Add files using upload-large-folder tool

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

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: transformers
+model_name: Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_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/8nm68no9) 
+
+
+
+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}
+}
+```

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: transformers
+model_name: Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_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/0sjhdwt0) 
+
+
+
+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}
+}
+```

overgeneralisation_original_Estonian/Qwen3-14B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/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_test2/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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.09184864657147984,
+  "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": 16,
+  "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_test2/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_test2/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_test2/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": 1.719682201743126,
+      "epoch": 0.049079754601226995,
+      "grad_norm": 0.8067639470100403,
+      "learning_rate": 7.740423047216553e-05,
+      "loss": 1.700193214416504,
+      "mean_token_accuracy": 0.6428261503577233,
+      "num_tokens": 54280.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.049079754601226995,
+      "eval_entropy": 1.315366074017116,
+      "eval_loss": 1.23488187789917,
+      "eval_mean_token_accuracy": 0.7063105702400208,
+      "eval_num_tokens": 54280.0,
+      "eval_runtime": 105.4535,
+      "eval_samples_per_second": 13.229,
+      "eval_steps_per_second": 1.659,
+      "step": 20
+    },
+    {
+      "entropy": 0.95277059674263,
+      "epoch": 0.09815950920245399,
+      "grad_norm": 0.572104811668396,
+      "learning_rate": 0.00015888236781128713,
+      "loss": 0.9082255363464355,
+      "mean_token_accuracy": 0.7559243977069855,
+      "num_tokens": 113362.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.09815950920245399,
+      "eval_entropy": 0.8220351917403085,
+      "eval_loss": 0.7917433381080627,
+      "eval_mean_token_accuracy": 0.774279066153935,
+      "eval_num_tokens": 113362.0,
+      "eval_runtime": 104.9915,
+      "eval_samples_per_second": 13.287,
+      "eval_steps_per_second": 1.667,
+      "step": 40
+    },
+    {
+      "entropy": 0.7833507835865021,
+      "epoch": 0.147239263803681,
+      "grad_norm": 0.5184682011604309,
+      "learning_rate": 0.00024036050515040874,
+      "loss": 0.7395487308502198,
+      "mean_token_accuracy": 0.7903637677431107,
+      "num_tokens": 165819.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.147239263803681,
+      "eval_entropy": 0.7486384316853114,
+      "eval_loss": 0.7170758843421936,
+      "eval_mean_token_accuracy": 0.7953836243493216,
+      "eval_num_tokens": 165819.0,
+      "eval_runtime": 105.0262,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "step": 60
+    },
+    {
+      "entropy": 0.7294519171118736,
+      "epoch": 0.19631901840490798,
+      "grad_norm": 0.44408509135246277,
+      "learning_rate": 0.00032183864248953035,
+      "loss": 0.6858654499053956,
+      "mean_token_accuracy": 0.8006252631545067,
+      "num_tokens": 215870.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.19631901840490798,
+      "eval_entropy": 0.7126145311764308,
+      "eval_loss": 0.6875877976417542,
+      "eval_mean_token_accuracy": 0.8029442460196359,
+      "eval_num_tokens": 215870.0,
+      "eval_runtime": 105.0224,
+      "eval_samples_per_second": 13.283,
+      "eval_steps_per_second": 1.666,
+      "step": 80
+    },
+    {
+      "entropy": 0.729012505710125,
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.6172338724136353,
+      "learning_rate": 0.0003336184073169935,
+      "loss": 0.6861891746520996,
+      "mean_token_accuracy": 0.8014167010784149,
+      "num_tokens": 267691.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "eval_entropy": 0.7107754983220782,
+      "eval_loss": 0.6713247299194336,
+      "eval_mean_token_accuracy": 0.8043575610433306,
+      "eval_num_tokens": 267691.0,
+      "eval_runtime": 104.9968,
+      "eval_samples_per_second": 13.286,
+      "eval_steps_per_second": 1.667,
+      "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": 5.665608529330176e+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_test2/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_test2/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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.09184864657147984,
+  "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": 16,
+  "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_test2/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_test2/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_test2/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": 1.719682201743126,
+      "epoch": 0.049079754601226995,
+      "grad_norm": 0.8067639470100403,
+      "learning_rate": 7.740423047216553e-05,
+      "loss": 1.700193214416504,
+      "mean_token_accuracy": 0.6428261503577233,
+      "num_tokens": 54280.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.049079754601226995,
+      "eval_entropy": 1.315366074017116,
+      "eval_loss": 1.23488187789917,
+      "eval_mean_token_accuracy": 0.7063105702400208,
+      "eval_num_tokens": 54280.0,
+      "eval_runtime": 105.4535,
+      "eval_samples_per_second": 13.229,
+      "eval_steps_per_second": 1.659,
+      "step": 20
+    },
+    {
+      "entropy": 0.95277059674263,
+      "epoch": 0.09815950920245399,
+      "grad_norm": 0.572104811668396,
+      "learning_rate": 0.00015888236781128713,
+      "loss": 0.9082255363464355,
+      "mean_token_accuracy": 0.7559243977069855,
+      "num_tokens": 113362.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.09815950920245399,
+      "eval_entropy": 0.8220351917403085,
+      "eval_loss": 0.7917433381080627,
+      "eval_mean_token_accuracy": 0.774279066153935,
+      "eval_num_tokens": 113362.0,
+      "eval_runtime": 104.9915,
+      "eval_samples_per_second": 13.287,
+      "eval_steps_per_second": 1.667,
+      "step": 40
+    },
+    {
+      "entropy": 0.7833507835865021,
+      "epoch": 0.147239263803681,
+      "grad_norm": 0.5184682011604309,
+      "learning_rate": 0.00024036050515040874,
