": 0.2728305757045746,
+      "learning_rate": 0.00013963295029489697,
+      "loss": 0.44966583251953124,
+      "mean_token_accuracy": 0.8587929052114487,
+      "num_tokens": 3927164.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.4743427449464798,
+      "epoch": 2.9205607476635516,
+      "grad_norm": 0.29242947697639465,
+      "learning_rate": 0.0001377299098064774,
+      "loss": 0.4463462829589844,
+      "mean_token_accuracy": 0.8596956437826156,
+      "num_tokens": 4090727.0,
+      "step": 1250
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.611924365356371,
+      "eval_loss": 0.6364901661872864,
+      "eval_mean_token_accuracy": 0.8110434765165503,
+      "eval_num_tokens": 4199010.0,
+      "eval_runtime": 45.6331,
+      "eval_samples_per_second": 26.976,
+      "eval_steps_per_second": 3.375,
+      "step": 1284
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.7771258761728e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-1712/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.19.1

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-1712/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-Base",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.030195310029781444,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-1712/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-1712/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-1712/trainer_state.json

@@ -0,0 +1,418 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1712,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6439054441452026,
+      "epoch": 0.11682242990654206,
+      "grad_norm": 0.49546942114830017,
+      "learning_rate": 1.7676515353317202e-05,
+      "loss": 1.6080712890625,
+      "mean_token_accuracy": 0.6552277088165284,
+      "num_tokens": 162248.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8895833045244217,
+      "epoch": 0.2336448598130841,
+      "grad_norm": 0.6087712645530701,
+      "learning_rate": 3.571377591792659e-05,
+      "loss": 0.8471942138671875,
+      "mean_token_accuracy": 0.7710993754863739,
+      "num_tokens": 327614.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7270394039154052,
+      "epoch": 0.35046728971962615,
+      "grad_norm": 0.4936729371547699,
+      "learning_rate": 5.375103648253598e-05,
+      "loss": 0.6940426635742187,
+      "mean_token_accuracy": 0.7985459506511688,
+      "num_tokens": 494582.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6873268783092499,
+      "epoch": 0.4672897196261682,
+      "grad_norm": 0.5290274620056152,
+      "learning_rate": 7.178829704714537e-05,
+      "loss": 0.6487248229980469,
+      "mean_token_accuracy": 0.8118354797363281,
+      "num_tokens": 653981.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6600921255350113,
+      "epoch": 0.5841121495327103,
+      "grad_norm": 0.3852632939815521,
+      "learning_rate": 8.982555761175476e-05,
+      "loss": 0.6241029357910156,
+      "mean_token_accuracy": 0.8171858608722686,
+      "num_tokens": 814840.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.6286565268039703,
+      "epoch": 0.7009345794392523,
+      "grad_norm": 0.44116389751434326,
+      "learning_rate": 0.00010786281817636416,
+      "loss": 0.5951404190063476,
+      "mean_token_accuracy": 0.8241004174947739,
+      "num_tokens": 979542.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6199766182899475,
+      "epoch": 0.8177570093457944,
+      "grad_norm": 0.38574621081352234,
+      "learning_rate": 0.00012590007874097354,
+      "loss": 0.5904315948486328,
+      "mean_token_accuracy": 0.8250177747011185,
+      "num_tokens": 1147400.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.5950348073244095,
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.41016682982444763,
+      "learning_rate": 0.0001439373393055829,
+      "loss": 0.5652639389038085,
+      "mean_token_accuracy": 0.83076107442379,
+      "num_tokens": 1310490.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.7618740917026222,
+      "eval_loss": 0.6691045761108398,
+      "eval_mean_token_accuracy": 0.8110752314716191,
+      "eval_num_tokens": 1399670.0,
+      "eval_runtime": 45.674,
+      "eval_samples_per_second": 26.952,
+      "eval_steps_per_second": 3.372,
+      "step": 428
+    },
+    {
+      "entropy": 0.5888169056177139,
+      "epoch": 1.0514018691588785,
+      "grad_norm": 0.339750200510025,
+      "learning_rate": 0.00015438762800645052,
+      "loss": 0.5587311935424805,
+      "mean_token_accuracy": 0.832102472782135,
+      "num_tokens": 1471726.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.5644756412506103,
+      "epoch": 1.1682242990654206,
+      "grad_norm": 0.32897934317588806,
+      "learning_rate": 0.00015426955859477223,
+      "loss": 0.5355723571777343,
+      "mean_token_accuracy": 0.8378035259246827,
+      "num_tokens": 1638060.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.5603723293542862,
+      "epoch": 1.2850467289719627,
+      "grad_norm": 0.3474414646625519,
+      "learning_rate": 0.00015402334678635756,
+      "loss": 0.5328482437133789,
+      "mean_token_accuracy": 0.8384119784832,
+      "num_tokens": 1802005.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.551156692802906,
+      "epoch": 1.4018691588785046,
+      "grad_norm": 0.21533823013305664,
+      "learning_rate": 0.00015364940195109232,
+      "loss": 0.5259516525268555,
+      "mean_token_accuracy": 0.8401002615690232,
+      "num_tokens": 1969267.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.5456148293614388,
+      "epoch": 1.5186915887850467,
+      "grad_norm": 0.3005809485912323,
+      "learning_rate": 0.0001531483458372002,
+      "loss": 0.5163665008544922,
+      "mean_token_accuracy": 0.8423654067516327,
+      "num_tokens": 2134793.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.540266016125679,
+      "epoch": 1.6355140186915889,
+      "grad_norm": 0.2895597815513611,
+      "learning_rate": 0.00015252101153747827,
+      "loss": 0.5159417343139648,
+      "mean_token_accuracy": 0.8422912752628327,
+      "num_tokens": 2300672.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5450576081871986,
+      "epoch": 1.7523364485981308,
+      "grad_norm": 0.26751118898391724,
+      "learning_rate": 0.00015176844210413562,
+      "loss": 0.5150370788574219,
+      "mean_token_accuracy": 0.8433581227064133,
+      "num_tokens": 2459315.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.540363709628582,
+      "epoch": 1.8691588785046729,
+      "grad_norm": 0.25945547223091125,
+      "learning_rate": 0.0001508918888145379,
+      "loss": 0.5133833312988281,
+      "mean_token_accuracy": 0.8442667639255523,
+      "num_tokens": 2616878.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5406239181756973,
+      "epoch": 1.985981308411215,
+      "grad_norm": 0.2768362760543823,
+      "learning_rate": 0.0001498928090907414,
+      "loss": 0.5116788864135742,
+      "mean_token_accuracy": 0.8440770989656449,
+      "num_tokens": 2778909.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.6602114913138476,
+      "eval_loss": 0.6344706416130066,
+      "eval_mean_token_accuracy": 0.8167721358212557,
+      "eval_num_tokens": 2799340.0,
+      "eval_runtime": 45.6608,
+      "eval_samples_per_second": 26.96,
+      "eval_steps_per_second": 3.373,
+      "step": 856
+    },
+    {
+      "entropy": 0.47262389928102494,
+      "epoch": 2.102803738317757,
+      "grad_norm": 0.2535194158554077,
+      "learning_rate": 0.00014877286407627584,
+      "loss": 0.4428855514526367,
+      "mean_token_accuracy": 0.8600562286376953,
+      "num_tokens": 2951115.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.47976606965065005,
+      "epoch": 2.2196261682242993,
+      "grad_norm": 0.30369797348976135,
+      "learning_rate": 0.00014753391587420475,
+      "loss": 0.44907299041748044,
+      "mean_token_accuracy": 0.8582676541805268,
+      "num_tokens": 3115016.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.47275764375925067,
+      "epoch": 2.336448598130841,
+      "grad_norm": 0.3171652853488922,
+      "learning_rate": 0.0001461780244510558,
+      "loss": 0.44435993194580076,
+      "mean_token_accuracy": 0.8601345640420913,
+      "num_tokens": 3274313.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.4735608258843422,
+      "epoch": 2.453271028037383,
+      "grad_norm": 0.29764947295188904,
+      "learning_rate": 0.00014470744421176885,
+      "loss": 0.44539962768554686,
+      "mean_token_accuracy": 0.8607082539796829,
+      "num_tokens": 3440379.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.4744651636481285,
+      "epoch": 2.5700934579439254,
+      "grad_norm": 0.23777751624584198,
+      "learning_rate": 0.00014312462025135595,
+      "loss": 0.44422054290771484,
+      "mean_token_accuracy": 0.859566843509674,
+      "num_tokens": 3606755.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.47177853137254716,
+      "epoch": 2.6869158878504673,
+      "grad_norm": 0.28442806005477905,
+      "learning_rate": 0.00014143218428950668,
+      "loss": 0.4431512069702148,
+      "mean_token_accuracy": 0.8603039968013764,
+      "num_tokens": 3766555.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.4803256571292877,
+      "epoch": 2.803738317757009,
+      "grad_norm": 0.2728305757045746,
+      "learning_rate": 0.00013963295029489697,
+      "loss": 0.44966583251953124,
+      "mean_token_accuracy": 0.8587929052114487,
+      "num_tokens": 3927164.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.4743427449464798,
+      "epoch": 2.9205607476635516,
+      "grad_norm": 0.29242947697639465,
+      "learning_rate": 0.0001377299098064774,
+      "loss": 0.4463462829589844,
+      "mean_token_accuracy": 0.8596956437826156,
+      "num_tokens": 4090727.0,
+      "step": 1250
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.611924365356371,
+      "eval_loss": 0.6364901661872864,
+      "eval_mean_token_accuracy": 0.8110434765165503,
+      "eval_num_tokens": 4199010.0,
+      "eval_runtime": 45.6331,
+      "eval_samples_per_second": 26.976,
+      "eval_steps_per_second": 3.375,
+      "step": 1284
+    },
+    {
+      "entropy": 0.4497017902135849,
+      "epoch": 3.0373831775700935,
+      "grad_norm": 0.36632540822029114,
+      "learning_rate": 0.0001357262269595206,
+      "loss": 0.41871109008789065,
+      "mean_token_accuracy": 0.8677674496173858,
+      "num_tokens": 4252535.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.39628969103097916,
+      "epoch": 3.1542056074766354,
+      "grad_norm": 0.3463972210884094,
+      "learning_rate": 0.00013362523322469648,
+      "loss": 0.3633641815185547,
+      "mean_token_accuracy": 0.8810112345218658,
+      "num_tokens": 4414122.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.405142662525177,
+      "epoch": 3.2710280373831777,
+      "grad_norm": 0.3261754512786865,
+      "learning_rate": 0.00013143042186892402,
+      "loss": 0.37408100128173827,
+      "mean_token_accuracy": 0.8773768872022629,
+      "num_tokens": 4571859.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.3960475382208824,
+      "epoch": 3.3878504672897196,
+      "grad_norm": 0.32290324568748474,
+      "learning_rate": 0.00012914544214720838,
+      "loss": 0.3667728424072266,
+      "mean_token_accuracy": 0.8809277415275574,
+      "num_tokens": 4735006.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.39949932754039763,
+      "epoch": 3.5046728971962615,
+      "grad_norm": 0.3406212627887726,
+      "learning_rate": 0.0001267740932351207,
+      "loss": 0.37073043823242186,
+      "mean_token_accuracy": 0.879340250492096,
+      "num_tokens": 4898228.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.4047835928201675,
+      "epoch": 3.621495327102804,
+      "grad_norm": 0.30698826909065247,
+      "learning_rate": 0.00012432031791200892,
+      "loss": 0.3761457824707031,
+      "mean_token_accuracy": 0.8780743163824082,
+      "num_tokens": 5063413.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.4085030257701874,
+      "epoch": 3.7383177570093458,
+      "grad_norm": 0.30055665969848633,
+      "learning_rate": 0.00012178819600544269,
+      "loss": 0.379119873046875,
+      "mean_token_accuracy": 0.8756581097841263,
+      "num_tokens": 5227672.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.4101005423069,
+      "epoch": 3.8551401869158877,
+      "grad_norm": 0.32962530851364136,
+      "learning_rate": 0.00011918193760779132,
+      "loss": 0.3822117614746094,
+      "mean_token_accuracy": 0.8762752747535706,
+      "num_tokens": 5389834.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.40136953949928283,
+      "epoch": 3.97196261682243,
+      "grad_norm": 0.2512304186820984,
+      "learning_rate": 0.00011650587607621428,
+      "loss": 0.3733771514892578,
+      "mean_token_accuracy": 0.8783003056049347,
+      "num_tokens": 5559167.0,
+      "step": 1700
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.5574058420085287,
+      "eval_loss": 0.6562352180480957,
+      "eval_mean_token_accuracy": 0.8172229067845778,
+      "eval_num_tokens": 5598680.0,
+      "eval_runtime": 45.6372,
+      "eval_samples_per_second": 26.974,
+      "eval_steps_per_second": 3.374,
+      "step": 1712
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.036135513426944e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-2140/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.19.1