+      "loss": 0.7395487308502198,
+      "mean_token_accuracy": 0.7903637677431107,
+      "num_tokens": 165819.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.147239263803681,
+      "eval_entropy": 0.7486384316853114,
+      "eval_loss": 0.7170758843421936,
+      "eval_mean_token_accuracy": 0.7953836243493216,
+      "eval_num_tokens": 165819.0,
+      "eval_runtime": 105.0262,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "step": 60
+    },
+    {
+      "entropy": 0.7294519171118736,
+      "epoch": 0.19631901840490798,
+      "grad_norm": 0.44408509135246277,
+      "learning_rate": 0.00032183864248953035,
+      "loss": 0.6858654499053956,
+      "mean_token_accuracy": 0.8006252631545067,
+      "num_tokens": 215870.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.19631901840490798,
+      "eval_entropy": 0.7126145311764308,
+      "eval_loss": 0.6875877976417542,
+      "eval_mean_token_accuracy": 0.8029442460196359,
+      "eval_num_tokens": 215870.0,
+      "eval_runtime": 105.0224,
+      "eval_samples_per_second": 13.283,
+      "eval_steps_per_second": 1.666,
+      "step": 80
+    },
+    {
+      "entropy": 0.729012505710125,
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.6172338724136353,
+      "learning_rate": 0.0003336184073169935,
+      "loss": 0.6861891746520996,
+      "mean_token_accuracy": 0.8014167010784149,
+      "num_tokens": 267691.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "eval_entropy": 0.7107754983220782,
+      "eval_loss": 0.6713247299194336,
+      "eval_mean_token_accuracy": 0.8043575610433306,
+      "eval_num_tokens": 267691.0,
+      "eval_runtime": 104.9968,
+      "eval_samples_per_second": 13.286,
+      "eval_steps_per_second": 1.667,
+      "step": 100
+    },
+    {
+      "entropy": 0.6980620548129082,
+      "epoch": 0.294478527607362,
+      "grad_norm": 0.39251449704170227,
+      "learning_rate": 0.0003319702576276399,
+      "loss": 0.6606289863586425,
+      "mean_token_accuracy": 0.8069421723484993,
+      "num_tokens": 323653.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.294478527607362,
+      "eval_entropy": 0.6927587161745344,
+      "eval_loss": 0.6542542576789856,
+      "eval_mean_token_accuracy": 0.8079089961733137,
+      "eval_num_tokens": 323653.0,
+      "eval_runtime": 104.9951,
+      "eval_samples_per_second": 13.286,
+      "eval_steps_per_second": 1.667,
+      "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": 6.768750043840512e+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_test2/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_test2/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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.09184864657147984,
+  "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": 16,
+  "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_test2/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_test2/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_test2/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": 1.719682201743126,
+      "epoch": 0.049079754601226995,
+      "grad_norm": 0.8067639470100403,
+      "learning_rate": 7.740423047216553e-05,
+      "loss": 1.700193214416504,
+      "mean_token_accuracy": 0.6428261503577233,
+      "num_tokens": 54280.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.049079754601226995,
+      "eval_entropy": 1.315366074017116,
+      "eval_loss": 1.23488187789917,
+      "eval_mean_token_accuracy": 0.7063105702400208,
+      "eval_num_tokens": 54280.0,
+      "eval_runtime": 105.4535,
+      "eval_samples_per_second": 13.229,
+      "eval_steps_per_second": 1.659,
+      "step": 20
+    },
+    {
+      "entropy": 0.95277059674263,
+      "epoch": 0.09815950920245399,
+      "grad_norm": 0.572104811668396,
+      "learning_rate": 0.00015888236781128713,
+      "loss": 0.9082255363464355,
+      "mean_token_accuracy": 0.7559243977069855,
+      "num_tokens": 113362.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.09815950920245399,
+      "eval_entropy": 0.8220351917403085,
+      "eval_loss": 0.7917433381080627,
+      "eval_mean_token_accuracy": 0.774279066153935,
+      "eval_num_tokens": 113362.0,
+      "eval_runtime": 104.9915,
+      "eval_samples_per_second": 13.287,
+      "eval_steps_per_second": 1.667,
+      "step": 40
+    },
+    {
+      "entropy": 0.7833507835865021,
+      "epoch": 0.147239263803681,
+      "grad_norm": 0.5184682011604309,
+      "learning_rate": 0.00024036050515040874,
+      "loss": 0.7395487308502198,
+      "mean_token_accuracy": 0.7903637677431107,
+      "num_tokens": 165819.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.147239263803681,
+      "eval_entropy": 0.7486384316853114,
+      "eval_loss": 0.7170758843421936,
+      "eval_mean_token_accuracy": 0.7953836243493216,
+      "eval_num_tokens": 165819.0,
+      "eval_runtime": 105.0262,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "step": 60
+    },
+    {
+      "entropy": 0.7294519171118736,
+      "epoch": 0.19631901840490798,
+      "grad_norm": 0.44408509135246277,
+      "learning_rate": 0.00032183864248953035,
+      "loss": 0.6858654499053956,
+      "mean_token_accuracy": 0.8006252631545067,
+      "num_tokens": 215870.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.19631901840490798,
+      "eval_entropy": 0.7126145311764308,
+      "eval_loss": 0.6875877976417542,
+      "eval_mean_token_accuracy": 0.8029442460196359,
+      "eval_num_tokens": 215870.0,
+      "eval_runtime": 105.0224,
+      "eval_samples_per_second": 13.283,
+      "eval_steps_per_second": 1.666,
+      "step": 80
+    },
+    {
+      "entropy": 0.729012505710125,
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.6172338724136353,
+      "learning_rate": 0.0003336184073169935,
+      "loss": 0.6861891746520996,
+      "mean_token_accuracy": 0.8014167010784149,
+      "num_tokens": 267691.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "eval_entropy": 0.7107754983220782,
+      "eval_loss": 0.6713247299194336,
+      "eval_mean_token_accuracy": 0.8043575610433306,
+      "eval_num_tokens": 267691.0,
+      "eval_runtime": 104.9968,
+      "eval_samples_per_second": 13.286,
+      "eval_steps_per_second": 1.667,
+      "step": 100
+    },
+    {
+      "entropy": 0.6980620548129082,
+      "epoch": 0.294478527607362,
+      "grad_norm": 0.39251449704170227,
+      "learning_rate": 0.0003319702576276399,
+      "loss": 0.6606289863586425,
+      "mean_token_accuracy": 0.8069421723484993,