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-2140/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-Base",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.030195310029781444,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-2140/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-2140/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-2140/trainer_state.json

@@ -0,0 +1,509 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6439054441452026,
+      "epoch": 0.11682242990654206,
+      "grad_norm": 0.49546942114830017,
+      "learning_rate": 1.7676515353317202e-05,
+      "loss": 1.6080712890625,
+      "mean_token_accuracy": 0.6552277088165284,
+      "num_tokens": 162248.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8895833045244217,
+      "epoch": 0.2336448598130841,
+      "grad_norm": 0.6087712645530701,
+      "learning_rate": 3.571377591792659e-05,
+      "loss": 0.8471942138671875,
+      "mean_token_accuracy": 0.7710993754863739,
+      "num_tokens": 327614.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7270394039154052,
+      "epoch": 0.35046728971962615,
+      "grad_norm": 0.4936729371547699,
+      "learning_rate": 5.375103648253598e-05,
+      "loss": 0.6940426635742187,
+      "mean_token_accuracy": 0.7985459506511688,
+      "num_tokens": 494582.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6873268783092499,
+      "epoch": 0.4672897196261682,
+      "grad_norm": 0.5290274620056152,
+      "learning_rate": 7.178829704714537e-05,
+      "loss": 0.6487248229980469,
+      "mean_token_accuracy": 0.8118354797363281,
+      "num_tokens": 653981.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6600921255350113,
+      "epoch": 0.5841121495327103,
+      "grad_norm": 0.3852632939815521,
+      "learning_rate": 8.982555761175476e-05,
+      "loss": 0.6241029357910156,
+      "mean_token_accuracy": 0.8171858608722686,
+      "num_tokens": 814840.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.6286565268039703,
+      "epoch": 0.7009345794392523,
+      "grad_norm": 0.44116389751434326,
+      "learning_rate": 0.00010786281817636416,
+      "loss": 0.5951404190063476,
+      "mean_token_accuracy": 0.8241004174947739,
+      "num_tokens": 979542.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6199766182899475,
+      "epoch": 0.8177570093457944,
+      "grad_norm": 0.38574621081352234,
+      "learning_rate": 0.00012590007874097354,
+      "loss": 0.5904315948486328,
+      "mean_token_accuracy": 0.8250177747011185,
+      "num_tokens": 1147400.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.5950348073244095,
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.41016682982444763,
+      "learning_rate": 0.0001439373393055829,
+      "loss": 0.5652639389038085,
+      "mean_token_accuracy": 0.83076107442379,
+      "num_tokens": 1310490.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.7618740917026222,
+      "eval_loss": 0.6691045761108398,
+      "eval_mean_token_accuracy": 0.8110752314716191,
+      "eval_num_tokens": 1399670.0,
+      "eval_runtime": 45.674,
+      "eval_samples_per_second": 26.952,
+      "eval_steps_per_second": 3.372,
+      "step": 428
+    },
+    {
+      "entropy": 0.5888169056177139,
+      "epoch": 1.0514018691588785,
+      "grad_norm": 0.339750200510025,
+      "learning_rate": 0.00015438762800645052,
+      "loss": 0.5587311935424805,
+      "mean_token_accuracy": 0.832102472782135,
+      "num_tokens": 1471726.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.5644756412506103,
+      "epoch": 1.1682242990654206,
+      "grad_norm": 0.32897934317588806,
+      "learning_rate": 0.00015426955859477223,
+      "loss": 0.5355723571777343,
+      "mean_token_accuracy": 0.8378035259246827,
+      "num_tokens": 1638060.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.5603723293542862,
+      "epoch": 1.2850467289719627,
+      "grad_norm": 0.3474414646625519,
+      "learning_rate": 0.00015402334678635756,
+      "loss": 0.5328482437133789,
+      "mean_token_accuracy": 0.8384119784832,
+      "num_tokens": 1802005.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.551156692802906,
+      "epoch": 1.4018691588785046,
+      "grad_norm": 0.21533823013305664,
+      "learning_rate": 0.00015364940195109232,
+      "loss": 0.5259516525268555,
+      "mean_token_accuracy": 0.8401002615690232,
+      "num_tokens": 1969267.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.5456148293614388,
+      "epoch": 1.5186915887850467,
+      "grad_norm": 0.3005809485912323,
+      "learning_rate": 0.0001531483458372002,
+      "loss": 0.5163665008544922,
+      "mean_token_accuracy": 0.8423654067516327,
+      "num_tokens": 2134793.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.540266016125679,
+      "epoch": 1.6355140186915889,
+      "grad_norm": 0.2895597815513611,
+      "learning_rate": 0.00015252101153747827,
+      "loss": 0.5159417343139648,
+      "mean_token_accuracy": 0.8422912752628327,
+      "num_tokens": 2300672.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5450576081871986,
+      "epoch": 1.7523364485981308,
+      "grad_norm": 0.26751118898391724,
+      "learning_rate": 0.00015176844210413562,
+      "loss": 0.5150370788574219,
+      "mean_token_accuracy": 0.8433581227064133,
+      "num_tokens": 2459315.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.540363709628582,
+      "epoch": 1.8691588785046729,
+      "grad_norm": 0.25945547223091125,
+      "learning_rate": 0.0001508918888145379,
+      "loss": 0.5133833312988281,
+      "mean_token_accuracy": 0.8442667639255523,
+      "num_tokens": 2616878.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5406239181756973,
+      "epoch": 1.985981308411215,
+      "grad_norm": 0.2768362760543823,
+      "learning_rate": 0.0001498928090907414,
+      "loss": 0.5116788864135742,
+      "mean_token_accuracy": 0.8440770989656449,
+      "num_tokens": 2778909.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.6602114913138476,
+      "eval_loss": 0.6344706416130066,
+      "eval_mean_token_accuracy": 0.8167721358212557,
+      "eval_num_tokens": 2799340.0,
+      "eval_runtime": 45.6608,
+      "eval_samples_per_second": 26.96,
+      "eval_steps_per_second": 3.373,
+      "step": 856
+    },
+    {
+      "entropy": 0.47262389928102494,
+      "epoch": 2.102803738317757,
+      "grad_norm": 0.2535194158554077,
+      "learning_rate": 0.00014877286407627584,
+      "loss": 0.4428855514526367,
+      "mean_token_accuracy": 0.8600562286376953,
+      "num_tokens": 2951115.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.47976606965065005,
+      "epoch": 2.2196261682242993,
+      "grad_norm": 0.30369797348976135,
+      "learning_rate": 0.00014753391587420475,
+      "loss": 0.44907299041748044,
+      "mean_token_accuracy": 0.8582676541805268,
+      "num_tokens": 3115016.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.47275764375925067,
+      "epoch": 2.336448598130841,
+      "grad_norm": 0.3171652853488922,
+      "learning_rate": 0.0001461780244510558,
+      "loss": 0.44435993194580076,
+      "mean_token_accuracy": 0.8601345640420913,
+      "num_tokens": 3274313.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.4735608258843422,
+      "epoch": 2.453271028037383,
+      "grad_norm": 0.29764947295188904,
+      "learning_rate": 0.00014470744421176885,
+      "loss": 0.44539962768554686,
+      "mean_token_accuracy": 0.8607082539796829,
+      "num_tokens": 3440379.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.4744651636481285,
+      "epoch": 2.5700934579439254,
+      "grad_norm": 0.23777751624584198,
+      "learning_rate": 0.00014312462025135595,
+      "loss": 0.44422054290771484,
+      "mean_token_accuracy": 0.859566843509674,
+      "num_tokens": 3606755.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.47177853137254716,
+      "epoch": 2.6869158878504673,
+      "grad_norm": 0.28442806005477905,
+      "learning_rate": 0.00014143218428950668,
+      "loss": 0.4431512069702148,
+      "mean_token_accuracy": 0.8603039968013764,
+      "num_tokens": 3766555.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.4803256571292877,
+      "epoch": 2.803738317757009,
+      "grad_norm": 0.2728305757045746,
+      "learning_rate": 0.00013963295029489697,
+      "loss": 0.44966583251953124,
+      "mean_token_accuracy": 0.8587929052114487,
+      "num_tokens": 3927164.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.4743427449464798,
+      "epoch": 2.9205607476635516,
+      "grad_norm": 0.29242947697639465,
+      "learning_rate": 0.0001377299098064774,
+      "loss": 0.4463462829589844,
+      "mean_token_accuracy": 0.8596956437826156,
+      "num_tokens": 4090727.0,
+      "step": 1250
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.611924365356371,
+      "eval_loss": 0.6364901661872864,
+      "eval_mean_token_accuracy": 0.8110434765165503,
+      "eval_num_tokens": 4199010.0,
+      "eval_runtime": 45.6331,
+      "eval_samples_per_second": 26.976,
+      "eval_steps_per_second": 3.375,
+      "step": 1284
+    },
+    {
+      "entropy": 0.4497017902135849,
+      "epoch": 3.0373831775700935,
+      "grad_norm": 0.36632540822029114,
+      "learning_rate": 0.0001357262269595206,
+      "loss": 0.41871109008789065,
+      "mean_token_accuracy": 0.8677674496173858,
+      "num_tokens": 4252535.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.39628969103097916,
+      "epoch": 3.1542056074766354,
+      "grad_norm": 0.3463972210884094,
+      "learning_rate": 0.00013362523322469648,
+      "loss": 0.3633641815185547,
+      "mean_token_accuracy": 0.8810112345218658,
+      "num_tokens": 4414122.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.405142662525177,
+      "epoch": 3.2710280373831777,
+      "grad_norm": 0.3261754512786865,
+      "learning_rate": 0.00013143042186892402,
+      "loss": 0.37408100128173827,
+      "mean_token_accuracy": 0.8773768872022629,
+      "num_tokens": 4571859.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.3960475382208824,
+      "epoch": 3.3878504672897196,
+      "grad_norm": 0.32290324568748474,
+      "learning_rate": 0.00012914544214720838,
+      "loss": 0.3667728424072266,
+      "mean_token_accuracy": 0.8809277415275574,
+      "num_tokens": 4735006.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.39949932754039763,
+      "epoch": 3.5046728971962615,
+      "grad_norm": 0.3406212627887726,
+      "learning_rate": 0.0001267740932351207,
+      "loss": 0.37073043823242186,
+      "mean_token_accuracy": 0.879340250492096,
+      "num_tokens": 4898228.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.4047835928201675,
+      "epoch": 3.621495327102804,
+      "grad_norm": 0.30698826909065247,
+      "learning_rate": 0.00012432031791200892,
+      "loss": 0.3761457824707031,
+      "mean_token_accuracy": 0.8780743163824082,
+      "num_tokens": 5063413.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.4085030257701874,
+      "epoch": 3.7383177570093458,
+      "grad_norm": 0.30055665969848633,
+      "learning_rate": 0.00012178819600544269,
+      "loss": 0.379119873046875,
+      "mean_token_accuracy": 0.8756581097841263,
+      "num_tokens": 5227672.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.4101005423069,
+      "epoch": 3.8551401869158877,
+      "grad_norm": 0.32962530851364136,
+      "learning_rate": 0.00011918193760779132,
+      "loss": 0.3822117614746094,
+      "mean_token_accuracy": 0.8762752747535706,
+      "num_tokens": 5389834.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.40136953949928283,
+      "epoch": 3.97196261682243,
+      "grad_norm": 0.2512304186820984,
+      "learning_rate": 0.00011650587607621428,
+      "loss": 0.3733771514892578,
+      "mean_token_accuracy": 0.8783003056049347,
+      "num_tokens": 5559167.0,
+      "step": 1700
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.5574058420085287,
+      "eval_loss": 0.6562352180480957,
+      "eval_mean_token_accuracy": 0.8172229067845778,
+      "eval_num_tokens": 5598680.0,
+      "eval_runtime": 45.6372,
+      "eval_samples_per_second": 26.974,
+      "eval_steps_per_second": 3.374,
+      "step": 1712
+    },
+    {
+      "entropy": 0.33769124254584315,
+      "epoch": 4.088785046728972,
+      "grad_norm": 0.35916072130203247,
+      "learning_rate": 0.00011376446082770247,
+      "loss": 0.3022454833984375,
+      "mean_token_accuracy": 0.898470618724823,
+      "num_tokens": 5721701.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.3153342293202877,
+      "epoch": 4.205607476635514,
+      "grad_norm": 0.4674874544143677,
+      "learning_rate": 0.00011096224994114971,
+      "loss": 0.28416419982910157,
+      "mean_token_accuracy": 0.9044169551134109,
+      "num_tokens": 5884163.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.32269440904259683,
+      "epoch": 4.322429906542056,
+      "grad_norm": 0.4200516641139984,
+      "learning_rate": 0.00010810390257875522,
+      "loss": 0.29085651397705076,
+      "mean_token_accuracy": 0.9013593572378159,
+      "num_tokens": 6053869.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.324297761619091,
+      "epoch": 4.4392523364485985,
+      "grad_norm": 0.35716596245765686,
+      "learning_rate": 0.0001051941712393573,
+      "loss": 0.2931093406677246,
+      "mean_token_accuracy": 0.9010413753986358,
+      "num_tokens": 6217351.0,
+      "step": 1900
+    },
+    {
+      "entropy": 0.3256940242648125,
+      "epoch": 4.55607476635514,
+      "grad_norm": 0.35059621930122375,
+      "learning_rate": 0.00010223789385657872,
+      "loss": 0.29291555404663083,
+      "mean_token_accuracy": 0.9013585340976715,
+      "num_tokens": 6379796.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.32556063055992124,
+      "epoch": 4.672897196261682,
+      "grad_norm": 0.31053468585014343,
+      "learning_rate": 9.923998575492214e-05,
+      "loss": 0.29418453216552737,
+      "mean_token_accuracy": 0.9006082111597061,
+      "num_tokens": 6550276.0,
+      "step": 2000
+    },
+    {
+      "entropy": 0.3271982085704803,
+      "epoch": 4.789719626168225,
+      "grad_norm": 0.3549234867095947,
+      "learning_rate": 9.62054314771894e-05,
+      "loss": 0.293514575958252,
+      "mean_token_accuracy": 0.9009167104959488,
+      "num_tokens": 6709429.0,
+      "step": 2050
+    },
+    {
+      "entropy": 0.32230626583099364,
+      "epoch": 4.906542056074766,
+      "grad_norm": 0.36930036544799805,
+      "learning_rate": 9.313927649681362e-05,
+      "loss": 0.29048364639282226,
+      "mean_token_accuracy": 0.9017211717367172,
+      "num_tokens": 6870956.0,
+      "step": 2100
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.5097629334051887,
+      "eval_loss": 0.7178825736045837,
+      "eval_mean_token_accuracy": 0.8133898025209253,
+      "eval_num_tokens": 6998350.0,
+      "eval_runtime": 45.6467,
+      "eval_samples_per_second": 26.968,
+      "eval_steps_per_second": 3.374,
+      "step": 2140
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.296106037517312e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-2568/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.19.1