+      "num_tokens": 323653.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.294478527607362,
+      "eval_entropy": 0.6927587161745344,
+      "eval_loss": 0.6542542576789856,
+      "eval_mean_token_accuracy": 0.8079089961733137,
+      "eval_num_tokens": 323653.0,
+      "eval_runtime": 104.9951,
+      "eval_samples_per_second": 13.286,
+      "eval_steps_per_second": 1.667,
+      "step": 120
+    },
+    {
+      "entropy": 0.6662331499159336,
+      "epoch": 0.34355828220858897,
+      "grad_norm": 0.3216697573661804,
+      "learning_rate": 0.0003291142145808027,
+      "loss": 0.6278485298156739,
+      "mean_token_accuracy": 0.8151775613427162,
+      "num_tokens": 382063.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.34355828220858897,
+      "eval_entropy": 0.6883142059189933,
+      "eval_loss": 0.6383033990859985,
+      "eval_mean_token_accuracy": 0.8143898207800729,
+      "eval_num_tokens": 382063.0,
+      "eval_runtime": 105.044,
+      "eval_samples_per_second": 13.28,
+      "eval_steps_per_second": 1.666,
+      "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": 7.864538181083136e+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_test2/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_test2/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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.09184864657147984,
+  "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": 16,
+  "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_test2/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_test2/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_test2/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": 1.719682201743126,
+      "epoch": 0.049079754601226995,
+      "grad_norm": 0.8067639470100403,
+      "learning_rate": 7.740423047216553e-05,
+      "loss": 1.700193214416504,
+      "mean_token_accuracy": 0.6428261503577233,
+      "num_tokens": 54280.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.049079754601226995,
+      "eval_entropy": 1.315366074017116,
+      "eval_loss": 1.23488187789917,
+      "eval_mean_token_accuracy": 0.7063105702400208,
+      "eval_num_tokens": 54280.0,
+      "eval_runtime": 105.4535,
+      "eval_samples_per_second": 13.229,
+      "eval_steps_per_second": 1.659,
+      "step": 20
+    },
+    {
+      "entropy": 0.95277059674263,
+      "epoch": 0.09815950920245399,
+      "grad_norm": 0.572104811668396,
+      "learning_rate": 0.00015888236781128713,
+      "loss": 0.9082255363464355,
+      "mean_token_accuracy": 0.7559243977069855,
+      "num_tokens": 113362.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.09815950920245399,
+      "eval_entropy": 0.8220351917403085,
+      "eval_loss": 0.7917433381080627,
+      "eval_mean_token_accuracy": 0.774279066153935,
+      "eval_num_tokens": 113362.0,
+      "eval_runtime": 104.9915,
+      "eval_samples_per_second": 13.287,
+      "eval_steps_per_second": 1.667,
+      "step": 40
+    },
+    {
+      "entropy": 0.7833507835865021,
+      "epoch": 0.147239263803681,
+      "grad_norm": 0.5184682011604309,
+      "learning_rate": 0.00024036050515040874,
+      "loss": 0.7395487308502198,
+      "mean_token_accuracy": 0.7903637677431107,
+      "num_tokens": 165819.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.147239263803681,
+      "eval_entropy": 0.7486384316853114,
+      "eval_loss": 0.7170758843421936,
+      "eval_mean_token_accuracy": 0.7953836243493216,
+      "eval_num_tokens": 165819.0,
+      "eval_runtime": 105.0262,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "step": 60
+    },
+    {
+      "entropy": 0.7294519171118736,
+      "epoch": 0.19631901840490798,
+      "grad_norm": 0.44408509135246277,
+      "learning_rate": 0.00032183864248953035,
+      "loss": 0.6858654499053956,
+      "mean_token_accuracy": 0.8006252631545067,
+      "num_tokens": 215870.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.19631901840490798,
+      "eval_entropy": 0.7126145311764308,
+      "eval_loss": 0.6875877976417542,
+      "eval_mean_token_accuracy": 0.8029442460196359,
+      "eval_num_tokens": 215870.0,
+      "eval_runtime": 105.0224,
+      "eval_samples_per_second": 13.283,
+      "eval_steps_per_second": 1.666,
+      "step": 80
+    },
+    {
+      "entropy": 0.729012505710125,
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.6172338724136353,
+      "learning_rate": 0.0003336184073169935,
+      "loss": 0.6861891746520996,
+      "mean_token_accuracy": 0.8014167010784149,
+      "num_tokens": 267691.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "eval_entropy": 0.7107754983220782,
+      "eval_loss": 0.6713247299194336,
+      "eval_mean_token_accuracy": 0.8043575610433306,
+      "eval_num_tokens": 267691.0,
+      "eval_runtime": 104.9968,
+      "eval_samples_per_second": 13.286,
+      "eval_steps_per_second": 1.667,
+      "step": 100
+    },
+    {
+      "entropy": 0.6980620548129082,
+      "epoch": 0.294478527607362,
+      "grad_norm": 0.39251449704170227,
+      "learning_rate": 0.0003319702576276399,
+      "loss": 0.6606289863586425,
+      "mean_token_accuracy": 0.8069421723484993,
+      "num_tokens": 323653.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.294478527607362,
+      "eval_entropy": 0.6927587161745344,
+      "eval_loss": 0.6542542576789856,
+      "eval_mean_token_accuracy": 0.8079089961733137,
+      "eval_num_tokens": 323653.0,
+      "eval_runtime": 104.9951,
+      "eval_samples_per_second": 13.286,
+      "eval_steps_per_second": 1.667,
+      "step": 120
+    },
+    {
+      "entropy": 0.6662331499159336,
+      "epoch": 0.34355828220858897,
+      "grad_norm": 0.3216697573661804,
+      "learning_rate": 0.0003291142145808027,
+      "loss": 0.6278485298156739,
+      "mean_token_accuracy": 0.8151775613427162,
+      "num_tokens": 382063.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.34355828220858897,
+      "eval_entropy": 0.6883142059189933,
+      "eval_loss": 0.6383033990859985,
+      "eval_mean_token_accuracy": 0.8143898207800729,
+      "eval_num_tokens": 382063.0,
+      "eval_runtime": 105.044,
+      "eval_samples_per_second": 13.28,
+      "eval_steps_per_second": 1.666,
+      "step": 140
+    },
+    {
+      "entropy": 0.6582960978150367,
+      "epoch": 0.39263803680981596,
+      "grad_norm": 0.3135772943496704,
+      "learning_rate": 0.00032507119362351535,
+      "loss": 0.6200582027435303,
+      "mean_token_accuracy": 0.8181118443608284,
+      "num_tokens": 440825.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.39263803680981596,