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-2568/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-Base",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.030195310029781444,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-2568/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-2568/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-2568/trainer_state.json

@@ -0,0 +1,610 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 2568,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6439054441452026,
+      "epoch": 0.11682242990654206,
+      "grad_norm": 0.49546942114830017,
+      "learning_rate": 1.7676515353317202e-05,
+      "loss": 1.6080712890625,
+      "mean_token_accuracy": 0.6552277088165284,
+      "num_tokens": 162248.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8895833045244217,
+      "epoch": 0.2336448598130841,
+      "grad_norm": 0.6087712645530701,
+      "learning_rate": 3.571377591792659e-05,
+      "loss": 0.8471942138671875,
+      "mean_token_accuracy": 0.7710993754863739,
+      "num_tokens": 327614.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7270394039154052,
+      "epoch": 0.35046728971962615,
+      "grad_norm": 0.4936729371547699,
+      "learning_rate": 5.375103648253598e-05,
+      "loss": 0.6940426635742187,
+      "mean_token_accuracy": 0.7985459506511688,
+      "num_tokens": 494582.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6873268783092499,
+      "epoch": 0.4672897196261682,
+      "grad_norm": 0.5290274620056152,
+      "learning_rate": 7.178829704714537e-05,
+      "loss": 0.6487248229980469,
+      "mean_token_accuracy": 0.8118354797363281,
+      "num_tokens": 653981.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6600921255350113,
+      "epoch": 0.5841121495327103,
+      "grad_norm": 0.3852632939815521,
+      "learning_rate": 8.982555761175476e-05,
+      "loss": 0.6241029357910156,
+      "mean_token_accuracy": 0.8171858608722686,
+      "num_tokens": 814840.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.6286565268039703,
+      "epoch": 0.7009345794392523,
+      "grad_norm": 0.44116389751434326,
+      "learning_rate": 0.00010786281817636416,
+      "loss": 0.5951404190063476,
+      "mean_token_accuracy": 0.8241004174947739,
+      "num_tokens": 979542.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6199766182899475,
+      "epoch": 0.8177570093457944,
+      "grad_norm": 0.38574621081352234,
+      "learning_rate": 0.00012590007874097354,
+      "loss": 0.5904315948486328,
+      "mean_token_accuracy": 0.8250177747011185,
+      "num_tokens": 1147400.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.5950348073244095,
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.41016682982444763,
+      "learning_rate": 0.0001439373393055829,
+      "loss": 0.5652639389038085,
+      "mean_token_accuracy": 0.83076107442379,
+      "num_tokens": 1310490.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.7618740917026222,
+      "eval_loss": 0.6691045761108398,
+      "eval_mean_token_accuracy": 0.8110752314716191,
+      "eval_num_tokens": 1399670.0,
+      "eval_runtime": 45.674,
+      "eval_samples_per_second": 26.952,
+      "eval_steps_per_second": 3.372,
+      "step": 428
+    },
+    {
+      "entropy": 0.5888169056177139,
+      "epoch": 1.0514018691588785,
+      "grad_norm": 0.339750200510025,
+      "learning_rate": 0.00015438762800645052,
+      "loss": 0.5587311935424805,
+      "mean_token_accuracy": 0.832102472782135,
+      "num_tokens": 1471726.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.5644756412506103,
+      "epoch": 1.1682242990654206,
+      "grad_norm": 0.32897934317588806,
+      "learning_rate": 0.00015426955859477223,
+      "loss": 0.5355723571777343,
+      "mean_token_accuracy": 0.8378035259246827,
+      "num_tokens": 1638060.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.5603723293542862,
+      "epoch": 1.2850467289719627,
+      "grad_norm": 0.3474414646625519,
+      "learning_rate": 0.00015402334678635756,
+      "loss": 0.5328482437133789,
+      "mean_token_accuracy": 0.8384119784832,
+      "num_tokens": 1802005.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.551156692802906,
+      "epoch": 1.4018691588785046,
+      "grad_norm": 0.21533823013305664,
+      "learning_rate": 0.00015364940195109232,
+      "loss": 0.5259516525268555,
+      "mean_token_accuracy": 0.8401002615690232,
+      "num_tokens": 1969267.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.5456148293614388,
+      "epoch": 1.5186915887850467,
+      "grad_norm": 0.3005809485912323,
+      "learning_rate": 0.0001531483458372002,
+      "loss": 0.5163665008544922,
+      "mean_token_accuracy": 0.8423654067516327,
+      "num_tokens": 2134793.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.540266016125679,
+      "epoch": 1.6355140186915889,
+      "grad_norm": 0.2895597815513611,
+      "learning_rate": 0.00015252101153747827,
+      "loss": 0.5159417343139648,
+      "mean_token_accuracy": 0.8422912752628327,
+      "num_tokens": 2300672.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5450576081871986,
+      "epoch": 1.7523364485981308,
+      "grad_norm": 0.26751118898391724,
+      "learning_rate": 0.00015176844210413562,
+      "loss": 0.5150370788574219,
+      "mean_token_accuracy": 0.8433581227064133,
+      "num_tokens": 2459315.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.540363709628582,
+      "epoch": 1.8691588785046729,
+      "grad_norm": 0.25945547223091125,
+      "learning_rate": 0.0001508918888145379,
+      "loss": 0.5133833312988281,
+      "mean_token_accuracy": 0.8442667639255523,
+      "num_tokens": 2616878.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5406239181756973,
+      "epoch": 1.985981308411215,
+      "grad_norm": 0.2768362760543823,
+      "learning_rate": 0.0001498928090907414,
+      "loss": 0.5116788864135742,
+      "mean_token_accuracy": 0.8440770989656449,
+      "num_tokens": 2778909.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.6602114913138476,
+      "eval_loss": 0.6344706416130066,
+      "eval_mean_token_accuracy": 0.8167721358212557,
+      "eval_num_tokens": 2799340.0,
+      "eval_runtime": 45.6608,
+      "eval_samples_per_second": 26.96,
+      "eval_steps_per_second": 3.373,
+      "step": 856
+    },
+    {
+      "entropy": 0.47262389928102494,
+      "epoch": 2.102803738317757,
+      "grad_norm": 0.2535194158554077,
+      "learning_rate": 0.00014877286407627584,
+      "loss": 0.4428855514526367,
+      "mean_token_accuracy": 0.8600562286376953,
+      "num_tokens": 2951115.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.47976606965065005,
+      "epoch": 2.2196261682242993,
+      "grad_norm": 0.30369797348976135,
+      "learning_rate": 0.00014753391587420475,
+      "loss": 0.44907299041748044,
+      "mean_token_accuracy": 0.8582676541805268,
+      "num_tokens": 3115016.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.47275764375925067,
+      "epoch": 2.336448598130841,
+      "grad_norm": 0.3171652853488922,
+      "learning_rate": 0.0001461780244510558,
+      "loss": 0.44435993194580076,
+      "mean_token_accuracy": 0.8601345640420913,
+      "num_tokens": 3274313.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.4735608258843422,
+      "epoch": 2.453271028037383,
+      "grad_norm": 0.29764947295188904,
+      "learning_rate": 0.00014470744421176885,
+      "loss": 0.44539962768554686,
+      "mean_token_accuracy": 0.8607082539796829,
+      "num_tokens": 3440379.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.4744651636481285,
+      "epoch": 2.5700934579439254,
+      "grad_norm": 0.23777751624584198,
+      "learning_rate": 0.00014312462025135595,
+      "loss": 0.44422054290771484,
+      "mean_token_accuracy": 0.859566843509674,
+      "num_tokens": 3606755.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.47177853137254716,
+      "epoch": 2.6869158878504673,
+      "grad_norm": 0.28442806005477905,
+      "learning_rate": 0.00014143218428950668,
+      "loss": 0.4431512069702148,
+      "mean_token_accuracy": 0.8603039968013764,
+      "num_tokens": 3766555.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.4803256571292877,
+      "epoch": 2.803738317757009,
+      "grad_norm": 0.2728305757045746,
+      "learning_rate": 0.00013963295029489697,
+      "loss": 0.44966583251953124,
+      "mean_token_accuracy": 0.8587929052114487,
+      "num_tokens": 3927164.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.4743427449464798,
+      "epoch": 2.9205607476635516,
+      "grad_norm": 0.29242947697639465,
+      "learning_rate": 0.0001377299098064774,
+      "loss": 0.4463462829589844,
+      "mean_token_accuracy": 0.8596956437826156,
+      "num_tokens": 4090727.0,
+      "step": 1250
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.611924365356371,
+      "eval_loss": 0.6364901661872864,
+      "eval_mean_token_accuracy": 0.8110434765165503,
+      "eval_num_tokens": 4199010.0,
+      "eval_runtime": 45.6331,
+      "eval_samples_per_second": 26.976,
+      "eval_steps_per_second": 3.375,
+      "step": 1284
+    },
+    {
+      "entropy": 0.4497017902135849,