+      "eval_entropy": 0.6579666543006897,
+      "eval_loss": 0.6228571534156799,
+      "eval_mean_token_accuracy": 0.8177092627116612,
+      "eval_num_tokens": 440825.0,
+      "eval_runtime": 105.0261,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "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": 9.036288729366528e+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_test2/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_test2/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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.09184864657147984,
+  "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": 16,
+  "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_test2/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_test2/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_test2/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": 1.719682201743126,
+      "epoch": 0.049079754601226995,
+      "grad_norm": 0.8067639470100403,
+      "learning_rate": 7.740423047216553e-05,
+      "loss": 1.700193214416504,
+      "mean_token_accuracy": 0.6428261503577233,
+      "num_tokens": 54280.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.049079754601226995,
+      "eval_entropy": 1.315366074017116,
+      "eval_loss": 1.23488187789917,
+      "eval_mean_token_accuracy": 0.7063105702400208,
+      "eval_num_tokens": 54280.0,
+      "eval_runtime": 105.4535,
+      "eval_samples_per_second": 13.229,
+      "eval_steps_per_second": 1.659,
+      "step": 20
+    },
+    {
+      "entropy": 0.95277059674263,
+      "epoch": 0.09815950920245399,
+      "grad_norm": 0.572104811668396,
+      "learning_rate": 0.00015888236781128713,
+      "loss": 0.9082255363464355,
+      "mean_token_accuracy": 0.7559243977069855,
+      "num_tokens": 113362.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.09815950920245399,
+      "eval_entropy": 0.8220351917403085,
+      "eval_loss": 0.7917433381080627,
+      "eval_mean_token_accuracy": 0.774279066153935,
+      "eval_num_tokens": 113362.0,
+      "eval_runtime": 104.9915,
+      "eval_samples_per_second": 13.287,
+      "eval_steps_per_second": 1.667,
+      "step": 40
+    },
+    {
+      "entropy": 0.7833507835865021,
+      "epoch": 0.147239263803681,
+      "grad_norm": 0.5184682011604309,
+      "learning_rate": 0.00024036050515040874,
+      "loss": 0.7395487308502198,
+      "mean_token_accuracy": 0.7903637677431107,
+      "num_tokens": 165819.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.147239263803681,
+      "eval_entropy": 0.7486384316853114,
+      "eval_loss": 0.7170758843421936,
+      "eval_mean_token_accuracy": 0.7953836243493216,
+      "eval_num_tokens": 165819.0,
+      "eval_runtime": 105.0262,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "step": 60
+    },
+    {
+      "entropy": 0.7294519171118736,
+      "epoch": 0.19631901840490798,
+      "grad_norm": 0.44408509135246277,
+      "learning_rate": 0.00032183864248953035,
+      "loss": 0.6858654499053956,
+      "mean_token_accuracy": 0.8006252631545067,
+      "num_tokens": 215870.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.19631901840490798,
+      "eval_entropy": 0.7126145311764308,
+      "eval_loss": 0.6875877976417542,
+      "eval_mean_token_accuracy": 0.8029442460196359,
+      "eval_num_tokens": 215870.0,
+      "eval_runtime": 105.0224,
+      "eval_samples_per_second": 13.283,
+      "eval_steps_per_second": 1.666,
+      "step": 80
+    },
+    {
+      "entropy": 0.729012505710125,
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.6172338724136353,
+      "learning_rate": 0.0003336184073169935,
+      "loss": 0.6861891746520996,
+      "mean_token_accuracy": 0.8014167010784149,
+      "num_tokens": 267691.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "eval_entropy": 0.7107754983220782,
+      "eval_loss": 0.6713247299194336,
+      "eval_mean_token_accuracy": 0.8043575610433306,
+      "eval_num_tokens": 267691.0,
+      "eval_runtime": 104.9968,
+      "eval_samples_per_second": 13.286,
+      "eval_steps_per_second": 1.667,
+      "step": 100
+    },
+    {
+      "entropy": 0.6980620548129082,
+      "epoch": 0.294478527607362,
+      "grad_norm": 0.39251449704170227,
+      "learning_rate": 0.0003319702576276399,
+      "loss": 0.6606289863586425,
+      "mean_token_accuracy": 0.8069421723484993,
+      "num_tokens": 323653.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.294478527607362,
+      "eval_entropy": 0.6927587161745344,
+      "eval_loss": 0.6542542576789856,
+      "eval_mean_token_accuracy": 0.8079089961733137,
+      "eval_num_tokens": 323653.0,
+      "eval_runtime": 104.9951,
+      "eval_samples_per_second": 13.286,
+      "eval_steps_per_second": 1.667,
+      "step": 120
+    },
+    {
+      "entropy": 0.6662331499159336,
+      "epoch": 0.34355828220858897,
+      "grad_norm": 0.3216697573661804,
+      "learning_rate": 0.0003291142145808027,
+      "loss": 0.6278485298156739,
+      "mean_token_accuracy": 0.8151775613427162,
+      "num_tokens": 382063.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.34355828220858897,
+      "eval_entropy": 0.6883142059189933,
+      "eval_loss": 0.6383033990859985,
+      "eval_mean_token_accuracy": 0.8143898207800729,
+      "eval_num_tokens": 382063.0,
+      "eval_runtime": 105.044,
+      "eval_samples_per_second": 13.28,
+      "eval_steps_per_second": 1.666,
+      "step": 140
+    },
+    {
+      "entropy": 0.6582960978150367,
+      "epoch": 0.39263803680981596,
+      "grad_norm": 0.3135772943496704,
+      "learning_rate": 0.00032507119362351535,
+      "loss": 0.6200582027435303,
+      "mean_token_accuracy": 0.8181118443608284,
+      "num_tokens": 440825.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.39263803680981596,
+      "eval_entropy": 0.6579666543006897,
+      "eval_loss": 0.6228571534156799,
+      "eval_mean_token_accuracy": 0.8177092627116612,
+      "eval_num_tokens": 440825.0,
+      "eval_runtime": 105.0261,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "step": 160
+    },
+    {
+      "entropy": 0.6583003848791122,
+      "epoch": 0.44171779141104295,
+      "grad_norm": 0.4423973858356476,
+      "learning_rate": 0.0003198708027096144,
+      "loss": 0.620824670791626,
+      "mean_token_accuracy": 0.8163372203707695,
+      "num_tokens": 494124.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.44171779141104295,
+      "eval_entropy": 0.6453603114400591,
+      "eval_loss": 0.6144688129425049,
+      "eval_mean_token_accuracy": 0.8197193598747253,
+      "eval_num_tokens": 494124.0,
+      "eval_runtime": 105.0276,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "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": 1.0027645416972288e+17,
+  "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_test2/checkpoint-20/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_test2/checkpoint-20/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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.09184864657147984,
+  "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": 16,
+  "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_test2/checkpoint-20/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_test2/checkpoint-20/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_test2/checkpoint-20/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.049079754601226995,
+  "eval_steps": 20,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.719682201743126,
+      "epoch": 0.049079754601226995,
+      "grad_norm": 0.8067639470100403,
+      "learning_rate": 7.740423047216553e-05,
+      "loss": 1.700193214416504,
+      "mean_token_accuracy": 0.6428261503577233,
+      "num_tokens": 54280.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.049079754601226995,
+      "eval_entropy": 1.315366074017116,
+      "eval_loss": 1.23488187789917,
+      "eval_mean_token_accuracy": 0.7063105702400208,
+      "eval_num_tokens": 54280.0,
+      "eval_runtime": 105.4535,
+      "eval_samples_per_second": 13.229,
+      "eval_steps_per_second": 1.659,
+      "step": 20
+    }
+  ],
+  "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": 1.122300772712448e+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_test2/checkpoint-200/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_test2/checkpoint-200/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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.09184864657147984,
+  "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": 16,
+  "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_test2/checkpoint-200/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_test2/checkpoint-200/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_test2/checkpoint-200/trainer_state.json

@@ -0,0 +1,244 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.49079754601226994,
+  "eval_steps": 20,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.719682201743126,
+      "epoch": 0.049079754601226995,
+      "grad_norm": 0.8067639470100403,
+      "learning_rate": 7.740423047216553e-05,
+      "loss": 1.700193214416504,
+      "mean_token_accuracy": 0.6428261503577233,
+      "num_tokens": 54280.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.049079754601226995,
+      "eval_entropy": 1.315366074017116,
+      "eval_loss": 1.23488187789917,
+      "eval_mean_token_accuracy": 0.7063105702400208,
+      "eval_num_tokens": 54280.0,
+      "eval_runtime": 105.4535,
+      "eval_samples_per_second": 13.229,
+      "eval_steps_per_second": 1.659,
+      "step": 20
+    },
+    {
+      "entropy": 0.95277059674263,
+      "epoch": 0.09815950920245399,
+      "grad_norm": 0.572104811668396,
+      "learning_rate": 0.00015888236781128713,
+      "loss": 0.9082255363464355,
+      "mean_token_accuracy": 0.7559243977069855,
+      "num_tokens": 113362.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.09815950920245399,
+      "eval_entropy": 0.8220351917403085,
+      "eval_loss": 0.7917433381080627,
+      "eval_mean_token_accuracy": 0.774279066153935,
+      "eval_num_tokens": 113362.0,
+      "eval_runtime": 104.9915,
+      "eval_samples_per_second": 13.287,
+      "eval_steps_per_second": 1.667,
+      "step": 40
+    },
+    {
+      "entropy": 0.7833507835865021,
+      "epoch": 0.147239263803681,
+      "grad_norm": 0.5184682011604309,
+      "learning_rate": 0.00024036050515040874,
+      "loss": 0.7395487308502198,
+      "mean_token_accuracy": 0.7903637677431107,
+      "num_tokens": 165819.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.147239263803681,
+      "eval_entropy": 0.7486384316853114,
+      "eval_loss": 0.7170758843421936,
+      "eval_mean_token_accuracy": 0.7953836243493216,
+      "eval_num_tokens": 165819.0,
+      "eval_runtime": 105.0262,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "step": 60
+    },
+    {
+      "entropy": 0.7294519171118736,
+      "epoch": 0.19631901840490798,
+      "grad_norm": 0.44408509135246277,
+      "learning_rate": 0.00032183864248953035,
+      "loss": 0.6858654499053956,
+      "mean_token_accuracy": 0.8006252631545067,
+      "num_tokens": 215870.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.19631901840490798,
+      "eval_entropy": 0.7126145311764308,
+      "eval_loss": 0.6875877976417542,
+      "eval_mean_token_accuracy": 0.8029442460196359,
+      "eval_num_tokens": 215870.0,
+      "eval_runtime": 105.0224,
+      "eval_samples_per_second": 13.283,
+      "eval_steps_per_second": 1.666,
+      "step": 80
+    },
+    {
+      "entropy": 0.729012505710125,
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.6172338724136353,
+      "learning_rate": 0.0003336184073169935,
+      "loss": 0.6861891746520996,
+      "mean_token_accuracy": 0.8014167010784149,
+      "num_tokens": 267691.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "eval_entropy": 0.7107754983220782,
+      "eval_loss": 0.6713247299194336,
+      "eval_mean_token_accuracy": 0.8043575610433306,
+      "eval_num_tokens": 267691.0,
+      "eval_runtime": 104.9968,
+      "eval_samples_per_second": 13.286,
+      "eval_steps_per_second": 1.667,
+      "step": 100
+    },
+    {
+      "entropy": 0.6980620548129082,
+      "epoch": 0.294478527607362,
+      "grad_norm": 0.39251449704170227,
+      "learning_rate": 0.0003319702576276399,
+      "loss": 0.6606289863586425,
+      "mean_token_accuracy": 0.8069421723484993,
+      "num_tokens": 323653.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.294478527607362,
+      "eval_entropy": 0.6927587161745344,
+      "eval_loss": 0.6542542576789856,
+      "eval_mean_token_accuracy": 0.8079089961733137,
+      "eval_num_tokens": 323653.0,
+      "eval_runtime": 104.9951,
+      "eval_samples_per_second": 13.286,
+      "eval_steps_per_second": 1.667,
+      "step": 120
+    },
+    {
+      "entropy": 0.6662331499159336,
+      "epoch": 0.34355828220858897,
+      "grad_norm": 0.3216697573661804,
+      "learning_rate": 0.0003291142145808027,