+      "epoch": 3.0373831775700935,
+      "grad_norm": 0.36632540822029114,
+      "learning_rate": 0.0001357262269595206,
+      "loss": 0.41871109008789065,
+      "mean_token_accuracy": 0.8677674496173858,
+      "num_tokens": 4252535.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.39628969103097916,
+      "epoch": 3.1542056074766354,
+      "grad_norm": 0.3463972210884094,
+      "learning_rate": 0.00013362523322469648,
+      "loss": 0.3633641815185547,
+      "mean_token_accuracy": 0.8810112345218658,
+      "num_tokens": 4414122.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.405142662525177,
+      "epoch": 3.2710280373831777,
+      "grad_norm": 0.3261754512786865,
+      "learning_rate": 0.00013143042186892402,
+      "loss": 0.37408100128173827,
+      "mean_token_accuracy": 0.8773768872022629,
+      "num_tokens": 4571859.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.3960475382208824,
+      "epoch": 3.3878504672897196,
+      "grad_norm": 0.32290324568748474,
+      "learning_rate": 0.00012914544214720838,
+      "loss": 0.3667728424072266,
+      "mean_token_accuracy": 0.8809277415275574,
+      "num_tokens": 4735006.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.39949932754039763,
+      "epoch": 3.5046728971962615,
+      "grad_norm": 0.3406212627887726,
+      "learning_rate": 0.0001267740932351207,
+      "loss": 0.37073043823242186,
+      "mean_token_accuracy": 0.879340250492096,
+      "num_tokens": 4898228.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.4047835928201675,
+      "epoch": 3.621495327102804,
+      "grad_norm": 0.30698826909065247,
+      "learning_rate": 0.00012432031791200892,
+      "loss": 0.3761457824707031,
+      "mean_token_accuracy": 0.8780743163824082,
+      "num_tokens": 5063413.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.4085030257701874,
+      "epoch": 3.7383177570093458,
+      "grad_norm": 0.30055665969848633,
+      "learning_rate": 0.00012178819600544269,
+      "loss": 0.379119873046875,
+      "mean_token_accuracy": 0.8756581097841263,
+      "num_tokens": 5227672.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.4101005423069,
+      "epoch": 3.8551401869158877,
+      "grad_norm": 0.32962530851364136,
+      "learning_rate": 0.00011918193760779132,
+      "loss": 0.3822117614746094,
+      "mean_token_accuracy": 0.8762752747535706,
+      "num_tokens": 5389834.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.40136953949928283,
+      "epoch": 3.97196261682243,
+      "grad_norm": 0.2512304186820984,
+      "learning_rate": 0.00011650587607621428,
+      "loss": 0.3733771514892578,
+      "mean_token_accuracy": 0.8783003056049347,
+      "num_tokens": 5559167.0,
+      "step": 1700
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.5574058420085287,
+      "eval_loss": 0.6562352180480957,
+      "eval_mean_token_accuracy": 0.8172229067845778,
+      "eval_num_tokens": 5598680.0,
+      "eval_runtime": 45.6372,
+      "eval_samples_per_second": 26.974,
+      "eval_steps_per_second": 3.374,
+      "step": 1712
+    },
+    {
+      "entropy": 0.33769124254584315,
+      "epoch": 4.088785046728972,
+      "grad_norm": 0.35916072130203247,
+      "learning_rate": 0.00011376446082770247,
+      "loss": 0.3022454833984375,
+      "mean_token_accuracy": 0.898470618724823,
+      "num_tokens": 5721701.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.3153342293202877,
+      "epoch": 4.205607476635514,
+      "grad_norm": 0.4674874544143677,
+      "learning_rate": 0.00011096224994114971,
+      "loss": 0.28416419982910157,
+      "mean_token_accuracy": 0.9044169551134109,
+      "num_tokens": 5884163.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.32269440904259683,
+      "epoch": 4.322429906542056,
+      "grad_norm": 0.4200516641139984,
+      "learning_rate": 0.00010810390257875522,
+      "loss": 0.29085651397705076,
+      "mean_token_accuracy": 0.9013593572378159,
+      "num_tokens": 6053869.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.324297761619091,
+      "epoch": 4.4392523364485985,
+      "grad_norm": 0.35716596245765686,
+      "learning_rate": 0.0001051941712393573,
+      "loss": 0.2931093406677246,
+      "mean_token_accuracy": 0.9010413753986358,
+      "num_tokens": 6217351.0,
+      "step": 1900
+    },
+    {
+      "entropy": 0.3256940242648125,
+      "epoch": 4.55607476635514,
+      "grad_norm": 0.35059621930122375,
+      "learning_rate": 0.00010223789385657872,
+      "loss": 0.29291555404663083,
+      "mean_token_accuracy": 0.9013585340976715,
+      "num_tokens": 6379796.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.32556063055992124,
+      "epoch": 4.672897196261682,
+      "grad_norm": 0.31053468585014343,
+      "learning_rate": 9.923998575492214e-05,
+      "loss": 0.29418453216552737,
+      "mean_token_accuracy": 0.9006082111597061,
+      "num_tokens": 6550276.0,
+      "step": 2000
+    },
+    {
+      "entropy": 0.3271982085704803,
+      "epoch": 4.789719626168225,
+      "grad_norm": 0.3549234867095947,
+      "learning_rate": 9.62054314771894e-05,
+      "loss": 0.293514575958252,
+      "mean_token_accuracy": 0.9009167104959488,
+      "num_tokens": 6709429.0,
+      "step": 2050
+    },
+    {
+      "entropy": 0.32230626583099364,
+      "epoch": 4.906542056074766,
+      "grad_norm": 0.36930036544799805,
+      "learning_rate": 9.313927649681362e-05,
+      "loss": 0.29048364639282226,
+      "mean_token_accuracy": 0.9017211717367172,
+      "num_tokens": 6870956.0,
+      "step": 2100
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.5097629334051887,
+      "eval_loss": 0.7178825736045837,
+      "eval_mean_token_accuracy": 0.8133898025209253,
+      "eval_num_tokens": 6998350.0,
+      "eval_runtime": 45.6467,
+      "eval_samples_per_second": 26.968,
+      "eval_steps_per_second": 3.374,
+      "step": 2140
+    },
+    {
+      "entropy": 0.30689359933137894,
+      "epoch": 5.0233644859813085,
+      "grad_norm": 0.6219972372055054,
+      "learning_rate": 9.004661882888355e-05,
+      "loss": 0.27355791091918946,
+      "mean_token_accuracy": 0.9078934907913208,
+      "num_tokens": 7034085.0,
+      "step": 2150
+    },
+    {
+      "entropy": 0.23060906335711479,
+      "epoch": 5.140186915887851,
+      "grad_norm": 0.39721137285232544,
+      "learning_rate": 8.69326005538081e-05,
+      "loss": 0.19190786361694337,
+      "mean_token_accuracy": 0.9332777208089829,
+      "num_tokens": 7198745.0,
+      "step": 2200
+    },
+    {
+      "entropy": 0.23536642283201217,
+      "epoch": 5.257009345794392,
+      "grad_norm": 0.4206141233444214,
+      "learning_rate": 8.380239926771483e-05,
+      "loss": 0.19819820404052735,
+      "mean_token_accuracy": 0.9311726182699204,
+      "num_tokens": 7366588.0,
+      "step": 2250
+    },
+    {
+      "entropy": 0.2427162781357765,
+      "epoch": 5.373831775700935,
+      "grad_norm": 0.543883204460144,
+      "learning_rate": 8.066121947379727e-05,
+      "loss": 0.20555742263793944,
+      "mean_token_accuracy": 0.9283805179595948,
+      "num_tokens": 7531696.0,
+      "step": 2300
+    },
+    {
+      "entropy": 0.24081297397613524,
+      "epoch": 5.490654205607477,
+      "grad_norm": 0.4346058666706085,
+      "learning_rate": 7.751428392892456e-05,
+      "loss": 0.20357828140258788,
+      "mean_token_accuracy": 0.9291914713382721,
+      "num_tokens": 7688960.0,
+      "step": 2350
+    },
+    {
+      "entropy": 0.2414954523742199,
+      "epoch": 5.607476635514018,
+      "grad_norm": 0.48998570442199707,
+      "learning_rate": 7.43668249599014e-05,
+      "loss": 0.20533323287963867,
+      "mean_token_accuracy": 0.9290326738357544,
+      "num_tokens": 7851053.0,
+      "step": 2400
+    },
+    {
+      "entropy": 0.24239167034626008,
+      "epoch": 5.724299065420561,
+      "grad_norm": 0.5171953439712524,
+      "learning_rate": 7.122407576381592e-05,
+      "loss": 0.20603450775146484,
+      "mean_token_accuracy": 0.9289826327562332,
+      "num_tokens": 8001524.0,
+      "step": 2450
+    },
+    {
+      "entropy": 0.24068919852375983,
+      "epoch": 5.841121495327103,
+      "grad_norm": 0.5036585330963135,
+      "learning_rate": 6.809126170694096e-05,
+      "loss": 0.20551023483276368,
+      "mean_token_accuracy": 0.9283198803663254,
+      "num_tokens": 8166394.0,
+      "step": 2500
+    },
+    {
+      "entropy": 0.23394863292574883,
+      "epoch": 5.957943925233645,
+      "grad_norm": 0.4463285505771637,
+      "learning_rate": 6.497359163665513e-05,
+      "loss": 0.20060670852661133,
+      "mean_token_accuracy": 0.9296612071990967,
+      "num_tokens": 8339045.0,
+      "step": 2550
+    },
+    {
+      "epoch": 6.0,
+      "eval_entropy": 0.4407621825283224,
+      "eval_loss": 0.7988200187683105,
+      "eval_mean_token_accuracy": 0.810667238839261,
+      "eval_num_tokens": 8398020.0,
+      "eval_runtime": 45.6554,
+      "eval_samples_per_second": 26.963,
+      "eval_steps_per_second": 3.373,
+      "step": 2568
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.55513965942272e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-2996/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.19.1