+      "loss": 0.6278485298156739,
+      "mean_token_accuracy": 0.8151775613427162,
+      "num_tokens": 382063.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.34355828220858897,
+      "eval_entropy": 0.6883142059189933,
+      "eval_loss": 0.6383033990859985,
+      "eval_mean_token_accuracy": 0.8143898207800729,
+      "eval_num_tokens": 382063.0,
+      "eval_runtime": 105.044,
+      "eval_samples_per_second": 13.28,
+      "eval_steps_per_second": 1.666,
+      "step": 140
+    },
+    {
+      "entropy": 0.6582960978150367,
+      "epoch": 0.39263803680981596,
+      "grad_norm": 0.3135772943496704,
+      "learning_rate": 0.00032507119362351535,
+      "loss": 0.6200582027435303,
+      "mean_token_accuracy": 0.8181118443608284,
+      "num_tokens": 440825.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.39263803680981596,
+      "eval_entropy": 0.6579666543006897,
+      "eval_loss": 0.6228571534156799,
+      "eval_mean_token_accuracy": 0.8177092627116612,
+      "eval_num_tokens": 440825.0,
+      "eval_runtime": 105.0261,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "step": 160
+    },
+    {
+      "entropy": 0.6583003848791122,
+      "epoch": 0.44171779141104295,
+      "grad_norm": 0.4423973858356476,
+      "learning_rate": 0.0003198708027096144,
+      "loss": 0.620824670791626,
+      "mean_token_accuracy": 0.8163372203707695,
+      "num_tokens": 494124.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.44171779141104295,
+      "eval_entropy": 0.6453603114400591,
+      "eval_loss": 0.6144688129425049,
+      "eval_mean_token_accuracy": 0.8197193598747253,
+      "eval_num_tokens": 494124.0,
+      "eval_runtime": 105.0276,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "step": 180
+    },
+    {
+      "entropy": 0.6454010501503944,
+      "epoch": 0.49079754601226994,
+      "grad_norm": 0.3798937201499939,
+      "learning_rate": 0.00031355112547402,
+      "loss": 0.6067435264587402,
+      "mean_token_accuracy": 0.8212858110666275,
+      "num_tokens": 542703.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.49079754601226994,
+      "eval_entropy": 0.6678816018785749,
+      "eval_loss": 0.6147017478942871,
+      "eval_mean_token_accuracy": 0.8175191504614694,
+      "eval_num_tokens": 542703.0,
+      "eval_runtime": 105.0272,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "step": 200
+    }
+  ],
+  "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": 1.0981223285587968e+17,
+  "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_test2/checkpoint-220/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_test2/checkpoint-220/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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.09184864657147984,
+  "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": 16,
+  "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_test2/checkpoint-220/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_test2/checkpoint-220/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_test2/checkpoint-220/trainer_state.json

@@ -0,0 +1,265 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5398773006134969,
+  "eval_steps": 20,
+  "global_step": 220,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.719682201743126,
+      "epoch": 0.049079754601226995,
+      "grad_norm": 0.8067639470100403,
+      "learning_rate": 7.740423047216553e-05,
+      "loss": 1.700193214416504,
+      "mean_token_accuracy": 0.6428261503577233,
+      "num_tokens": 54280.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.049079754601226995,
+      "eval_entropy": 1.315366074017116,
+      "eval_loss": 1.23488187789917,
+      "eval_mean_token_accuracy": 0.7063105702400208,
+      "eval_num_tokens": 54280.0,
+      "eval_runtime": 105.4535,
+      "eval_samples_per_second": 13.229,
+      "eval_steps_per_second": 1.659,
+      "step": 20
+    },
+    {
+      "entropy": 0.95277059674263,
+      "epoch": 0.09815950920245399,
+      "grad_norm": 0.572104811668396,
+      "learning_rate": 0.00015888236781128713,
+      "loss": 0.9082255363464355,
+      "mean_token_accuracy": 0.7559243977069855,
+      "num_tokens": 113362.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.09815950920245399,
+      "eval_entropy": 0.8220351917403085,
+      "eval_loss": 0.7917433381080627,
+      "eval_mean_token_accuracy": 0.774279066153935,
+      "eval_num_tokens": 113362.0,
+      "eval_runtime": 104.9915,
+      "eval_samples_per_second": 13.287,
+      "eval_steps_per_second": 1.667,
+      "step": 40
+    },
+    {
+      "entropy": 0.7833507835865021,
+      "epoch": 0.147239263803681,
+      "grad_norm": 0.5184682011604309,
+      "learning_rate": 0.00024036050515040874,
+      "loss": 0.7395487308502198,
+      "mean_token_accuracy": 0.7903637677431107,
+      "num_tokens": 165819.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.147239263803681,
+      "eval_entropy": 0.7486384316853114,
+      "eval_loss": 0.7170758843421936,
+      "eval_mean_token_accuracy": 0.7953836243493216,
+      "eval_num_tokens": 165819.0,
+      "eval_runtime": 105.0262,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "step": 60
+    },
+    {
+      "entropy": 0.7294519171118736,
+      "epoch": 0.19631901840490798,
+      "grad_norm": 0.44408509135246277,
+      "learning_rate": 0.00032183864248953035,
+      "loss": 0.6858654499053956,
+      "mean_token_accuracy": 0.8006252631545067,
+      "num_tokens": 215870.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.19631901840490798,
+      "eval_entropy": 0.7126145311764308,
+      "eval_loss": 0.6875877976417542,
+      "eval_mean_token_accuracy": 0.8029442460196359,
+      "eval_num_tokens": 215870.0,
+      "eval_runtime": 105.0224,
+      "eval_samples_per_second": 13.283,
+      "eval_steps_per_second": 1.666,
+      "step": 80
+    },
+    {
+      "entropy": 0.729012505710125,
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.6172338724136353,
+      "learning_rate": 0.0003336184073169935,
+      "loss": 0.6861891746520996,
+      "mean_token_accuracy": 0.8014167010784149,
+      "num_tokens": 267691.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "eval_entropy": 0.7107754983220782,
+      "eval_loss": 0.6713247299194336,
+      "eval_mean_token_accuracy": 0.8043575610433306,
+      "eval_num_tokens": 267691.0,
+      "eval_runtime": 104.9968,
+      "eval_samples_per_second": 13.286,
+      "eval_steps_per_second": 1.667,
+      "step": 100
+    },
+    {
+      "entropy": 0.6980620548129082,