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-2996/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-Base",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.030195310029781444,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-2996/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-100/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.19.1

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-100/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-Base",
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.08754516765392441,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-100/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-100/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-100/trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.24539877300613497,
+  "eval_steps": 20,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.8042113453149795,
+      "epoch": 0.049079754601226995,
+      "grad_norm": 0.8720105886459351,
+      "learning_rate": 1.6156391946879574e-05,
+      "loss": 1.7916599273681642,
+      "mean_token_accuracy": 0.6300179943442344,
+      "num_tokens": 54280.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.049079754601226995,
+      "eval_entropy": 1.6253603546960014,
+      "eval_loss": 1.5587899684906006,
+      "eval_mean_token_accuracy": 0.6712809375354222,
+      "eval_num_tokens": 54280.0,
+      "eval_runtime": 110.7816,
+      "eval_samples_per_second": 12.601,
+      "eval_steps_per_second": 1.58,
+      "step": 20
+    },
+    {
+      "entropy": 1.2205769553780557,
+      "epoch": 0.09815950920245399,
+      "grad_norm": 0.6686593890190125,
+      "learning_rate": 3.316312031201596e-05,
+      "loss": 1.136343288421631,
+      "mean_token_accuracy": 0.7222879514098167,
+      "num_tokens": 113362.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.09815950920245399,
+      "eval_entropy": 0.9434821823665074,
+      "eval_loss": 0.881726086139679,
+      "eval_mean_token_accuracy": 0.7615073473112923,
+      "eval_num_tokens": 113362.0,
+      "eval_runtime": 110.6353,
+      "eval_samples_per_second": 12.618,
+      "eval_steps_per_second": 1.582,
+      "step": 40
+    },
+    {
+      "entropy": 0.8354097574949264,
+      "epoch": 0.147239263803681,
+      "grad_norm": 0.6986415982246399,
+      "learning_rate": 5.016984867715235e-05,
+      "loss": 0.8029017448425293,
+      "mean_token_accuracy": 0.7783494427800178,
+      "num_tokens": 165819.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.147239263803681,
+      "eval_entropy": 0.7871972390583584,
+      "eval_loss": 0.7541570067405701,
+      "eval_mean_token_accuracy": 0.7862869017464774,
+      "eval_num_tokens": 165819.0,
+      "eval_runtime": 110.5664,
+      "eval_samples_per_second": 12.626,
+      "eval_steps_per_second": 1.583,
+      "step": 60
+    },
+    {
+      "entropy": 0.7618587836623192,
+      "epoch": 0.19631901840490798,
+      "grad_norm": 0.6989718675613403,
+      "learning_rate": 6.717657704228874e-05,
+      "loss": 0.7183277606964111,
+      "mean_token_accuracy": 0.7918156325817108,
+      "num_tokens": 215870.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.19631901840490798,
+      "eval_entropy": 0.7207223660605294,
+      "eval_loss": 0.7117754817008972,
+      "eval_mean_token_accuracy": 0.7968860483169555,
+      "eval_num_tokens": 215870.0,
+      "eval_runtime": 110.6199,
+      "eval_samples_per_second": 12.62,
+      "eval_steps_per_second": 1.582,
+      "step": 80
+    },
+    {
+      "entropy": 0.7375246778130531,
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.9057678580284119,
+      "learning_rate": 6.96353379709049e-05,
+      "loss": 0.702963924407959,
+      "mean_token_accuracy": 0.797600856423378,
+      "num_tokens": 267691.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "eval_entropy": 0.7367377580915179,
+      "eval_loss": 0.6845751404762268,
+      "eval_mean_token_accuracy": 0.8011933132580349,
+      "eval_num_tokens": 267691.0,
+      "eval_runtime": 110.6372,
+      "eval_samples_per_second": 12.618,
+      "eval_steps_per_second": 1.582,
+      "step": 100
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 816,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.7432787808256e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-120/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.19.1

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-120/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-Base",
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.08754516765392441,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-120/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-120/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-120/trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.294478527607362,
+  "eval_steps": 20,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.8042113453149795,
+      "epoch": 0.049079754601226995,
+      "grad_norm": 0.8720105886459351,
+      "learning_rate": 1.6156391946879574e-05,
+      "loss": 1.7916599273681642,
+      "mean_token_accuracy": 0.6300179943442344,
+      "num_tokens": 54280.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.049079754601226995,
+      "eval_entropy": 1.6253603546960014,
+      "eval_loss": 1.5587899684906006,
+      "eval_mean_token_accuracy": 0.6712809375354222,
+      "eval_num_tokens": 54280.0,
+      "eval_runtime": 110.7816,
+      "eval_samples_per_second": 12.601,
+      "eval_steps_per_second": 1.58,
+      "step": 20
+    },
+    {
+      "entropy": 1.2205769553780557,
+      "epoch": 0.09815950920245399,
+      "grad_norm": 0.6686593890190125,
+      "learning_rate": 3.316312031201596e-05,
+      "loss": 1.136343288421631,
+      "mean_token_accuracy": 0.7222879514098167,
+      "num_tokens": 113362.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.09815950920245399,
+      "eval_entropy": 0.9434821823665074,
+      "eval_loss": 0.881726086139679,
+      "eval_mean_token_accuracy": 0.7615073473112923,
+      "eval_num_tokens": 113362.0,
+      "eval_runtime": 110.6353,
+      "eval_samples_per_second": 12.618,
+      "eval_steps_per_second": 1.582,
+      "step": 40
+    },
+    {
+      "entropy": 0.8354097574949264,
+      "epoch": 0.147239263803681,
+      "grad_norm": 0.6986415982246399,
+      "learning_rate": 5.016984867715235e-05,
+      "loss": 0.8029017448425293,
+      "mean_token_accuracy": 0.7783494427800178,
+      "num_tokens": 165819.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.147239263803681,
+      "eval_entropy": 0.7871972390583584,
+      "eval_loss": 0.7541570067405701,
+      "eval_mean_token_accuracy": 0.7862869017464774,
+      "eval_num_tokens": 165819.0,
+      "eval_runtime": 110.5664,
+      "eval_samples_per_second": 12.626,
+      "eval_steps_per_second": 1.583,
+      "step": 60
+    },
+    {
+      "entropy": 0.7618587836623192,
+      "epoch": 0.19631901840490798,
+      "grad_norm": 0.6989718675613403,
+      "learning_rate": 6.717657704228874e-05,
+      "loss": 0.7183277606964111,
+      "mean_token_accuracy": 0.7918156325817108,
+      "num_tokens": 215870.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.19631901840490798,
+      "eval_entropy": 0.7207223660605294,
+      "eval_loss": 0.7117754817008972,
+      "eval_mean_token_accuracy": 0.7968860483169555,
+      "eval_num_tokens": 215870.0,
+      "eval_runtime": 110.6199,
+      "eval_samples_per_second": 12.62,
+      "eval_steps_per_second": 1.582,
+      "step": 80
+    },
+    {
+      "entropy": 0.7375246778130531,
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.9057678580284119,
+      "learning_rate": 6.96353379709049e-05,
+      "loss": 0.702963924407959,
+      "mean_token_accuracy": 0.797600856423378,
+      "num_tokens": 267691.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "eval_entropy": 0.7367377580915179,
+      "eval_loss": 0.6845751404762268,
+      "eval_mean_token_accuracy": 0.8011933132580349,
+      "eval_num_tokens": 267691.0,
+      "eval_runtime": 110.6372,
+      "eval_samples_per_second": 12.618,
+      "eval_steps_per_second": 1.582,
+      "step": 100
+    },
+    {
+      "entropy": 0.7158783033490181,
+      "epoch": 0.294478527607362,
+      "grad_norm": 0.4919581413269043,
+      "learning_rate": 6.929132379744316e-05,
+      "loss": 0.6752747058868408,
+      "mean_token_accuracy": 0.8034310981631279,
+      "num_tokens": 323653.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.294478527607362,
+      "eval_entropy": 0.7097335999352591,
+      "eval_loss": 0.6642724275588989,
+      "eval_mean_token_accuracy": 0.8056706874711173,
+      "eval_num_tokens": 323653.0,
+      "eval_runtime": 110.6492,
+      "eval_samples_per_second": 12.616,
+      "eval_steps_per_second": 1.582,
+      "step": 120
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 816,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.8615433449472e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-140/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.19.1