+      "epoch": 0.294478527607362,
+      "grad_norm": 0.39251449704170227,
+      "learning_rate": 0.0003319702576276399,
+      "loss": 0.6606289863586425,
+      "mean_token_accuracy": 0.8069421723484993,
+      "num_tokens": 323653.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.294478527607362,
+      "eval_entropy": 0.6927587161745344,
+      "eval_loss": 0.6542542576789856,
+      "eval_mean_token_accuracy": 0.8079089961733137,
+      "eval_num_tokens": 323653.0,
+      "eval_runtime": 104.9951,
+      "eval_samples_per_second": 13.286,
+      "eval_steps_per_second": 1.667,
+      "step": 120
+    },
+    {
+      "entropy": 0.6662331499159336,
+      "epoch": 0.34355828220858897,
+      "grad_norm": 0.3216697573661804,
+      "learning_rate": 0.0003291142145808027,
+      "loss": 0.6278485298156739,
+      "mean_token_accuracy": 0.8151775613427162,
+      "num_tokens": 382063.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.34355828220858897,
+      "eval_entropy": 0.6883142059189933,
+      "eval_loss": 0.6383033990859985,
+      "eval_mean_token_accuracy": 0.8143898207800729,
+      "eval_num_tokens": 382063.0,
+      "eval_runtime": 105.044,
+      "eval_samples_per_second": 13.28,
+      "eval_steps_per_second": 1.666,
+      "step": 140
+    },
+    {
+      "entropy": 0.6582960978150367,
+      "epoch": 0.39263803680981596,
+      "grad_norm": 0.3135772943496704,
+      "learning_rate": 0.00032507119362351535,
+      "loss": 0.6200582027435303,
+      "mean_token_accuracy": 0.8181118443608284,
+      "num_tokens": 440825.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.39263803680981596,
+      "eval_entropy": 0.6579666543006897,
+      "eval_loss": 0.6228571534156799,
+      "eval_mean_token_accuracy": 0.8177092627116612,
+      "eval_num_tokens": 440825.0,
+      "eval_runtime": 105.0261,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "step": 160
+    },
+    {
+      "entropy": 0.6583003848791122,
+      "epoch": 0.44171779141104295,
+      "grad_norm": 0.4423973858356476,
+      "learning_rate": 0.0003198708027096144,
+      "loss": 0.620824670791626,
+      "mean_token_accuracy": 0.8163372203707695,
+      "num_tokens": 494124.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.44171779141104295,
+      "eval_entropy": 0.6453603114400591,
+      "eval_loss": 0.6144688129425049,
+      "eval_mean_token_accuracy": 0.8197193598747253,
+      "eval_num_tokens": 494124.0,
+      "eval_runtime": 105.0276,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "step": 180
+    },
+    {
+      "entropy": 0.6454010501503944,
+      "epoch": 0.49079754601226994,
+      "grad_norm": 0.3798937201499939,
+      "learning_rate": 0.00031355112547402,
+      "loss": 0.6067435264587402,
+      "mean_token_accuracy": 0.8212858110666275,
+      "num_tokens": 542703.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.49079754601226994,
+      "eval_entropy": 0.6678816018785749,
+      "eval_loss": 0.6147017478942871,
+      "eval_mean_token_accuracy": 0.8175191504614694,
+      "eval_num_tokens": 542703.0,
+      "eval_runtime": 105.0272,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "step": 200
+    },
+    {
+      "entropy": 0.6504128783941269,
+      "epoch": 0.5398773006134969,
+      "grad_norm": 0.4333654046058655,
+      "learning_rate": 0.00030615844233769247,
+      "loss": 0.609531021118164,
+      "mean_token_accuracy": 0.8201618298888207,
+      "num_tokens": 597461.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.5398773006134969,
+      "eval_entropy": 0.6659639770644051,
+      "eval_loss": 0.6074424982070923,
+      "eval_mean_token_accuracy": 0.8188560080528259,
+      "eval_num_tokens": 597461.0,
+      "eval_runtime": 104.9219,
+      "eval_samples_per_second": 13.296,
+      "eval_steps_per_second": 1.668,
+      "step": 220
+    }
+  ],
+  "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": 1.2097047689330688e+17,
+  "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_test2/checkpoint-240/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_test2/checkpoint-240/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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.09184864657147984,
+  "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": 16,
+  "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_test2/checkpoint-240/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_test2/checkpoint-240/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_test2/checkpoint-240/trainer_state.json

@@ -0,0 +1,286 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.588957055214724,
+  "eval_steps": 20,
+  "global_step": 240,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.719682201743126,
+      "epoch": 0.049079754601226995,
+      "grad_norm": 0.8067639470100403,
+      "learning_rate": 7.740423047216553e-05,
+      "loss": 1.700193214416504,
+      "mean_token_accuracy": 0.6428261503577233,
+      "num_tokens": 54280.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.049079754601226995,
+      "eval_entropy": 1.315366074017116,
+      "eval_loss": 1.23488187789917,
+      "eval_mean_token_accuracy": 0.7063105702400208,
+      "eval_num_tokens": 54280.0,
+      "eval_runtime": 105.4535,
+      "eval_samples_per_second": 13.229,
+      "eval_steps_per_second": 1.659,
+      "step": 20
+    },
+    {
+      "entropy": 0.95277059674263,
+      "epoch": 0.09815950920245399,
+      "grad_norm": 0.572104811668396,
+      "learning_rate": 0.00015888236781128713,
+      "loss": 0.9082255363464355,
+      "mean_token_accuracy": 0.7559243977069855,
+      "num_tokens": 113362.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.09815950920245399,
+      "eval_entropy": 0.8220351917403085,
+      "eval_loss": 0.7917433381080627,
+      "eval_mean_token_accuracy": 0.774279066153935,
+      "eval_num_tokens": 113362.0,
+      "eval_runtime": 104.9915,
+      "eval_samples_per_second": 13.287,
+      "eval_steps_per_second": 1.667,
+      "step": 40
+    },
+    {
+      "entropy": 0.7833507835865021,
+      "epoch": 0.147239263803681,
+      "grad_norm": 0.5184682011604309,
+      "learning_rate": 0.00024036050515040874,
+      "loss": 0.7395487308502198,
+      "mean_token_accuracy": 0.7903637677431107,
+      "num_tokens": 165819.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.147239263803681,
+      "eval_entropy": 0.7486384316853114,
+      "eval_loss": 0.7170758843421936,
+      "eval_mean_token_accuracy": 0.7953836243493216,
+      "eval_num_tokens": 165819.0,