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-140/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-Base",
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.08754516765392441,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-140/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-140/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-140/trainer_state.json

@@ -0,0 +1,181 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.34355828220858897,
+  "eval_steps": 20,
+  "global_step": 140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.8042113453149795,
+      "epoch": 0.049079754601226995,
+      "grad_norm": 0.8720105886459351,
+      "learning_rate": 1.6156391946879574e-05,
+      "loss": 1.7916599273681642,
+      "mean_token_accuracy": 0.6300179943442344,
+      "num_tokens": 54280.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.049079754601226995,
+      "eval_entropy": 1.6253603546960014,
+      "eval_loss": 1.5587899684906006,
+      "eval_mean_token_accuracy": 0.6712809375354222,
+      "eval_num_tokens": 54280.0,
+      "eval_runtime": 110.7816,
+      "eval_samples_per_second": 12.601,
+      "eval_steps_per_second": 1.58,
+      "step": 20
+    },
+    {
+      "entropy": 1.2205769553780557,
+      "epoch": 0.09815950920245399,
+      "grad_norm": 0.6686593890190125,
+      "learning_rate": 3.316312031201596e-05,
+      "loss": 1.136343288421631,
+      "mean_token_accuracy": 0.7222879514098167,
+      "num_tokens": 113362.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.09815950920245399,
+      "eval_entropy": 0.9434821823665074,
+      "eval_loss": 0.881726086139679,
+      "eval_mean_token_accuracy": 0.7615073473112923,
+      "eval_num_tokens": 113362.0,
+      "eval_runtime": 110.6353,
+      "eval_samples_per_second": 12.618,
+      "eval_steps_per_second": 1.582,
+      "step": 40
+    },
+    {
+      "entropy": 0.8354097574949264,
+      "epoch": 0.147239263803681,
+      "grad_norm": 0.6986415982246399,
+      "learning_rate": 5.016984867715235e-05,
+      "loss": 0.8029017448425293,
+      "mean_token_accuracy": 0.7783494427800178,
+      "num_tokens": 165819.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.147239263803681,
+      "eval_entropy": 0.7871972390583584,
+      "eval_loss": 0.7541570067405701,
+      "eval_mean_token_accuracy": 0.7862869017464774,
+      "eval_num_tokens": 165819.0,
+      "eval_runtime": 110.5664,
+      "eval_samples_per_second": 12.626,
+      "eval_steps_per_second": 1.583,
+      "step": 60
+    },
+    {
+      "entropy": 0.7618587836623192,
+      "epoch": 0.19631901840490798,
+      "grad_norm": 0.6989718675613403,
+      "learning_rate": 6.717657704228874e-05,
+      "loss": 0.7183277606964111,
+      "mean_token_accuracy": 0.7918156325817108,
+      "num_tokens": 215870.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.19631901840490798,
+      "eval_entropy": 0.7207223660605294,
+      "eval_loss": 0.7117754817008972,
+      "eval_mean_token_accuracy": 0.7968860483169555,
+      "eval_num_tokens": 215870.0,
+      "eval_runtime": 110.6199,
+      "eval_samples_per_second": 12.62,
+      "eval_steps_per_second": 1.582,
+      "step": 80
+    },
+    {
+      "entropy": 0.7375246778130531,
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.9057678580284119,
+      "learning_rate": 6.96353379709049e-05,
+      "loss": 0.702963924407959,
+      "mean_token_accuracy": 0.797600856423378,
+      "num_tokens": 267691.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "eval_entropy": 0.7367377580915179,
+      "eval_loss": 0.6845751404762268,
+      "eval_mean_token_accuracy": 0.8011933132580349,
+      "eval_num_tokens": 267691.0,
+      "eval_runtime": 110.6372,
+      "eval_samples_per_second": 12.618,
+      "eval_steps_per_second": 1.582,
+      "step": 100
+    },
+    {
+      "entropy": 0.7158783033490181,
+      "epoch": 0.294478527607362,
+      "grad_norm": 0.4919581413269043,
+      "learning_rate": 6.929132379744316e-05,
+      "loss": 0.6752747058868408,
+      "mean_token_accuracy": 0.8034310981631279,
+      "num_tokens": 323653.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.294478527607362,
+      "eval_entropy": 0.7097335999352591,
+      "eval_loss": 0.6642724275588989,
+      "eval_mean_token_accuracy": 0.8056706874711173,
+      "eval_num_tokens": 323653.0,
+      "eval_runtime": 110.6492,
+      "eval_samples_per_second": 12.616,
+      "eval_steps_per_second": 1.582,
+      "step": 120
+    },
+    {
+      "entropy": 0.6817873455584049,
+      "epoch": 0.34355828220858897,
+      "grad_norm": 0.4943574368953705,
+      "learning_rate": 6.86951890564815e-05,
+      "loss": 0.6389606952667236,
+      "mean_token_accuracy": 0.8110431596636772,
+      "num_tokens": 382063.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.34355828220858897,
+      "eval_entropy": 0.6846639224461146,
+      "eval_loss": 0.6477498412132263,
+      "eval_mean_token_accuracy": 0.8120035709653581,
+      "eval_num_tokens": 382063.0,
+      "eval_runtime": 110.6491,
+      "eval_samples_per_second": 12.616,
+      "eval_steps_per_second": 1.582,
+      "step": 140
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 816,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.9723537238016e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-160/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.19.1

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-160/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-Base",
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.08754516765392441,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-160/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-160/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-160/trainer_state.json

@@ -0,0 +1,202 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.39263803680981596,
+  "eval_steps": 20,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.8042113453149795,
+      "epoch": 0.049079754601226995,
+      "grad_norm": 0.8720105886459351,
+      "learning_rate": 1.6156391946879574e-05,
+      "loss": 1.7916599273681642,
+      "mean_token_accuracy": 0.6300179943442344,
+      "num_tokens": 54280.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.049079754601226995,
+      "eval_entropy": 1.6253603546960014,
+      "eval_loss": 1.5587899684906006,
+      "eval_mean_token_accuracy": 0.6712809375354222,
+      "eval_num_tokens": 54280.0,
+      "eval_runtime": 110.7816,
+      "eval_samples_per_second": 12.601,
+      "eval_steps_per_second": 1.58,
+      "step": 20
+    },
+    {
+      "entropy": 1.2205769553780557,
+      "epoch": 0.09815950920245399,
+      "grad_norm": 0.6686593890190125,
+      "learning_rate": 3.316312031201596e-05,
+      "loss": 1.136343288421631,
+      "mean_token_accuracy": 0.7222879514098167,
+      "num_tokens": 113362.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.09815950920245399,
+      "eval_entropy": 0.9434821823665074,
+      "eval_loss": 0.881726086139679,
+      "eval_mean_token_accuracy": 0.7615073473112923,
+      "eval_num_tokens": 113362.0,
+      "eval_runtime": 110.6353,
+      "eval_samples_per_second": 12.618,
+      "eval_steps_per_second": 1.582,
+      "step": 40
+    },
+    {
+      "entropy": 0.8354097574949264,
+      "epoch": 0.147239263803681,
+      "grad_norm": 0.6986415982246399,
+      "learning_rate": 5.016984867715235e-05,
+      "loss": 0.8029017448425293,
+      "mean_token_accuracy": 0.7783494427800178,
+      "num_tokens": 165819.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.147239263803681,
+      "eval_entropy": 0.7871972390583584,
+      "eval_loss": 0.7541570067405701,
+      "eval_mean_token_accuracy": 0.7862869017464774,
+      "eval_num_tokens": 165819.0,
+      "eval_runtime": 110.5664,
+      "eval_samples_per_second": 12.626,
+      "eval_steps_per_second": 1.583,
+      "step": 60
+    },
+    {
+      "entropy": 0.7618587836623192,
+      "epoch": 0.19631901840490798,
+      "grad_norm": 0.6989718675613403,
+      "learning_rate": 6.717657704228874e-05,
+      "loss": 0.7183277606964111,
+      "mean_token_accuracy": 0.7918156325817108,
+      "num_tokens": 215870.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.19631901840490798,
+      "eval_entropy": 0.7207223660605294,
+      "eval_loss": 0.7117754817008972,
+      "eval_mean_token_accuracy": 0.7968860483169555,
+      "eval_num_tokens": 215870.0,
+      "eval_runtime": 110.6199,
+      "eval_samples_per_second": 12.62,
+      "eval_steps_per_second": 1.582,
+      "step": 80
+    },
+    {
+      "entropy": 0.7375246778130531,
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.9057678580284119,
+      "learning_rate": 6.96353379709049e-05,
+      "loss": 0.702963924407959,
+      "mean_token_accuracy": 0.797600856423378,
+      "num_tokens": 267691.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "eval_entropy": 0.7367377580915179,
+      "eval_loss": 0.6845751404762268,
+      "eval_mean_token_accuracy": 0.8011933132580349,
+      "eval_num_tokens": 267691.0,
+      "eval_runtime": 110.6372,
+      "eval_samples_per_second": 12.618,
+      "eval_steps_per_second": 1.582,
+      "step": 100
+    },
+    {
+      "entropy": 0.7158783033490181,
+      "epoch": 0.294478527607362,
+      "grad_norm": 0.4919581413269043,
+      "learning_rate": 6.929132379744316e-05,
+      "loss": 0.6752747058868408,
+      "mean_token_accuracy": 0.8034310981631279,
+      "num_tokens": 323653.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.294478527607362,
+      "eval_entropy": 0.7097335999352591,
+      "eval_loss": 0.6642724275588989,
+      "eval_mean_token_accuracy": 0.8056706874711173,
+      "eval_num_tokens": 323653.0,
+      "eval_runtime": 110.6492,
+      "eval_samples_per_second": 12.616,
+      "eval_steps_per_second": 1.582,
+      "step": 120
+    },
+    {
+      "entropy": 0.6817873455584049,
+      "epoch": 0.34355828220858897,
+      "grad_norm": 0.4943574368953705,
+      "learning_rate": 6.86951890564815e-05,
+      "loss": 0.6389606952667236,
+      "mean_token_accuracy": 0.8110431596636772,
+      "num_tokens": 382063.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.34355828220858897,
+      "eval_entropy": 0.6846639224461146,
+      "eval_loss": 0.6477498412132263,
+      "eval_mean_token_accuracy": 0.8120035709653581,
+      "eval_num_tokens": 382063.0,
+      "eval_runtime": 110.6491,
+      "eval_samples_per_second": 12.616,
+      "eval_steps_per_second": 1.582,
+      "step": 140
+    },
+    {
+      "entropy": 0.6678083419799805,
+      "epoch": 0.39263803680981596,
+      "grad_norm": 0.4057321548461914,
+      "learning_rate": 6.785129937710703e-05,
+      "loss": 0.6308637619018554,
+      "mean_token_accuracy": 0.816147631406784,
+      "num_tokens": 440825.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.39263803680981596,
+      "eval_entropy": 0.6869715414728437,
+      "eval_loss": 0.6331504583358765,
+      "eval_mean_token_accuracy": 0.8155754739897592,
+      "eval_num_tokens": 440825.0,
+      "eval_runtime": 110.673,
+      "eval_samples_per_second": 12.614,
+      "eval_steps_per_second": 1.581,
+      "step": 160
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 816,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.1601678880768e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-180/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.19.1