+      "eval_runtime": 105.0262,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "step": 60
+    },
+    {
+      "entropy": 0.7294519171118736,
+      "epoch": 0.19631901840490798,
+      "grad_norm": 0.44408509135246277,
+      "learning_rate": 0.00032183864248953035,
+      "loss": 0.6858654499053956,
+      "mean_token_accuracy": 0.8006252631545067,
+      "num_tokens": 215870.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.19631901840490798,
+      "eval_entropy": 0.7126145311764308,
+      "eval_loss": 0.6875877976417542,
+      "eval_mean_token_accuracy": 0.8029442460196359,
+      "eval_num_tokens": 215870.0,
+      "eval_runtime": 105.0224,
+      "eval_samples_per_second": 13.283,
+      "eval_steps_per_second": 1.666,
+      "step": 80
+    },
+    {
+      "entropy": 0.729012505710125,
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.6172338724136353,
+      "learning_rate": 0.0003336184073169935,
+      "loss": 0.6861891746520996,
+      "mean_token_accuracy": 0.8014167010784149,
+      "num_tokens": 267691.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "eval_entropy": 0.7107754983220782,
+      "eval_loss": 0.6713247299194336,
+      "eval_mean_token_accuracy": 0.8043575610433306,
+      "eval_num_tokens": 267691.0,
+      "eval_runtime": 104.9968,
+      "eval_samples_per_second": 13.286,
+      "eval_steps_per_second": 1.667,
+      "step": 100
+    },
+    {
+      "entropy": 0.6980620548129082,
+      "epoch": 0.294478527607362,
+      "grad_norm": 0.39251449704170227,
+      "learning_rate": 0.0003319702576276399,
+      "loss": 0.6606289863586425,
+      "mean_token_accuracy": 0.8069421723484993,
+      "num_tokens": 323653.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.294478527607362,
+      "eval_entropy": 0.6927587161745344,
+      "eval_loss": 0.6542542576789856,
+      "eval_mean_token_accuracy": 0.8079089961733137,
+      "eval_num_tokens": 323653.0,
+      "eval_runtime": 104.9951,
+      "eval_samples_per_second": 13.286,
+      "eval_steps_per_second": 1.667,
+      "step": 120
+    },
+    {
+      "entropy": 0.6662331499159336,
+      "epoch": 0.34355828220858897,
+      "grad_norm": 0.3216697573661804,
+      "learning_rate": 0.0003291142145808027,
+      "loss": 0.6278485298156739,
+      "mean_token_accuracy": 0.8151775613427162,
+      "num_tokens": 382063.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.34355828220858897,
+      "eval_entropy": 0.6883142059189933,
+      "eval_loss": 0.6383033990859985,
+      "eval_mean_token_accuracy": 0.8143898207800729,
+      "eval_num_tokens": 382063.0,
+      "eval_runtime": 105.044,
+      "eval_samples_per_second": 13.28,
+      "eval_steps_per_second": 1.666,
+      "step": 140
+    },
+    {
+      "entropy": 0.6582960978150367,
+      "epoch": 0.39263803680981596,
+      "grad_norm": 0.3135772943496704,
+      "learning_rate": 0.00032507119362351535,
+      "loss": 0.6200582027435303,
+      "mean_token_accuracy": 0.8181118443608284,
+      "num_tokens": 440825.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.39263803680981596,
+      "eval_entropy": 0.6579666543006897,
+      "eval_loss": 0.6228571534156799,
+      "eval_mean_token_accuracy": 0.8177092627116612,
+      "eval_num_tokens": 440825.0,
+      "eval_runtime": 105.0261,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "step": 160
+    },
+    {
+      "entropy": 0.6583003848791122,
+      "epoch": 0.44171779141104295,
+      "grad_norm": 0.4423973858356476,
+      "learning_rate": 0.0003198708027096144,
+      "loss": 0.620824670791626,
+      "mean_token_accuracy": 0.8163372203707695,
+      "num_tokens": 494124.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.44171779141104295,
+      "eval_entropy": 0.6453603114400591,
+      "eval_loss": 0.6144688129425049,
+      "eval_mean_token_accuracy": 0.8197193598747253,
+      "eval_num_tokens": 494124.0,
+      "eval_runtime": 105.0276,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "step": 180
+    },
+    {
+      "entropy": 0.6454010501503944,
+      "epoch": 0.49079754601226994,
+      "grad_norm": 0.3798937201499939,
+      "learning_rate": 0.00031355112547402,
+      "loss": 0.6067435264587402,
+      "mean_token_accuracy": 0.8212858110666275,
+      "num_tokens": 542703.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.49079754601226994,
+      "eval_entropy": 0.6678816018785749,
+      "eval_loss": 0.6147017478942871,
+      "eval_mean_token_accuracy": 0.8175191504614694,
+      "eval_num_tokens": 542703.0,
+      "eval_runtime": 105.0272,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.666,
+      "step": 200
+    },
+    {
+      "entropy": 0.6504128783941269,
+      "epoch": 0.5398773006134969,
+      "grad_norm": 0.4333654046058655,
+      "learning_rate": 0.00030615844233769247,
+      "loss": 0.609531021118164,
+      "mean_token_accuracy": 0.8201618298888207,
+      "num_tokens": 597461.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.5398773006134969,
+      "eval_entropy": 0.6659639770644051,
+      "eval_loss": 0.6074424982070923,
+      "eval_mean_token_accuracy": 0.8188560080528259,
+      "eval_num_tokens": 597461.0,
+      "eval_runtime": 104.9219,
+      "eval_samples_per_second": 13.296,
+      "eval_steps_per_second": 1.668,
+      "step": 220
+    },
+    {
+      "entropy": 0.6530551195144654,
+      "epoch": 0.588957055214724,
+      "grad_norm": 0.3736813962459564,
+      "learning_rate": 0.00029774689158567713,
+      "loss": 0.6050861358642579,
+      "mean_token_accuracy": 0.819097925722599,
+      "num_tokens": 651354.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.588957055214724,
+      "eval_entropy": 0.6647280216217041,
+      "eval_loss": 0.6030699014663696,
+      "eval_mean_token_accuracy": 0.8212648391723633,
+      "eval_num_tokens": 651354.0,
+      "eval_runtime": 104.9747,
+      "eval_samples_per_second": 13.289,
+      "eval_steps_per_second": 1.667,
+      "step": 240
+    }
+  ],
+  "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": 1.313927085821952e+17,
+  "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_test2/checkpoint-260/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_test2/checkpoint-260/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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.09184864657147984,
+  "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": 16,
+  "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_test2/checkpoint-260/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 %}