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-180/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-Base",
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.08754516765392441,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-180/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-180/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-180/trainer_state.json

@@ -0,0 +1,223 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.44171779141104295,
+  "eval_steps": 20,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.8042113453149795,
+      "epoch": 0.049079754601226995,
+      "grad_norm": 0.8720105886459351,
+      "learning_rate": 1.6156391946879574e-05,
+      "loss": 1.7916599273681642,
+      "mean_token_accuracy": 0.6300179943442344,
+      "num_tokens": 54280.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.049079754601226995,
+      "eval_entropy": 1.6253603546960014,
+      "eval_loss": 1.5587899684906006,
+      "eval_mean_token_accuracy": 0.6712809375354222,
+      "eval_num_tokens": 54280.0,
+      "eval_runtime": 110.7816,
+      "eval_samples_per_second": 12.601,
+      "eval_steps_per_second": 1.58,
+      "step": 20
+    },
+    {
+      "entropy": 1.2205769553780557,
+      "epoch": 0.09815950920245399,
+      "grad_norm": 0.6686593890190125,
+      "learning_rate": 3.316312031201596e-05,
+      "loss": 1.136343288421631,
+      "mean_token_accuracy": 0.7222879514098167,
+      "num_tokens": 113362.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.09815950920245399,
+      "eval_entropy": 0.9434821823665074,
+      "eval_loss": 0.881726086139679,
+      "eval_mean_token_accuracy": 0.7615073473112923,
+      "eval_num_tokens": 113362.0,
+      "eval_runtime": 110.6353,
+      "eval_samples_per_second": 12.618,
+      "eval_steps_per_second": 1.582,
+      "step": 40
+    },
+    {
+      "entropy": 0.8354097574949264,
+      "epoch": 0.147239263803681,
+      "grad_norm": 0.6986415982246399,
+      "learning_rate": 5.016984867715235e-05,
+      "loss": 0.8029017448425293,
+      "mean_token_accuracy": 0.7783494427800178,
+      "num_tokens": 165819.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.147239263803681,
+      "eval_entropy": 0.7871972390583584,
+      "eval_loss": 0.7541570067405701,
+      "eval_mean_token_accuracy": 0.7862869017464774,
+      "eval_num_tokens": 165819.0,
+      "eval_runtime": 110.5664,
+      "eval_samples_per_second": 12.626,
+      "eval_steps_per_second": 1.583,
+      "step": 60
+    },
+    {
+      "entropy": 0.7618587836623192,
+      "epoch": 0.19631901840490798,
+      "grad_norm": 0.6989718675613403,
+      "learning_rate": 6.717657704228874e-05,
+      "loss": 0.7183277606964111,
+      "mean_token_accuracy": 0.7918156325817108,
+      "num_tokens": 215870.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.19631901840490798,
+      "eval_entropy": 0.7207223660605294,
+      "eval_loss": 0.7117754817008972,
+      "eval_mean_token_accuracy": 0.7968860483169555,
+      "eval_num_tokens": 215870.0,
+      "eval_runtime": 110.6199,
+      "eval_samples_per_second": 12.62,
+      "eval_steps_per_second": 1.582,
+      "step": 80
+    },
+    {
+      "entropy": 0.7375246778130531,
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.9057678580284119,
+      "learning_rate": 6.96353379709049e-05,
+      "loss": 0.702963924407959,
+      "mean_token_accuracy": 0.797600856423378,
+      "num_tokens": 267691.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "eval_entropy": 0.7367377580915179,
+      "eval_loss": 0.6845751404762268,
+      "eval_mean_token_accuracy": 0.8011933132580349,
+      "eval_num_tokens": 267691.0,
+      "eval_runtime": 110.6372,
+      "eval_samples_per_second": 12.618,
+      "eval_steps_per_second": 1.582,
+      "step": 100
+    },
+    {
+      "entropy": 0.7158783033490181,
+      "epoch": 0.294478527607362,
+      "grad_norm": 0.4919581413269043,
+      "learning_rate": 6.929132379744316e-05,
+      "loss": 0.6752747058868408,
+      "mean_token_accuracy": 0.8034310981631279,
+      "num_tokens": 323653.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.294478527607362,
+      "eval_entropy": 0.7097335999352591,
+      "eval_loss": 0.6642724275588989,
+      "eval_mean_token_accuracy": 0.8056706874711173,
+      "eval_num_tokens": 323653.0,
+      "eval_runtime": 110.6492,
+      "eval_samples_per_second": 12.616,
+      "eval_steps_per_second": 1.582,
+      "step": 120
+    },
+    {
+      "entropy": 0.6817873455584049,
+      "epoch": 0.34355828220858897,
+      "grad_norm": 0.4943574368953705,
+      "learning_rate": 6.86951890564815e-05,
+      "loss": 0.6389606952667236,
+      "mean_token_accuracy": 0.8110431596636772,
+      "num_tokens": 382063.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.34355828220858897,
+      "eval_entropy": 0.6846639224461146,
+      "eval_loss": 0.6477498412132263,
+      "eval_mean_token_accuracy": 0.8120035709653581,
+      "eval_num_tokens": 382063.0,
+      "eval_runtime": 110.6491,
+      "eval_samples_per_second": 12.616,
+      "eval_steps_per_second": 1.582,
+      "step": 140
+    },
+    {
+      "entropy": 0.6678083419799805,
+      "epoch": 0.39263803680981596,
+      "grad_norm": 0.4057321548461914,
+      "learning_rate": 6.785129937710703e-05,
+      "loss": 0.6308637619018554,
+      "mean_token_accuracy": 0.816147631406784,
+      "num_tokens": 440825.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.39263803680981596,
+      "eval_entropy": 0.6869715414728437,
+      "eval_loss": 0.6331504583358765,
+      "eval_mean_token_accuracy": 0.8155754739897592,
+      "eval_num_tokens": 440825.0,
+      "eval_runtime": 110.673,
+      "eval_samples_per_second": 12.614,
+      "eval_steps_per_second": 1.581,
+      "step": 160
+    },
+    {
+      "entropy": 0.6723565131425857,
+      "epoch": 0.44171779141104295,
+      "grad_norm": 0.6217795610427856,
+      "learning_rate": 6.676583475366906e-05,
+      "loss": 0.62900390625,
+      "mean_token_accuracy": 0.8144089907407761,
+      "num_tokens": 494124.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.44171779141104295,
+      "eval_entropy": 0.6551390927178519,
+      "eval_loss": 0.6275219917297363,
+      "eval_mean_token_accuracy": 0.8162073765482222,
+      "eval_num_tokens": 494124.0,
+      "eval_runtime": 110.6478,
+      "eval_samples_per_second": 12.617,
+      "eval_steps_per_second": 1.582,
+      "step": 180
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 816,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.01651151587328e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}